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: 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/usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 W20220409 02:02:52.805091 6894 rpc_client.cpp:190] LoadServer 10.7.208.28 Failed at 0 times error_code 14 error_message failed to connect to all addresses W20220409 02:02:52.807613 6892 rpc_client.cpp:190] LoadServer 10.7.208.28 Failed at 0 times error_code 14 error_message failed to connect to all addresses W20220409 02:02:52.810293 6893 rpc_client.cpp:190] LoadServer 10.7.208.28 Failed at 0 times error_code 14 error_message failed to connect to all addresses ------------------------ arguments ------------------------ batches_per_epoch ............................... 625 channel_last .................................... False ddp ............................................. True exit_num ........................................ 300 fuse_bn_add_relu ................................ False fuse_bn_relu .................................... False gpu_stat_file ................................... None grad_clipping ................................... 0.0 graph ........................................... False label_smoothing ................................. 0.1 learning_rate ................................... 2.048 legacy_init ..................................... False load_path ....................................... None lr_decay_type ................................... cosine metric_local .................................... True metric_train_acc ................................ True momentum ........................................ 0.875 nccl_fusion_max_ops ............................. 24 nccl_fusion_threshold_mb ........................ 16 num_classes ..................................... 1000 num_devices_per_node ............................ 8 num_epochs ...................................... 1 num_nodes ....................................... 1 ofrecord_part_num ............................... 256 ofrecord_path ................................... /dataset/79846248 print_interval .................................. 100 print_timestamp ................................. False samples_per_epoch ............................... 1281167 save_init ....................................... False save_path ....................................... None scale_grad ...................................... False skip_eval ....................................... True synthetic_data .................................. False total_batches ................................... -1 train_batch_size ................................ 256 train_global_batch_size ......................... 2048 use_fp16 ........................................ False use_gpu_decode .................................. False val_batch_size .................................. 50 val_batches_per_epoch ........................... 125 val_global_batch_size ........................... 400 val_samples_per_epoch ........................... 50000 warmup_epochs ................................... 5 weight_decay .................................... 3.0517578125e-05 zero_init_residual .............................. True -------------------- end of arguments --------------------- ***** Model Init ***** ***** Model Init Finish, time escapled: 2.69987 s ***** W20220409 02:03:14.811733 7384 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.806540 7792 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.813154 7511 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.814667 7588 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.804136 7368 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.810811 7767 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.814780 7117 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 W20220409 02:03:14.811722 7252 cudnn_conv_util.cpp:102] Currently available alogrithm (algo=0, require memory=0, idx=1) meeting requirments (max_workspace_size=1073741824, determinism=0) is not fastest. Fastest algorithm (3) requires memory 1520566288 [rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86741, lr: 0.000000, top1: 0.00117, throughput: 292.35 | 2022-04-09 02:04:35.582 [rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86739, lr: 0.000000, top1: 0.00133, throughput: 292.14 | 2022-04-09 02:04:35.615 [rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86743, lr: 0.000000, top1: 0.00117, throughput: 292.37 | 2022-04-09 02:04:35.626 [rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86747, lr: 0.000000, top1: 0.00094, throughput: 292.17 | 2022-04-09 02:04:35.627 [rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86731, lr: 0.000000, top1: 0.00113, throughput: 292.27 | 2022-04-09 02:04:35.629 [rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86756, lr: 0.000000, top1: 0.00102, throughput: 292.14 | 2022-04-09 02:04:35.640 [rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86748, lr: 0.000000, top1: 0.00117, throughput: 292.23 | 2022-04-09 02:04:35.647 [rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86775, lr: 0.000000, top1: 0.00102, throughput: 291.84 | 2022-04-09 02:04:35.683 timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/09 02:04:35.732, Tesla V100-SXM2-32GB, 470.57.02, 21 %, 16 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.737, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 32 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.741, Tesla V100-SXM2-32GB, 470.57.02, 62 %, 46 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:35.747, Tesla V100-SXM2-32GB, 470.57.02, 40 %, 7 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:35.752, Tesla V100-SXM2-32GB, 470.57.02, 67 %, 37 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:35.756, Tesla V100-SXM2-32GB, 470.57.02, 43 %, 31 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:35.759, Tesla V100-SXM2-32GB, 470.57.02, 32 %, 18 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:35.764, Tesla V100-SXM2-32GB, 470.57.02, 45 %, 20 %, 32510 MiB, 5220 MiB, 27290 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] timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/09 02:04:35.827, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 37 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.828, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 37 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.828, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 37 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.834, Tesla V100-SXM2-32GB, 470.57.02, 53 %, 13 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.835, Tesla V100-SXM2-32GB, 470.57.02, 53 %, 13 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.839, Tesla V100-SXM2-32GB, 470.57.02, 53 %, 13 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.851, Tesla V100-SXM2-32GB, 470.57.02, 79 %, 41 %, 32510 MiB, 5280 MiB, 27230 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/09 02:04:35.851, Tesla V100-SXM2-32GB, 470.57.02, 79 %, 41 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:35.852, Tesla V100-SXM2-32GB, 470.57.02, 79 %, 41 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:35.861, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 76 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:35.862, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 76 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:35.862, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 37 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.863, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 76 %, 32510 MiB, 5256 MiB, 27254 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/09 02:04:35.870, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:35.871, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:35.871, Tesla V100-SXM2-32GB, 470.57.02, 53 %, 13 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.872, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 50 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:35.873, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 37 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.877, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 38 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:35.879, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 38 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:35.879, Tesla V100-SXM2-32GB, 470.57.02, 79 %, 41 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:35.891, Tesla V100-SXM2-32GB, 470.57.02, 73 %, 38 %, 32510 MiB, 5196 MiB, 27314 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/09 02:04:35.893, Tesla V100-SXM2-32GB, 470.57.02, 53 %, 12 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.896, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 53 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:35.916, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 53 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:35.920, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:35.922, Tesla V100-SXM2-32GB, 470.57.02, 89 %, 53 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:35.944, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 36 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:35.954, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:35.963, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB 2022/04/09 02:04:35.976, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB 2022/04/09 02:04:35.976, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 68 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:35.978, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB 2022/04/09 02:04:35.979, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 81 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:35.983, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:36.014, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:36.015, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:36.025, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 68 %, 32510 MiB, 5264 MiB, 27246 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/09 02:04:36.035, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:36.037, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:36.038, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:36.040, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 71 %, 32510 MiB, 5184 MiB, 27326 MiB 2022/04/09 02:04:36.055, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB 2022/04/09 02:04:36.058, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 68 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:36.059, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:36.062, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 81 %, 32510 MiB, 5204 MiB, 27306 MiB 2022/04/09 02:04:36.073, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:36.074, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB 2022/04/09 02:04:36.080, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5280 MiB, 27230 MiB 2022/04/09 02:04:36.091, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:36.094, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 5256 MiB, 27254 MiB 2022/04/09 02:04:36.096, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB 2022/04/09 02:04:36.098, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 68 %, 32510 MiB, 5264 MiB, 27246 MiB 2022/04/09 02:04:36.102, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 5196 MiB, 27314 MiB 2022/04/09 02:04:36.112, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5140 MiB, 27370 MiB 2022/04/09 02:04:36.123, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 5220 MiB, 27290 MiB [rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86739, lr: 0.000000, top1: 0.00078, throughput: 319.09 | 2022-04-09 02:05:55.858 [rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86751, lr: 0.000000, top1: 0.00121, throughput: 319.01 | 2022-04-09 02:05:55.863 [rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86754, lr: 0.000000, top1: 0.00109, throughput: 319.02 | 2022-04-09 02:05:55.871 [rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86747, lr: 0.000000, top1: 0.00098, throughput: 319.02 | 2022-04-09 02:05:55.873 [rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86765, lr: 0.000000, top1: 0.00098, throughput: 318.77 | 2022-04-09 02:05:55.890 [rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86741, lr: 0.000000, top1: 0.00059, throughput: 319.00 | 2022-04-09 02:05:55.897 [rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86764, lr: 0.000000, top1: 0.00102, throughput: 318.93 | 2022-04-09 02:05:55.908 [rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86772, lr: 0.000000, top1: 0.00113, throughput: 318.90 | 2022-04-09 02:05:55.958 [rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86758, lr: 0.000000, top1: 0.00109, throughput: 321.06 | 2022-04-09 02:07:15.595 [rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86753, lr: 0.000000, top1: 0.00070, throughput: 321.04 | 2022-04-09 02:07:15.603 [rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86738, lr: 0.000000, top1: 0.00094, throughput: 321.03 | 2022-04-09 02:07:15.616 [rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86760, lr: 0.000000, top1: 0.00109, throughput: 321.16 | 2022-04-09 02:07:15.619 [rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86767, lr: 0.000000, top1: 0.00102, throughput: 321.07 | 2022-04-09 02:07:15.625 [rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86762, lr: 0.000000, top1: 0.00074, throughput: 321.04 | 2022-04-09 02:07:15.637 [rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86749, lr: 0.000000, top1: 0.00117, throughput: 320.81 | 2022-04-09 02:07:15.669 [rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86728, lr: 0.000000, top1: 0.00109, throughput: 320.91 | 2022-04-09 02:07:15.730