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 W20220429 01:47:41.673611 3667 rpc_client.cpp:190] LoadServer 10.7.155.237 Failed at 0 times error_code 14 error_message failed to connect to all addresses ------------------------ arguments ------------------------ batches_per_epoch ............................... 312 channel_last .................................... True ddp ............................................. False exit_num ........................................ 300 fuse_bn_add_relu ................................ True fuse_bn_relu .................................... True gpu_stat_file ................................... None grad_clipping ................................... 0.0 graph ........................................... True label_smoothing ................................. 0.1 learning_rate ................................... 4.096 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 ...................................... True skip_eval ....................................... True synthetic_data .................................. False total_batches ................................... -1 train_batch_size ................................ 512 train_global_batch_size ......................... 4096 use_fp16 ........................................ True 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: 3.06434 s ***** [rank:1] [train], epoch: 0/1, iter: 100/312, loss: 0.86735, top1: 0.00109, throughput: 454.83 | 2022-04-29 01:49:49.670 [rank:0] [train], epoch: 0/1, iter: 100/312, loss: 0.86755, top1: 0.00135, throughput: 454.80 | 2022-04-29 01:49:49.674 [rank:6] [train], epoch: 0/1, iter: 100/312, loss: 0.86749, top1: 0.00113, throughput: 454.83 | 2022-04-29 01:49:49.673 [rank:3] [train], epoch: 0/1, iter: 100/312, loss: 0.86755, top1: 0.00102, throughput: 454.83 | 2022-04-29 01:49:49.671 [rank:5] [train], epoch: 0/1, iter: 100/312, loss: 0.86760, top1: 0.00123, throughput: 454.82 | 2022-04-29 01:49:49.673 [rank:2] [train], epoch: 0/1, iter: 100/312, loss: 0.86747, top1: 0.00117, throughput: 454.80 | 2022-04-29 01:49:49.674 [rank:7] [train], epoch: 0/1, iter: 100/312, loss: 0.86722, top1: 0.00123, throughput: 454.83 | 2022-04-29 01:49:49.673 [rank:4] [train], epoch: 0/1, iter: 100/312, loss: 0.86763, top1: 0.00104, throughput: 454.82 | 2022-04-29 01:49:49.675 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] timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 01:49:50.008, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 90 %, 32510 MiB, 8561 MiB, 23949 MiB 2022/04/29 01:49:50.009, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 90 %, 32510 MiB, 8561 MiB, 23949 MiB 2022/04/29 01:49:50.010, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 01:49:50.026, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB 2022/04/29 01:49:50.030, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.031, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.052, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.053, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/04/29 01:49:50.055, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 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 01:49:50.068, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.069, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.070, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.072, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.073, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.073, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB 2022/04/29 01:49:50.074, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB 2022/04/29 01:49:50.082, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.083, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.082, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB 2022/04/29 01:49:50.084, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.085, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.086, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.087, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.089, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.090, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.092, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.092, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 93 %, 32510 MiB, 8570 MiB, 23940 MiB 2022/04/29 01:49:50.093, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.095, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.102, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.102, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.109, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.113, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 92 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.113, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 92 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.114, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8720 MiB, 23790 MiB 2022/04/29 01:49:50.114, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 92 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.122, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.124, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.124, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.126, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.128, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.129, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.129, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 67 %, 32510 MiB, 8694 MiB, 23816 MiB 2022/04/29 01:49:50.130, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.133, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.134, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.137, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.142, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.144, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.145, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.145, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 81 %, 32510 MiB, 8690 MiB, 23820 MiB 2022/04/29 01:49:50.146, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.147, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.153, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.154, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.160, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.163, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8554 MiB, 23956 MiB 2022/04/29 01:49:50.165, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.167, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.169, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.171, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 70 %, 32510 MiB, 8442 MiB, 24068 MiB 2022/04/29 01:49:50.174, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.176, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB 2022/04/29 01:49:50.180, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 56 %, 32510 MiB, 8622 MiB, 23888 MiB [rank:7] [train], epoch: 0/1, iter: 200/312, loss: 0.86746, top1: 0.00121, throughput: 1339.80 | 2022-04-29 01:50:27.887 [rank:5] [train], epoch: 0/1, iter: 200/312, loss: 0.86743, top1: 0.00092, throughput: 1339.78 | 2022-04-29 01:50:27.888 [rank:6] [train], epoch: 0/1, iter: 200/312, loss: 0.86751, top1: 0.00096, throughput: 1339.79 | 2022-04-29 01:50:27.888 [rank:2] [train], epoch: 0/1, iter: 200/312, loss: 0.86741, top1: 0.00104, throughput: 1339.75 | 2022-04-29 01:50:27.890 [rank:1] [train], epoch: 0/1, iter: 200/312, loss: 0.86748, top1: 0.00115, throughput: 1339.67 | 2022-04-29 01:50:27.888 [rank:0] [train], epoch: 0/1, iter: 200/312, loss: 0.86737, top1: 0.00115, throughput: 1339.81 | 2022-04-29 01:50:27.888 [rank:3] [train], epoch: 0/1, iter: 200/312, loss: 0.86758, top1: 0.00131, throughput: 1339.72 | 2022-04-29 01:50:27.888 [rank:4] [train], epoch: 0/1, iter: 200/312, loss: 0.86760, top1: 0.00107, throughput: 1339.78 | 2022-04-29 01:50:27.890 [rank:7] [train], epoch: 0/1, iter: 300/312, loss: 0.86732, top1: 0.00084, throughput: 1343.22 | 2022-04-29 01:51:06.005 [rank:1] [train], epoch: 0/1, iter: 300/312, loss: 0.86754, top1: 0.00127, throughput: 1343.34 | 2022-04-29 01:51:06.002 [rank:3] [train], epoch: 0/1, iter: 300/312, loss: 0.86736, top1: 0.00102, throughput: 1343.28 | 2022-04-29 01:51:06.004 [rank:0] [train], epoch: 0/1, iter: 300/312, loss: 0.86753, top1: 0.00094, throughput: 1343.18 | 2022-04-29 01:51:06.006 [rank:5] [train], epoch: 0/1, iter: 300/312, loss: 0.86751, top1: 0.00125, throughput: 1343.12 | 2022-04-29 01:51:06.009 [rank:4] [train], epoch: 0/1, iter: 300/312, loss: 0.86727, top1: 0.00098, throughput: 1343.28 | 2022-04-29 01:51:06.006 [rank:2] [train], epoch: 0/1, iter: 300/312, loss: 0.86756, top1: 0.00133, throughput: 1343.26 | 2022-04-29 01:51:06.006 [rank:6] [train], epoch: 0/1, iter: 300/312, loss: 0.86755, top1: 0.00092, throughput: 1343.02 | 2022-04-29 01:51:06.011