loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1 ------------------------ arguments ------------------------ batches_per_epoch ............................... 2502 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 ................................... 0.512 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 ............................ 1 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 ......................... 512 use_fp16 ........................................ True use_gpu_decode .................................. False val_batch_size .................................. 50 val_batches_per_epoch ........................... 1000 val_global_batch_size ........................... 50 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: 1.71355 s ***** [rank:0] [train], epoch: 0/1, iter: 100/2502, loss: 6.93612, top1: 0.00135, throughput: 805.79 | 2022-05-12 01:49:44.142 timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB] 2022/05/12 01:49:44.168, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 75 %, 32510 MiB, 9604 MiB, 22906 MiB [rank:0] [train], epoch: 0/1, iter: 200/2502, loss: 6.93889, top1: 0.00127, throughput: 1515.18 | 2022-05-12 01:50:17.933 [rank:0] [train], epoch: 0/1, iter: 300/2502, loss: 6.93766, top1: 0.00125, throughput: 1513.49 | 2022-05-12 01:50:51.762