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: 0.4951139688491821, latency(ms): 229.0780197083950043 | 2022-04-05 01:44:00.068
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/05 01:44:00.090, Tesla V100-SXM2-32GB, 470.57.02, 63 %, 26 %, 32510 MiB, 28242 MiB, 4268 MiB
[rank:0] iter: 200/1100, loss: 0.4649443924427032, latency(ms): 173.1481068208813667 | 2022-04-05 01:44:17.383
[rank:0] iter: 300/1100, loss: 0.4582479596138000, latency(ms): 159.8178940266370773 | 2022-04-05 01:44:33.365
[rank:0] iter: 400/1100, loss: 0.4504209160804749, latency(ms): 150.1754613965749741 | 2022-04-05 01:44:48.382
[rank:0] iter: 500/1100, loss: 0.4485841095447540, latency(ms): 152.9047063738107681 | 2022-04-05 01:45:03.673
[rank:0] iter: 600/1100, loss: 0.4441446065902710, latency(ms): 154.6259986236691475 | 2022-04-05 01:45:19.135
[rank:0] iter: 700/1100, loss: 0.4376365244388580, latency(ms): 158.2740684598684311 | 2022-04-05 01:45:34.963
[rank:0] iter: 800/1100, loss: 0.4382947981357574, latency(ms): 157.9934443905949593 | 2022-04-05 01:45:50.762
[rank:0] iter: 900/1100, loss: 0.4307458996772766, latency(ms): 154.6891175210475922 | 2022-04-05 01:46:06.231
[rank:0] iter: 1000/1100, loss: 0.4265954196453094, latency(ms): 175.3262706845998764 | 2022-04-05 01:46:23.764
[rank:0] iter: 1100/1100, loss: 0.4277782142162323, latency(ms): 169.1384132206439972 | 2022-04-05 01:46:40.677