loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 ***************************************** Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. ***************************************** loaded library: loaded library: loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: loaded library: loaded library: loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1 ------------------------ arguments ------------------------ batch_size ...................................... 65536 batch_size_per_proc ............................. 8192 data_dir ........................................ /dataset/f9f659c5/wdl_ofrecord data_part_name_suffix_length .................... 5 data_part_num ................................... 256 dataset_format .................................. ofrecord ddp ............................................. True 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 .................................. eager 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: 0.5047271847724915, latency(ms): 86.0208693146705627 | 2022-04-29 02:19:45.589 timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 02:19:45.724, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 02:19:45.729, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.730, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 02:19:45.732, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.735, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB 2022/04/29 02:19:45.735, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.734, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.736, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.737, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.739, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 02:19:45.741, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.742, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 02:19:45.742, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB 2022/04/29 02:19:45.744, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB 2022/04/29 02:19:45.745, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB 2022/04/29 02:19:45.746, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.746, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.748, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.748, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.749, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.748, Tesla V100-SXM2-32GB, 470.57.02, 24 %, 11 %, 32510 MiB, 30118 MiB, 2392 MiB 2022/04/29 02:19:45.751, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.753, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.754, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.755, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB 2022/04/29 02:19:45.757, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.757, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.758, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.758, Tesla V100-SXM2-32GB, 470.57.02, 6 %, 4 %, 32510 MiB, 30138 MiB, 2372 MiB 2022/04/29 02:19:45.760, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.762, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.763, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.764, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.766, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.766, Tesla V100-SXM2-32GB, 470.57.02, 70 %, 26 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.767, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.768, Tesla V100-SXM2-32GB, 470.57.02, 35 %, 22 %, 32510 MiB, 30214 MiB, 2296 MiB 2022/04/29 02:19:45.769, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.771, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.772, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.773, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.776, Tesla V100-SXM2-32GB, 470.57.02, 70 %, 26 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.776, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.776, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.777, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 18 %, 32510 MiB, 30190 MiB, 2320 MiB 2022/04/29 02:19:45.779, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.781, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.782, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.783, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.785, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.786, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.787, Tesla V100-SXM2-32GB, 470.57.02, 17 %, 7 %, 32510 MiB, 30198 MiB, 2312 MiB 2022/04/29 02:19:45.789, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.790, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.791, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.793, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.795, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.796, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 17 %, 32510 MiB, 30130 MiB, 2380 MiB 2022/04/29 02:19:45.798, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.799, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.802, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.805, Tesla V100-SXM2-32GB, 470.57.02, 0 %, 0 %, 32510 MiB, 30074 MiB, 2436 MiB 2022/04/29 02:19:45.810, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB 2022/04/29 02:19:45.813, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 9 %, 32510 MiB, 30154 MiB, 2356 MiB [rank:0] iter: 200/1100, loss: 0.4710450768470764, latency(ms): 24.0367643535137177 | 2022-04-29 02:19:47.993 [rank:0] iter: 300/1100, loss: 0.4639663696289062, latency(ms): 21.3644026592373848 | 2022-04-29 02:19:50.129 [rank:0] iter: 400/1100, loss: 0.4605610966682434, latency(ms): 22.0015610381960869 | 2022-04-29 02:19:52.329 [rank:0] iter: 500/1100, loss: 0.4578646719455719, latency(ms): 21.7298460006713867 | 2022-04-29 02:19:54.502 [rank:0] iter: 600/1100, loss: 0.4530711770057678, latency(ms): 21.2055749446153641 | 2022-04-29 02:19:56.623 [rank:0] iter: 700/1100, loss: 0.4461924731731415, latency(ms): 20.8267747983336449 | 2022-04-29 02:19:58.706 [rank:0] iter: 800/1100, loss: 0.4460234940052032, latency(ms): 20.8092525973916054 | 2022-04-29 02:20:00.787 [rank:0] iter: 900/1100, loss: 0.4463414251804352, latency(ms): 21.0556147992610931 | 2022-04-29 02:20:02.892 [rank:0] iter: 1000/1100, loss: 0.4443537592887878, latency(ms): 21.1479892954230309 | 2022-04-29 02:20:05.007 [rank:0] iter: 1100/1100, loss: 0.4474797546863556, latency(ms): 21.4985000714659691 | 2022-04-29 02:20:07.157