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: 0.4947637617588043, latency(ms): 225.2170887216925621 | 2022-04-08 01:42:48.889
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/08 01:42:48.907, Tesla V100-SXM2-32GB, 470.57.02, 45 %, 23 %, 32510 MiB, 28242 MiB, 4268 MiB
[rank:0] iter: 200/1100, loss: 0.4646290242671967, latency(ms): 172.9650761932134628 | 2022-04-08 01:43:06.186
[rank:0] iter: 300/1100, loss: 0.4578996300697327, latency(ms): 170.7755450159311295 | 2022-04-08 01:43:23.263
[rank:0] iter: 400/1100, loss: 0.4500375390052795, latency(ms): 156.0072856023907661 | 2022-04-08 01:43:38.864
[rank:0] iter: 500/1100, loss: 0.4483630359172821, latency(ms): 154.2298819869756699 | 2022-04-08 01:43:54.287
[rank:0] iter: 600/1100, loss: 0.4438415169715881, latency(ms): 158.0012786388397217 | 2022-04-08 01:44:10.087
[rank:0] iter: 700/1100, loss: 0.4372779130935669, latency(ms): 162.7409847825765610 | 2022-04-08 01:44:26.361
[rank:0] iter: 800/1100, loss: 0.4379817545413971, latency(ms): 162.0293151214718819 | 2022-04-08 01:44:42.564
[rank:0] iter: 900/1100, loss: 0.4305220544338226, latency(ms): 163.2349459826946259 | 2022-04-08 01:44:58.888
[rank:0] iter: 1000/1100, loss: 0.4264397919178009, latency(ms): 171.7662369087338448 | 2022-04-08 01:45:16.064
[rank:0] iter: 1100/1100, loss: 0.4275740683078766, latency(ms): 172.6651822030544281 | 2022-04-08 01:45:33.331