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: /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: /usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: loaded library: /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 ------------------------ arguments ------------------------ batches_per_epoch ............................... 625 channel_last .................................... False 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 ................................... 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 ...................................... True 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: 3.10015 s ***** [rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86730, top1: 0.00125, throughput: 275.15 | 2022-05-22 18:55:35.993 [rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86740, top1: 0.00133, throughput: 275.15 | 2022-05-22 18:55:35.993 [rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86754, top1: 0.00145, throughput: 275.17 | 2022-05-22 18:55:35.994 [rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86730, top1: 0.00105, throughput: 275.15 | 2022-05-22 18:55:35.993 [rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86761, top1: 0.00148, throughput: 275.16 | 2022-05-22 18:55:35.996 [rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86727, top1: 0.00152, throughput: 275.15 | 2022-05-22 18:55:35.993 [rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86744, top1: 0.00109, throughput: 275.15 | 2022-05-22 18:55:35.993 [rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86737, top1: 0.00137, throughput: 275.16 | 2022-05-22 18:55:35.995 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] 2022/05/22 18:55:36.308, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB 2022/05/22 18:55:36.310, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 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] 2022/05/22 18:55:36.313, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/05/22 18:55:36.315, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.317, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.318, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/05/22 18:55:36.321, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.321, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/05/22 18:55:36.323, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.322, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB 2022/05/22 18:55:36.325, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.328, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.329, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.329, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.328, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB 2022/05/22 18:55:36.329, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8516 MiB, 23994 MiB 2022/05/22 18:55:36.330, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.331, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.334, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.337, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.337, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.338, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.338, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.339, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8470 MiB, 24040 MiB 2022/05/22 18:55:36.341, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.342, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.345, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.348, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.349, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.349, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.349, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.350, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8606 MiB, 23904 MiB 2022/05/22 18:55:36.351, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.351, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.354, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.356, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.357, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.357, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.358, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.359, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8604 MiB, 23906 MiB 2022/05/22 18:55:36.362, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.362, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.365, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.368, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.369, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.369, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.369, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.370, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8646 MiB, 23864 MiB 2022/05/22 18:55:36.371, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.371, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.374, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.377, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.378, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.378, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.378, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.380, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8488 MiB, 24022 MiB 2022/05/22 18:55:36.380, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.386, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.386, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.387, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.388, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8362 MiB, 24148 MiB 2022/05/22 18:55:36.393, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.399, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8506 MiB, 24004 MiB 2022/05/22 18:55:36.400, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8506 MiB, 24004 MiB [rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86754, top1: 0.00105, throughput: 380.19 | 2022-05-22 18:56:43.328 [rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86726, top1: 0.00086, throughput: 380.19 | 2022-05-22 18:56:43.328 [rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86738, top1: 0.00121, throughput: 380.18 | 2022-05-22 18:56:43.329 [rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86737, top1: 0.00137, throughput: 380.18 | 2022-05-22 18:56:43.330 [rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86743, top1: 0.00145, throughput: 380.18 | 2022-05-22 18:56:43.330 [rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86746, top1: 0.00125, throughput: 380.18 | 2022-05-22 18:56:43.329 [rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86745, top1: 0.00113, throughput: 380.19 | 2022-05-22 18:56:43.330 [rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86739, top1: 0.00156, throughput: 380.18 | 2022-05-22 18:56:43.332 [rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86763, top1: 0.00133, throughput: 379.59 | 2022-05-22 18:57:50.770 [rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86724, top1: 0.00105, throughput: 379.59 | 2022-05-22 18:57:50.769 [rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86727, top1: 0.00121, throughput: 379.60 | 2022-05-22 18:57:50.769 [rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86713, top1: 0.00168, throughput: 379.59 | 2022-05-22 18:57:50.771 [rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86730, top1: 0.00102, throughput: 379.58 | 2022-05-22 18:57:50.771 [rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86711, top1: 0.00160, throughput: 379.59 | 2022-05-22 18:57:50.771 [rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86729, top1: 0.00117, throughput: 379.59 | 2022-05-22 18:57:50.772 [rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86723, top1: 0.00094, throughput: 379.58 | 2022-05-22 18:57:50.773