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: /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

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: 3.00766 s *****
[rank:3] [train], epoch: 0/1, iter: 100/312, loss: 0.86727, top1: 0.00096, throughput: 424.63 | 2022-04-30 02:29:54.518
[rank:5] [train], epoch: 0/1, iter: 100/312, loss: 0.86733, top1: 0.00096, throughput: 424.64 | 2022-04-30 02:29:54.517
[rank:7] [train], epoch: 0/1, iter: 100/312, loss: 0.86725, top1: 0.00092, throughput: 424.63 | 2022-04-30 02:29:54.518
[rank:2] [train], epoch: 0/1, iter: 100/312, loss: 0.86733, top1: 0.00078, throughput: 424.64 | 2022-04-30 02:29:54.519
[rank:1] [train], epoch: 0/1, iter: 100/312, loss: 0.86737, top1: 0.00104, throughput: 424.64 | 2022-04-30 02:29:54.517
[rank:4] [train], epoch: 0/1, iter: 100/312, loss: 0.86765, top1: 0.00096, throughput: 424.62 | 2022-04-30 02:29:54.519
[rank:0] [train], epoch: 0/1, iter: 100/312, loss: 0.86739, top1: 0.00094, throughput: 424.65 | 2022-04-30 02:29:54.521
[rank:6] [train], epoch: 0/1, iter: 100/312, loss: 0.86742, top1: 0.00092, throughput: 424.62 | 2022-04-30 02:29:54.519
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:29:54.763, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 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]
2022/04/30 02:29:54.769, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7724 MiB, 24786 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]
2022/04/30 02:29:54.770, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 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]
2022/04/30 02:29:54.772, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 MiB
2022/04/30 02:29:54.772, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 MiB
2022/04/30 02:29:54.774, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.775, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 MiB
2022/04/30 02:29:54.776, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.775, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 MiB
2022/04/30 02:29:54.776, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 MiB
2022/04/30 02:29:54.776, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7773 MiB, 24737 MiB
2022/04/30 02:29:54.778, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.778, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.781, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.782, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 65 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.783, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.784, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 65 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.785, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 65 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.785, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 65 %, 32510 MiB, 7724 MiB, 24786 MiB
2022/04/30 02:29:54.786, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.786, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.789, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.790, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.791, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.792, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.792, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.793, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7956 MiB, 24554 MiB
2022/04/30 02:29:54.794, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.794, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.797, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.799, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.800, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.800, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.801, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.801, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7912 MiB, 24598 MiB
2022/04/30 02:29:54.802, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.803, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.805, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.806, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.807, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.808, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.809, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.809, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 87 %, 32510 MiB, 7914 MiB, 24596 MiB
2022/04/30 02:29:54.810, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.810, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.813, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.814, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.815, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.815, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.816, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.816, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7808 MiB, 24702 MiB
2022/04/30 02:29:54.817, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.817, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.821, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.822, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.822, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.823, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.824, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 81 %, 32510 MiB, 7670 MiB, 24840 MiB
2022/04/30 02:29:54.824, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.824, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.828, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.829, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.830, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
2022/04/30 02:29:54.831, Tesla V100-SXM2-32GB, 470.57.02, 82 %, 73 %, 32510 MiB, 7822 MiB, 24688 MiB
[rank:6] [train], epoch: 0/1, iter: 200/312, loss: 0.86744, top1: 0.00074, throughput: 1318.91 | 2022-04-30 02:30:33.339
[rank:1] [train], epoch: 0/1, iter: 200/312, loss: 0.86729, top1: 0.00088, throughput: 1318.89 | 2022-04-30 02:30:33.338
[rank:3] [train], epoch: 0/1, iter: 200/312, loss: 0.86738, top1: 0.00086, throughput: 1318.93 | 2022-04-30 02:30:33.337[rank:2] [train], epoch: 0/1, iter: 200/312, loss: 0.86755, top1: 0.00062, throughput: 1318.91
 | 2022-04-30 02:30:33.339
[rank:7] [train], epoch: 0/1, iter: 200/312, loss: 0.86748, top1: 0.00080, throughput: 1318.73 | 2022-04-30 02:30:33.343
[rank:0] [train], epoch: 0/1, iter: 200/312, loss: 0.86719, top1: 0.00105, throughput: 1318.86 | 2022-04-30 02:30:33.342
[rank:4] [train], epoch: 0/1, iter: 200/312, loss: 0.86753, top1: 0.00082, throughput: 1318.74 | 2022-04-30 02:30:33.344
[rank:5] [train], epoch: 0/1, iter: 200/312, loss: 0.86755, top1: 0.00074, throughput: 1318.48 | 2022-04-30 02:30:33.350
[rank:3] [train], epoch: 0/1, iter: 300/312, loss: 0.86756, top1: 0.00105, throughput: 1382.26 | 2022-04-30 02:31:10.378
[rank:1] [train], epoch: 0/1, iter: 300/312, loss: 0.86723, top1: 0.00078, throughput: 1382.27 | 2022-04-30 02:31:10.378
[rank:0] [train], epoch: 0/1, iter: 300/312, loss: 0.86773, top1: 0.00061, throughput: 1382.33 | 2022-04-30 02:31:10.381
[rank:5] [train], epoch: 0/1, iter: 300/312, loss: 0.86710, top1: 0.00094, throughput: 1382.74 | 2022-04-30 02:31:10.378
[rank:7] [train], epoch: 0/1, iter: 300/312, loss: 0.86737, top1: 0.00096, throughput: 1382.44 | 2022-04-30 02:31:10.379
[rank:4] [train], epoch: 0/1, iter: 300/312, loss: 0.86744, top1: 0.00080, throughput: 1382.45 | 2022-04-30 02:31:10.380
[rank:2] [train], epoch: 0/1, iter: 300/312, loss: 0.86774, top1: 0.00082, throughput: 1382.20 | 2022-04-30 02:31:10.381
[rank:6] [train], epoch: 0/1, iter: 300/312, loss: 0.86746, top1: 0.00080, throughput: 1382.27 | 2022-04-30 02:31:10.379