loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
------------------------ arguments ------------------------
  batch_size ...................................... 65536
  batch_size_per_proc ............................. 65536
  data_dir ........................................ /dataset/f9f659c5/wdl_ofrecord
  data_part_name_suffix_length .................... 5
  data_part_num ................................... 256
  dataset_format .................................. ofrecord
  ddp ............................................. False
  deep_dropout_rate ............................... 0.5
  deep_embedding_vec_size ......................... 16
  deep_vocab_size ................................. 2322444
  eval_after_training ............................. False
  eval_batchs ..................................... 20
  eval_interval ................................... 0
  execution_mode .................................. graph
  hidden_size ..................................... 1024
  hidden_units_num ................................ 2
  learning_rate ................................... 0.001
  loss_print_every_n_iter ......................... 100
  max_iter ........................................ 1100
  model_load_dir .................................. 
  model_save_dir .................................. ./checkpoint
  num_deep_sparse_fields .......................... 26
  num_dense_fields ................................ 13
  num_wide_sparse_fields .......................... 2
  save_initial_model .............................. False
  save_model_after_each_eval ...................... False
  test_name ....................................... noname_test
  wide_vocab_size ................................. 2322444
-------------------- end of arguments ---------------------
[rank:0] iter: 100/1100, loss: 0.4983343482017517, latency(ms): 136.7804575338959694 | 2022-04-30 02:09:12.862
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:09:12.882, Tesla V100-SXM2-32GB, 470.57.02, 47 %, 20 %, 32510 MiB, 29404 MiB, 3106 MiB
[rank:0] iter: 200/1100, loss: 0.4674114882946014, latency(ms): 101.9225480407476425 | 2022-04-30 02:09:23.054
[rank:0] iter: 300/1100, loss: 0.4618190824985504, latency(ms): 98.9796762913465500 | 2022-04-30 02:09:32.952
[rank:0] iter: 400/1100, loss: 0.4591855108737946, latency(ms): 100.0538479909300804 | 2022-04-30 02:09:42.957
[rank:0] iter: 500/1100, loss: 0.4563924670219421, latency(ms): 99.9763040617108345 | 2022-04-30 02:09:52.955
[rank:0] iter: 600/1100, loss: 0.4524722695350647, latency(ms): 100.0255566090345383 | 2022-04-30 02:10:02.958
[rank:0] iter: 700/1100, loss: 0.4467251896858215, latency(ms): 93.9425370469689369 | 2022-04-30 02:10:12.352
[rank:0] iter: 800/1100, loss: 0.4464100897312164, latency(ms): 93.9895234256982803 | 2022-04-30 02:10:21.751
[rank:0] iter: 900/1100, loss: 0.4456058144569397, latency(ms): 96.0640751197934151 | 2022-04-30 02:10:31.357
[rank:0] iter: 1000/1100, loss: 0.4451504647731781, latency(ms): 98.9246735721826553 | 2022-04-30 02:10:41.250
[rank:0] iter: 1100/1100, loss: 0.4449225962162018, latency(ms): 96.0446977242827415 | 2022-04-30 02:10:50.854