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 ...................................... 131072
  batch_size_per_proc ............................. 131072
  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: 0.4946961700916290, latency(ms): 220.2279852703213692 | 2022-04-03 01:41:24.486
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/03 01:41:24.503, Tesla V100-SXM2-32GB, 470.57.02, 83 %, 35 %, 32510 MiB, 28242 MiB, 4268 MiB
[rank:0] iter: 200/1100, loss: 0.4647310674190521, latency(ms): 171.9837891310453415 | 2022-04-03 01:41:41.684
[rank:0] iter: 300/1100, loss: 0.4580749869346619, latency(ms): 173.9937758445739746 | 2022-04-03 01:41:59.084
[rank:0] iter: 400/1100, loss: 0.4501821994781494, latency(ms): 154.8362097144126892 | 2022-04-03 01:42:14.567
[rank:0] iter: 500/1100, loss: 0.4485051035881042, latency(ms): 153.0598768219351768 | 2022-04-03 01:42:29.873
[rank:0] iter: 600/1100, loss: 0.4439891874790192, latency(ms): 154.0343130379915237 | 2022-04-03 01:42:45.277
[rank:0] iter: 700/1100, loss: 0.4374271333217621, latency(ms): 156.0760721191763878 | 2022-04-03 01:43:00.884
[rank:0] iter: 800/1100, loss: 0.4381194710731506, latency(ms): 159.8174318298697472 | 2022-04-03 01:43:16.866
[rank:0] iter: 900/1100, loss: 0.4305673539638519, latency(ms): 159.0093600749969482 | 2022-04-03 01:43:32.767
[rank:0] iter: 1000/1100, loss: 0.4263567328453064, latency(ms): 164.1289329528808594 | 2022-04-03 01:43:49.180
[rank:0] iter: 1100/1100, loss: 0.4275286197662354, latency(ms): 173.0171026289463043 | 2022-04-03 01:44:06.482