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: 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
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: 3.08945 s *****
[rank:7] [train], epoch: 0/1, iter: 100/312, loss: 0.86807, top1: 0.00096, throughput: 449.92 | 2022-05-06 21:54:08.060
[rank:1] [train], epoch: 0/1, iter: 100/312, loss: 0.86775, top1: 0.00102, throughput: 449.90 | 2022-05-06 21:54:08.064
[rank:0] [train], epoch: 0/1, iter: 100/312, loss: 0.86790, top1: 0.00117, throughput: 449.89 | 2022-05-06 21:54:08.064
[rank:4] [train], epoch: 0/1, iter: 100/312, loss: 0.86794, top1: 0.00094, throughput: 449.93 | 2022-05-06 21:54:08.063
[rank:6] [train], epoch: 0/1, iter: 100/312, loss: 0.86802, top1: 0.00115, throughput: 449.90 | 2022-05-06 21:54:08.063
[rank:3] [train], epoch: 0/1, iter: 100/312, loss: 0.86776, top1: 0.00115, throughput: 449.91 | 2022-05-06 21:54:08.063
[rank:2] [train], epoch: 0/1, iter: 100/312, loss: 0.86815, top1: 0.00117, throughput: 449.89 | 2022-05-06 21:54:08.063
[rank:5] [train], epoch: 0/1, iter: 100/312, loss: 0.86803, top1: 0.00104, throughput: 449.92 | 2022-05-06 21:54:08.062
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]
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/06 21:54:08.385, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/05/06 21:54:08.387, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/06 21:54:08.389, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/05/06 21:54:08.389, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/06 21:54:08.392, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/06 21:54:08.394, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/06 21:54:08.395, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/05/06 21:54:08.395, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
2022/05/06 21:54:08.396, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
2022/05/06 21:54:08.397, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.397, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/05/06 21:54:08.400, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.400, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/05/06 21:54:08.401, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 71 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/05/06 21:54:08.402, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
2022/05/06 21:54:08.402, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.403, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.405, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.405, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
2022/05/06 21:54:08.408, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.412, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
2022/05/06 21:54:08.413, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8590 MiB, 23920 MiB
2022/05/06 21:54:08.413, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.414, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.414, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.416, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 76 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.417, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.420, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 76 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.420, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.421, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 86 %, 32510 MiB, 8722 MiB, 23788 MiB
2022/05/06 21:54:08.422, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.422, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.422, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.424, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.425, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.428, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.428, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.433, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8674 MiB, 23836 MiB
2022/05/06 21:54:08.434, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.434, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.435, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.436, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.437, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.440, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.441, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.442, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 8710 MiB, 23800 MiB
2022/05/06 21:54:08.442, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.443, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.443, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.445, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 76 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.446, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.449, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.453, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.466, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 91 %, 32510 MiB, 8534 MiB, 23976 MiB
2022/05/06 21:54:08.467, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.467, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.468, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.486, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.506, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.507, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 89 %, 32510 MiB, 8462 MiB, 24048 MiB
2022/05/06 21:54:08.508, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.512, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.522, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
2022/05/06 21:54:08.523, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 70 %, 32510 MiB, 8602 MiB, 23908 MiB
[rank:7] [train], epoch: 0/1, iter: 200/312, loss: 0.86784, top1: 0.00137, throughput: 1340.82 | 2022-05-06 21:54:46.246
[rank:5] [train], epoch: 0/1, iter: 200/312, loss: 0.86793, top1: 0.00098, throughput: 1340.91 | 2022-05-06 21:54:46.245
[rank:1] [train], epoch: 0/1, iter: 200/312, loss: 0.86796, top1: 0.00096, throughput: 1340.95 | 2022-05-06 21:54:46.246
[rank:2] [train], epoch: 0/1, iter: 200/312, loss: 0.86773, top1: 0.00127, throughput: 1340.84 | 2022-05-06 21:54:46.248
[rank:0] [train], epoch: 0/1, iter: 200/312, loss: 0.86777, top1: 0.00121, throughput: 1340.90 | 2022-05-06 21:54:46.247
[rank:3] [train], epoch: 0/1, iter: 200/312, loss: 0.86784, top1: 0.00117, throughput: 1340.93 | 2022-05-06 21:54:46.245
[rank:4] [train], epoch: 0/1, iter: 200/312, loss: 0.86792, top1: 0.00115, throughput: 1340.80 | 2022-05-06 21:54:46.249
[rank:6] [train], epoch: 0/1, iter: 200/312, loss: 0.86810, top1: 0.00117, throughput: 1340.94 | 2022-05-06 21:54:46.245
[rank:5] [train], epoch: 0/1, iter: 300/312, loss: 0.86768, top1: 0.00117, throughput: 1349.78 | 2022-05-06 21:55:24.177
[rank:7] [train], epoch: 0/1, iter: 300/312, loss: 0.86801, top1: 0.00094, throughput: 1349.77 | 2022-05-06 21:55:24.178
[rank:0] [train], epoch: 0/1, iter: 300/312, loss: 0.86789, top1: 0.00125, throughput: 1349.78 [rank:2] [train], epoch: 0/1, iter: 300/312, loss: 0.86791, top1: 0.00104, throughput: 1349.78 | 2022-05-06 21:55:24.180| 2022-05-06 21:55:24.180

[rank:6] [train], epoch: 0/1, iter: 300/312, loss: 0.86788, top1: 0.00119, throughput: 1349.69 | 2022-05-06 21:55:24.180
[rank:1] [train], epoch: 0/1, iter: 300/312, loss: 0.86787, top1: 0.00111, throughput: 1349.70 | 2022-05-06 21:55:24.180
[rank:4] [train], epoch: 0/1, iter: 300/312, loss: 0.86786, top1: 0.00086, throughput: 1349.82 | 2022-05-06 21:55:24.180
[rank:3] [train], epoch: 0/1, iter: 300/312, loss: 0.86788, top1: 0.00107, throughput: 1349.70 | 2022-05-06 21:55:24.180