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: 0.4951168894767761, latency(ms): 236.1299443989992142 | 2022-04-22 12:01:42.481
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/22 12:01:43.173, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 27764 MiB, 4746 MiB
[rank:0] iter: 200/1100, loss: 0.4649785757064819, latency(ms): 184.4676768407225609 | 2022-04-22 12:02:00.927
[rank:0] iter: 300/1100, loss: 0.4582313299179077, latency(ms): 172.3231128603219986 | 2022-04-22 12:02:18.160
[rank:0] iter: 400/1100, loss: 0.4504278898239136, latency(ms): 174.0021282806992531 | 2022-04-22 12:02:35.560
[rank:0] iter: 500/1100, loss: 0.4486331045627594, latency(ms): 174.9612712860107422 | 2022-04-22 12:02:53.056
[rank:0] iter: 600/1100, loss: 0.4441379308700562, latency(ms): 175.1667858660221100 | 2022-04-22 12:03:10.573
[rank:0] iter: 700/1100, loss: 0.4376407563686371, latency(ms): 175.0137977674603462 | 2022-04-22 12:03:28.074
[rank:0] iter: 800/1100, loss: 0.4382936954498291, latency(ms): 176.9752439111471176 | 2022-04-22 12:03:45.772
[rank:0] iter: 900/1100, loss: 0.4308568537235260, latency(ms): 174.0472866967320442 | 2022-04-22 12:04:03.176
[rank:0] iter: 1000/1100, loss: 0.4266597330570221, latency(ms): 177.9760573431849480 | 2022-04-22 12:04:20.974
[rank:0] iter: 1100/1100, loss: 0.4277389943599701, latency(ms): 176.8304808065295219 | 2022-04-22 12:04:38.657