[2026-06-09 14:22:43,613 INFO train.py line 139 726] => Loading config ... [2026-06-09 14:22:43,613 INFO train.py line 141 726] Save path: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609 [2026-06-09 14:22:44,765 INFO train.py line 142 726] Config: weight = 'exp/s3dis/bidit_pycut_w1a1_stage3_sem_strong_protected_20260604/model/model_best.pth' resume = False evaluate = True test_only = False seed = 25326354 save_path = 'exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609' num_worker = 0 batch_size = 4 batch_size_val = 2 batch_size_test = 2 epoch = 20 eval_epoch = 2 sync_bn = False enable_amp = True empty_cache = False find_unused_parameters = True mix_prob = 0.8 param_dicts = [ dict(keyword='block', lr=2e-06), dict(keyword='superpoint_after_pool', lr=0.0002) ] hooks = [ dict(type='CheckpointLoader'), dict(type='IterationTimer', warmup_iter=2), dict(type='InformationWriter'), dict(type='SemSegEvaluator'), dict(type='CheckpointSaver', save_freq=1, save_step_freq=50), dict(type='PreciseEvaluator', test_last=False) ] train = dict(type='DefaultTrainer') test = dict(type='SemSegTester', verbose=True) model = dict( type='DefaultSegmentorV2', num_classes=13, backbone_out_channels=64, backbone=dict( type='PT-v3m1', in_channels=6, order=['z', 'z-trans', 'hilbert', 'hilbert-trans'], stride=(2, 2, 2, 2), enc_depths=(2, 2, 2, 6, 2), enc_channels=(32, 64, 128, 256, 512), enc_num_head=(2, 4, 8, 16, 32), enc_patch_size=(128, 128, 128, 128, 128), dec_depths=(2, 2, 2, 2), dec_channels=(64, 64, 128, 256), dec_num_head=(4, 4, 8, 16), dec_patch_size=(128, 128, 128, 128), mlp_ratio=4, qkv_bias=True, qk_scale=None, attn_drop=0.0, proj_drop=0.0, drop_path=0.3, shuffle_orders=True, pre_norm=True, enable_rpe=True, enable_flash=False, upcast_attention=True, upcast_softmax=True, cls_mode=False, pdnorm_bn=False, pdnorm_ln=False, pdnorm_decouple=True, pdnorm_adaptive=False, pdnorm_affine=True, pdnorm_conditions=('ScanNet', 'S3DIS', 'Structured3D'), enable_superpoint_after_pool=True, superpoint_reduce='mean', superpoint_residual=True, superpoint_after_pool_norm=False, superpoint_after_pool_zero_init=True), criteria=[ dict( type='CrossEntropyLoss', weight=[ 0.65, 0.65, 0.85, 8.0, 5.0, 2.9, 4.2, 0.95, 0.85, 1.6, 1.1, 1.7, 1.45 ], loss_weight=1.0, ignore_index=-1), dict( type='LovaszLoss', mode='multiclass', loss_weight=1.0, ignore_index=-1) ], superpoint_contrastive_weight=0.01, superpoint_contrastive_temperature=0.1, superpoint_contrastive_max_samples=2048, superpoint_contrastive_max_points_per_superpoint=4, superpoint_contrastive_min_points_per_superpoint=2, superpoint_edge_aux_weight=0.2, superpoint_edge_boost=3.0, semantic_contrastive_weight=0.01, semantic_contrastive_temperature=0.1, semantic_contrastive_max_samples=2048, semantic_contrastive_max_points_per_class=16, semantic_contrastive_min_points_per_class=2) optimizer = dict(type='AdamW', lr=2e-05, weight_decay=0.05) scheduler = dict( type='OneCycleLR', max_lr=[2e-05, 2e-06, 0.0002], pct_start=0.05, anneal_strategy='cos', div_factor=10.0, final_div_factor=1000.0) dataset_type = 'S3DISDataset' data_root = '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958' data = dict( num_classes=13, ignore_index=-1, names=[ 'ceiling', 'floor', 'wall', 'beam', 'column', 'window', 'door', 'table', 'chair', 'sofa', 'bookcase', 'board', 'clutter' ], train=dict( type='S3DISDataset', split=('Area_1', 'Area_2', 'Area_3', 'Area_4', 'Area_6'), data_root= '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958', transform=[ dict(type='CenterShift', apply_z=True), dict( type='RandomDropout', dropout_ratio=0.2, dropout_application_ratio=0.2), dict( type='RandomRotate', angle=[-1, 1], axis='z', center=[0, 0, 0], p=0.5), dict( type='RandomRotate', angle=[-0.015625, 0.015625], axis='x', p=0.5), dict( type='RandomRotate', angle=[-0.015625, 0.015625], axis='y', p=0.5), dict(type='RandomScale', scale=[0.9, 1.1]), dict(type='RandomFlip', p=0.5), dict(type='RandomJitter', sigma=0.005, clip=0.02), dict(type='ChromaticAutoContrast', p=0.2, blend_factor=None), dict(type='ChromaticTranslation', p=0.95, ratio=0.05), dict(type='ChromaticJitter', p=0.95, std=0.05), dict( type='GridSample', grid_size=0.02, hash_type='fnv', mode='train', return_grid_coord=True), dict(type='SphereCrop', sample_rate=0.6, mode='random'), dict(type='SphereCrop', point_max=204800, mode='random'), dict(type='CenterShift', apply_z=False), dict(type='NormalizeColor'), dict(type='ToTensor'), dict( type='Collect', keys=('coord', 'grid_coord', 'segment', 'superpoint'), feat_keys=('color', 'normal')) ], test_mode=False, loop=10), val=dict( type='S3DISDataset', split='Area_5', data_root= '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958', transform=[ dict(type='CenterShift', apply_z=True), dict( type='Copy', keys_dict=dict(coord='origin_coord', segment='origin_segment')), dict( type='GridSample', grid_size=0.02, hash_type='fnv', mode='train', return_grid_coord=True), dict(type='CenterShift', apply_z=False), dict(type='NormalizeColor'), dict(type='ToTensor'), dict( type='Collect', keys=('coord', 'grid_coord', 'origin_coord', 'segment', 'origin_segment', 'superpoint'), offset_keys_dict=dict( offset='coord', origin_offset='origin_coord'), feat_keys=('color', 'normal')) ], test_mode=False), test=dict( type='S3DISDataset', split='Area_5', data_root= '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958', transform=[ dict(type='CenterShift', apply_z=True), dict(type='NormalizeColor') ], test_mode=True, test_cfg=dict( voxelize=dict( type='GridSample', grid_size=0.02, hash_type='fnv', mode='test', return_grid_coord=True), crop=None, post_transform=[ dict(type='CenterShift', apply_z=False), dict(type='ToTensor'), dict( type='Collect', keys=('coord', 'grid_coord', 'index', 'superpoint'), feat_keys=('color', 'normal')) ], aug_transform=[[{ 'type': 'RandomScale', 'scale': [0.9, 0.9] }], [{ 'type': 'RandomScale', 'scale': [0.95, 0.95] }], [{ 'type': 'RandomScale', 'scale': [1, 1] }], [{ 'type': 'RandomScale', 'scale': [1.05, 1.05] }], [{ 'type': 'RandomScale', 'scale': [1.1, 1.1] }], [{ 'type': 'RandomScale', 'scale': [0.9, 0.9] }, { 'type': 'RandomFlip', 'p': 1 }], [{ 'type': 'RandomScale', 'scale': [0.95, 0.95] }, { 'type': 'RandomFlip', 'p': 1 }], [{ 'type': 'RandomScale', 'scale': [1, 1] }, { 'type': 'RandomFlip', 'p': 1 }], [{ 'type': 'RandomScale', 'scale': [1.05, 1.05] }, { 'type': 'RandomFlip', 'p': 1 }], [{ 'type': 'RandomScale', 'scale': [1.1, 1.1] }, { 'type': 'RandomFlip', 'p': 1 }]]))) quantize = False enable_wandb = False amp_dtype = 'float16' clip_grad = None empty_cache_per_epoch = False num_worker_per_gpu = 0 batch_size_per_gpu = 4 batch_size_val_per_gpu = 2 batch_size_test_per_gpu = 2 [2026-06-09 14:22:44,766 INFO train.py line 143 726] => Building model ... [2026-06-09 14:22:47,927 INFO train.py line 266 726] Num params: 46539695 [2026-06-09 14:22:47,978 INFO train.py line 145 726] => Building writer ... [2026-06-09 14:22:47,980 INFO train.py line 276 726] Tensorboard writer logging dir: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609 [2026-06-09 14:22:47,980 INFO train.py line 147 726] => Building train dataset & dataloader ... [2026-06-09 14:22:47,982 INFO defaults.py line 120 726] [INFO] Listing scenes from directory: /map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_1 [2026-06-09 14:22:47,982 INFO defaults.py line 120 726] [INFO] Listing scenes from directory: /map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_2 [2026-06-09 14:22:47,983 INFO defaults.py line 120 726] [INFO] Listing scenes from directory: /map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_3 [2026-06-09 14:22:47,983 INFO defaults.py line 120 726] [INFO] Listing scenes from directory: /map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_4 [2026-06-09 14:22:47,984 INFO defaults.py line 120 726] [INFO] Listing scenes from directory: /map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_6 [2026-06-09 14:22:47,984 INFO defaults.py line 72 726] Totally 204 x 10 samples in s3dis_official_pycut_20260501_185958 ('Area_1', 'Area_2', 'Area_3', 'Area_4', 'Area_6') set. [2026-06-09 14:22:47,984 INFO defaults.py line 79 726] [DEBUG] First 3 data paths: ['/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_1/office_9', '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_1/office_30', '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_1/hallway_4'] [2026-06-09 14:22:47,985 INFO train.py line 149 726] => Building val dataset & dataloader ... [2026-06-09 14:22:47,985 INFO defaults.py line 120 726] [INFO] Listing scenes from directory: /map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_5 [2026-06-09 14:22:47,985 INFO defaults.py line 72 726] Totally 68 x 1 samples in s3dis_official_pycut_20260501_185958 Area_5 set. [2026-06-09 14:22:47,986 INFO defaults.py line 79 726] [DEBUG] First 3 data paths: ['/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_5/office_9', '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_5/WC_2', '/map-vepfs/haozhe/PAMI_superpoint/data/s3dis_official_pycut_20260501_185958/Area_5/office_30'] [2026-06-09 14:22:47,986 INFO train.py line 151 726] => Building optimize, scheduler, scaler(amp) ... [2026-06-09 14:22:47,989 INFO optimizer.py line 56 726] Params Group 1 - lr: 2e-05; Params: ['seg_head.weight', 'seg_head.bias', 'backbone.embedding.stem.conv.weight', 'backbone.embedding.stem.norm.weight', 'backbone.embedding.stem.norm.bias', 'backbone.enc.enc1.down.proj.weight', 'backbone.enc.enc1.down.proj.bias', 'backbone.enc.enc1.down.norm.0.weight', 'backbone.enc.enc1.down.norm.0.bias', 'backbone.enc.enc2.down.proj.weight', 'backbone.enc.enc2.down.proj.bias', 'backbone.enc.enc2.down.norm.0.weight', 'backbone.enc.enc2.down.norm.0.bias', 'backbone.enc.enc3.down.proj.weight', 'backbone.enc.enc3.down.proj.bias', 'backbone.enc.enc3.down.norm.0.weight', 'backbone.enc.enc3.down.norm.0.bias', 'backbone.enc.enc4.down.proj.weight', 'backbone.enc.enc4.down.proj.bias', 'backbone.enc.enc4.down.norm.0.weight', 'backbone.enc.enc4.down.norm.0.bias', 'backbone.dec.dec3.up.proj.0.weight', 'backbone.dec.dec3.up.proj.0.bias', 'backbone.dec.dec3.up.proj.1.weight', 'backbone.dec.dec3.up.proj.1.bias', 'backbone.dec.dec3.up.proj_skip.0.weight', 'backbone.dec.dec3.up.proj_skip.0.bias', 'backbone.dec.dec3.up.proj_skip.1.weight', 'backbone.dec.dec3.up.proj_skip.1.bias', 'backbone.dec.dec2.up.proj.0.weight', 'backbone.dec.dec2.up.proj.0.bias', 'backbone.dec.dec2.up.proj.1.weight', 'backbone.dec.dec2.up.proj.1.bias', 'backbone.dec.dec2.up.proj_skip.0.weight', 'backbone.dec.dec2.up.proj_skip.0.bias', 'backbone.dec.dec2.up.proj_skip.1.weight', 'backbone.dec.dec2.up.proj_skip.1.bias', 'backbone.dec.dec1.up.proj.0.weight', 'backbone.dec.dec1.up.proj.0.bias', 'backbone.dec.dec1.up.proj.1.weight', 'backbone.dec.dec1.up.proj.1.bias', 'backbone.dec.dec1.up.proj_skip.0.weight', 'backbone.dec.dec1.up.proj_skip.0.bias', 'backbone.dec.dec1.up.proj_skip.1.weight', 'backbone.dec.dec1.up.proj_skip.1.bias', 'backbone.dec.dec0.up.proj.0.weight', 'backbone.dec.dec0.up.proj.0.bias', 'backbone.dec.dec0.up.proj.1.weight', 'backbone.dec.dec0.up.proj.1.bias', 'backbone.dec.dec0.up.proj_skip.0.weight', 'backbone.dec.dec0.up.proj_skip.0.bias', 'backbone.dec.dec0.up.proj_skip.1.weight', 'backbone.dec.dec0.up.proj_skip.1.bias']. [2026-06-09 14:22:47,989 INFO optimizer.py line 56 726] Params Group 2 - lr: 2e-06; Params: ['backbone.enc.enc0.block0.cpe.0.weight', 'backbone.enc.enc0.block0.cpe.0.bias', 'backbone.enc.enc0.block0.cpe.1.weight', 'backbone.enc.enc0.block0.cpe.1.bias', 'backbone.enc.enc0.block0.cpe.2.weight', 'backbone.enc.enc0.block0.cpe.2.bias', 'backbone.enc.enc0.block0.norm1.0.weight', 'backbone.enc.enc0.block0.norm1.0.bias', 'backbone.enc.enc0.block0.attn.ema_offset', 'backbone.enc.enc0.block0.attn.rpe.rpe_table', 'backbone.enc.enc0.block0.attn.qkv.weight', 'backbone.enc.enc0.block0.attn.qkv.bias', 'backbone.enc.enc0.block0.attn.proj.weight', 'backbone.enc.enc0.block0.attn.proj.bias', 'backbone.enc.enc0.block0.norm2.0.weight', 'backbone.enc.enc0.block0.norm2.0.bias', 'backbone.enc.enc0.block0.mlp.0.fc1.weight', 'backbone.enc.enc0.block0.mlp.0.fc1.bias', 'backbone.enc.enc0.block0.mlp.0.fc2.weight', 'backbone.enc.enc0.block0.mlp.0.fc2.bias', 'backbone.enc.enc0.block1.cpe.0.weight', 'backbone.enc.enc0.block1.cpe.0.bias', 'backbone.enc.enc0.block1.cpe.1.weight', 'backbone.enc.enc0.block1.cpe.1.bias', 'backbone.enc.enc0.block1.cpe.2.weight', 'backbone.enc.enc0.block1.cpe.2.bias', 'backbone.enc.enc0.block1.norm1.0.weight', 'backbone.enc.enc0.block1.norm1.0.bias', 'backbone.enc.enc0.block1.attn.ema_offset', 'backbone.enc.enc0.block1.attn.rpe.rpe_table', 'backbone.enc.enc0.block1.attn.qkv.weight', 'backbone.enc.enc0.block1.attn.qkv.bias', 'backbone.enc.enc0.block1.attn.proj.weight', 'backbone.enc.enc0.block1.attn.proj.bias', 'backbone.enc.enc0.block1.norm2.0.weight', 'backbone.enc.enc0.block1.norm2.0.bias', 'backbone.enc.enc0.block1.mlp.0.fc1.weight', 'backbone.enc.enc0.block1.mlp.0.fc1.bias', 'backbone.enc.enc0.block1.mlp.0.fc2.weight', 'backbone.enc.enc0.block1.mlp.0.fc2.bias', 'backbone.enc.enc1.block0.cpe.0.weight', 'backbone.enc.enc1.block0.cpe.0.bias', 'backbone.enc.enc1.block0.cpe.1.weight', 'backbone.enc.enc1.block0.cpe.1.bias', 'backbone.enc.enc1.block0.cpe.2.weight', 'backbone.enc.enc1.block0.cpe.2.bias', 'backbone.enc.enc1.block0.norm1.0.weight', 'backbone.enc.enc1.block0.norm1.0.bias', 'backbone.enc.enc1.block0.attn.ema_offset', 'backbone.enc.enc1.block0.attn.rpe.rpe_table', 'backbone.enc.enc1.block0.attn.qkv.weight', 'backbone.enc.enc1.block0.attn.qkv.bias', 'backbone.enc.enc1.block0.attn.proj.weight', 'backbone.enc.enc1.block0.attn.proj.bias', 'backbone.enc.enc1.block0.norm2.0.weight', 'backbone.enc.enc1.block0.norm2.0.bias', 'backbone.enc.enc1.block0.mlp.0.fc1.weight', 'backbone.enc.enc1.block0.mlp.0.fc1.bias', 'backbone.enc.enc1.block0.mlp.0.fc2.weight', 'backbone.enc.enc1.block0.mlp.0.fc2.bias', 'backbone.enc.enc1.block1.cpe.0.weight', 'backbone.enc.enc1.block1.cpe.0.bias', 'backbone.enc.enc1.block1.cpe.1.weight', 'backbone.enc.enc1.block1.cpe.1.bias', 'backbone.enc.enc1.block1.cpe.2.weight', 'backbone.enc.enc1.block1.cpe.2.bias', 'backbone.enc.enc1.block1.norm1.0.weight', 'backbone.enc.enc1.block1.norm1.0.bias', 'backbone.enc.enc1.block1.attn.ema_offset', 'backbone.enc.enc1.block1.attn.rpe.rpe_table', 'backbone.enc.enc1.block1.attn.qkv.weight', 'backbone.enc.enc1.block1.attn.qkv.bias', 'backbone.enc.enc1.block1.attn.proj.weight', 'backbone.enc.enc1.block1.attn.proj.bias', 'backbone.enc.enc1.block1.norm2.0.weight', 'backbone.enc.enc1.block1.norm2.0.bias', 'backbone.enc.enc1.block1.mlp.0.fc1.weight', 'backbone.enc.enc1.block1.mlp.0.fc1.bias', 'backbone.enc.enc1.block1.mlp.0.fc2.weight', 'backbone.enc.enc1.block1.mlp.0.fc2.bias', 'backbone.enc.enc2.block0.cpe.0.weight', 'backbone.enc.enc2.block0.cpe.0.bias', 'backbone.enc.enc2.block0.cpe.1.weight', 'backbone.enc.enc2.block0.cpe.1.bias', 'backbone.enc.enc2.block0.cpe.2.weight', 'backbone.enc.enc2.block0.cpe.2.bias', 'backbone.enc.enc2.block0.norm1.0.weight', 'backbone.enc.enc2.block0.norm1.0.bias', 'backbone.enc.enc2.block0.attn.ema_offset', 'backbone.enc.enc2.block0.attn.rpe.rpe_table', 'backbone.enc.enc2.block0.attn.qkv.weight', 'backbone.enc.enc2.block0.attn.qkv.bias', 'backbone.enc.enc2.block0.attn.proj.weight', 'backbone.enc.enc2.block0.attn.proj.bias', 'backbone.enc.enc2.block0.norm2.0.weight', 'backbone.enc.enc2.block0.norm2.0.bias', 'backbone.enc.enc2.block0.mlp.0.fc1.weight', 'backbone.enc.enc2.block0.mlp.0.fc1.bias', 'backbone.enc.enc2.block0.mlp.0.fc2.weight', 'backbone.enc.enc2.block0.mlp.0.fc2.bias', 'backbone.enc.enc2.block1.cpe.0.weight', 'backbone.enc.enc2.block1.cpe.0.bias', 'backbone.enc.enc2.block1.cpe.1.weight', 'backbone.enc.enc2.block1.cpe.1.bias', 'backbone.enc.enc2.block1.cpe.2.weight', 'backbone.enc.enc2.block1.cpe.2.bias', 'backbone.enc.enc2.block1.norm1.0.weight', 'backbone.enc.enc2.block1.norm1.0.bias', 'backbone.enc.enc2.block1.attn.ema_offset', 'backbone.enc.enc2.block1.attn.rpe.rpe_table', 'backbone.enc.enc2.block1.attn.qkv.weight', 'backbone.enc.enc2.block1.attn.qkv.bias', 'backbone.enc.enc2.block1.attn.proj.weight', 'backbone.enc.enc2.block1.attn.proj.bias', 'backbone.enc.enc2.block1.norm2.0.weight', 'backbone.enc.enc2.block1.norm2.0.bias', 'backbone.enc.enc2.block1.mlp.0.fc1.weight', 'backbone.enc.enc2.block1.mlp.0.fc1.bias', 'backbone.enc.enc2.block1.mlp.0.fc2.weight', 'backbone.enc.enc2.block1.mlp.0.fc2.bias', 'backbone.enc.enc3.block0.cpe.0.weight', 'backbone.enc.enc3.block0.cpe.0.bias', 'backbone.enc.enc3.block0.cpe.1.weight', 'backbone.enc.enc3.block0.cpe.1.bias', 'backbone.enc.enc3.block0.cpe.2.weight', 'backbone.enc.enc3.block0.cpe.2.bias', 'backbone.enc.enc3.block0.norm1.0.weight', 'backbone.enc.enc3.block0.norm1.0.bias', 'backbone.enc.enc3.block0.attn.ema_offset', 'backbone.enc.enc3.block0.attn.rpe.rpe_table', 'backbone.enc.enc3.block0.attn.qkv.weight', 'backbone.enc.enc3.block0.attn.qkv.bias', 'backbone.enc.enc3.block0.attn.proj.weight', 'backbone.enc.enc3.block0.attn.proj.bias', 'backbone.enc.enc3.block0.norm2.0.weight', 'backbone.enc.enc3.block0.norm2.0.bias', 'backbone.enc.enc3.block0.mlp.0.fc1.weight', 'backbone.enc.enc3.block0.mlp.0.fc1.bias', 'backbone.enc.enc3.block0.mlp.0.fc2.weight', 'backbone.enc.enc3.block0.mlp.0.fc2.bias', 'backbone.enc.enc3.block1.cpe.0.weight', 'backbone.enc.enc3.block1.cpe.0.bias', 'backbone.enc.enc3.block1.cpe.1.weight', 'backbone.enc.enc3.block1.cpe.1.bias', 'backbone.enc.enc3.block1.cpe.2.weight', 'backbone.enc.enc3.block1.cpe.2.bias', 'backbone.enc.enc3.block1.norm1.0.weight', 'backbone.enc.enc3.block1.norm1.0.bias', 'backbone.enc.enc3.block1.attn.ema_offset', 'backbone.enc.enc3.block1.attn.rpe.rpe_table', 'backbone.enc.enc3.block1.attn.qkv.weight', 'backbone.enc.enc3.block1.attn.qkv.bias', 'backbone.enc.enc3.block1.attn.proj.weight', 'backbone.enc.enc3.block1.attn.proj.bias', 'backbone.enc.enc3.block1.norm2.0.weight', 'backbone.enc.enc3.block1.norm2.0.bias', 'backbone.enc.enc3.block1.mlp.0.fc1.weight', 'backbone.enc.enc3.block1.mlp.0.fc1.bias', 'backbone.enc.enc3.block1.mlp.0.fc2.weight', 'backbone.enc.enc3.block1.mlp.0.fc2.bias', 'backbone.enc.enc3.block2.cpe.0.weight', 'backbone.enc.enc3.block2.cpe.0.bias', 'backbone.enc.enc3.block2.cpe.1.weight', 'backbone.enc.enc3.block2.cpe.1.bias', 'backbone.enc.enc3.block2.cpe.2.weight', 'backbone.enc.enc3.block2.cpe.2.bias', 'backbone.enc.enc3.block2.norm1.0.weight', 'backbone.enc.enc3.block2.norm1.0.bias', 'backbone.enc.enc3.block2.attn.ema_offset', 'backbone.enc.enc3.block2.attn.rpe.rpe_table', 'backbone.enc.enc3.block2.attn.qkv.weight', 'backbone.enc.enc3.block2.attn.qkv.bias', 'backbone.enc.enc3.block2.attn.proj.weight', 'backbone.enc.enc3.block2.attn.proj.bias', 'backbone.enc.enc3.block2.norm2.0.weight', 'backbone.enc.enc3.block2.norm2.0.bias', 'backbone.enc.enc3.block2.mlp.0.fc1.weight', 'backbone.enc.enc3.block2.mlp.0.fc1.bias', 'backbone.enc.enc3.block2.mlp.0.fc2.weight', 'backbone.enc.enc3.block2.mlp.0.fc2.bias', 'backbone.enc.enc3.block3.cpe.0.weight', 'backbone.enc.enc3.block3.cpe.0.bias', 'backbone.enc.enc3.block3.cpe.1.weight', 'backbone.enc.enc3.block3.cpe.1.bias', 'backbone.enc.enc3.block3.cpe.2.weight', 'backbone.enc.enc3.block3.cpe.2.bias', 'backbone.enc.enc3.block3.norm1.0.weight', 'backbone.enc.enc3.block3.norm1.0.bias', 'backbone.enc.enc3.block3.attn.ema_offset', 'backbone.enc.enc3.block3.attn.rpe.rpe_table', 'backbone.enc.enc3.block3.attn.qkv.weight', 'backbone.enc.enc3.block3.attn.qkv.bias', 'backbone.enc.enc3.block3.attn.proj.weight', 'backbone.enc.enc3.block3.attn.proj.bias', 'backbone.enc.enc3.block3.norm2.0.weight', 'backbone.enc.enc3.block3.norm2.0.bias', 'backbone.enc.enc3.block3.mlp.0.fc1.weight', 'backbone.enc.enc3.block3.mlp.0.fc1.bias', 'backbone.enc.enc3.block3.mlp.0.fc2.weight', 'backbone.enc.enc3.block3.mlp.0.fc2.bias', 'backbone.enc.enc3.block4.cpe.0.weight', 'backbone.enc.enc3.block4.cpe.0.bias', 'backbone.enc.enc3.block4.cpe.1.weight', 'backbone.enc.enc3.block4.cpe.1.bias', 'backbone.enc.enc3.block4.cpe.2.weight', 'backbone.enc.enc3.block4.cpe.2.bias', 'backbone.enc.enc3.block4.norm1.0.weight', 'backbone.enc.enc3.block4.norm1.0.bias', 'backbone.enc.enc3.block4.attn.ema_offset', 'backbone.enc.enc3.block4.attn.rpe.rpe_table', 'backbone.enc.enc3.block4.attn.qkv.weight', 'backbone.enc.enc3.block4.attn.qkv.bias', 'backbone.enc.enc3.block4.attn.proj.weight', 'backbone.enc.enc3.block4.attn.proj.bias', 'backbone.enc.enc3.block4.norm2.0.weight', 'backbone.enc.enc3.block4.norm2.0.bias', 'backbone.enc.enc3.block4.mlp.0.fc1.weight', 'backbone.enc.enc3.block4.mlp.0.fc1.bias', 'backbone.enc.enc3.block4.mlp.0.fc2.weight', 'backbone.enc.enc3.block4.mlp.0.fc2.bias', 'backbone.enc.enc3.block5.cpe.0.weight', 'backbone.enc.enc3.block5.cpe.0.bias', 'backbone.enc.enc3.block5.cpe.1.weight', 'backbone.enc.enc3.block5.cpe.1.bias', 'backbone.enc.enc3.block5.cpe.2.weight', 'backbone.enc.enc3.block5.cpe.2.bias', 'backbone.enc.enc3.block5.norm1.0.weight', 'backbone.enc.enc3.block5.norm1.0.bias', 'backbone.enc.enc3.block5.attn.ema_offset', 'backbone.enc.enc3.block5.attn.rpe.rpe_table', 'backbone.enc.enc3.block5.attn.qkv.weight', 'backbone.enc.enc3.block5.attn.qkv.bias', 'backbone.enc.enc3.block5.attn.proj.weight', 'backbone.enc.enc3.block5.attn.proj.bias', 'backbone.enc.enc3.block5.norm2.0.weight', 'backbone.enc.enc3.block5.norm2.0.bias', 'backbone.enc.enc3.block5.mlp.0.fc1.weight', 'backbone.enc.enc3.block5.mlp.0.fc1.bias', 'backbone.enc.enc3.block5.mlp.0.fc2.weight', 'backbone.enc.enc3.block5.mlp.0.fc2.bias', 'backbone.enc.enc4.block0.cpe.0.weight', 'backbone.enc.enc4.block0.cpe.0.bias', 'backbone.enc.enc4.block0.cpe.1.weight', 'backbone.enc.enc4.block0.cpe.1.bias', 'backbone.enc.enc4.block0.cpe.2.weight', 'backbone.enc.enc4.block0.cpe.2.bias', 'backbone.enc.enc4.block0.norm1.0.weight', 'backbone.enc.enc4.block0.norm1.0.bias', 'backbone.enc.enc4.block0.attn.ema_offset', 'backbone.enc.enc4.block0.attn.rpe.rpe_table', 'backbone.enc.enc4.block0.attn.qkv.weight', 'backbone.enc.enc4.block0.attn.qkv.bias', 'backbone.enc.enc4.block0.attn.proj.weight', 'backbone.enc.enc4.block0.attn.proj.bias', 'backbone.enc.enc4.block0.norm2.0.weight', 'backbone.enc.enc4.block0.norm2.0.bias', 'backbone.enc.enc4.block0.mlp.0.fc1.weight', 'backbone.enc.enc4.block0.mlp.0.fc1.bias', 'backbone.enc.enc4.block0.mlp.0.fc2.weight', 'backbone.enc.enc4.block0.mlp.0.fc2.bias', 'backbone.enc.enc4.block1.cpe.0.weight', 'backbone.enc.enc4.block1.cpe.0.bias', 'backbone.enc.enc4.block1.cpe.1.weight', 'backbone.enc.enc4.block1.cpe.1.bias', 'backbone.enc.enc4.block1.cpe.2.weight', 'backbone.enc.enc4.block1.cpe.2.bias', 'backbone.enc.enc4.block1.norm1.0.weight', 'backbone.enc.enc4.block1.norm1.0.bias', 'backbone.enc.enc4.block1.attn.ema_offset', 'backbone.enc.enc4.block1.attn.rpe.rpe_table', 'backbone.enc.enc4.block1.attn.qkv.weight', 'backbone.enc.enc4.block1.attn.qkv.bias', 'backbone.enc.enc4.block1.attn.proj.weight', 'backbone.enc.enc4.block1.attn.proj.bias', 'backbone.enc.enc4.block1.norm2.0.weight', 'backbone.enc.enc4.block1.norm2.0.bias', 'backbone.enc.enc4.block1.mlp.0.fc1.weight', 'backbone.enc.enc4.block1.mlp.0.fc1.bias', 'backbone.enc.enc4.block1.mlp.0.fc2.weight', 'backbone.enc.enc4.block1.mlp.0.fc2.bias', 'backbone.dec.dec3.block0.cpe.0.weight', 'backbone.dec.dec3.block0.cpe.0.bias', 'backbone.dec.dec3.block0.cpe.1.weight', 'backbone.dec.dec3.block0.cpe.1.bias', 'backbone.dec.dec3.block0.cpe.2.weight', 'backbone.dec.dec3.block0.cpe.2.bias', 'backbone.dec.dec3.block0.norm1.0.weight', 'backbone.dec.dec3.block0.norm1.0.bias', 'backbone.dec.dec3.block0.attn.ema_offset', 'backbone.dec.dec3.block0.attn.rpe.rpe_table', 'backbone.dec.dec3.block0.attn.qkv.weight', 'backbone.dec.dec3.block0.attn.qkv.bias', 'backbone.dec.dec3.block0.attn.proj.weight', 'backbone.dec.dec3.block0.attn.proj.bias', 'backbone.dec.dec3.block0.norm2.0.weight', 'backbone.dec.dec3.block0.norm2.0.bias', 'backbone.dec.dec3.block0.mlp.0.fc1.weight', 'backbone.dec.dec3.block0.mlp.0.fc1.bias', 'backbone.dec.dec3.block0.mlp.0.fc2.weight', 'backbone.dec.dec3.block0.mlp.0.fc2.bias', 'backbone.dec.dec3.block1.cpe.0.weight', 'backbone.dec.dec3.block1.cpe.0.bias', 'backbone.dec.dec3.block1.cpe.1.weight', 'backbone.dec.dec3.block1.cpe.1.bias', 'backbone.dec.dec3.block1.cpe.2.weight', 'backbone.dec.dec3.block1.cpe.2.bias', 'backbone.dec.dec3.block1.norm1.0.weight', 'backbone.dec.dec3.block1.norm1.0.bias', 'backbone.dec.dec3.block1.attn.ema_offset', 'backbone.dec.dec3.block1.attn.rpe.rpe_table', 'backbone.dec.dec3.block1.attn.qkv.weight', 'backbone.dec.dec3.block1.attn.qkv.bias', 'backbone.dec.dec3.block1.attn.proj.weight', 'backbone.dec.dec3.block1.attn.proj.bias', 'backbone.dec.dec3.block1.norm2.0.weight', 'backbone.dec.dec3.block1.norm2.0.bias', 'backbone.dec.dec3.block1.mlp.0.fc1.weight', 'backbone.dec.dec3.block1.mlp.0.fc1.bias', 'backbone.dec.dec3.block1.mlp.0.fc2.weight', 'backbone.dec.dec3.block1.mlp.0.fc2.bias', 'backbone.dec.dec2.block0.cpe.0.weight', 'backbone.dec.dec2.block0.cpe.0.bias', 'backbone.dec.dec2.block0.cpe.1.weight', 'backbone.dec.dec2.block0.cpe.1.bias', 'backbone.dec.dec2.block0.cpe.2.weight', 'backbone.dec.dec2.block0.cpe.2.bias', 'backbone.dec.dec2.block0.norm1.0.weight', 'backbone.dec.dec2.block0.norm1.0.bias', 'backbone.dec.dec2.block0.attn.ema_offset', 'backbone.dec.dec2.block0.attn.rpe.rpe_table', 'backbone.dec.dec2.block0.attn.qkv.weight', 'backbone.dec.dec2.block0.attn.qkv.bias', 'backbone.dec.dec2.block0.attn.proj.weight', 'backbone.dec.dec2.block0.attn.proj.bias', 'backbone.dec.dec2.block0.norm2.0.weight', 'backbone.dec.dec2.block0.norm2.0.bias', 'backbone.dec.dec2.block0.mlp.0.fc1.weight', 'backbone.dec.dec2.block0.mlp.0.fc1.bias', 'backbone.dec.dec2.block0.mlp.0.fc2.weight', 'backbone.dec.dec2.block0.mlp.0.fc2.bias', 'backbone.dec.dec2.block1.cpe.0.weight', 'backbone.dec.dec2.block1.cpe.0.bias', 'backbone.dec.dec2.block1.cpe.1.weight', 'backbone.dec.dec2.block1.cpe.1.bias', 'backbone.dec.dec2.block1.cpe.2.weight', 'backbone.dec.dec2.block1.cpe.2.bias', 'backbone.dec.dec2.block1.norm1.0.weight', 'backbone.dec.dec2.block1.norm1.0.bias', 'backbone.dec.dec2.block1.attn.ema_offset', 'backbone.dec.dec2.block1.attn.rpe.rpe_table', 'backbone.dec.dec2.block1.attn.qkv.weight', 'backbone.dec.dec2.block1.attn.qkv.bias', 'backbone.dec.dec2.block1.attn.proj.weight', 'backbone.dec.dec2.block1.attn.proj.bias', 'backbone.dec.dec2.block1.norm2.0.weight', 'backbone.dec.dec2.block1.norm2.0.bias', 'backbone.dec.dec2.block1.mlp.0.fc1.weight', 'backbone.dec.dec2.block1.mlp.0.fc1.bias', 'backbone.dec.dec2.block1.mlp.0.fc2.weight', 'backbone.dec.dec2.block1.mlp.0.fc2.bias', 'backbone.dec.dec1.block0.cpe.0.weight', 'backbone.dec.dec1.block0.cpe.0.bias', 'backbone.dec.dec1.block0.cpe.1.weight', 'backbone.dec.dec1.block0.cpe.1.bias', 'backbone.dec.dec1.block0.cpe.2.weight', 'backbone.dec.dec1.block0.cpe.2.bias', 'backbone.dec.dec1.block0.norm1.0.weight', 'backbone.dec.dec1.block0.norm1.0.bias', 'backbone.dec.dec1.block0.attn.ema_offset', 'backbone.dec.dec1.block0.attn.rpe.rpe_table', 'backbone.dec.dec1.block0.attn.qkv.weight', 'backbone.dec.dec1.block0.attn.qkv.bias', 'backbone.dec.dec1.block0.attn.proj.weight', 'backbone.dec.dec1.block0.attn.proj.bias', 'backbone.dec.dec1.block0.norm2.0.weight', 'backbone.dec.dec1.block0.norm2.0.bias', 'backbone.dec.dec1.block0.mlp.0.fc1.weight', 'backbone.dec.dec1.block0.mlp.0.fc1.bias', 'backbone.dec.dec1.block0.mlp.0.fc2.weight', 'backbone.dec.dec1.block0.mlp.0.fc2.bias', 'backbone.dec.dec1.block1.cpe.0.weight', 'backbone.dec.dec1.block1.cpe.0.bias', 'backbone.dec.dec1.block1.cpe.1.weight', 'backbone.dec.dec1.block1.cpe.1.bias', 'backbone.dec.dec1.block1.cpe.2.weight', 'backbone.dec.dec1.block1.cpe.2.bias', 'backbone.dec.dec1.block1.norm1.0.weight', 'backbone.dec.dec1.block1.norm1.0.bias', 'backbone.dec.dec1.block1.attn.ema_offset', 'backbone.dec.dec1.block1.attn.rpe.rpe_table', 'backbone.dec.dec1.block1.attn.qkv.weight', 'backbone.dec.dec1.block1.attn.qkv.bias', 'backbone.dec.dec1.block1.attn.proj.weight', 'backbone.dec.dec1.block1.attn.proj.bias', 'backbone.dec.dec1.block1.norm2.0.weight', 'backbone.dec.dec1.block1.norm2.0.bias', 'backbone.dec.dec1.block1.mlp.0.fc1.weight', 'backbone.dec.dec1.block1.mlp.0.fc1.bias', 'backbone.dec.dec1.block1.mlp.0.fc2.weight', 'backbone.dec.dec1.block1.mlp.0.fc2.bias', 'backbone.dec.dec0.block0.cpe.0.weight', 'backbone.dec.dec0.block0.cpe.0.bias', 'backbone.dec.dec0.block0.cpe.1.weight', 'backbone.dec.dec0.block0.cpe.1.bias', 'backbone.dec.dec0.block0.cpe.2.weight', 'backbone.dec.dec0.block0.cpe.2.bias', 'backbone.dec.dec0.block0.norm1.0.weight', 'backbone.dec.dec0.block0.norm1.0.bias', 'backbone.dec.dec0.block0.attn.ema_offset', 'backbone.dec.dec0.block0.attn.rpe.rpe_table', 'backbone.dec.dec0.block0.attn.qkv.weight', 'backbone.dec.dec0.block0.attn.qkv.bias', 'backbone.dec.dec0.block0.attn.proj.weight', 'backbone.dec.dec0.block0.attn.proj.bias', 'backbone.dec.dec0.block0.norm2.0.weight', 'backbone.dec.dec0.block0.norm2.0.bias', 'backbone.dec.dec0.block0.mlp.0.fc1.weight', 'backbone.dec.dec0.block0.mlp.0.fc1.bias', 'backbone.dec.dec0.block0.mlp.0.fc2.weight', 'backbone.dec.dec0.block0.mlp.0.fc2.bias', 'backbone.dec.dec0.block1.cpe.0.weight', 'backbone.dec.dec0.block1.cpe.0.bias', 'backbone.dec.dec0.block1.cpe.1.weight', 'backbone.dec.dec0.block1.cpe.1.bias', 'backbone.dec.dec0.block1.cpe.2.weight', 'backbone.dec.dec0.block1.cpe.2.bias', 'backbone.dec.dec0.block1.norm1.0.weight', 'backbone.dec.dec0.block1.norm1.0.bias', 'backbone.dec.dec0.block1.attn.ema_offset', 'backbone.dec.dec0.block1.attn.rpe.rpe_table', 'backbone.dec.dec0.block1.attn.qkv.weight', 'backbone.dec.dec0.block1.attn.qkv.bias', 'backbone.dec.dec0.block1.attn.proj.weight', 'backbone.dec.dec0.block1.attn.proj.bias', 'backbone.dec.dec0.block1.norm2.0.weight', 'backbone.dec.dec0.block1.norm2.0.bias', 'backbone.dec.dec0.block1.mlp.0.fc1.weight', 'backbone.dec.dec0.block1.mlp.0.fc1.bias', 'backbone.dec.dec0.block1.mlp.0.fc2.weight', 'backbone.dec.dec0.block1.mlp.0.fc2.bias']. [2026-06-09 14:22:47,990 INFO optimizer.py line 56 726] Params Group 3 - lr: 0.0002; Params: ['backbone.enc.enc1.superpoint_after_pool.proj.weight', 'backbone.enc.enc1.superpoint_after_pool.proj.bias', 'backbone.enc.enc2.superpoint_after_pool.proj.weight', 'backbone.enc.enc2.superpoint_after_pool.proj.bias', 'backbone.enc.enc3.superpoint_after_pool.proj.weight', 'backbone.enc.enc3.superpoint_after_pool.proj.bias', 'backbone.enc.enc4.superpoint_after_pool.proj.weight', 'backbone.enc.enc4.superpoint_after_pool.proj.bias']. [2026-06-09 14:22:47,991 INFO train.py line 155 726] => Building hooks ... [2026-06-09 14:22:47,991 INFO misc.py line 252 726] => Loading checkpoint & weight ... [2026-06-09 14:22:47,993 INFO misc.py line 254 726] Loading weight at: exp/s3dis/bidit_pycut_w1a1_stage3_sem_strong_protected_20260604/model/model_best.pth [2026-06-09 14:22:48,954 INFO misc.py line 260 726] Loading layer weights with keyword: , replace keyword with: [2026-06-09 14:22:48,969 INFO misc.py line 277 726] Missing keys: [] [2026-06-09 14:22:48,969 INFO train.py line 162 726] >>>>>>>>>>>>>>>> Start Training >>>>>>>>>>>>>>>> [2026-06-09 14:23:22,334 INFO misc.py line 117 726] Train: [1/20][1/510] Data 2.922 (2.922) Batch 33.361 (33.361) Remain 94:30:50 loss: 0.2059 loss_seg: 0.1158 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:24:01,174 INFO misc.py line 117 726] Train: [1/20][2/510] Data 7.455 (7.455) Batch 38.839 (38.839) Remain 110:01:20 loss: 0.2851 loss_seg: 0.1908 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:24:28,796 INFO misc.py line 117 726] Train: [1/20][3/510] Data 3.365 (3.365) Batch 27.623 (27.623) Remain 78:14:27 loss: 0.2486 loss_seg: 0.1491 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:24:56,502 INFO misc.py line 117 726] Train: [1/20][4/510] Data 3.465 (3.465) Batch 27.706 (27.706) Remain 78:28:05 loss: 0.2448 loss_seg: 0.1462 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:25:21,799 INFO misc.py line 117 726] Train: [1/20][5/510] Data 2.881 (3.173) Batch 25.297 (26.501) Remain 75:02:59 loss: 0.1989 loss_seg: 0.1112 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:25:54,921 INFO misc.py line 117 726] Train: [1/20][6/510] Data 3.955 (3.434) Batch 33.122 (28.708) Remain 81:17:29 loss: 0.4063 loss_seg: 0.3089 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:26:20,229 INFO misc.py line 117 726] Train: [1/20][7/510] Data 6.265 (4.142) Batch 25.308 (27.858) Remain 78:52:38 loss: 0.2527 loss_seg: 0.1531 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:26:52,219 INFO misc.py line 117 726] Train: [1/20][8/510] Data 8.580 (5.029) Batch 31.990 (28.685) Remain 81:12:32 loss: 0.2340 loss_seg: 0.1521 loss_superpoint_edge: 0.0121 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:27:23,731 INFO misc.py line 117 726] Train: [1/20][9/510] Data 8.003 (5.525) Batch 31.512 (29.156) Remain 82:32:05 loss: 0.2007 loss_seg: 0.1108 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:27:45,890 INFO misc.py line 117 726] Train: [1/20][10/510] Data 2.559 (5.101) Batch 22.159 (28.156) Remain 79:41:51 loss: 0.3397 loss_seg: 0.2265 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:28:09,382 INFO misc.py line 117 726] Train: [1/20][11/510] Data 2.864 (4.822) Batch 23.492 (27.573) Remain 78:02:23 loss: 0.2415 loss_seg: 0.1486 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:28:38,616 INFO misc.py line 117 726] Train: [1/20][12/510] Data 3.783 (4.706) Batch 29.234 (27.758) Remain 78:33:16 loss: 0.2251 loss_seg: 0.1343 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:29:11,748 INFO misc.py line 117 726] Train: [1/20][13/510] Data 4.738 (4.709) Batch 33.131 (28.295) Remain 80:04:02 loss: 0.2108 loss_seg: 0.1214 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:29:42,465 INFO misc.py line 117 726] Train: [1/20][14/510] Data 2.535 (4.512) Batch 30.717 (28.515) Remain 80:40:56 loss: 0.2564 loss_seg: 0.1604 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:30:21,724 INFO misc.py line 117 726] Train: [1/20][15/510] Data 6.371 (4.667) Batch 39.259 (29.411) Remain 83:12:26 loss: 0.2446 loss_seg: 0.1496 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:30:52,143 INFO misc.py line 117 726] Train: [1/20][16/510] Data 3.783 (4.599) Batch 30.420 (29.488) Remain 83:25:07 loss: 0.2010 loss_seg: 0.1120 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:31:13,602 INFO misc.py line 117 726] Train: [1/20][17/510] Data 2.458 (4.446) Batch 21.459 (28.915) Remain 81:47:18 loss: 0.2804 loss_seg: 0.1834 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:31:47,011 INFO misc.py line 117 726] Train: [1/20][18/510] Data 5.349 (4.506) Batch 33.409 (29.214) Remain 82:37:40 loss: 0.2066 loss_seg: 0.1136 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:32:20,979 INFO misc.py line 117 726] Train: [1/20][19/510] Data 6.916 (4.657) Batch 33.967 (29.511) Remain 83:27:35 loss: 0.2102 loss_seg: 0.1162 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:32:44,478 INFO misc.py line 117 726] Train: [1/20][20/510] Data 2.345 (4.521) Batch 23.500 (29.158) Remain 82:27:05 loss: 0.3398 loss_seg: 0.2370 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:33:11,239 INFO misc.py line 117 726] Train: [1/20][21/510] Data 3.584 (4.469) Batch 26.761 (29.025) Remain 82:04:01 loss: 0.2659 loss_seg: 0.1731 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:33:36,735 INFO misc.py line 117 726] Train: [1/20][22/510] Data 2.778 (4.380) Batch 25.496 (28.839) Remain 81:32:01 loss: 0.2695 loss_seg: 0.1788 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:34:02,525 INFO misc.py line 117 726] Train: [1/20][23/510] Data 3.706 (4.346) Batch 25.790 (28.686) Remain 81:05:41 loss: 0.2239 loss_seg: 0.1274 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:34:29,599 INFO misc.py line 117 726] Train: [1/20][24/510] Data 4.468 (4.352) Batch 27.074 (28.610) Remain 80:52:11 loss: 0.3175 loss_seg: 0.2098 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:34:49,639 INFO misc.py line 117 726] Train: [1/20][25/510] Data 2.584 (4.271) Batch 20.040 (28.220) Remain 79:45:39 loss: 0.2950 loss_seg: 0.1848 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:35:13,772 INFO misc.py line 117 726] Train: [1/20][26/510] Data 3.972 (4.258) Batch 24.133 (28.042) Remain 79:15:03 loss: 0.2161 loss_seg: 0.1293 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:35:35,324 INFO misc.py line 117 726] Train: [1/20][27/510] Data 3.361 (4.221) Batch 21.552 (27.772) Remain 78:28:44 loss: 0.2587 loss_seg: 0.1659 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:36:04,855 INFO misc.py line 117 726] Train: [1/20][28/510] Data 3.748 (4.202) Batch 29.531 (27.842) Remain 78:40:12 loss: 0.2064 loss_seg: 0.1204 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:36:35,867 INFO misc.py line 117 726] Train: [1/20][29/510] Data 4.413 (4.210) Batch 31.012 (27.964) Remain 79:00:24 loss: 0.3445 loss_seg: 0.2380 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:37:04,639 INFO misc.py line 117 726] Train: [1/20][30/510] Data 2.744 (4.156) Batch 28.773 (27.994) Remain 79:05:00 loss: 0.2161 loss_seg: 0.1240 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:37:29,367 INFO misc.py line 117 726] Train: [1/20][31/510] Data 2.906 (4.111) Batch 24.728 (27.878) Remain 78:44:46 loss: 0.2642 loss_seg: 0.1633 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:37:53,083 INFO misc.py line 117 726] Train: [1/20][32/510] Data 2.529 (4.057) Batch 23.716 (27.734) Remain 78:19:59 loss: 0.2379 loss_seg: 0.1434 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:38:22,686 INFO misc.py line 117 726] Train: [1/20][33/510] Data 3.309 (4.032) Batch 29.602 (27.796) Remain 78:30:04 loss: 0.2713 loss_seg: 0.1683 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:38:59,790 INFO misc.py line 117 726] Train: [1/20][34/510] Data 4.079 (4.033) Batch 37.104 (28.097) Remain 79:20:29 loss: 0.2910 loss_seg: 0.1852 loss_superpoint_edge: 0.0415 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:39:34,411 INFO misc.py line 117 726] Train: [1/20][35/510] Data 5.678 (4.085) Batch 34.622 (28.300) Remain 79:54:34 loss: 0.2353 loss_seg: 0.1399 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:40:01,891 INFO misc.py line 117 726] Train: [1/20][36/510] Data 4.849 (4.108) Batch 27.479 (28.276) Remain 79:49:52 loss: 0.3317 loss_seg: 0.2247 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:40:32,182 INFO misc.py line 117 726] Train: [1/20][37/510] Data 4.118 (4.108) Batch 30.292 (28.335) Remain 79:59:27 loss: 0.2402 loss_seg: 0.1463 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:41:09,227 INFO misc.py line 117 726] Train: [1/20][38/510] Data 4.655 (4.124) Batch 37.044 (28.584) Remain 80:41:07 loss: 0.2339 loss_seg: 0.1438 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:41:31,209 INFO misc.py line 117 726] Train: [1/20][39/510] Data 2.774 (4.086) Batch 21.982 (28.400) Remain 80:09:35 loss: 0.2497 loss_seg: 0.1550 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:42:03,580 INFO misc.py line 117 726] Train: [1/20][40/510] Data 2.796 (4.051) Batch 32.371 (28.508) Remain 80:27:17 loss: 0.2464 loss_seg: 0.1493 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:42:32,107 INFO misc.py line 117 726] Train: [1/20][41/510] Data 3.459 (4.036) Batch 28.527 (28.508) Remain 80:26:54 loss: 0.2941 loss_seg: 0.2018 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:43:02,905 INFO misc.py line 117 726] Train: [1/20][42/510] Data 2.878 (4.006) Batch 30.797 (28.567) Remain 80:36:22 loss: 0.2044 loss_seg: 0.1151 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:43:34,651 INFO misc.py line 117 726] Train: [1/20][43/510] Data 9.148 (4.135) Batch 31.746 (28.646) Remain 80:49:21 loss: 0.2466 loss_seg: 0.1545 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:44:11,790 INFO misc.py line 117 726] Train: [1/20][44/510] Data 4.943 (4.154) Batch 37.139 (28.853) Remain 81:23:56 loss: 0.2594 loss_seg: 0.1581 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:44:39,231 INFO misc.py line 117 726] Train: [1/20][45/510] Data 3.931 (4.149) Batch 27.442 (28.820) Remain 81:17:45 loss: 0.4616 loss_seg: 0.3542 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:44:52,842 INFO misc.py line 117 726] Train: [1/20][46/510] Data 1.989 (4.099) Batch 13.610 (28.466) Remain 80:17:25 loss: 0.2513 loss_seg: 0.1559 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:45:21,296 INFO misc.py line 117 726] Train: [1/20][47/510] Data 2.880 (4.071) Batch 28.454 (28.466) Remain 80:16:54 loss: 0.2585 loss_seg: 0.1604 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:45:46,743 INFO misc.py line 117 726] Train: [1/20][48/510] Data 2.816 (4.043) Batch 25.448 (28.399) Remain 80:05:04 loss: 0.2588 loss_seg: 0.1602 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:46:14,050 INFO misc.py line 117 726] Train: [1/20][49/510] Data 3.542 (4.032) Batch 27.307 (28.375) Remain 80:00:35 loss: 0.2382 loss_seg: 0.1417 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:46:45,462 INFO misc.py line 117 726] Train: [1/20][50/510] Data 4.240 (4.037) Batch 31.412 (28.440) Remain 80:11:02 loss: 0.3595 loss_seg: 0.2568 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:46:45,463 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 14:47:19,746 INFO misc.py line 117 726] Train: [1/20][51/510] Data 5.584 (4.069) Batch 34.284 (28.561) Remain 80:31:10 loss: 0.2301 loss_seg: 0.1338 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:47:50,775 INFO misc.py line 117 726] Train: [1/20][52/510] Data 4.149 (4.071) Batch 31.025 (28.612) Remain 80:39:11 loss: 0.1793 loss_seg: 0.0973 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:48:18,904 INFO misc.py line 117 726] Train: [1/20][53/510] Data 3.329 (4.056) Batch 28.132 (28.602) Remain 80:37:05 loss: 0.2396 loss_seg: 0.1407 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:48:54,852 INFO misc.py line 117 726] Train: [1/20][54/510] Data 6.569 (4.105) Batch 35.947 (28.746) Remain 81:00:58 loss: 0.5789 loss_seg: 0.4594 loss_superpoint_edge: 0.0498 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0342 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:49:18,438 INFO misc.py line 117 726] Train: [1/20][55/510] Data 2.868 (4.081) Batch 23.586 (28.647) Remain 80:43:43 loss: 0.3333 loss_seg: 0.2472 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:49:40,296 INFO misc.py line 117 726] Train: [1/20][56/510] Data 2.478 (4.051) Batch 21.858 (28.519) Remain 80:21:35 loss: 0.2418 loss_seg: 0.1494 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:50:09,602 INFO misc.py line 117 726] Train: [1/20][57/510] Data 3.579 (4.042) Batch 29.306 (28.533) Remain 80:23:34 loss: 0.2401 loss_seg: 0.1400 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:50:43,461 INFO misc.py line 117 726] Train: [1/20][58/510] Data 4.513 (4.051) Batch 33.859 (28.630) Remain 80:39:28 loss: 0.2754 loss_seg: 0.1706 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:51:17,003 INFO misc.py line 117 726] Train: [1/20][59/510] Data 5.190 (4.071) Batch 33.542 (28.718) Remain 80:53:48 loss: 0.3765 loss_seg: 0.2681 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:51:54,159 INFO misc.py line 117 726] Train: [1/20][60/510] Data 5.706 (4.100) Batch 37.155 (28.866) Remain 81:18:21 loss: 0.2861 loss_seg: 0.1829 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:52:20,338 INFO misc.py line 117 726] Train: [1/20][61/510] Data 2.580 (4.074) Batch 26.179 (28.820) Remain 81:10:02 loss: 0.3209 loss_seg: 0.2058 loss_superpoint_edge: 0.0470 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:52:45,517 INFO misc.py line 117 726] Train: [1/20][62/510] Data 2.837 (4.053) Batch 25.179 (28.758) Remain 80:59:08 loss: 0.2486 loss_seg: 0.1567 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:53:11,367 INFO misc.py line 117 726] Train: [1/20][63/510] Data 3.929 (4.051) Batch 25.850 (28.710) Remain 80:50:28 loss: 0.2187 loss_seg: 0.1231 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:53:45,103 INFO misc.py line 117 726] Train: [1/20][64/510] Data 5.277 (4.071) Batch 33.736 (28.792) Remain 81:03:54 loss: 0.2950 loss_seg: 0.1869 loss_superpoint_edge: 0.0440 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:54:08,858 INFO misc.py line 117 726] Train: [1/20][65/510] Data 2.446 (4.045) Batch 23.755 (28.711) Remain 80:49:42 loss: 0.2499 loss_seg: 0.1477 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:54:40,790 INFO misc.py line 117 726] Train: [1/20][66/510] Data 2.625 (4.022) Batch 31.931 (28.762) Remain 80:57:51 loss: 0.2032 loss_seg: 0.1187 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:55:05,927 INFO misc.py line 117 726] Train: [1/20][67/510] Data 2.512 (3.998) Batch 25.137 (28.705) Remain 80:47:49 loss: 0.2596 loss_seg: 0.1595 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:55:32,020 INFO misc.py line 117 726] Train: [1/20][68/510] Data 2.426 (3.974) Batch 26.093 (28.665) Remain 80:40:33 loss: 0.3021 loss_seg: 0.1984 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:56:02,907 INFO misc.py line 117 726] Train: [1/20][69/510] Data 3.096 (3.961) Batch 30.887 (28.699) Remain 80:45:45 loss: 0.3340 loss_seg: 0.2201 loss_superpoint_edge: 0.0467 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:56:36,749 INFO misc.py line 117 726] Train: [1/20][70/510] Data 5.576 (3.985) Batch 33.842 (28.775) Remain 80:58:14 loss: 0.2568 loss_seg: 0.1689 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:57:12,706 INFO misc.py line 117 726] Train: [1/20][71/510] Data 5.108 (4.002) Batch 35.958 (28.881) Remain 81:15:35 loss: 0.2912 loss_seg: 0.1929 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:57:37,095 INFO misc.py line 117 726] Train: [1/20][72/510] Data 3.054 (3.988) Batch 24.388 (28.816) Remain 81:04:07 loss: 0.2184 loss_seg: 0.1249 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:58:13,537 INFO misc.py line 117 726] Train: [1/20][73/510] Data 5.285 (4.006) Batch 36.443 (28.925) Remain 81:22:02 loss: 0.2646 loss_seg: 0.1719 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:58:37,569 INFO misc.py line 117 726] Train: [1/20][74/510] Data 1.995 (3.978) Batch 24.032 (28.856) Remain 81:09:55 loss: 0.2067 loss_seg: 0.1163 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:59:00,110 INFO misc.py line 117 726] Train: [1/20][75/510] Data 3.067 (3.965) Batch 22.541 (28.768) Remain 80:54:38 loss: 0.3510 loss_seg: 0.2550 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:59:24,924 INFO misc.py line 117 726] Train: [1/20][76/510] Data 2.900 (3.951) Batch 24.815 (28.714) Remain 80:45:01 loss: 0.2844 loss_seg: 0.1829 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 14:59:49,158 INFO misc.py line 117 726] Train: [1/20][77/510] Data 2.097 (3.926) Batch 24.234 (28.654) Remain 80:34:19 loss: 0.2731 loss_seg: 0.1684 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:00:20,479 INFO misc.py line 117 726] Train: [1/20][78/510] Data 3.177 (3.916) Batch 31.321 (28.689) Remain 80:39:51 loss: 0.2573 loss_seg: 0.1644 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:00:37,286 INFO misc.py line 117 726] Train: [1/20][79/510] Data 1.927 (3.890) Batch 16.807 (28.533) Remain 80:12:59 loss: 0.2247 loss_seg: 0.1321 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:00:51,002 INFO misc.py line 117 726] Train: [1/20][80/510] Data 1.717 (3.861) Batch 13.714 (28.340) Remain 79:40:03 loss: 0.2812 loss_seg: 0.1805 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:01:13,157 INFO misc.py line 117 726] Train: [1/20][81/510] Data 3.079 (3.851) Batch 22.157 (28.261) Remain 79:26:13 loss: 0.2258 loss_seg: 0.1276 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:01:43,819 INFO misc.py line 117 726] Train: [1/20][82/510] Data 4.275 (3.857) Batch 30.661 (28.291) Remain 79:30:52 loss: 0.3105 loss_seg: 0.2127 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:02:07,792 INFO misc.py line 117 726] Train: [1/20][83/510] Data 3.643 (3.854) Batch 23.974 (28.237) Remain 79:21:18 loss: 0.2673 loss_seg: 0.1641 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:02:45,167 INFO misc.py line 117 726] Train: [1/20][84/510] Data 6.128 (3.882) Batch 37.374 (28.350) Remain 79:39:51 loss: 0.3068 loss_seg: 0.2053 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:03:16,911 INFO misc.py line 117 726] Train: [1/20][85/510] Data 3.766 (3.881) Batch 31.744 (28.392) Remain 79:46:21 loss: 0.2375 loss_seg: 0.1431 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:03:39,785 INFO misc.py line 117 726] Train: [1/20][86/510] Data 2.519 (3.864) Batch 22.874 (28.325) Remain 79:34:40 loss: 0.2779 loss_seg: 0.1698 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:04:11,050 INFO misc.py line 117 726] Train: [1/20][87/510] Data 3.744 (3.863) Batch 31.266 (28.360) Remain 79:40:06 loss: 0.3380 loss_seg: 0.2333 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:04:31,091 INFO misc.py line 117 726] Train: [1/20][88/510] Data 2.478 (3.847) Batch 20.040 (28.262) Remain 79:23:08 loss: 0.2484 loss_seg: 0.1508 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:05:07,663 INFO misc.py line 117 726] Train: [1/20][89/510] Data 4.000 (3.848) Batch 36.572 (28.359) Remain 79:38:56 loss: 0.3081 loss_seg: 0.2072 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:05:37,195 INFO misc.py line 117 726] Train: [1/20][90/510] Data 2.853 (3.837) Batch 29.533 (28.372) Remain 79:40:44 loss: 0.2523 loss_seg: 0.1533 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:06:07,960 INFO misc.py line 117 726] Train: [1/20][91/510] Data 3.838 (3.837) Batch 30.765 (28.400) Remain 79:44:51 loss: 0.2301 loss_seg: 0.1388 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:06:33,749 INFO misc.py line 117 726] Train: [1/20][92/510] Data 2.493 (3.822) Batch 25.789 (28.370) Remain 79:39:26 loss: 0.2698 loss_seg: 0.1705 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:07:01,139 INFO misc.py line 117 726] Train: [1/20][93/510] Data 2.379 (3.806) Batch 27.391 (28.359) Remain 79:37:08 loss: 0.3832 loss_seg: 0.2780 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:07:25,477 INFO misc.py line 117 726] Train: [1/20][94/510] Data 3.200 (3.799) Batch 24.338 (28.315) Remain 79:29:13 loss: 0.2873 loss_seg: 0.1836 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:08:01,636 INFO misc.py line 117 726] Train: [1/20][95/510] Data 4.523 (3.807) Batch 36.159 (28.400) Remain 79:43:06 loss: 0.2813 loss_seg: 0.1839 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:08:36,734 INFO misc.py line 117 726] Train: [1/20][96/510] Data 4.090 (3.810) Batch 35.098 (28.472) Remain 79:54:45 loss: 0.3461 loss_seg: 0.2366 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:09:05,735 INFO misc.py line 117 726] Train: [1/20][97/510] Data 5.395 (3.827) Batch 29.001 (28.478) Remain 79:55:13 loss: 0.2505 loss_seg: 0.1597 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:09:27,138 INFO misc.py line 117 726] Train: [1/20][98/510] Data 2.789 (3.816) Batch 21.402 (28.404) Remain 79:42:13 loss: 0.2525 loss_seg: 0.1506 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:09:42,679 INFO misc.py line 117 726] Train: [1/20][99/510] Data 2.056 (3.798) Batch 15.541 (28.270) Remain 79:19:11 loss: 0.3640 loss_seg: 0.2547 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:10:18,267 INFO misc.py line 117 726] Train: [1/20][100/510] Data 7.551 (3.836) Batch 35.588 (28.345) Remain 79:31:25 loss: 0.2463 loss_seg: 0.1582 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:10:18,267 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 15:10:50,286 INFO misc.py line 117 726] Train: [1/20][101/510] Data 3.763 (3.836) Batch 32.019 (28.383) Remain 79:37:15 loss: 0.2056 loss_seg: 0.1145 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:11:24,205 INFO misc.py line 117 726] Train: [1/20][102/510] Data 3.215 (3.829) Batch 33.919 (28.438) Remain 79:46:11 loss: 0.2008 loss_seg: 0.1118 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:12:02,086 INFO misc.py line 117 726] Train: [1/20][103/510] Data 6.409 (3.855) Batch 37.881 (28.533) Remain 80:01:36 loss: 0.2669 loss_seg: 0.1672 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:12:23,808 INFO misc.py line 117 726] Train: [1/20][104/510] Data 2.783 (3.845) Batch 21.722 (28.465) Remain 79:49:47 loss: 0.2997 loss_seg: 0.1995 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:12:53,507 INFO misc.py line 117 726] Train: [1/20][105/510] Data 3.093 (3.837) Batch 29.700 (28.478) Remain 79:51:20 loss: 0.2127 loss_seg: 0.1238 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:13:21,391 INFO misc.py line 117 726] Train: [1/20][106/510] Data 3.129 (3.830) Batch 27.883 (28.472) Remain 79:49:54 loss: 0.2188 loss_seg: 0.1256 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:13:58,845 INFO misc.py line 117 726] Train: [1/20][107/510] Data 12.505 (3.914) Batch 37.454 (28.558) Remain 80:03:57 loss: 0.3383 loss_seg: 0.2392 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:14:20,428 INFO misc.py line 117 726] Train: [1/20][108/510] Data 3.864 (3.913) Batch 21.583 (28.492) Remain 79:52:18 loss: 0.2081 loss_seg: 0.1179 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:14:45,721 INFO misc.py line 117 726] Train: [1/20][109/510] Data 4.242 (3.916) Batch 25.293 (28.462) Remain 79:46:45 loss: 0.3121 loss_seg: 0.2001 loss_superpoint_edge: 0.0441 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:15:14,554 INFO misc.py line 117 726] Train: [1/20][110/510] Data 3.517 (3.913) Batch 28.833 (28.465) Remain 79:46:52 loss: 0.2037 loss_seg: 0.1181 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:15:34,937 INFO misc.py line 117 726] Train: [1/20][111/510] Data 2.476 (3.899) Batch 20.383 (28.390) Remain 79:33:48 loss: 0.2108 loss_seg: 0.1237 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:16:03,548 INFO misc.py line 117 726] Train: [1/20][112/510] Data 4.157 (3.902) Batch 28.611 (28.392) Remain 79:33:40 loss: 0.2487 loss_seg: 0.1526 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:16:24,420 INFO misc.py line 117 726] Train: [1/20][113/510] Data 2.421 (3.888) Batch 20.871 (28.324) Remain 79:21:42 loss: 0.2371 loss_seg: 0.1468 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:16:39,690 INFO misc.py line 117 726] Train: [1/20][114/510] Data 2.139 (3.872) Batch 15.270 (28.206) Remain 79:01:28 loss: 0.2019 loss_seg: 0.1083 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:17:04,279 INFO misc.py line 117 726] Train: [1/20][115/510] Data 3.613 (3.870) Batch 24.590 (28.174) Remain 78:55:34 loss: 0.2223 loss_seg: 0.1296 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:17:30,604 INFO misc.py line 117 726] Train: [1/20][116/510] Data 2.884 (3.861) Batch 26.325 (28.158) Remain 78:52:21 loss: 0.2805 loss_seg: 0.1881 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:18:00,069 INFO misc.py line 117 726] Train: [1/20][117/510] Data 3.465 (3.858) Batch 29.465 (28.169) Remain 78:53:48 loss: 0.2212 loss_seg: 0.1292 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:18:29,427 INFO misc.py line 117 726] Train: [1/20][118/510] Data 3.585 (3.856) Batch 29.358 (28.179) Remain 78:55:04 loss: 0.2008 loss_seg: 0.1121 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:18:55,012 INFO misc.py line 117 726] Train: [1/20][119/510] Data 2.983 (3.848) Batch 25.586 (28.157) Remain 78:50:51 loss: 0.3521 loss_seg: 0.2435 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:19:28,213 INFO misc.py line 117 726] Train: [1/20][120/510] Data 3.963 (3.849) Batch 33.201 (28.200) Remain 78:57:37 loss: 0.2437 loss_seg: 0.1479 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:20:02,549 INFO misc.py line 117 726] Train: [1/20][121/510] Data 4.322 (3.853) Batch 34.336 (28.252) Remain 79:05:53 loss: 0.2436 loss_seg: 0.1495 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:20:26,164 INFO misc.py line 117 726] Train: [1/20][122/510] Data 2.868 (3.845) Batch 23.615 (28.213) Remain 78:58:52 loss: 0.2773 loss_seg: 0.1739 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:20:52,265 INFO misc.py line 117 726] Train: [1/20][123/510] Data 3.087 (3.838) Batch 26.101 (28.196) Remain 78:55:26 loss: 0.3470 loss_seg: 0.2525 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:21:15,536 INFO misc.py line 117 726] Train: [1/20][124/510] Data 2.642 (3.829) Batch 23.271 (28.155) Remain 78:48:08 loss: 0.1955 loss_seg: 0.1071 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:21:57,155 INFO misc.py line 117 726] Train: [1/20][125/510] Data 8.130 (3.864) Batch 41.619 (28.265) Remain 79:06:12 loss: 0.2289 loss_seg: 0.1350 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:22:23,267 INFO misc.py line 117 726] Train: [1/20][126/510] Data 5.272 (3.875) Batch 26.112 (28.248) Remain 79:02:47 loss: 0.1909 loss_seg: 0.0989 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0446 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:22:47,331 INFO misc.py line 117 726] Train: [1/20][127/510] Data 2.455 (3.864) Batch 24.064 (28.214) Remain 78:56:39 loss: 0.3559 loss_seg: 0.2459 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:23:17,616 INFO misc.py line 117 726] Train: [1/20][128/510] Data 6.180 (3.882) Batch 30.284 (28.231) Remain 78:58:58 loss: 0.2744 loss_seg: 0.1761 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:23:46,521 INFO misc.py line 117 726] Train: [1/20][129/510] Data 3.090 (3.876) Batch 28.905 (28.236) Remain 78:59:23 loss: 0.2124 loss_seg: 0.1239 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:24:15,638 INFO misc.py line 117 726] Train: [1/20][130/510] Data 3.325 (3.872) Batch 29.117 (28.243) Remain 79:00:05 loss: 0.3238 loss_seg: 0.2197 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:24:41,524 INFO misc.py line 117 726] Train: [1/20][131/510] Data 2.842 (3.864) Batch 25.887 (28.224) Remain 78:56:31 loss: 0.2616 loss_seg: 0.1652 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:25:08,111 INFO misc.py line 117 726] Train: [1/20][132/510] Data 4.428 (3.868) Batch 26.587 (28.212) Remain 78:53:55 loss: 0.1992 loss_seg: 0.1093 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:25:44,671 INFO misc.py line 117 726] Train: [1/20][133/510] Data 4.627 (3.874) Batch 36.561 (28.276) Remain 79:04:14 loss: 0.2764 loss_seg: 0.1794 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:26:13,591 INFO misc.py line 117 726] Train: [1/20][134/510] Data 3.654 (3.872) Batch 28.920 (28.281) Remain 79:04:35 loss: 0.2581 loss_seg: 0.1585 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:26:31,545 INFO misc.py line 117 726] Train: [1/20][135/510] Data 1.889 (3.857) Batch 17.954 (28.203) Remain 78:50:59 loss: 0.2661 loss_seg: 0.1732 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:27:10,819 INFO misc.py line 117 726] Train: [1/20][136/510] Data 5.642 (3.871) Batch 39.274 (28.286) Remain 79:04:29 loss: 0.3011 loss_seg: 0.1937 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-09 15:27:36,247 INFO misc.py line 117 726] Train: [1/20][137/510] Data 2.920 (3.863) Batch 25.428 (28.265) Remain 79:00:26 loss: 0.2715 loss_seg: 0.1692 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:28:08,404 INFO misc.py line 117 726] Train: [1/20][138/510] Data 3.898 (3.864) Batch 32.156 (28.293) Remain 79:04:47 loss: 0.1941 loss_seg: 0.1101 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:28:40,608 INFO misc.py line 117 726] Train: [1/20][139/510] Data 3.844 (3.864) Batch 32.205 (28.322) Remain 79:09:09 loss: 0.2124 loss_seg: 0.1267 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:29:02,922 INFO misc.py line 117 726] Train: [1/20][140/510] Data 7.066 (3.887) Batch 22.314 (28.278) Remain 79:01:19 loss: 0.1869 loss_seg: 0.0952 loss_superpoint_edge: 0.0124 loss_superpoint_contrast: 0.0492 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:29:27,182 INFO misc.py line 117 726] Train: [1/20][141/510] Data 3.391 (3.883) Batch 24.260 (28.249) Remain 78:55:58 loss: 0.2243 loss_seg: 0.1355 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:29:57,565 INFO misc.py line 117 726] Train: [1/20][142/510] Data 4.744 (3.890) Batch 30.383 (28.265) Remain 78:58:04 loss: 0.2550 loss_seg: 0.1613 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:30:17,879 INFO misc.py line 117 726] Train: [1/20][143/510] Data 3.072 (3.884) Batch 20.314 (28.208) Remain 78:48:05 loss: 0.4114 loss_seg: 0.3066 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:30:39,806 INFO misc.py line 117 726] Train: [1/20][144/510] Data 2.995 (3.877) Batch 21.927 (28.163) Remain 78:40:08 loss: 0.2675 loss_seg: 0.1694 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:31:02,182 INFO misc.py line 117 726] Train: [1/20][145/510] Data 2.394 (3.867) Batch 22.376 (28.122) Remain 78:32:51 loss: 0.2265 loss_seg: 0.1328 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:31:34,869 INFO misc.py line 117 726] Train: [1/20][146/510] Data 3.743 (3.866) Batch 32.687 (28.154) Remain 78:37:43 loss: 0.3382 loss_seg: 0.2384 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:32:06,415 INFO misc.py line 117 726] Train: [1/20][147/510] Data 2.737 (3.858) Batch 31.546 (28.178) Remain 78:41:12 loss: 0.2566 loss_seg: 0.1605 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:32:30,204 INFO misc.py line 117 726] Train: [1/20][148/510] Data 3.103 (3.853) Batch 23.790 (28.148) Remain 78:35:40 loss: 0.2193 loss_seg: 0.1293 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:32:53,457 INFO misc.py line 117 726] Train: [1/20][149/510] Data 3.009 (3.847) Batch 23.253 (28.114) Remain 78:29:34 loss: 0.2461 loss_seg: 0.1522 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:33:09,595 INFO misc.py line 117 726] Train: [1/20][150/510] Data 2.334 (3.837) Batch 16.138 (28.033) Remain 78:15:28 loss: 0.2422 loss_seg: 0.1495 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:33:09,595 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 15:33:38,006 INFO misc.py line 117 726] Train: [1/20][151/510] Data 4.530 (3.842) Batch 28.411 (28.035) Remain 78:15:25 loss: 0.2598 loss_seg: 0.1613 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:34:13,259 INFO misc.py line 117 726] Train: [1/20][152/510] Data 8.087 (3.870) Batch 35.254 (28.084) Remain 78:23:04 loss: 0.4419 loss_seg: 0.3174 loss_superpoint_edge: 0.0533 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0344 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:34:48,090 INFO misc.py line 117 726] Train: [1/20][153/510] Data 4.565 (3.875) Batch 34.831 (28.129) Remain 78:30:08 loss: 0.1949 loss_seg: 0.1042 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:35:22,817 INFO misc.py line 117 726] Train: [1/20][154/510] Data 6.650 (3.893) Batch 34.726 (28.172) Remain 78:36:59 loss: 0.2656 loss_seg: 0.1676 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:35:44,102 INFO misc.py line 117 726] Train: [1/20][155/510] Data 2.395 (3.883) Batch 21.285 (28.127) Remain 78:28:55 loss: 0.2684 loss_seg: 0.1713 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:36:15,167 INFO misc.py line 117 726] Train: [1/20][156/510] Data 2.966 (3.877) Batch 31.065 (28.146) Remain 78:31:40 loss: 0.2452 loss_seg: 0.1478 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:36:52,963 INFO misc.py line 117 726] Train: [1/20][157/510] Data 6.995 (3.898) Batch 37.796 (28.209) Remain 78:41:41 loss: 0.2368 loss_seg: 0.1437 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:37:18,895 INFO misc.py line 117 726] Train: [1/20][158/510] Data 3.820 (3.897) Batch 25.932 (28.194) Remain 78:38:45 loss: 0.3114 loss_seg: 0.2177 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:37:57,258 INFO misc.py line 117 726] Train: [1/20][159/510] Data 8.488 (3.927) Batch 38.363 (28.259) Remain 78:49:12 loss: 0.3879 loss_seg: 0.2716 loss_superpoint_edge: 0.0468 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:38:28,978 INFO misc.py line 117 726] Train: [1/20][160/510] Data 3.787 (3.926) Batch 31.720 (28.281) Remain 78:52:25 loss: 0.2205 loss_seg: 0.1277 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:38:50,686 INFO misc.py line 117 726] Train: [1/20][161/510] Data 2.567 (3.917) Batch 21.709 (28.240) Remain 78:44:59 loss: 0.2634 loss_seg: 0.1659 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:39:30,097 INFO misc.py line 117 726] Train: [1/20][162/510] Data 8.938 (3.949) Batch 39.411 (28.310) Remain 78:56:16 loss: 0.3294 loss_seg: 0.2281 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:39:48,073 INFO misc.py line 117 726] Train: [1/20][163/510] Data 1.805 (3.935) Batch 17.976 (28.245) Remain 78:44:59 loss: 0.3219 loss_seg: 0.2295 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:40:21,921 INFO misc.py line 117 726] Train: [1/20][164/510] Data 4.155 (3.937) Batch 33.847 (28.280) Remain 78:50:20 loss: 0.3216 loss_seg: 0.2277 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:40:54,837 INFO misc.py line 117 726] Train: [1/20][165/510] Data 6.567 (3.953) Batch 32.916 (28.309) Remain 78:54:39 loss: 0.2962 loss_seg: 0.1918 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:41:19,398 INFO misc.py line 117 726] Train: [1/20][166/510] Data 2.532 (3.944) Batch 24.561 (28.286) Remain 78:50:20 loss: 0.2365 loss_seg: 0.1424 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:41:52,843 INFO misc.py line 117 726] Train: [1/20][167/510] Data 4.936 (3.950) Batch 33.445 (28.317) Remain 78:55:07 loss: 0.1901 loss_seg: 0.1017 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:42:23,213 INFO misc.py line 117 726] Train: [1/20][168/510] Data 5.466 (3.959) Batch 30.371 (28.330) Remain 78:56:44 loss: 0.3009 loss_seg: 0.1973 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:42:58,578 INFO misc.py line 117 726] Train: [1/20][169/510] Data 4.908 (3.965) Batch 35.361 (28.372) Remain 79:03:21 loss: 0.3437 loss_seg: 0.2352 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:43:32,523 INFO misc.py line 117 726] Train: [1/20][170/510] Data 3.214 (3.961) Batch 33.949 (28.406) Remain 79:08:27 loss: 0.1978 loss_seg: 0.1111 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:43:53,065 INFO misc.py line 117 726] Train: [1/20][171/510] Data 2.474 (3.952) Batch 20.542 (28.359) Remain 79:00:09 loss: 0.2299 loss_seg: 0.1330 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:44:27,162 INFO misc.py line 117 726] Train: [1/20][172/510] Data 5.076 (3.958) Batch 34.097 (28.393) Remain 79:05:21 loss: 0.2788 loss_seg: 0.1788 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:44:58,511 INFO misc.py line 117 726] Train: [1/20][173/510] Data 4.262 (3.960) Batch 31.349 (28.410) Remain 79:07:47 loss: 0.2686 loss_seg: 0.1706 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:45:25,445 INFO misc.py line 117 726] Train: [1/20][174/510] Data 3.662 (3.958) Batch 26.934 (28.401) Remain 79:05:52 loss: 0.2474 loss_seg: 0.1567 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:45:52,758 INFO misc.py line 117 726] Train: [1/20][175/510] Data 3.635 (3.957) Batch 27.314 (28.395) Remain 79:04:21 loss: 0.2601 loss_seg: 0.1569 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:46:23,217 INFO misc.py line 117 726] Train: [1/20][176/510] Data 3.020 (3.951) Batch 30.458 (28.407) Remain 79:05:52 loss: 0.2033 loss_seg: 0.1172 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:46:44,580 INFO misc.py line 117 726] Train: [1/20][177/510] Data 2.738 (3.944) Batch 21.363 (28.367) Remain 78:58:38 loss: 0.3695 loss_seg: 0.2522 loss_superpoint_edge: 0.0460 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:47:09,038 INFO misc.py line 117 726] Train: [1/20][178/510] Data 2.721 (3.937) Batch 24.458 (28.344) Remain 78:54:25 loss: 0.2455 loss_seg: 0.1485 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:47:35,961 INFO misc.py line 117 726] Train: [1/20][179/510] Data 3.393 (3.934) Batch 26.923 (28.336) Remain 78:52:36 loss: 0.2170 loss_seg: 0.1265 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:47:59,769 INFO misc.py line 117 726] Train: [1/20][180/510] Data 2.446 (3.926) Batch 23.809 (28.311) Remain 78:47:51 loss: 0.2578 loss_seg: 0.1588 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:48:26,904 INFO misc.py line 117 726] Train: [1/20][181/510] Data 2.552 (3.918) Batch 27.135 (28.304) Remain 78:46:17 loss: 0.2336 loss_seg: 0.1423 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:48:49,109 INFO misc.py line 117 726] Train: [1/20][182/510] Data 2.081 (3.908) Batch 22.205 (28.270) Remain 78:40:07 loss: 0.2334 loss_seg: 0.1351 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:49:20,191 INFO misc.py line 117 726] Train: [1/20][183/510] Data 4.209 (3.909) Batch 31.083 (28.286) Remain 78:42:16 loss: 0.2646 loss_seg: 0.1689 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:49:51,634 INFO misc.py line 117 726] Train: [1/20][184/510] Data 2.882 (3.904) Batch 31.443 (28.303) Remain 78:44:42 loss: 0.2075 loss_seg: 0.1155 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:50:14,164 INFO misc.py line 117 726] Train: [1/20][185/510] Data 2.558 (3.896) Batch 22.531 (28.271) Remain 78:38:56 loss: 0.3563 loss_seg: 0.2414 loss_superpoint_edge: 0.0455 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:50:44,089 INFO misc.py line 117 726] Train: [1/20][186/510] Data 4.884 (3.902) Batch 29.924 (28.280) Remain 78:39:58 loss: 0.2904 loss_seg: 0.1975 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:51:05,729 INFO misc.py line 117 726] Train: [1/20][187/510] Data 2.565 (3.894) Batch 21.640 (28.244) Remain 78:33:29 loss: 0.2337 loss_seg: 0.1459 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:51:28,133 INFO misc.py line 117 726] Train: [1/20][188/510] Data 2.182 (3.885) Batch 22.403 (28.213) Remain 78:27:44 loss: 0.3148 loss_seg: 0.2194 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:51:56,565 INFO misc.py line 117 726] Train: [1/20][189/510] Data 4.944 (3.891) Batch 28.432 (28.214) Remain 78:27:28 loss: 0.1987 loss_seg: 0.1134 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:52:25,146 INFO misc.py line 117 726] Train: [1/20][190/510] Data 3.531 (3.889) Batch 28.582 (28.216) Remain 78:27:19 loss: 0.2853 loss_seg: 0.1871 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:53:00,549 INFO misc.py line 117 726] Train: [1/20][191/510] Data 5.528 (3.898) Batch 35.402 (28.254) Remain 78:33:14 loss: 0.2610 loss_seg: 0.1626 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:53:28,617 INFO misc.py line 117 726] Train: [1/20][192/510] Data 3.116 (3.893) Batch 28.068 (28.253) Remain 78:32:36 loss: 0.3345 loss_seg: 0.2415 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:53:51,276 INFO misc.py line 117 726] Train: [1/20][193/510] Data 2.268 (3.885) Batch 22.659 (28.224) Remain 78:27:13 loss: 0.2852 loss_seg: 0.1763 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:54:36,229 INFO misc.py line 117 726] Train: [1/20][194/510] Data 13.625 (3.936) Batch 44.953 (28.311) Remain 78:41:21 loss: 0.3104 loss_seg: 0.2143 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:55:03,398 INFO misc.py line 117 726] Train: [1/20][195/510] Data 5.356 (3.943) Batch 27.169 (28.305) Remain 78:39:53 loss: 0.2374 loss_seg: 0.1439 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:55:35,610 INFO misc.py line 117 726] Train: [1/20][196/510] Data 3.842 (3.943) Batch 32.212 (28.325) Remain 78:42:47 loss: 0.2637 loss_seg: 0.1628 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:56:00,499 INFO misc.py line 117 726] Train: [1/20][197/510] Data 2.668 (3.936) Batch 24.889 (28.308) Remain 78:39:22 loss: 0.3539 loss_seg: 0.2533 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:56:25,698 INFO misc.py line 117 726] Train: [1/20][198/510] Data 3.368 (3.933) Batch 25.199 (28.292) Remain 78:36:14 loss: 0.2191 loss_seg: 0.1238 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:56:52,184 INFO misc.py line 117 726] Train: [1/20][199/510] Data 2.548 (3.926) Batch 26.485 (28.283) Remain 78:34:14 loss: 0.2949 loss_seg: 0.1881 loss_superpoint_edge: 0.0405 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:57:15,527 INFO misc.py line 117 726] Train: [1/20][200/510] Data 2.806 (3.921) Batch 23.344 (28.258) Remain 78:29:35 loss: 0.2722 loss_seg: 0.1756 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:57:15,528 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 15:57:42,610 INFO misc.py line 117 726] Train: [1/20][201/510] Data 4.206 (3.922) Batch 27.082 (28.252) Remain 78:28:07 loss: 0.2839 loss_seg: 0.1786 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:58:16,676 INFO misc.py line 117 726] Train: [1/20][202/510] Data 5.218 (3.929) Batch 34.066 (28.281) Remain 78:32:31 loss: 0.2460 loss_seg: 0.1484 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:58:41,811 INFO misc.py line 117 726] Train: [1/20][203/510] Data 3.377 (3.926) Batch 25.135 (28.265) Remain 78:29:25 loss: 0.3259 loss_seg: 0.2134 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:59:10,982 INFO misc.py line 117 726] Train: [1/20][204/510] Data 2.373 (3.918) Batch 29.171 (28.270) Remain 78:29:42 loss: 0.2968 loss_seg: 0.1928 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:59:34,722 INFO misc.py line 117 726] Train: [1/20][205/510] Data 3.600 (3.916) Batch 23.740 (28.247) Remain 78:25:30 loss: 0.2779 loss_seg: 0.1753 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 15:59:56,951 INFO misc.py line 117 726] Train: [1/20][206/510] Data 2.901 (3.911) Batch 22.229 (28.218) Remain 78:20:05 loss: 0.2220 loss_seg: 0.1299 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:00:23,064 INFO misc.py line 117 726] Train: [1/20][207/510] Data 4.533 (3.915) Batch 26.113 (28.207) Remain 78:17:54 loss: 0.2354 loss_seg: 0.1420 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:00:45,789 INFO misc.py line 117 726] Train: [1/20][208/510] Data 2.617 (3.908) Batch 22.725 (28.180) Remain 78:12:59 loss: 0.2597 loss_seg: 0.1669 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:01:13,302 INFO misc.py line 117 726] Train: [1/20][209/510] Data 3.282 (3.905) Batch 27.513 (28.177) Remain 78:11:58 loss: 0.2483 loss_seg: 0.1474 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:01:31,046 INFO misc.py line 117 726] Train: [1/20][210/510] Data 3.008 (3.901) Batch 17.743 (28.127) Remain 78:03:06 loss: 0.2090 loss_seg: 0.1183 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:01:56,105 INFO misc.py line 117 726] Train: [1/20][211/510] Data 2.861 (3.896) Batch 25.059 (28.112) Remain 78:00:11 loss: 0.2820 loss_seg: 0.1779 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:02:23,033 INFO misc.py line 117 726] Train: [1/20][212/510] Data 2.692 (3.890) Batch 26.928 (28.106) Remain 77:58:46 loss: 0.2005 loss_seg: 0.1110 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:02:42,934 INFO misc.py line 117 726] Train: [1/20][213/510] Data 3.026 (3.886) Batch 19.902 (28.067) Remain 77:51:48 loss: 0.2634 loss_seg: 0.1662 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:03:14,604 INFO misc.py line 117 726] Train: [1/20][214/510] Data 4.143 (3.887) Batch 31.669 (28.084) Remain 77:54:10 loss: 0.3115 loss_seg: 0.2187 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:03:52,416 INFO misc.py line 117 726] Train: [1/20][215/510] Data 5.704 (3.896) Batch 37.813 (28.130) Remain 78:01:20 loss: 0.2450 loss_seg: 0.1559 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:04:28,014 INFO misc.py line 117 726] Train: [1/20][216/510] Data 6.587 (3.908) Batch 35.598 (28.165) Remain 78:06:42 loss: 0.2938 loss_seg: 0.1929 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:05:00,001 INFO misc.py line 117 726] Train: [1/20][217/510] Data 4.674 (3.912) Batch 31.987 (28.183) Remain 78:09:12 loss: 0.2801 loss_seg: 0.1717 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:05:33,892 INFO misc.py line 117 726] Train: [1/20][218/510] Data 4.763 (3.916) Batch 33.891 (28.210) Remain 78:13:09 loss: 0.2397 loss_seg: 0.1480 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:06:05,407 INFO misc.py line 117 726] Train: [1/20][219/510] Data 5.860 (3.925) Batch 31.515 (28.225) Remain 78:15:14 loss: 0.3482 loss_seg: 0.2519 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:06:35,622 INFO misc.py line 117 726] Train: [1/20][220/510] Data 3.668 (3.924) Batch 30.215 (28.234) Remain 78:16:17 loss: 0.2226 loss_seg: 0.1341 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:07:04,525 INFO misc.py line 117 726] Train: [1/20][221/510] Data 3.114 (3.920) Batch 28.903 (28.237) Remain 78:16:19 loss: 0.3018 loss_seg: 0.1955 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:07:28,296 INFO misc.py line 117 726] Train: [1/20][222/510] Data 2.872 (3.915) Batch 23.771 (28.217) Remain 78:12:28 loss: 0.2409 loss_seg: 0.1486 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:07:56,808 INFO misc.py line 117 726] Train: [1/20][223/510] Data 3.486 (3.913) Batch 28.511 (28.218) Remain 78:12:13 loss: 0.1995 loss_seg: 0.1124 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:08:29,140 INFO misc.py line 117 726] Train: [1/20][224/510] Data 3.518 (3.911) Batch 32.333 (28.237) Remain 78:14:50 loss: 0.2536 loss_seg: 0.1567 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:08:46,915 INFO misc.py line 117 726] Train: [1/20][225/510] Data 2.430 (3.905) Batch 17.775 (28.190) Remain 78:06:32 loss: 0.2999 loss_seg: 0.1934 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:09:09,996 INFO misc.py line 117 726] Train: [1/20][226/510] Data 2.969 (3.901) Batch 23.080 (28.167) Remain 78:02:15 loss: 0.2316 loss_seg: 0.1372 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:09:36,004 INFO misc.py line 117 726] Train: [1/20][227/510] Data 2.389 (3.894) Batch 26.009 (28.157) Remain 78:00:11 loss: 0.2126 loss_seg: 0.1249 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:10:07,822 INFO misc.py line 117 726] Train: [1/20][228/510] Data 4.504 (3.897) Batch 31.818 (28.173) Remain 78:02:25 loss: 0.3116 loss_seg: 0.2027 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:10:34,570 INFO misc.py line 117 726] Train: [1/20][229/510] Data 2.075 (3.889) Batch 26.748 (28.167) Remain 78:00:54 loss: 0.2466 loss_seg: 0.1536 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:11:05,650 INFO misc.py line 117 726] Train: [1/20][230/510] Data 4.221 (3.890) Batch 31.079 (28.180) Remain 78:02:34 loss: 0.3344 loss_seg: 0.2402 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:11:34,550 INFO misc.py line 117 726] Train: [1/20][231/510] Data 4.366 (3.892) Batch 28.900 (28.183) Remain 78:02:37 loss: 0.2665 loss_seg: 0.1627 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:12:09,187 INFO misc.py line 117 726] Train: [1/20][232/510] Data 3.940 (3.892) Batch 34.637 (28.211) Remain 78:06:50 loss: 0.2822 loss_seg: 0.1804 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:12:39,492 INFO misc.py line 117 726] Train: [1/20][233/510] Data 4.094 (3.893) Batch 30.304 (28.220) Remain 78:07:52 loss: 0.2301 loss_seg: 0.1391 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:13:08,727 INFO misc.py line 117 726] Train: [1/20][234/510] Data 2.318 (3.886) Batch 29.235 (28.225) Remain 78:08:08 loss: 0.3072 loss_seg: 0.2029 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:13:34,186 INFO misc.py line 117 726] Train: [1/20][235/510] Data 3.034 (3.883) Batch 25.459 (28.213) Remain 78:05:41 loss: 0.2461 loss_seg: 0.1496 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:14:00,883 INFO misc.py line 117 726] Train: [1/20][236/510] Data 2.930 (3.879) Batch 26.696 (28.206) Remain 78:04:08 loss: 0.1971 loss_seg: 0.1090 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:14:33,692 INFO misc.py line 117 726] Train: [1/20][237/510] Data 4.126 (3.880) Batch 32.810 (28.226) Remain 78:06:56 loss: 0.2550 loss_seg: 0.1574 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:15:01,330 INFO misc.py line 117 726] Train: [1/20][238/510] Data 4.253 (3.881) Batch 27.638 (28.224) Remain 78:06:02 loss: 0.2481 loss_seg: 0.1524 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:15:29,870 INFO misc.py line 117 726] Train: [1/20][239/510] Data 4.626 (3.884) Batch 28.540 (28.225) Remain 78:05:48 loss: 0.2228 loss_seg: 0.1357 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:16:01,354 INFO misc.py line 117 726] Train: [1/20][240/510] Data 3.754 (3.884) Batch 31.484 (28.239) Remain 78:07:36 loss: 0.3011 loss_seg: 0.1933 loss_superpoint_edge: 0.0423 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:16:36,312 INFO misc.py line 117 726] Train: [1/20][241/510] Data 4.539 (3.887) Batch 34.959 (28.267) Remain 78:11:49 loss: 0.2163 loss_seg: 0.1294 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:17:05,511 INFO misc.py line 117 726] Train: [1/20][242/510] Data 3.103 (3.883) Batch 29.199 (28.271) Remain 78:12:00 loss: 0.3143 loss_seg: 0.2083 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:17:32,669 INFO misc.py line 117 726] Train: [1/20][243/510] Data 2.525 (3.878) Batch 27.158 (28.266) Remain 78:10:45 loss: 0.2445 loss_seg: 0.1451 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:17:55,585 INFO misc.py line 117 726] Train: [1/20][244/510] Data 2.262 (3.871) Batch 22.916 (28.244) Remain 78:06:36 loss: 0.2828 loss_seg: 0.1774 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:18:22,863 INFO misc.py line 117 726] Train: [1/20][245/510] Data 3.070 (3.868) Batch 27.278 (28.240) Remain 78:05:28 loss: 0.2488 loss_seg: 0.1509 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:18:55,137 INFO misc.py line 117 726] Train: [1/20][246/510] Data 4.437 (3.870) Batch 32.274 (28.257) Remain 78:07:45 loss: 0.2491 loss_seg: 0.1505 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:19:27,596 INFO misc.py line 117 726] Train: [1/20][247/510] Data 3.637 (3.869) Batch 32.459 (28.274) Remain 78:10:08 loss: 0.2353 loss_seg: 0.1390 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:19:54,582 INFO misc.py line 117 726] Train: [1/20][248/510] Data 8.739 (3.889) Batch 26.986 (28.269) Remain 78:08:48 loss: 0.5237 loss_seg: 0.3750 loss_superpoint_edge: 0.0796 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:20:22,288 INFO misc.py line 117 726] Train: [1/20][249/510] Data 3.033 (3.885) Batch 27.706 (28.266) Remain 78:07:57 loss: 0.3544 loss_seg: 0.2526 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:20:44,112 INFO misc.py line 117 726] Train: [1/20][250/510] Data 2.214 (3.879) Batch 21.823 (28.240) Remain 78:03:09 loss: 0.3416 loss_seg: 0.2357 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:20:44,112 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 16:21:11,311 INFO misc.py line 117 726] Train: [1/20][251/510] Data 4.961 (3.883) Batch 27.199 (28.236) Remain 78:01:59 loss: 0.1790 loss_seg: 0.0918 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:21:33,415 INFO misc.py line 117 726] Train: [1/20][252/510] Data 2.510 (3.877) Batch 22.104 (28.211) Remain 77:57:26 loss: 0.2372 loss_seg: 0.1474 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:21:55,306 INFO misc.py line 117 726] Train: [1/20][253/510] Data 2.225 (3.871) Batch 21.891 (28.186) Remain 77:52:46 loss: 0.2191 loss_seg: 0.1302 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:22:17,346 INFO misc.py line 117 726] Train: [1/20][254/510] Data 2.569 (3.866) Batch 22.040 (28.162) Remain 77:48:14 loss: 0.1836 loss_seg: 0.0981 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:22:45,870 INFO misc.py line 117 726] Train: [1/20][255/510] Data 3.847 (3.866) Batch 28.524 (28.163) Remain 77:48:00 loss: 0.2362 loss_seg: 0.1413 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:23:12,758 INFO misc.py line 117 726] Train: [1/20][256/510] Data 5.522 (3.872) Batch 26.888 (28.158) Remain 77:46:42 loss: 0.2631 loss_seg: 0.1613 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:23:37,714 INFO misc.py line 117 726] Train: [1/20][257/510] Data 2.328 (3.866) Batch 24.957 (28.145) Remain 77:44:09 loss: 0.2323 loss_seg: 0.1384 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:24:08,560 INFO misc.py line 117 726] Train: [1/20][258/510] Data 4.060 (3.867) Batch 30.845 (28.156) Remain 77:45:26 loss: 0.2280 loss_seg: 0.1381 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:24:35,470 INFO misc.py line 117 726] Train: [1/20][259/510] Data 2.881 (3.863) Batch 26.911 (28.151) Remain 77:44:09 loss: 0.2608 loss_seg: 0.1622 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:25:01,902 INFO misc.py line 117 726] Train: [1/20][260/510] Data 3.862 (3.863) Batch 26.432 (28.144) Remain 77:42:35 loss: 0.2542 loss_seg: 0.1566 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0444 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:25:25,411 INFO misc.py line 117 726] Train: [1/20][261/510] Data 3.474 (3.861) Batch 23.508 (28.126) Remain 77:39:08 loss: 0.2440 loss_seg: 0.1486 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:25:50,863 INFO misc.py line 117 726] Train: [1/20][262/510] Data 2.668 (3.857) Batch 25.453 (28.116) Remain 77:36:57 loss: 0.2451 loss_seg: 0.1543 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:26:14,040 INFO misc.py line 117 726] Train: [1/20][263/510] Data 1.909 (3.849) Batch 23.176 (28.097) Remain 77:33:20 loss: 0.2095 loss_seg: 0.1219 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:26:48,247 INFO misc.py line 117 726] Train: [1/20][264/510] Data 7.985 (3.865) Batch 34.207 (28.120) Remain 77:36:45 loss: 0.2713 loss_seg: 0.1726 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:27:14,226 INFO misc.py line 117 726] Train: [1/20][265/510] Data 2.390 (3.860) Batch 25.979 (28.112) Remain 77:34:55 loss: 0.1753 loss_seg: 0.0861 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:27:38,738 INFO misc.py line 117 726] Train: [1/20][266/510] Data 3.118 (3.857) Batch 24.512 (28.099) Remain 77:32:11 loss: 0.2180 loss_seg: 0.1256 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:28:13,123 INFO misc.py line 117 726] Train: [1/20][267/510] Data 9.235 (3.877) Batch 34.385 (28.122) Remain 77:35:40 loss: 0.2467 loss_seg: 0.1525 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:28:39,094 INFO misc.py line 117 726] Train: [1/20][268/510] Data 2.899 (3.873) Batch 25.971 (28.114) Remain 77:33:51 loss: 0.2129 loss_seg: 0.1206 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:29:01,230 INFO misc.py line 117 726] Train: [1/20][269/510] Data 2.611 (3.869) Batch 22.137 (28.092) Remain 77:29:40 loss: 0.2216 loss_seg: 0.1299 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:29:27,871 INFO misc.py line 117 726] Train: [1/20][270/510] Data 5.402 (3.874) Batch 26.641 (28.086) Remain 77:28:18 loss: 0.3902 loss_seg: 0.2800 loss_superpoint_edge: 0.0436 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:29:44,681 INFO misc.py line 117 726] Train: [1/20][271/510] Data 2.414 (3.869) Batch 16.810 (28.044) Remain 77:20:52 loss: 0.2431 loss_seg: 0.1552 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:30:09,877 INFO misc.py line 117 726] Train: [1/20][272/510] Data 4.020 (3.870) Batch 25.196 (28.034) Remain 77:18:39 loss: 0.3040 loss_seg: 0.2047 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:30:32,858 INFO misc.py line 117 726] Train: [1/20][273/510] Data 4.791 (3.873) Batch 22.981 (28.015) Remain 77:15:05 loss: 0.2681 loss_seg: 0.1690 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:31:06,231 INFO misc.py line 117 726] Train: [1/20][274/510] Data 3.846 (3.873) Batch 33.374 (28.035) Remain 77:17:53 loss: 0.2094 loss_seg: 0.1182 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:31:40,107 INFO misc.py line 117 726] Train: [1/20][275/510] Data 4.510 (3.875) Batch 33.876 (28.056) Remain 77:20:58 loss: 0.2240 loss_seg: 0.1313 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:32:02,153 INFO misc.py line 117 726] Train: [1/20][276/510] Data 2.766 (3.871) Batch 22.045 (28.034) Remain 77:16:52 loss: 0.2145 loss_seg: 0.1228 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:32:26,484 INFO misc.py line 117 726] Train: [1/20][277/510] Data 2.844 (3.867) Batch 24.331 (28.021) Remain 77:14:09 loss: 0.2161 loss_seg: 0.1246 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:32:50,378 INFO misc.py line 117 726] Train: [1/20][278/510] Data 3.292 (3.865) Batch 23.895 (28.006) Remain 77:11:13 loss: 0.2718 loss_seg: 0.1726 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:33:24,552 INFO misc.py line 117 726] Train: [1/20][279/510] Data 5.305 (3.871) Batch 34.174 (28.028) Remain 77:14:26 loss: 0.2655 loss_seg: 0.1722 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:33:51,333 INFO misc.py line 117 726] Train: [1/20][280/510] Data 3.848 (3.870) Batch 26.780 (28.024) Remain 77:13:14 loss: 0.2758 loss_seg: 0.1830 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:34:24,975 INFO misc.py line 117 726] Train: [1/20][281/510] Data 4.587 (3.873) Batch 33.642 (28.044) Remain 77:16:06 loss: 0.1877 loss_seg: 0.1061 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:35:00,972 INFO misc.py line 117 726] Train: [1/20][282/510] Data 8.214 (3.889) Batch 35.997 (28.072) Remain 77:20:21 loss: 0.3820 loss_seg: 0.2669 loss_superpoint_edge: 0.0472 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:35:34,249 INFO misc.py line 117 726] Train: [1/20][283/510] Data 6.197 (3.897) Batch 33.277 (28.091) Remain 77:22:57 loss: 0.1929 loss_seg: 0.1055 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:36:03,199 INFO misc.py line 117 726] Train: [1/20][284/510] Data 6.365 (3.906) Batch 28.950 (28.094) Remain 77:22:59 loss: 0.2827 loss_seg: 0.1969 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:36:27,820 INFO misc.py line 117 726] Train: [1/20][285/510] Data 2.570 (3.901) Batch 24.621 (28.082) Remain 77:20:29 loss: 0.2230 loss_seg: 0.1279 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:36:59,561 INFO misc.py line 117 726] Train: [1/20][286/510] Data 5.292 (3.906) Batch 31.741 (28.095) Remain 77:22:09 loss: 0.3130 loss_seg: 0.2157 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:37:26,809 INFO misc.py line 117 726] Train: [1/20][287/510] Data 5.240 (3.910) Batch 27.248 (28.092) Remain 77:21:11 loss: 0.2267 loss_seg: 0.1303 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:37:53,606 INFO misc.py line 117 726] Train: [1/20][288/510] Data 3.192 (3.908) Batch 26.797 (28.087) Remain 77:19:58 loss: 0.2032 loss_seg: 0.1145 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:38:26,107 INFO misc.py line 117 726] Train: [1/20][289/510] Data 4.782 (3.911) Batch 32.501 (28.102) Remain 77:22:03 loss: 0.2045 loss_seg: 0.1181 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:38:56,506 INFO misc.py line 117 726] Train: [1/20][290/510] Data 3.660 (3.910) Batch 30.399 (28.110) Remain 77:22:54 loss: 0.2349 loss_seg: 0.1420 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:39:14,056 INFO misc.py line 117 726] Train: [1/20][291/510] Data 1.917 (3.903) Batch 17.550 (28.074) Remain 77:16:23 loss: 0.1976 loss_seg: 0.1115 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:39:39,276 INFO misc.py line 117 726] Train: [1/20][292/510] Data 4.466 (3.905) Batch 25.220 (28.064) Remain 77:14:17 loss: 0.1864 loss_seg: 0.1009 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:40:18,327 INFO misc.py line 117 726] Train: [1/20][293/510] Data 5.928 (3.912) Batch 39.051 (28.102) Remain 77:20:04 loss: 0.2009 loss_seg: 0.1154 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:40:47,869 INFO misc.py line 117 726] Train: [1/20][294/510] Data 3.676 (3.911) Batch 29.542 (28.107) Remain 77:20:25 loss: 0.2882 loss_seg: 0.1849 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:41:10,510 INFO misc.py line 117 726] Train: [1/20][295/510] Data 2.226 (3.906) Batch 22.641 (28.088) Remain 77:16:52 loss: 0.2362 loss_seg: 0.1430 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:41:33,369 INFO misc.py line 117 726] Train: [1/20][296/510] Data 1.917 (3.899) Batch 22.858 (28.070) Remain 77:13:27 loss: 0.2250 loss_seg: 0.1308 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:42:00,872 INFO misc.py line 117 726] Train: [1/20][297/510] Data 3.551 (3.898) Batch 27.503 (28.068) Remain 77:12:40 loss: 0.2680 loss_seg: 0.1673 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:42:39,017 INFO misc.py line 117 726] Train: [1/20][298/510] Data 8.120 (3.912) Batch 38.145 (28.102) Remain 77:17:50 loss: 0.2547 loss_seg: 0.1644 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:43:09,428 INFO misc.py line 117 726] Train: [1/20][299/510] Data 7.638 (3.924) Batch 30.411 (28.110) Remain 77:18:39 loss: 0.2549 loss_seg: 0.1563 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0436 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:43:33,885 INFO misc.py line 117 726] Train: [1/20][300/510] Data 2.785 (3.921) Batch 24.457 (28.098) Remain 77:16:09 loss: 0.2273 loss_seg: 0.1345 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:43:33,885 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 16:43:56,828 INFO misc.py line 117 726] Train: [1/20][301/510] Data 2.495 (3.916) Batch 22.943 (28.081) Remain 77:12:50 loss: 0.2364 loss_seg: 0.1415 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:44:37,610 INFO misc.py line 117 726] Train: [1/20][302/510] Data 12.165 (3.943) Batch 40.782 (28.123) Remain 77:19:22 loss: 0.2188 loss_seg: 0.1246 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:44:58,861 INFO misc.py line 117 726] Train: [1/20][303/510] Data 2.331 (3.938) Batch 21.251 (28.100) Remain 77:15:07 loss: 0.2015 loss_seg: 0.1105 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:45:24,190 INFO misc.py line 117 726] Train: [1/20][304/510] Data 3.462 (3.937) Batch 25.329 (28.091) Remain 77:13:08 loss: 0.1798 loss_seg: 0.0929 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:45:59,689 INFO misc.py line 117 726] Train: [1/20][305/510] Data 6.216 (3.944) Batch 35.499 (28.116) Remain 77:16:43 loss: 0.2639 loss_seg: 0.1701 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:46:33,337 INFO misc.py line 117 726] Train: [1/20][306/510] Data 7.338 (3.955) Batch 33.648 (28.134) Remain 77:19:15 loss: 0.2793 loss_seg: 0.1827 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:47:00,041 INFO misc.py line 117 726] Train: [1/20][307/510] Data 2.308 (3.950) Batch 26.704 (28.129) Remain 77:18:01 loss: 0.2362 loss_seg: 0.1415 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:47:23,710 INFO misc.py line 117 726] Train: [1/20][308/510] Data 2.906 (3.946) Batch 23.669 (28.114) Remain 77:15:08 loss: 0.2787 loss_seg: 0.1741 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:47:49,945 INFO misc.py line 117 726] Train: [1/20][309/510] Data 3.163 (3.944) Batch 26.235 (28.108) Remain 77:13:39 loss: 0.2736 loss_seg: 0.1708 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:48:19,283 INFO misc.py line 117 726] Train: [1/20][310/510] Data 3.624 (3.943) Batch 29.338 (28.112) Remain 77:13:50 loss: 0.2765 loss_seg: 0.1753 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:48:41,510 INFO misc.py line 117 726] Train: [1/20][311/510] Data 2.378 (3.938) Batch 22.227 (28.093) Remain 77:10:13 loss: 0.2638 loss_seg: 0.1610 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:49:09,838 INFO misc.py line 117 726] Train: [1/20][312/510] Data 2.947 (3.935) Batch 28.328 (28.094) Remain 77:09:53 loss: 0.3487 loss_seg: 0.2430 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:49:37,960 INFO misc.py line 117 726] Train: [1/20][313/510] Data 2.848 (3.931) Batch 28.123 (28.094) Remain 77:09:26 loss: 0.1848 loss_seg: 0.0973 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:49:55,234 INFO misc.py line 117 726] Train: [1/20][314/510] Data 2.624 (3.927) Batch 17.274 (28.059) Remain 77:03:14 loss: 0.2587 loss_seg: 0.1570 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:50:23,451 INFO misc.py line 117 726] Train: [1/20][315/510] Data 2.797 (3.923) Batch 28.217 (28.060) Remain 77:02:51 loss: 0.2720 loss_seg: 0.1705 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:50:53,393 INFO misc.py line 117 726] Train: [1/20][316/510] Data 5.109 (3.927) Batch 29.941 (28.066) Remain 77:03:22 loss: 0.1776 loss_seg: 0.0938 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:51:19,261 INFO misc.py line 117 726] Train: [1/20][317/510] Data 2.892 (3.924) Batch 25.868 (28.059) Remain 77:01:45 loss: 0.2214 loss_seg: 0.1337 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:52:00,332 INFO misc.py line 117 726] Train: [1/20][318/510] Data 11.242 (3.947) Batch 41.071 (28.100) Remain 77:08:05 loss: 0.2737 loss_seg: 0.1760 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:52:32,325 INFO misc.py line 117 726] Train: [1/20][319/510] Data 3.514 (3.946) Batch 31.994 (28.112) Remain 77:09:38 loss: 0.2453 loss_seg: 0.1499 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:52:58,751 INFO misc.py line 117 726] Train: [1/20][320/510] Data 3.184 (3.943) Batch 26.426 (28.107) Remain 77:08:18 loss: 0.2377 loss_seg: 0.1428 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:53:22,767 INFO misc.py line 117 726] Train: [1/20][321/510] Data 3.011 (3.940) Batch 24.016 (28.094) Remain 77:05:43 loss: 0.2415 loss_seg: 0.1493 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:53:47,956 INFO misc.py line 117 726] Train: [1/20][322/510] Data 2.409 (3.935) Batch 25.189 (28.085) Remain 77:03:44 loss: 0.2473 loss_seg: 0.1526 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:54:19,329 INFO misc.py line 117 726] Train: [1/20][323/510] Data 4.633 (3.938) Batch 31.373 (28.095) Remain 77:04:58 loss: 0.3610 loss_seg: 0.2590 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:54:46,957 INFO misc.py line 117 726] Train: [1/20][324/510] Data 2.860 (3.934) Batch 27.628 (28.094) Remain 77:04:15 loss: 0.3093 loss_seg: 0.1992 loss_superpoint_edge: 0.0437 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:55:04,768 INFO misc.py line 117 726] Train: [1/20][325/510] Data 2.614 (3.930) Batch 17.811 (28.062) Remain 76:58:32 loss: 0.2348 loss_seg: 0.1414 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:55:33,638 INFO misc.py line 117 726] Train: [1/20][326/510] Data 3.182 (3.928) Batch 28.869 (28.065) Remain 76:58:29 loss: 0.2582 loss_seg: 0.1600 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:56:02,580 INFO misc.py line 117 726] Train: [1/20][327/510] Data 6.289 (3.935) Batch 28.942 (28.067) Remain 76:58:27 loss: 0.2507 loss_seg: 0.1543 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:56:28,447 INFO misc.py line 117 726] Train: [1/20][328/510] Data 2.771 (3.932) Batch 25.867 (28.060) Remain 76:56:52 loss: 0.2849 loss_seg: 0.1847 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:56:55,535 INFO misc.py line 117 726] Train: [1/20][329/510] Data 3.308 (3.930) Batch 27.088 (28.057) Remain 76:55:55 loss: 0.2036 loss_seg: 0.1168 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-09 16:57:25,043 INFO misc.py line 117 726] Train: [1/20][330/510] Data 3.805 (3.929) Batch 29.508 (28.062) Remain 76:56:11 loss: 0.2910 loss_seg: 0.1922 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 16:57:55,230 INFO misc.py line 117 726] Train: [1/20][331/510] Data 3.026 (3.926) Batch 30.187 (28.068) Remain 76:56:46 loss: 0.2811 loss_seg: 0.1834 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 16:58:23,997 INFO misc.py line 117 726] Train: [1/20][332/510] Data 4.394 (3.928) Batch 28.767 (28.071) Remain 76:56:39 loss: 0.3284 loss_seg: 0.2347 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 16:58:59,597 INFO misc.py line 117 726] Train: [1/20][333/510] Data 4.302 (3.929) Batch 35.600 (28.093) Remain 76:59:56 loss: 0.2383 loss_seg: 0.1461 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 16:59:34,837 INFO misc.py line 117 726] Train: [1/20][334/510] Data 7.686 (3.940) Batch 35.239 (28.115) Remain 77:03:01 loss: 0.2030 loss_seg: 0.1171 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:00:00,140 INFO misc.py line 117 726] Train: [1/20][335/510] Data 2.614 (3.936) Batch 25.303 (28.106) Remain 77:01:10 loss: 0.2283 loss_seg: 0.1326 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:00:30,893 INFO misc.py line 117 726] Train: [1/20][336/510] Data 4.245 (3.937) Batch 30.753 (28.114) Remain 77:02:00 loss: 0.3635 loss_seg: 0.2493 loss_superpoint_edge: 0.0489 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:00:49,955 INFO misc.py line 117 726] Train: [1/20][337/510] Data 2.674 (3.934) Batch 19.062 (28.087) Remain 76:57:05 loss: 0.2226 loss_seg: 0.1277 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:01:25,658 INFO misc.py line 117 726] Train: [1/20][338/510] Data 10.836 (3.954) Batch 35.703 (28.110) Remain 77:00:21 loss: 0.3800 loss_seg: 0.2634 loss_superpoint_edge: 0.0437 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:01:52,684 INFO misc.py line 117 726] Train: [1/20][339/510] Data 4.399 (3.955) Batch 27.026 (28.107) Remain 76:59:21 loss: 0.2300 loss_seg: 0.1334 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:02:22,569 INFO misc.py line 117 726] Train: [1/20][340/510] Data 3.370 (3.954) Batch 29.885 (28.112) Remain 76:59:45 loss: 0.3058 loss_seg: 0.2143 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:03:00,157 INFO misc.py line 117 726] Train: [1/20][341/510] Data 5.652 (3.959) Batch 37.588 (28.140) Remain 77:03:53 loss: 0.2121 loss_seg: 0.1219 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:03:28,130 INFO misc.py line 117 726] Train: [1/20][342/510] Data 5.055 (3.962) Batch 27.973 (28.140) Remain 77:03:20 loss: 0.2639 loss_seg: 0.1702 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:03:54,515 INFO misc.py line 117 726] Train: [1/20][343/510] Data 3.226 (3.960) Batch 26.385 (28.134) Remain 77:02:01 loss: 0.2700 loss_seg: 0.1669 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:04:17,988 INFO misc.py line 117 726] Train: [1/20][344/510] Data 3.526 (3.959) Batch 23.473 (28.121) Remain 76:59:18 loss: 0.3264 loss_seg: 0.2208 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:04:50,163 INFO misc.py line 117 726] Train: [1/20][345/510] Data 3.813 (3.958) Batch 32.175 (28.133) Remain 77:00:47 loss: 0.2909 loss_seg: 0.1906 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:05:18,899 INFO misc.py line 117 726] Train: [1/20][346/510] Data 2.611 (3.954) Batch 28.736 (28.134) Remain 77:00:36 loss: 0.2233 loss_seg: 0.1284 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:05:49,860 INFO misc.py line 117 726] Train: [1/20][347/510] Data 4.651 (3.956) Batch 30.961 (28.143) Remain 77:01:29 loss: 0.2095 loss_seg: 0.1177 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:06:21,651 INFO misc.py line 117 726] Train: [1/20][348/510] Data 4.725 (3.958) Batch 31.791 (28.153) Remain 77:02:45 loss: 0.3240 loss_seg: 0.2250 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:07:00,722 INFO misc.py line 117 726] Train: [1/20][349/510] Data 5.062 (3.962) Batch 39.072 (28.185) Remain 77:07:28 loss: 0.2420 loss_seg: 0.1450 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:07:16,862 INFO misc.py line 117 726] Train: [1/20][350/510] Data 2.019 (3.956) Batch 16.140 (28.150) Remain 77:01:17 loss: 0.1788 loss_seg: 0.0933 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:07:16,863 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 17:07:39,255 INFO misc.py line 117 726] Train: [1/20][351/510] Data 2.419 (3.952) Batch 22.393 (28.133) Remain 76:58:06 loss: 0.1991 loss_seg: 0.1100 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:08:12,930 INFO misc.py line 117 726] Train: [1/20][352/510] Data 3.183 (3.949) Batch 33.676 (28.149) Remain 77:00:15 loss: 0.2561 loss_seg: 0.1590 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:08:33,584 INFO misc.py line 117 726] Train: [1/20][353/510] Data 1.700 (3.943) Batch 20.653 (28.128) Remain 76:56:16 loss: 0.2257 loss_seg: 0.1344 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:08:58,601 INFO misc.py line 117 726] Train: [1/20][354/510] Data 2.795 (3.940) Batch 25.017 (28.119) Remain 76:54:20 loss: 0.2214 loss_seg: 0.1307 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:09:17,204 INFO misc.py line 117 726] Train: [1/20][355/510] Data 2.042 (3.934) Batch 18.603 (28.092) Remain 76:49:26 loss: 0.2452 loss_seg: 0.1477 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:09:44,212 INFO misc.py line 117 726] Train: [1/20][356/510] Data 3.783 (3.934) Batch 27.008 (28.089) Remain 76:48:28 loss: 0.2365 loss_seg: 0.1405 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:10:07,066 INFO misc.py line 117 726] Train: [1/20][357/510] Data 3.078 (3.931) Batch 22.854 (28.074) Remain 76:45:34 loss: 0.1797 loss_seg: 0.0940 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:10:40,392 INFO misc.py line 117 726] Train: [1/20][358/510] Data 3.897 (3.931) Batch 33.325 (28.089) Remain 76:47:31 loss: 0.2913 loss_seg: 0.1897 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:11:09,143 INFO misc.py line 117 726] Train: [1/20][359/510] Data 3.192 (3.929) Batch 28.751 (28.091) Remain 76:47:22 loss: 0.2239 loss_seg: 0.1305 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:11:37,264 INFO misc.py line 117 726] Train: [1/20][360/510] Data 4.636 (3.931) Batch 28.121 (28.091) Remain 76:46:54 loss: 0.2461 loss_seg: 0.1543 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:12:08,136 INFO misc.py line 117 726] Train: [1/20][361/510] Data 3.515 (3.930) Batch 30.872 (28.099) Remain 76:47:43 loss: 0.3609 loss_seg: 0.2519 loss_superpoint_edge: 0.0433 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:12:32,438 INFO misc.py line 117 726] Train: [1/20][362/510] Data 2.713 (3.927) Batch 24.302 (28.088) Remain 76:45:31 loss: 0.2168 loss_seg: 0.1234 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:12:55,572 INFO misc.py line 117 726] Train: [1/20][363/510] Data 2.371 (3.922) Batch 23.134 (28.074) Remain 76:42:47 loss: 0.2455 loss_seg: 0.1537 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:13:24,202 INFO misc.py line 117 726] Train: [1/20][364/510] Data 4.316 (3.924) Batch 28.630 (28.076) Remain 76:42:34 loss: 0.2310 loss_seg: 0.1371 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:13:55,783 INFO misc.py line 117 726] Train: [1/20][365/510] Data 4.823 (3.926) Batch 31.581 (28.086) Remain 76:43:41 loss: 0.2233 loss_seg: 0.1322 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:14:11,519 INFO misc.py line 117 726] Train: [1/20][366/510] Data 1.929 (3.920) Batch 15.736 (28.052) Remain 76:37:39 loss: 0.2107 loss_seg: 0.1212 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:14:25,404 INFO misc.py line 117 726] Train: [1/20][367/510] Data 1.686 (3.914) Batch 13.884 (28.013) Remain 76:30:48 loss: 0.3514 loss_seg: 0.2409 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:14:54,178 INFO misc.py line 117 726] Train: [1/20][368/510] Data 4.271 (3.915) Batch 28.774 (28.015) Remain 76:30:40 loss: 0.2412 loss_seg: 0.1477 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:15:15,049 INFO misc.py line 117 726] Train: [1/20][369/510] Data 2.265 (3.911) Batch 20.872 (27.995) Remain 76:27:01 loss: 0.2743 loss_seg: 0.1711 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:15:47,611 INFO misc.py line 117 726] Train: [1/20][370/510] Data 5.313 (3.915) Batch 32.562 (28.008) Remain 76:28:35 loss: 0.2057 loss_seg: 0.1153 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:16:24,944 INFO misc.py line 117 726] Train: [1/20][371/510] Data 8.871 (3.928) Batch 37.332 (28.033) Remain 76:32:16 loss: 0.2361 loss_seg: 0.1358 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:16:51,426 INFO misc.py line 117 726] Train: [1/20][372/510] Data 4.312 (3.929) Batch 26.483 (28.029) Remain 76:31:07 loss: 0.2447 loss_seg: 0.1519 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:17:23,218 INFO misc.py line 117 726] Train: [1/20][373/510] Data 6.546 (3.936) Batch 31.791 (28.039) Remain 76:32:18 loss: 0.3338 loss_seg: 0.2233 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:17:45,069 INFO misc.py line 117 726] Train: [1/20][374/510] Data 2.546 (3.932) Batch 21.851 (28.022) Remain 76:29:07 loss: 0.2181 loss_seg: 0.1275 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:18:13,804 INFO misc.py line 117 726] Train: [1/20][375/510] Data 3.317 (3.931) Batch 28.735 (28.024) Remain 76:28:57 loss: 0.2970 loss_seg: 0.1922 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:18:50,519 INFO misc.py line 117 726] Train: [1/20][376/510] Data 6.128 (3.937) Batch 36.715 (28.048) Remain 76:32:18 loss: 0.2872 loss_seg: 0.1806 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:19:21,519 INFO misc.py line 117 726] Train: [1/20][377/510] Data 3.731 (3.936) Batch 31.000 (28.055) Remain 76:33:08 loss: 0.2462 loss_seg: 0.1495 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:19:44,802 INFO misc.py line 117 726] Train: [1/20][378/510] Data 3.274 (3.934) Batch 23.283 (28.043) Remain 76:30:35 loss: 0.2405 loss_seg: 0.1455 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:20:07,459 INFO misc.py line 117 726] Train: [1/20][379/510] Data 2.540 (3.931) Batch 22.657 (28.028) Remain 76:27:46 loss: 0.3343 loss_seg: 0.2421 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:20:35,879 INFO misc.py line 117 726] Train: [1/20][380/510] Data 3.881 (3.931) Batch 28.420 (28.029) Remain 76:27:28 loss: 0.2649 loss_seg: 0.1757 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:21:01,763 INFO misc.py line 117 726] Train: [1/20][381/510] Data 3.887 (3.930) Batch 25.884 (28.024) Remain 76:26:04 loss: 0.2571 loss_seg: 0.1570 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:21:37,873 INFO misc.py line 117 726] Train: [1/20][382/510] Data 5.480 (3.935) Batch 36.110 (28.045) Remain 76:29:06 loss: 0.2344 loss_seg: 0.1420 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:22:11,805 INFO misc.py line 117 726] Train: [1/20][383/510] Data 6.766 (3.942) Batch 33.932 (28.061) Remain 76:31:10 loss: 0.2025 loss_seg: 0.1102 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:22:39,228 INFO misc.py line 117 726] Train: [1/20][384/510] Data 2.405 (3.938) Batch 27.423 (28.059) Remain 76:30:25 loss: 0.3255 loss_seg: 0.2236 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:23:05,166 INFO misc.py line 117 726] Train: [1/20][385/510] Data 4.915 (3.940) Batch 25.938 (28.053) Remain 76:29:03 loss: 0.1952 loss_seg: 0.1071 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:23:38,511 INFO misc.py line 117 726] Train: [1/20][386/510] Data 3.621 (3.940) Batch 33.345 (28.067) Remain 76:30:50 loss: 0.3674 loss_seg: 0.2729 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:24:05,995 INFO misc.py line 117 726] Train: [1/20][387/510] Data 4.067 (3.940) Batch 27.484 (28.066) Remain 76:30:07 loss: 0.2775 loss_seg: 0.1777 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:24:26,576 INFO misc.py line 117 726] Train: [1/20][388/510] Data 2.352 (3.936) Batch 20.582 (28.046) Remain 76:26:29 loss: 0.2160 loss_seg: 0.1255 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:24:57,430 INFO misc.py line 117 726] Train: [1/20][389/510] Data 4.153 (3.936) Batch 30.853 (28.053) Remain 76:27:12 loss: 0.2371 loss_seg: 0.1441 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:25:19,293 INFO misc.py line 117 726] Train: [1/20][390/510] Data 2.753 (3.933) Batch 21.863 (28.037) Remain 76:24:07 loss: 0.3282 loss_seg: 0.2199 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:25:56,329 INFO misc.py line 117 726] Train: [1/20][391/510] Data 4.112 (3.934) Batch 37.036 (28.061) Remain 76:27:26 loss: 0.2882 loss_seg: 0.1917 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:26:15,098 INFO misc.py line 117 726] Train: [1/20][392/510] Data 2.210 (3.929) Batch 18.769 (28.037) Remain 76:23:04 loss: 0.2139 loss_seg: 0.1240 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:26:37,311 INFO misc.py line 117 726] Train: [1/20][393/510] Data 4.088 (3.930) Batch 22.213 (28.022) Remain 76:20:10 loss: 0.2624 loss_seg: 0.1662 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:27:09,165 INFO misc.py line 117 726] Train: [1/20][394/510] Data 3.660 (3.929) Batch 31.854 (28.032) Remain 76:21:18 loss: 0.2029 loss_seg: 0.1155 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:27:33,080 INFO misc.py line 117 726] Train: [1/20][395/510] Data 2.426 (3.925) Batch 23.915 (28.021) Remain 76:19:07 loss: 0.3242 loss_seg: 0.2254 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:27:49,943 INFO misc.py line 117 726] Train: [1/20][396/510] Data 1.826 (3.920) Batch 16.863 (27.993) Remain 76:14:00 loss: 0.2153 loss_seg: 0.1227 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:28:04,730 INFO misc.py line 117 726] Train: [1/20][397/510] Data 1.862 (3.915) Batch 14.787 (27.959) Remain 76:08:04 loss: 0.2641 loss_seg: 0.1607 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:28:35,929 INFO misc.py line 117 726] Train: [1/20][398/510] Data 4.552 (3.916) Batch 31.198 (27.967) Remain 76:08:56 loss: 0.2305 loss_seg: 0.1384 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:29:11,877 INFO misc.py line 117 726] Train: [1/20][399/510] Data 9.609 (3.931) Batch 35.948 (27.988) Remain 76:11:46 loss: 0.1932 loss_seg: 0.1040 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:29:39,767 INFO misc.py line 117 726] Train: [1/20][400/510] Data 2.780 (3.928) Batch 27.890 (27.987) Remain 76:11:15 loss: 0.2185 loss_seg: 0.1265 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:29:39,768 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 17:30:10,207 INFO misc.py line 117 726] Train: [1/20][401/510] Data 3.547 (3.927) Batch 30.440 (27.993) Remain 76:11:48 loss: 0.2821 loss_seg: 0.1756 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:30:36,491 INFO misc.py line 117 726] Train: [1/20][402/510] Data 3.242 (3.925) Batch 26.284 (27.989) Remain 76:10:38 loss: 0.2478 loss_seg: 0.1515 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:31:05,799 INFO misc.py line 117 726] Train: [1/20][403/510] Data 3.692 (3.925) Batch 29.308 (27.993) Remain 76:10:42 loss: 0.2968 loss_seg: 0.1975 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:31:31,182 INFO misc.py line 117 726] Train: [1/20][404/510] Data 3.196 (3.923) Batch 25.382 (27.986) Remain 76:09:10 loss: 0.4141 loss_seg: 0.2981 loss_superpoint_edge: 0.0478 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:31:57,566 INFO misc.py line 117 726] Train: [1/20][405/510] Data 2.382 (3.919) Batch 26.384 (27.982) Remain 76:08:03 loss: 0.2328 loss_seg: 0.1417 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:32:38,874 INFO misc.py line 117 726] Train: [1/20][406/510] Data 7.940 (3.929) Batch 41.308 (28.015) Remain 76:12:59 loss: 0.2669 loss_seg: 0.1692 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:33:03,082 INFO misc.py line 117 726] Train: [1/20][407/510] Data 2.743 (3.926) Batch 24.207 (28.006) Remain 76:10:59 loss: 0.2480 loss_seg: 0.1503 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:33:28,356 INFO misc.py line 117 726] Train: [1/20][408/510] Data 3.020 (3.924) Batch 25.274 (27.999) Remain 76:09:25 loss: 0.2203 loss_seg: 0.1297 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:34:04,079 INFO misc.py line 117 726] Train: [1/20][409/510] Data 4.185 (3.924) Batch 35.723 (28.018) Remain 76:12:03 loss: 0.2113 loss_seg: 0.1244 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:34:38,195 INFO misc.py line 117 726] Train: [1/20][410/510] Data 4.512 (3.926) Batch 34.116 (28.033) Remain 76:14:02 loss: 0.2109 loss_seg: 0.1209 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:35:12,231 INFO misc.py line 117 726] Train: [1/20][411/510] Data 6.160 (3.931) Batch 34.036 (28.048) Remain 76:15:58 loss: 0.2359 loss_seg: 0.1379 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:35:37,802 INFO misc.py line 117 726] Train: [1/20][412/510] Data 3.149 (3.929) Batch 25.571 (28.042) Remain 76:14:30 loss: 0.1851 loss_seg: 0.0957 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:36:09,033 INFO misc.py line 117 726] Train: [1/20][413/510] Data 3.291 (3.928) Batch 31.231 (28.049) Remain 76:15:19 loss: 0.3132 loss_seg: 0.2046 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:36:45,304 INFO misc.py line 117 726] Train: [1/20][414/510] Data 5.849 (3.932) Batch 36.271 (28.069) Remain 76:18:06 loss: 0.3550 loss_seg: 0.2581 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:37:10,498 INFO misc.py line 117 726] Train: [1/20][415/510] Data 3.097 (3.930) Batch 25.195 (28.062) Remain 76:16:30 loss: 0.2322 loss_seg: 0.1352 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:37:33,202 INFO misc.py line 117 726] Train: [1/20][416/510] Data 3.073 (3.928) Batch 22.704 (28.049) Remain 76:13:55 loss: 0.2123 loss_seg: 0.1193 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:38:04,793 INFO misc.py line 117 726] Train: [1/20][417/510] Data 3.716 (3.928) Batch 31.591 (28.058) Remain 76:14:51 loss: 0.2136 loss_seg: 0.1217 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:38:23,123 INFO misc.py line 117 726] Train: [1/20][418/510] Data 1.792 (3.923) Batch 18.330 (28.035) Remain 76:10:33 loss: 0.3506 loss_seg: 0.2451 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:38:46,686 INFO misc.py line 117 726] Train: [1/20][419/510] Data 2.202 (3.919) Batch 23.563 (28.024) Remain 76:08:20 loss: 0.2408 loss_seg: 0.1451 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:39:11,797 INFO misc.py line 117 726] Train: [1/20][420/510] Data 3.909 (3.919) Batch 25.111 (28.017) Remain 76:06:44 loss: 0.2504 loss_seg: 0.1458 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:39:41,368 INFO misc.py line 117 726] Train: [1/20][421/510] Data 3.138 (3.917) Batch 29.571 (28.021) Remain 76:06:52 loss: 0.2305 loss_seg: 0.1360 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:40:06,109 INFO misc.py line 117 726] Train: [1/20][422/510] Data 2.659 (3.914) Batch 24.740 (28.013) Remain 76:05:07 loss: 0.2760 loss_seg: 0.1870 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:40:36,933 INFO misc.py line 117 726] Train: [1/20][423/510] Data 2.987 (3.911) Batch 30.825 (28.019) Remain 76:05:45 loss: 0.2288 loss_seg: 0.1367 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:41:09,385 INFO misc.py line 117 726] Train: [1/20][424/510] Data 4.352 (3.913) Batch 32.451 (28.030) Remain 76:07:00 loss: 0.3677 loss_seg: 0.2702 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:41:32,831 INFO misc.py line 117 726] Train: [1/20][425/510] Data 2.656 (3.910) Batch 23.446 (28.019) Remain 76:04:46 loss: 0.1816 loss_seg: 0.0954 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:42:00,553 INFO misc.py line 117 726] Train: [1/20][426/510] Data 5.855 (3.914) Batch 27.722 (28.018) Remain 76:04:11 loss: 0.5364 loss_seg: 0.4291 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:42:22,693 INFO misc.py line 117 726] Train: [1/20][427/510] Data 2.103 (3.910) Batch 22.140 (28.004) Remain 76:01:27 loss: 0.2766 loss_seg: 0.1741 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:42:58,299 INFO misc.py line 117 726] Train: [1/20][428/510] Data 6.271 (3.915) Batch 35.606 (28.022) Remain 76:03:54 loss: 0.2768 loss_seg: 0.1785 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:43:29,505 INFO misc.py line 117 726] Train: [1/20][429/510] Data 3.398 (3.914) Batch 31.206 (28.030) Remain 76:04:39 loss: 0.2611 loss_seg: 0.1607 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:43:57,727 INFO misc.py line 117 726] Train: [1/20][430/510] Data 4.714 (3.916) Batch 28.221 (28.030) Remain 76:04:15 loss: 0.2406 loss_seg: 0.1438 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:44:27,695 INFO misc.py line 117 726] Train: [1/20][431/510] Data 6.597 (3.922) Batch 29.968 (28.035) Remain 76:04:32 loss: 0.3321 loss_seg: 0.2195 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:44:59,859 INFO misc.py line 117 726] Train: [1/20][432/510] Data 6.687 (3.929) Batch 32.164 (28.044) Remain 76:05:38 loss: 0.2373 loss_seg: 0.1428 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:45:32,729 INFO misc.py line 117 726] Train: [1/20][433/510] Data 3.898 (3.929) Batch 32.870 (28.056) Remain 76:06:59 loss: 0.2453 loss_seg: 0.1517 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:46:00,108 INFO misc.py line 117 726] Train: [1/20][434/510] Data 3.203 (3.927) Batch 27.379 (28.054) Remain 76:06:16 loss: 0.2814 loss_seg: 0.1887 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:46:31,638 INFO misc.py line 117 726] Train: [1/20][435/510] Data 3.018 (3.925) Batch 31.530 (28.062) Remain 76:07:06 loss: 0.2885 loss_seg: 0.1805 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0441 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:47:02,114 INFO misc.py line 117 726] Train: [1/20][436/510] Data 4.253 (3.926) Batch 30.476 (28.068) Remain 76:07:33 loss: 0.2294 loss_seg: 0.1361 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:47:30,066 INFO misc.py line 117 726] Train: [1/20][437/510] Data 3.488 (3.925) Batch 27.952 (28.067) Remain 76:07:02 loss: 0.2688 loss_seg: 0.1721 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:48:03,338 INFO misc.py line 117 726] Train: [1/20][438/510] Data 3.815 (3.924) Batch 33.273 (28.079) Remain 76:08:31 loss: 0.2647 loss_seg: 0.1636 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:48:39,159 INFO misc.py line 117 726] Train: [1/20][439/510] Data 5.368 (3.928) Batch 35.820 (28.097) Remain 76:10:56 loss: 0.2650 loss_seg: 0.1656 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:49:02,192 INFO misc.py line 117 726] Train: [1/20][440/510] Data 2.687 (3.925) Batch 23.033 (28.086) Remain 76:08:35 loss: 0.2572 loss_seg: 0.1596 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:49:28,199 INFO misc.py line 117 726] Train: [1/20][441/510] Data 2.721 (3.922) Batch 26.008 (28.081) Remain 76:07:20 loss: 0.2378 loss_seg: 0.1409 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:50:00,841 INFO misc.py line 117 726] Train: [1/20][442/510] Data 3.333 (3.921) Batch 32.641 (28.091) Remain 76:08:34 loss: 0.2631 loss_seg: 0.1617 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:50:38,329 INFO misc.py line 117 726] Train: [1/20][443/510] Data 6.926 (3.928) Batch 37.489 (28.113) Remain 76:11:34 loss: 0.3113 loss_seg: 0.2011 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:50:50,819 INFO misc.py line 117 726] Train: [1/20][444/510] Data 1.775 (3.923) Batch 12.490 (28.077) Remain 76:05:20 loss: 0.4879 loss_seg: 0.3739 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:51:16,614 INFO misc.py line 117 726] Train: [1/20][445/510] Data 3.932 (3.923) Batch 25.795 (28.072) Remain 76:04:02 loss: 0.3035 loss_seg: 0.2111 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:51:35,315 INFO misc.py line 117 726] Train: [1/20][446/510] Data 2.454 (3.919) Batch 18.701 (28.051) Remain 76:00:07 loss: 0.2818 loss_seg: 0.1763 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:52:10,588 INFO misc.py line 117 726] Train: [1/20][447/510] Data 4.855 (3.922) Batch 35.273 (28.067) Remain 76:02:18 loss: 0.3198 loss_seg: 0.1986 loss_superpoint_edge: 0.0533 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:52:29,743 INFO misc.py line 117 726] Train: [1/20][448/510] Data 2.141 (3.918) Batch 19.155 (28.047) Remain 75:58:35 loss: 0.2615 loss_seg: 0.1615 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:52:57,476 INFO misc.py line 117 726] Train: [1/20][449/510] Data 3.472 (3.917) Batch 27.733 (28.046) Remain 75:58:00 loss: 0.2569 loss_seg: 0.1575 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:53:27,527 INFO misc.py line 117 726] Train: [1/20][450/510] Data 6.108 (3.921) Batch 30.051 (28.051) Remain 75:58:15 loss: 0.3021 loss_seg: 0.2023 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:53:27,528 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 17:53:59,409 INFO misc.py line 117 726] Train: [1/20][451/510] Data 5.257 (3.924) Batch 31.881 (28.059) Remain 75:59:11 loss: 0.3147 loss_seg: 0.2211 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:54:28,851 INFO misc.py line 117 726] Train: [1/20][452/510] Data 5.036 (3.927) Batch 29.442 (28.062) Remain 75:59:13 loss: 0.2612 loss_seg: 0.1623 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:54:57,415 INFO misc.py line 117 726] Train: [1/20][453/510] Data 2.923 (3.925) Batch 28.564 (28.064) Remain 75:58:55 loss: 0.2088 loss_seg: 0.1183 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:55:29,267 INFO misc.py line 117 726] Train: [1/20][454/510] Data 2.877 (3.922) Batch 31.852 (28.072) Remain 75:59:49 loss: 0.2276 loss_seg: 0.1360 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:55:44,468 INFO misc.py line 117 726] Train: [1/20][455/510] Data 2.267 (3.919) Batch 15.201 (28.044) Remain 75:54:44 loss: 0.2589 loss_seg: 0.1584 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:56:22,011 INFO misc.py line 117 726] Train: [1/20][456/510] Data 11.778 (3.936) Batch 37.543 (28.064) Remain 75:57:40 loss: 0.2865 loss_seg: 0.1794 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:56:46,896 INFO misc.py line 117 726] Train: [1/20][457/510] Data 2.472 (3.933) Batch 24.885 (28.057) Remain 75:56:04 loss: 0.2100 loss_seg: 0.1200 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:57:21,763 INFO misc.py line 117 726] Train: [1/20][458/510] Data 6.904 (3.939) Batch 34.867 (28.072) Remain 75:58:01 loss: 0.2799 loss_seg: 0.1790 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:57:40,787 INFO misc.py line 117 726] Train: [1/20][459/510] Data 2.980 (3.937) Batch 19.024 (28.053) Remain 75:54:20 loss: 0.1852 loss_seg: 0.0982 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:58:13,958 INFO misc.py line 117 726] Train: [1/20][460/510] Data 3.582 (3.936) Batch 33.172 (28.064) Remain 75:55:41 loss: 0.1862 loss_seg: 0.1037 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:58:46,022 INFO misc.py line 117 726] Train: [1/20][461/510] Data 4.274 (3.937) Batch 32.063 (28.073) Remain 75:56:38 loss: 0.2618 loss_seg: 0.1684 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:59:13,033 INFO misc.py line 117 726] Train: [1/20][462/510] Data 2.862 (3.935) Batch 27.011 (28.070) Remain 75:55:47 loss: 0.2434 loss_seg: 0.1483 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:59:36,116 INFO misc.py line 117 726] Train: [1/20][463/510] Data 2.254 (3.931) Batch 23.083 (28.059) Remain 75:53:34 loss: 0.2271 loss_seg: 0.1374 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 17:59:57,593 INFO misc.py line 117 726] Train: [1/20][464/510] Data 2.049 (3.927) Batch 21.477 (28.045) Remain 75:50:47 loss: 0.2193 loss_seg: 0.1325 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:00:26,043 INFO misc.py line 117 726] Train: [1/20][465/510] Data 2.587 (3.924) Batch 28.450 (28.046) Remain 75:50:27 loss: 0.2690 loss_seg: 0.1700 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:00:51,213 INFO misc.py line 117 726] Train: [1/20][466/510] Data 4.541 (3.926) Batch 25.169 (28.040) Remain 75:48:59 loss: 0.2983 loss_seg: 0.1949 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:01:17,318 INFO misc.py line 117 726] Train: [1/20][467/510] Data 3.843 (3.925) Batch 26.106 (28.036) Remain 75:47:50 loss: 0.2616 loss_seg: 0.1612 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:01:41,270 INFO misc.py line 117 726] Train: [1/20][468/510] Data 2.442 (3.922) Batch 23.951 (28.027) Remain 75:45:57 loss: 0.2075 loss_seg: 0.1175 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:02:10,065 INFO misc.py line 117 726] Train: [1/20][469/510] Data 3.624 (3.922) Batch 28.795 (28.028) Remain 75:45:45 loss: 0.1752 loss_seg: 0.0916 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:02:37,457 INFO misc.py line 117 726] Train: [1/20][470/510] Data 2.857 (3.919) Batch 27.392 (28.027) Remain 75:45:03 loss: 0.3715 loss_seg: 0.2622 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:03:05,589 INFO misc.py line 117 726] Train: [1/20][471/510] Data 2.954 (3.917) Batch 28.132 (28.027) Remain 75:44:37 loss: 0.2669 loss_seg: 0.1702 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:03:37,566 INFO misc.py line 117 726] Train: [1/20][472/510] Data 3.635 (3.917) Batch 31.977 (28.036) Remain 75:45:31 loss: 0.2685 loss_seg: 0.1707 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:04:05,237 INFO misc.py line 117 726] Train: [1/20][473/510] Data 3.926 (3.917) Batch 27.672 (28.035) Remain 75:44:56 loss: 0.2125 loss_seg: 0.1266 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:04:34,602 INFO misc.py line 117 726] Train: [1/20][474/510] Data 3.126 (3.915) Batch 29.365 (28.038) Remain 75:44:55 loss: 0.2443 loss_seg: 0.1460 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:05:05,831 INFO misc.py line 117 726] Train: [1/20][475/510] Data 5.671 (3.919) Batch 31.229 (28.045) Remain 75:45:33 loss: 0.2578 loss_seg: 0.1638 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:05:33,544 INFO misc.py line 117 726] Train: [1/20][476/510] Data 3.784 (3.918) Batch 27.713 (28.044) Remain 75:44:58 loss: 0.2603 loss_seg: 0.1611 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:05:57,482 INFO misc.py line 117 726] Train: [1/20][477/510] Data 3.375 (3.917) Batch 23.937 (28.035) Remain 75:43:06 loss: 0.2193 loss_seg: 0.1343 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:06:27,205 INFO misc.py line 117 726] Train: [1/20][478/510] Data 3.650 (3.917) Batch 29.724 (28.039) Remain 75:43:12 loss: 0.3759 loss_seg: 0.2557 loss_superpoint_edge: 0.0510 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:06:52,874 INFO misc.py line 117 726] Train: [1/20][479/510] Data 2.907 (3.915) Batch 25.668 (28.034) Remain 75:41:56 loss: 0.2355 loss_seg: 0.1376 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:07:20,894 INFO misc.py line 117 726] Train: [1/20][480/510] Data 3.842 (3.914) Batch 28.021 (28.034) Remain 75:41:28 loss: 0.2007 loss_seg: 0.1087 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:07:54,249 INFO misc.py line 117 726] Train: [1/20][481/510] Data 4.793 (3.916) Batch 33.354 (28.045) Remain 75:42:48 loss: 0.3713 loss_seg: 0.2644 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:08:21,694 INFO misc.py line 117 726] Train: [1/20][482/510] Data 2.194 (3.913) Batch 27.445 (28.044) Remain 75:42:07 loss: 0.2466 loss_seg: 0.1482 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:08:43,184 INFO misc.py line 117 726] Train: [1/20][483/510] Data 1.843 (3.908) Batch 21.490 (28.030) Remain 75:39:27 loss: 0.2503 loss_seg: 0.1550 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:09:22,694 INFO misc.py line 117 726] Train: [1/20][484/510] Data 9.606 (3.920) Batch 39.510 (28.054) Remain 75:42:51 loss: 0.3510 loss_seg: 0.2373 loss_superpoint_edge: 0.0429 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0339 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:09:41,694 INFO misc.py line 117 726] Train: [1/20][485/510] Data 2.108 (3.916) Batch 19.000 (28.035) Remain 75:39:20 loss: 0.2349 loss_seg: 0.1431 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:10:09,720 INFO misc.py line 117 726] Train: [1/20][486/510] Data 3.271 (3.915) Batch 28.026 (28.035) Remain 75:38:52 loss: 0.2648 loss_seg: 0.1715 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:10:37,729 INFO misc.py line 117 726] Train: [1/20][487/510] Data 2.563 (3.912) Batch 28.009 (28.035) Remain 75:38:23 loss: 0.2259 loss_seg: 0.1344 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:11:01,088 INFO misc.py line 117 726] Train: [1/20][488/510] Data 2.781 (3.910) Batch 23.359 (28.025) Remain 75:36:22 loss: 0.3478 loss_seg: 0.2378 loss_superpoint_edge: 0.0419 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:11:28,486 INFO misc.py line 117 726] Train: [1/20][489/510] Data 3.372 (3.909) Batch 27.398 (28.024) Remain 75:35:41 loss: 0.2595 loss_seg: 0.1567 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:11:56,305 INFO misc.py line 117 726] Train: [1/20][490/510] Data 3.031 (3.907) Batch 27.819 (28.024) Remain 75:35:09 loss: 0.2930 loss_seg: 0.1831 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:12:29,050 INFO misc.py line 117 726] Train: [1/20][491/510] Data 4.919 (3.909) Batch 32.745 (28.033) Remain 75:36:15 loss: 0.2654 loss_seg: 0.1718 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:13:05,510 INFO misc.py line 117 726] Train: [1/20][492/510] Data 5.202 (3.912) Batch 36.460 (28.051) Remain 75:38:34 loss: 0.2739 loss_seg: 0.1683 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:13:30,104 INFO misc.py line 117 726] Train: [1/20][493/510] Data 2.472 (3.909) Batch 24.594 (28.043) Remain 75:36:58 loss: 0.2387 loss_seg: 0.1438 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:13:59,442 INFO misc.py line 117 726] Train: [1/20][494/510] Data 3.525 (3.908) Batch 29.338 (28.046) Remain 75:36:55 loss: 0.2379 loss_seg: 0.1416 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:14:19,501 INFO misc.py line 117 726] Train: [1/20][495/510] Data 2.622 (3.905) Batch 20.059 (28.030) Remain 75:33:50 loss: 0.2729 loss_seg: 0.1738 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:14:41,192 INFO misc.py line 117 726] Train: [1/20][496/510] Data 3.246 (3.904) Batch 21.691 (28.017) Remain 75:31:17 loss: 0.1861 loss_seg: 0.0979 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:15:13,997 INFO misc.py line 117 726] Train: [1/20][497/510] Data 5.433 (3.907) Batch 32.806 (28.027) Remain 75:32:23 loss: 0.2717 loss_seg: 0.1697 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:15:41,041 INFO misc.py line 117 726] Train: [1/20][498/510] Data 5.048 (3.910) Batch 27.044 (28.025) Remain 75:31:35 loss: 0.2903 loss_seg: 0.1891 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:16:04,968 INFO misc.py line 117 726] Train: [1/20][499/510] Data 4.529 (3.911) Batch 23.927 (28.016) Remain 75:29:47 loss: 0.2808 loss_seg: 0.1854 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:16:36,238 INFO misc.py line 117 726] Train: [1/20][500/510] Data 3.568 (3.910) Batch 31.270 (28.023) Remain 75:30:23 loss: 0.2909 loss_seg: 0.1979 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:16:36,238 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 18:17:14,042 INFO misc.py line 117 726] Train: [1/20][501/510] Data 5.798 (3.914) Batch 37.804 (28.043) Remain 75:33:05 loss: 0.2663 loss_seg: 0.1657 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:17:34,822 INFO misc.py line 117 726] Train: [1/20][502/510] Data 2.274 (3.911) Batch 20.780 (28.028) Remain 75:30:16 loss: 0.2505 loss_seg: 0.1534 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:18:00,825 INFO misc.py line 117 726] Train: [1/20][503/510] Data 2.309 (3.907) Batch 26.003 (28.024) Remain 75:29:09 loss: 0.1978 loss_seg: 0.1102 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:18:33,623 INFO misc.py line 117 726] Train: [1/20][504/510] Data 3.458 (3.906) Batch 32.798 (28.034) Remain 75:30:13 loss: 0.2086 loss_seg: 0.1191 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:18:50,752 INFO misc.py line 117 726] Train: [1/20][505/510] Data 1.838 (3.902) Batch 17.129 (28.012) Remain 75:26:14 loss: 0.2650 loss_seg: 0.1630 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:19:25,241 INFO misc.py line 117 726] Train: [1/20][506/510] Data 4.575 (3.904) Batch 34.489 (28.025) Remain 75:27:51 loss: 0.2649 loss_seg: 0.1682 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:19:57,516 INFO misc.py line 117 726] Train: [1/20][507/510] Data 4.107 (3.904) Batch 32.275 (28.033) Remain 75:28:45 loss: 0.2078 loss_seg: 0.1203 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:20:29,593 INFO misc.py line 117 726] Train: [1/20][508/510] Data 4.774 (3.906) Batch 32.077 (28.041) Remain 75:29:35 loss: 0.2398 loss_seg: 0.1510 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:20:56,316 INFO misc.py line 117 726] Train: [1/20][509/510] Data 2.768 (3.904) Batch 26.723 (28.039) Remain 75:28:41 loss: 0.1845 loss_seg: 0.1007 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:21:33,536 INFO misc.py line 117 726] Train: [1/20][510/510] Data 5.469 (3.907) Batch 37.221 (28.057) Remain 75:31:09 loss: 0.2282 loss_seg: 0.1341 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:21:33,538 INFO misc.py line 147 726] Train result: loss: 0.2618 loss_seg: 0.1651 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 [2026-06-09 18:21:33,538 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-09 18:21:49,344 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.8091 [2026-06-09 18:22:05,309 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6805 [2026-06-09 18:23:20,525 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9939 [2026-06-09 18:24:01,670 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0977 [2026-06-09 18:24:20,941 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.1728 [2026-06-09 18:24:56,975 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2340 [2026-06-09 18:25:43,312 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.0309 [2026-06-09 18:25:58,684 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3494 [2026-06-09 18:26:16,261 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.0340 [2026-06-09 18:26:34,915 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3110 [2026-06-09 18:26:50,684 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5288 [2026-06-09 18:27:12,174 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7370 [2026-06-09 18:27:37,894 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 2.1947 [2026-06-09 18:27:49,083 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7331 [2026-06-09 18:28:20,380 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0417 [2026-06-09 18:28:46,228 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.4055 [2026-06-09 18:29:13,129 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.4374 [2026-06-09 18:29:55,563 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.0180 [2026-06-09 18:30:16,567 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3867 [2026-06-09 18:30:32,957 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8242 [2026-06-09 18:31:03,892 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9563 [2026-06-09 18:31:20,213 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.7504 [2026-06-09 18:31:42,026 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.4127 [2026-06-09 18:32:03,302 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8806 [2026-06-09 18:32:16,909 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6827 [2026-06-09 18:32:44,778 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5606 [2026-06-09 18:33:26,385 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.2247 [2026-06-09 18:33:43,642 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5823 [2026-06-09 18:34:02,139 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4819 [2026-06-09 18:34:18,906 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.5873 [2026-06-09 18:34:43,847 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2768 [2026-06-09 18:35:02,167 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6673 [2026-06-09 18:35:19,659 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9024 [2026-06-09 18:35:44,313 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6741 [2026-06-09 18:35:44,323 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6639/0.7372/0.8951. [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9249/0.9605 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9755/0.9880 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8388/0.9714 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0055/0.0343 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.2965/0.3441 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.5885/0.6143 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5932/0.6576 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7893/0.8964 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9151/0.9536 [2026-06-09 18:35:44,323 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6697/0.7646 [2026-06-09 18:35:44,324 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7624/0.8514 [2026-06-09 18:35:44,324 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6803/0.8381 [2026-06-09 18:35:44,324 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5908/0.7092 [2026-06-09 18:35:44,324 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-09 18:35:44,325 INFO misc.py line 213 726] Best validation mIoU updated to: 0.6639 [2026-06-09 18:35:44,325 INFO misc.py line 218 726] Currently Best mIoU: 0.6639 [2026-06-09 18:35:44,325 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 18:36:15,567 INFO misc.py line 117 726] Train: [2/20][1/510] Data 3.766 (3.766) Batch 29.220 (29.220) Remain 78:38:36 loss: 0.2095 loss_seg: 0.1190 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:36:47,194 INFO misc.py line 117 726] Train: [2/20][2/510] Data 4.907 (4.907) Batch 31.627 (31.627) Remain 85:06:43 loss: 0.2299 loss_seg: 0.1352 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:37:07,420 INFO misc.py line 117 726] Train: [2/20][3/510] Data 2.765 (2.765) Batch 20.226 (20.226) Remain 54:25:32 loss: 0.2735 loss_seg: 0.1726 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:37:36,841 INFO misc.py line 117 726] Train: [2/20][4/510] Data 3.069 (3.069) Batch 29.420 (29.420) Remain 79:09:24 loss: 0.2933 loss_seg: 0.1976 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:37:59,260 INFO misc.py line 117 726] Train: [2/20][5/510] Data 2.946 (3.008) Batch 22.420 (25.920) Remain 69:43:54 loss: 0.2425 loss_seg: 0.1496 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:38:24,415 INFO misc.py line 117 726] Train: [2/20][6/510] Data 2.867 (2.961) Batch 25.155 (25.665) Remain 69:02:18 loss: 0.2805 loss_seg: 0.1810 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:38:51,744 INFO misc.py line 117 726] Train: [2/20][7/510] Data 3.179 (3.015) Batch 27.329 (26.081) Remain 70:09:01 loss: 0.2151 loss_seg: 0.1261 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:39:18,218 INFO misc.py line 117 726] Train: [2/20][8/510] Data 4.818 (3.376) Batch 26.474 (26.159) Remain 70:21:16 loss: 0.1884 loss_seg: 0.1041 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:39:36,988 INFO misc.py line 117 726] Train: [2/20][9/510] Data 3.199 (3.346) Batch 18.770 (24.928) Remain 67:02:07 loss: 0.2841 loss_seg: 0.1781 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:40:08,815 INFO misc.py line 117 726] Train: [2/20][10/510] Data 3.846 (3.418) Batch 31.827 (25.914) Remain 69:40:43 loss: 0.2806 loss_seg: 0.1786 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:40:42,788 INFO misc.py line 117 726] Train: [2/20][11/510] Data 4.212 (3.517) Batch 33.973 (26.921) Remain 72:22:48 loss: 0.3810 loss_seg: 0.2676 loss_superpoint_edge: 0.0441 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:41:01,466 INFO misc.py line 117 726] Train: [2/20][12/510] Data 2.148 (3.365) Batch 18.677 (26.005) Remain 69:54:36 loss: 0.2036 loss_seg: 0.1158 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:41:21,915 INFO misc.py line 117 726] Train: [2/20][13/510] Data 3.236 (3.352) Batch 20.449 (25.449) Remain 68:24:34 loss: 0.3118 loss_seg: 0.2132 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:41:47,110 INFO misc.py line 117 726] Train: [2/20][14/510] Data 2.921 (3.313) Batch 25.195 (25.426) Remain 68:20:25 loss: 0.1969 loss_seg: 0.1124 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:42:22,097 INFO misc.py line 117 726] Train: [2/20][15/510] Data 8.756 (3.766) Batch 34.987 (26.223) Remain 70:28:27 loss: 0.3090 loss_seg: 0.2155 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:42:51,027 INFO misc.py line 117 726] Train: [2/20][16/510] Data 3.894 (3.776) Batch 28.930 (26.431) Remain 71:01:36 loss: 0.2640 loss_seg: 0.1736 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:43:20,463 INFO misc.py line 117 726] Train: [2/20][17/510] Data 3.444 (3.753) Batch 29.436 (26.646) Remain 71:35:45 loss: 0.2450 loss_seg: 0.1525 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:43:50,938 INFO misc.py line 117 726] Train: [2/20][18/510] Data 5.596 (3.875) Batch 30.475 (26.901) Remain 72:16:28 loss: 0.2447 loss_seg: 0.1509 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:44:23,858 INFO misc.py line 117 726] Train: [2/20][19/510] Data 4.431 (3.910) Batch 32.920 (27.277) Remain 73:16:39 loss: 0.2043 loss_seg: 0.1134 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:44:36,550 INFO misc.py line 117 726] Train: [2/20][20/510] Data 1.475 (3.767) Batch 12.692 (26.419) Remain 70:57:55 loss: 0.4972 loss_seg: 0.3536 loss_superpoint_edge: 0.0714 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:45:05,591 INFO misc.py line 117 726] Train: [2/20][21/510] Data 3.742 (3.766) Batch 29.041 (26.565) Remain 71:20:57 loss: 0.3021 loss_seg: 0.1986 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:45:24,821 INFO misc.py line 117 726] Train: [2/20][22/510] Data 1.957 (3.670) Batch 19.230 (26.179) Remain 70:18:18 loss: 0.2015 loss_seg: 0.1137 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:45:48,417 INFO misc.py line 117 726] Train: [2/20][23/510] Data 2.391 (3.606) Batch 23.596 (26.050) Remain 69:57:03 loss: 0.2545 loss_seg: 0.1629 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:46:18,234 INFO misc.py line 117 726] Train: [2/20][24/510] Data 2.966 (3.576) Batch 29.817 (26.229) Remain 70:25:31 loss: 0.2445 loss_seg: 0.1552 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:46:40,732 INFO misc.py line 117 726] Train: [2/20][25/510] Data 2.353 (3.520) Batch 22.499 (26.060) Remain 69:57:46 loss: 0.3968 loss_seg: 0.2918 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:47:05,095 INFO misc.py line 117 726] Train: [2/20][26/510] Data 2.992 (3.497) Batch 24.363 (25.986) Remain 69:45:27 loss: 0.2071 loss_seg: 0.1191 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:47:29,672 INFO misc.py line 117 726] Train: [2/20][27/510] Data 2.389 (3.451) Batch 24.577 (25.927) Remain 69:35:34 loss: 0.2508 loss_seg: 0.1550 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:47:59,879 INFO misc.py line 117 726] Train: [2/20][28/510] Data 3.651 (3.459) Batch 30.207 (26.098) Remain 70:02:42 loss: 0.2272 loss_seg: 0.1386 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:48:24,512 INFO misc.py line 117 726] Train: [2/20][29/510] Data 3.683 (3.468) Batch 24.633 (26.042) Remain 69:53:11 loss: 0.2366 loss_seg: 0.1435 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:48:58,059 INFO misc.py line 117 726] Train: [2/20][30/510] Data 3.338 (3.463) Batch 33.546 (26.320) Remain 70:37:30 loss: 0.2835 loss_seg: 0.1831 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:49:27,858 INFO misc.py line 117 726] Train: [2/20][31/510] Data 3.605 (3.468) Batch 29.799 (26.444) Remain 70:57:04 loss: 0.3102 loss_seg: 0.2042 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:50:00,352 INFO misc.py line 117 726] Train: [2/20][32/510] Data 3.859 (3.482) Batch 32.494 (26.653) Remain 71:30:12 loss: 0.3395 loss_seg: 0.2393 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:50:38,159 INFO misc.py line 117 726] Train: [2/20][33/510] Data 9.013 (3.666) Batch 37.807 (27.025) Remain 72:29:36 loss: 0.2303 loss_seg: 0.1367 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:51:13,247 INFO misc.py line 117 726] Train: [2/20][34/510] Data 5.273 (3.718) Batch 35.089 (27.285) Remain 73:11:01 loss: 0.3496 loss_seg: 0.2541 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:51:42,336 INFO misc.py line 117 726] Train: [2/20][35/510] Data 4.989 (3.757) Batch 29.088 (27.341) Remain 73:19:38 loss: 0.2578 loss_seg: 0.1578 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:52:10,028 INFO misc.py line 117 726] Train: [2/20][36/510] Data 3.137 (3.739) Batch 27.692 (27.352) Remain 73:20:53 loss: 0.2841 loss_seg: 0.1837 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:52:31,251 INFO misc.py line 117 726] Train: [2/20][37/510] Data 2.321 (3.697) Batch 21.224 (27.171) Remain 72:51:26 loss: 0.2426 loss_seg: 0.1430 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:52:57,763 INFO misc.py line 117 726] Train: [2/20][38/510] Data 3.430 (3.689) Batch 26.512 (27.153) Remain 72:47:57 loss: 0.3686 loss_seg: 0.2645 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:53:27,424 INFO misc.py line 117 726] Train: [2/20][39/510] Data 3.247 (3.677) Batch 29.660 (27.222) Remain 72:58:42 loss: 0.2375 loss_seg: 0.1489 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:53:57,830 INFO misc.py line 117 726] Train: [2/20][40/510] Data 4.200 (3.691) Batch 30.406 (27.308) Remain 73:12:05 loss: 0.2397 loss_seg: 0.1400 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:54:32,273 INFO misc.py line 117 726] Train: [2/20][41/510] Data 5.409 (3.736) Batch 34.443 (27.496) Remain 73:41:49 loss: 0.2597 loss_seg: 0.1556 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:55:03,631 INFO misc.py line 117 726] Train: [2/20][42/510] Data 3.317 (3.726) Batch 31.358 (27.595) Remain 73:57:17 loss: 0.2496 loss_seg: 0.1559 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:55:31,889 INFO misc.py line 117 726] Train: [2/20][43/510] Data 2.279 (3.689) Batch 28.258 (27.612) Remain 73:59:30 loss: 0.2596 loss_seg: 0.1598 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:56:10,283 INFO misc.py line 117 726] Train: [2/20][44/510] Data 9.771 (3.838) Batch 38.395 (27.875) Remain 74:41:19 loss: 0.2997 loss_seg: 0.1990 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:56:33,515 INFO misc.py line 117 726] Train: [2/20][45/510] Data 4.090 (3.844) Batch 23.231 (27.764) Remain 74:23:05 loss: 0.2557 loss_seg: 0.1649 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:57:08,131 INFO misc.py line 117 726] Train: [2/20][46/510] Data 6.854 (3.914) Batch 34.616 (27.923) Remain 74:48:14 loss: 0.2970 loss_seg: 0.1916 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:57:43,440 INFO misc.py line 117 726] Train: [2/20][47/510] Data 4.676 (3.931) Batch 35.310 (28.091) Remain 75:14:44 loss: 0.3309 loss_seg: 0.2315 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:58:15,050 INFO misc.py line 117 726] Train: [2/20][48/510] Data 5.277 (3.961) Batch 31.610 (28.170) Remain 75:26:50 loss: 0.2207 loss_seg: 0.1302 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:58:34,811 INFO misc.py line 117 726] Train: [2/20][49/510] Data 2.147 (3.922) Batch 19.761 (27.987) Remain 74:57:00 loss: 0.3193 loss_seg: 0.2063 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0430 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:59:13,336 INFO misc.py line 117 726] Train: [2/20][50/510] Data 5.738 (3.960) Batch 38.525 (28.211) Remain 75:32:33 loss: 0.2634 loss_seg: 0.1639 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 18:59:13,337 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 18:59:44,810 INFO misc.py line 117 726] Train: [2/20][51/510] Data 4.077 (3.963) Batch 31.473 (28.279) Remain 75:43:00 loss: 0.2377 loss_seg: 0.1398 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:00:20,439 INFO misc.py line 117 726] Train: [2/20][52/510] Data 6.113 (4.007) Batch 35.630 (28.429) Remain 76:06:38 loss: 0.3351 loss_seg: 0.2100 loss_superpoint_edge: 0.0531 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:00:50,273 INFO misc.py line 117 726] Train: [2/20][53/510] Data 3.746 (4.001) Batch 29.834 (28.457) Remain 76:10:40 loss: 0.3115 loss_seg: 0.2023 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:01:27,346 INFO misc.py line 117 726] Train: [2/20][54/510] Data 4.606 (4.013) Batch 37.073 (28.626) Remain 76:37:20 loss: 0.3028 loss_seg: 0.2066 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:01:49,144 INFO misc.py line 117 726] Train: [2/20][55/510] Data 1.846 (3.971) Batch 21.798 (28.495) Remain 76:15:46 loss: 0.2503 loss_seg: 0.1506 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:02:22,561 INFO misc.py line 117 726] Train: [2/20][56/510] Data 5.666 (4.003) Batch 33.417 (28.588) Remain 76:30:12 loss: 0.2238 loss_seg: 0.1334 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:02:52,449 INFO misc.py line 117 726] Train: [2/20][57/510] Data 5.744 (4.036) Batch 29.888 (28.612) Remain 76:33:35 loss: 0.2753 loss_seg: 0.1802 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:03:18,890 INFO misc.py line 117 726] Train: [2/20][58/510] Data 5.248 (4.058) Batch 26.441 (28.572) Remain 76:26:47 loss: 0.2882 loss_seg: 0.1889 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:03:43,137 INFO misc.py line 117 726] Train: [2/20][59/510] Data 2.056 (4.022) Batch 24.247 (28.495) Remain 76:13:54 loss: 0.2392 loss_seg: 0.1415 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:04:14,489 INFO misc.py line 117 726] Train: [2/20][60/510] Data 9.558 (4.119) Batch 31.352 (28.545) Remain 76:21:28 loss: 0.2100 loss_seg: 0.1175 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:04:32,287 INFO misc.py line 117 726] Train: [2/20][61/510] Data 1.576 (4.075) Batch 17.799 (28.360) Remain 75:51:16 loss: 0.2284 loss_seg: 0.1336 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:04:56,992 INFO misc.py line 117 726] Train: [2/20][62/510] Data 3.061 (4.058) Batch 24.704 (28.298) Remain 75:40:51 loss: 0.2726 loss_seg: 0.1744 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:05:34,401 INFO misc.py line 117 726] Train: [2/20][63/510] Data 6.256 (4.095) Batch 37.410 (28.450) Remain 76:04:45 loss: 0.2337 loss_seg: 0.1433 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:06:07,722 INFO misc.py line 117 726] Train: [2/20][64/510] Data 4.313 (4.098) Batch 33.320 (28.530) Remain 76:17:05 loss: 0.2488 loss_seg: 0.1517 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:06:37,573 INFO misc.py line 117 726] Train: [2/20][65/510] Data 6.271 (4.133) Batch 29.851 (28.551) Remain 76:20:01 loss: 0.2169 loss_seg: 0.1228 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:07:02,727 INFO misc.py line 117 726] Train: [2/20][66/510] Data 2.251 (4.103) Batch 25.154 (28.497) Remain 76:10:54 loss: 0.2554 loss_seg: 0.1572 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:07:29,217 INFO misc.py line 117 726] Train: [2/20][67/510] Data 4.733 (4.113) Batch 26.490 (28.466) Remain 76:05:24 loss: 0.1671 loss_seg: 0.0849 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:07:39,591 INFO misc.py line 117 726] Train: [2/20][68/510] Data 1.919 (4.080) Batch 10.374 (28.187) Remain 75:20:17 loss: 0.1894 loss_seg: 0.1007 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:08:08,666 INFO misc.py line 117 726] Train: [2/20][69/510] Data 6.018 (4.109) Batch 29.076 (28.201) Remain 75:21:58 loss: 0.2226 loss_seg: 0.1259 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:08:49,152 INFO misc.py line 117 726] Train: [2/20][70/510] Data 8.367 (4.172) Batch 40.486 (28.384) Remain 75:50:54 loss: 0.2543 loss_seg: 0.1649 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:09:18,495 INFO misc.py line 117 726] Train: [2/20][71/510] Data 3.248 (4.159) Batch 29.343 (28.398) Remain 75:52:41 loss: 0.2214 loss_seg: 0.1291 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:09:38,656 INFO misc.py line 117 726] Train: [2/20][72/510] Data 3.000 (4.142) Batch 20.160 (28.279) Remain 75:33:05 loss: 0.2934 loss_seg: 0.1904 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:10:12,938 INFO misc.py line 117 726] Train: [2/20][73/510] Data 3.535 (4.133) Batch 34.282 (28.365) Remain 75:46:21 loss: 0.2226 loss_seg: 0.1270 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:10:32,228 INFO misc.py line 117 726] Train: [2/20][74/510] Data 2.574 (4.111) Batch 19.291 (28.237) Remain 75:25:24 loss: 0.2561 loss_seg: 0.1580 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:10:59,068 INFO misc.py line 117 726] Train: [2/20][75/510] Data 3.649 (4.105) Batch 26.840 (28.217) Remain 75:21:49 loss: 0.2936 loss_seg: 0.1898 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:11:35,442 INFO misc.py line 117 726] Train: [2/20][76/510] Data 6.010 (4.131) Batch 36.374 (28.329) Remain 75:39:15 loss: 0.3087 loss_seg: 0.2109 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:12:00,664 INFO misc.py line 117 726] Train: [2/20][77/510] Data 2.561 (4.110) Batch 25.222 (28.287) Remain 75:32:03 loss: 0.1991 loss_seg: 0.1081 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:12:34,428 INFO misc.py line 117 726] Train: [2/20][78/510] Data 3.882 (4.107) Batch 33.764 (28.360) Remain 75:43:17 loss: 0.3089 loss_seg: 0.2020 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:12:49,894 INFO misc.py line 117 726] Train: [2/20][79/510] Data 1.940 (4.078) Batch 15.466 (28.190) Remain 75:15:38 loss: 0.2290 loss_seg: 0.1293 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:13:16,498 INFO misc.py line 117 726] Train: [2/20][80/510] Data 3.126 (4.066) Batch 26.605 (28.170) Remain 75:11:52 loss: 0.2238 loss_seg: 0.1323 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:13:45,812 INFO misc.py line 117 726] Train: [2/20][81/510] Data 3.129 (4.054) Batch 29.314 (28.185) Remain 75:13:44 loss: 0.2391 loss_seg: 0.1412 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:14:09,030 INFO misc.py line 117 726] Train: [2/20][82/510] Data 2.508 (4.034) Batch 23.217 (28.122) Remain 75:03:12 loss: 0.2272 loss_seg: 0.1330 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:14:43,296 INFO misc.py line 117 726] Train: [2/20][83/510] Data 4.102 (4.035) Batch 34.267 (28.198) Remain 75:15:02 loss: 0.1835 loss_seg: 0.1000 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:15:01,617 INFO misc.py line 117 726] Train: [2/20][84/510] Data 2.553 (4.017) Batch 18.321 (28.077) Remain 74:55:02 loss: 0.3242 loss_seg: 0.2216 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:15:30,435 INFO misc.py line 117 726] Train: [2/20][85/510] Data 3.311 (4.008) Batch 28.818 (28.086) Remain 74:56:01 loss: 0.2171 loss_seg: 0.1286 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:15:59,822 INFO misc.py line 117 726] Train: [2/20][86/510] Data 4.924 (4.019) Batch 29.387 (28.101) Remain 74:58:04 loss: 0.2256 loss_seg: 0.1292 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:16:32,441 INFO misc.py line 117 726] Train: [2/20][87/510] Data 3.278 (4.011) Batch 32.619 (28.155) Remain 75:06:12 loss: 0.2166 loss_seg: 0.1266 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:16:59,814 INFO misc.py line 117 726] Train: [2/20][88/510] Data 3.295 (4.002) Batch 27.373 (28.146) Remain 75:04:16 loss: 0.2249 loss_seg: 0.1396 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:17:30,826 INFO misc.py line 117 726] Train: [2/20][89/510] Data 4.120 (4.003) Batch 31.012 (28.179) Remain 75:09:07 loss: 0.2994 loss_seg: 0.2079 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:17:59,192 INFO misc.py line 117 726] Train: [2/20][90/510] Data 2.930 (3.991) Batch 28.367 (28.181) Remain 75:09:00 loss: 0.2593 loss_seg: 0.1590 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:18:23,984 INFO misc.py line 117 726] Train: [2/20][91/510] Data 3.329 (3.984) Batch 24.792 (28.143) Remain 75:02:22 loss: 0.3714 loss_seg: 0.2639 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:18:53,510 INFO misc.py line 117 726] Train: [2/20][92/510] Data 2.835 (3.971) Batch 29.525 (28.158) Remain 75:04:23 loss: 0.2090 loss_seg: 0.1197 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:19:20,741 INFO misc.py line 117 726] Train: [2/20][93/510] Data 4.561 (3.977) Batch 27.232 (28.148) Remain 75:02:16 loss: 0.2714 loss_seg: 0.1802 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:19:47,700 INFO misc.py line 117 726] Train: [2/20][94/510] Data 3.092 (3.968) Batch 26.958 (28.135) Remain 74:59:42 loss: 0.2091 loss_seg: 0.1187 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:20:16,702 INFO misc.py line 117 726] Train: [2/20][95/510] Data 3.213 (3.959) Batch 29.002 (28.144) Remain 75:00:45 loss: 0.3525 loss_seg: 0.2536 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:20:38,788 INFO misc.py line 117 726] Train: [2/20][96/510] Data 2.933 (3.948) Batch 22.086 (28.079) Remain 74:49:52 loss: 0.3247 loss_seg: 0.2066 loss_superpoint_edge: 0.0475 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:21:01,378 INFO misc.py line 117 726] Train: [2/20][97/510] Data 2.407 (3.932) Batch 22.590 (28.021) Remain 74:40:03 loss: 0.2183 loss_seg: 0.1252 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:21:23,512 INFO misc.py line 117 726] Train: [2/20][98/510] Data 2.648 (3.918) Batch 22.134 (27.959) Remain 74:29:41 loss: 0.2288 loss_seg: 0.1358 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:21:46,979 INFO misc.py line 117 726] Train: [2/20][99/510] Data 4.365 (3.923) Batch 23.466 (27.912) Remain 74:21:44 loss: 0.2090 loss_seg: 0.1197 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:22:13,641 INFO misc.py line 117 726] Train: [2/20][100/510] Data 3.046 (3.914) Batch 26.663 (27.899) Remain 74:19:13 loss: 0.3067 loss_seg: 0.2016 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:22:13,642 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 19:22:44,450 INFO misc.py line 117 726] Train: [2/20][101/510] Data 3.345 (3.908) Batch 30.808 (27.929) Remain 74:23:29 loss: 0.2281 loss_seg: 0.1360 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:23:19,100 INFO misc.py line 117 726] Train: [2/20][102/510] Data 6.373 (3.933) Batch 34.650 (27.997) Remain 74:33:52 loss: 0.2406 loss_seg: 0.1452 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:23:36,241 INFO misc.py line 117 726] Train: [2/20][103/510] Data 2.107 (3.915) Batch 17.141 (27.888) Remain 74:16:04 loss: 0.2788 loss_seg: 0.1843 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:23:59,403 INFO misc.py line 117 726] Train: [2/20][104/510] Data 2.481 (3.901) Batch 23.163 (27.841) Remain 74:08:07 loss: 0.4537 loss_seg: 0.3548 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:24:27,036 INFO misc.py line 117 726] Train: [2/20][105/510] Data 3.011 (3.892) Batch 27.633 (27.839) Remain 74:07:20 loss: 0.2244 loss_seg: 0.1368 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:24:51,808 INFO misc.py line 117 726] Train: [2/20][106/510] Data 2.823 (3.882) Batch 24.772 (27.810) Remain 74:02:07 loss: 0.2450 loss_seg: 0.1464 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:25:15,163 INFO misc.py line 117 726] Train: [2/20][107/510] Data 2.089 (3.864) Batch 23.356 (27.767) Remain 73:54:48 loss: 0.2257 loss_seg: 0.1300 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:25:47,272 INFO misc.py line 117 726] Train: [2/20][108/510] Data 3.441 (3.860) Batch 32.109 (27.808) Remain 74:00:57 loss: 0.2336 loss_seg: 0.1368 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:26:16,873 INFO misc.py line 117 726] Train: [2/20][109/510] Data 3.768 (3.859) Batch 29.601 (27.825) Remain 74:03:11 loss: 0.3157 loss_seg: 0.2072 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:26:53,248 INFO misc.py line 117 726] Train: [2/20][110/510] Data 8.489 (3.903) Batch 36.375 (27.905) Remain 74:15:29 loss: 0.2959 loss_seg: 0.1992 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:27:13,041 INFO misc.py line 117 726] Train: [2/20][111/510] Data 2.177 (3.887) Batch 19.793 (27.830) Remain 74:03:01 loss: 0.2591 loss_seg: 0.1589 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:27:36,599 INFO misc.py line 117 726] Train: [2/20][112/510] Data 3.606 (3.884) Batch 23.557 (27.791) Remain 73:56:18 loss: 0.3407 loss_seg: 0.2360 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:27:59,109 INFO misc.py line 117 726] Train: [2/20][113/510] Data 2.585 (3.872) Batch 22.510 (27.743) Remain 73:48:11 loss: 0.2004 loss_seg: 0.1109 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:28:35,234 INFO misc.py line 117 726] Train: [2/20][114/510] Data 6.327 (3.894) Batch 36.125 (27.818) Remain 73:59:46 loss: 0.3070 loss_seg: 0.2010 loss_superpoint_edge: 0.0404 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:28:56,958 INFO misc.py line 117 726] Train: [2/20][115/510] Data 1.946 (3.877) Batch 21.724 (27.764) Remain 73:50:37 loss: 0.3102 loss_seg: 0.2023 loss_superpoint_edge: 0.0412 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:29:20,910 INFO misc.py line 117 726] Train: [2/20][116/510] Data 2.580 (3.866) Batch 23.952 (27.730) Remain 73:44:46 loss: 0.2042 loss_seg: 0.1109 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:29:43,907 INFO misc.py line 117 726] Train: [2/20][117/510] Data 2.435 (3.853) Batch 22.997 (27.688) Remain 73:37:41 loss: 0.2737 loss_seg: 0.1699 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:30:14,775 INFO misc.py line 117 726] Train: [2/20][118/510] Data 3.452 (3.850) Batch 30.868 (27.716) Remain 73:41:38 loss: 0.3206 loss_seg: 0.2162 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:30:44,111 INFO misc.py line 117 726] Train: [2/20][119/510] Data 3.332 (3.845) Batch 29.337 (27.730) Remain 73:43:24 loss: 0.2053 loss_seg: 0.1174 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:31:05,498 INFO misc.py line 117 726] Train: [2/20][120/510] Data 3.008 (3.838) Batch 21.387 (27.676) Remain 73:34:18 loss: 0.2425 loss_seg: 0.1471 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:31:33,789 INFO misc.py line 117 726] Train: [2/20][121/510] Data 3.131 (3.832) Batch 28.291 (27.681) Remain 73:34:40 loss: 0.2435 loss_seg: 0.1446 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:32:02,423 INFO misc.py line 117 726] Train: [2/20][122/510] Data 3.577 (3.830) Batch 28.634 (27.689) Remain 73:35:29 loss: 0.3291 loss_seg: 0.2208 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:32:22,777 INFO misc.py line 117 726] Train: [2/20][123/510] Data 2.175 (3.816) Batch 20.353 (27.628) Remain 73:25:16 loss: 0.2146 loss_seg: 0.1209 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:32:47,348 INFO misc.py line 117 726] Train: [2/20][124/510] Data 2.034 (3.801) Batch 24.571 (27.603) Remain 73:20:47 loss: 0.2417 loss_seg: 0.1556 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:33:15,149 INFO misc.py line 117 726] Train: [2/20][125/510] Data 2.796 (3.793) Batch 27.801 (27.604) Remain 73:20:35 loss: 0.3638 loss_seg: 0.2601 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:33:51,879 INFO misc.py line 117 726] Train: [2/20][126/510] Data 3.963 (3.794) Batch 36.730 (27.679) Remain 73:31:57 loss: 0.2837 loss_seg: 0.1818 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:34:23,876 INFO misc.py line 117 726] Train: [2/20][127/510] Data 4.956 (3.804) Batch 31.997 (27.713) Remain 73:37:02 loss: 0.2085 loss_seg: 0.1176 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:34:50,431 INFO misc.py line 117 726] Train: [2/20][128/510] Data 3.437 (3.801) Batch 26.555 (27.704) Remain 73:35:06 loss: 0.2338 loss_seg: 0.1384 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:35:23,390 INFO misc.py line 117 726] Train: [2/20][129/510] Data 4.148 (3.804) Batch 32.960 (27.746) Remain 73:41:17 loss: 0.2232 loss_seg: 0.1302 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:35:55,194 INFO misc.py line 117 726] Train: [2/20][130/510] Data 3.475 (3.801) Batch 31.804 (27.778) Remain 73:45:55 loss: 0.2354 loss_seg: 0.1405 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:36:25,403 INFO misc.py line 117 726] Train: [2/20][131/510] Data 3.535 (3.799) Batch 30.209 (27.797) Remain 73:48:29 loss: 0.2796 loss_seg: 0.1900 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:36:56,118 INFO misc.py line 117 726] Train: [2/20][132/510] Data 10.092 (3.848) Batch 30.715 (27.819) Remain 73:51:37 loss: 0.2138 loss_seg: 0.1277 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:37:28,692 INFO misc.py line 117 726] Train: [2/20][133/510] Data 5.979 (3.864) Batch 32.574 (27.856) Remain 73:56:59 loss: 0.2947 loss_seg: 0.1933 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:37:51,370 INFO misc.py line 117 726] Train: [2/20][134/510] Data 2.939 (3.857) Batch 22.679 (27.816) Remain 73:50:13 loss: 0.3316 loss_seg: 0.2230 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:38:18,216 INFO misc.py line 117 726] Train: [2/20][135/510] Data 2.517 (3.847) Batch 26.845 (27.809) Remain 73:48:35 loss: 0.2508 loss_seg: 0.1529 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:38:38,349 INFO misc.py line 117 726] Train: [2/20][136/510] Data 2.390 (3.836) Batch 20.133 (27.751) Remain 73:38:56 loss: 0.3518 loss_seg: 0.2563 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:39:10,340 INFO misc.py line 117 726] Train: [2/20][137/510] Data 5.209 (3.846) Batch 31.992 (27.783) Remain 73:43:30 loss: 0.2469 loss_seg: 0.1481 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:39:45,855 INFO misc.py line 117 726] Train: [2/20][138/510] Data 6.301 (3.864) Batch 35.514 (27.840) Remain 73:52:10 loss: 0.2919 loss_seg: 0.1894 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:40:18,335 INFO misc.py line 117 726] Train: [2/20][139/510] Data 3.092 (3.859) Batch 32.480 (27.874) Remain 73:57:08 loss: 0.2737 loss_seg: 0.1781 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:40:51,812 INFO misc.py line 117 726] Train: [2/20][140/510] Data 3.129 (3.853) Batch 33.477 (27.915) Remain 74:03:10 loss: 0.2594 loss_seg: 0.1609 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:41:20,208 INFO misc.py line 117 726] Train: [2/20][141/510] Data 3.026 (3.847) Batch 28.396 (27.919) Remain 74:03:16 loss: 0.2690 loss_seg: 0.1675 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:41:41,785 INFO misc.py line 117 726] Train: [2/20][142/510] Data 2.502 (3.838) Batch 21.577 (27.873) Remain 73:55:32 loss: 0.3056 loss_seg: 0.1985 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:42:17,229 INFO misc.py line 117 726] Train: [2/20][143/510] Data 3.705 (3.837) Batch 35.445 (27.927) Remain 74:03:41 loss: 0.3090 loss_seg: 0.2060 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:42:42,341 INFO misc.py line 117 726] Train: [2/20][144/510] Data 3.224 (3.832) Batch 25.111 (27.907) Remain 74:00:02 loss: 0.3033 loss_seg: 0.2089 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:43:18,917 INFO misc.py line 117 726] Train: [2/20][145/510] Data 4.751 (3.839) Batch 36.576 (27.968) Remain 74:09:17 loss: 0.2437 loss_seg: 0.1498 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:43:36,082 INFO misc.py line 117 726] Train: [2/20][146/510] Data 2.442 (3.829) Batch 17.165 (27.893) Remain 73:56:48 loss: 0.3319 loss_seg: 0.2159 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:44:04,039 INFO misc.py line 117 726] Train: [2/20][147/510] Data 3.300 (3.825) Batch 27.957 (27.893) Remain 73:56:24 loss: 0.2418 loss_seg: 0.1452 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:44:29,857 INFO misc.py line 117 726] Train: [2/20][148/510] Data 3.348 (3.822) Batch 25.818 (27.879) Remain 73:53:40 loss: 0.2340 loss_seg: 0.1401 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:45:00,497 INFO misc.py line 117 726] Train: [2/20][149/510] Data 4.556 (3.827) Batch 30.640 (27.898) Remain 73:56:12 loss: 0.3246 loss_seg: 0.2179 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:45:33,978 INFO misc.py line 117 726] Train: [2/20][150/510] Data 3.717 (3.826) Batch 33.481 (27.936) Remain 74:01:47 loss: 0.2405 loss_seg: 0.1406 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:45:33,978 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 19:46:09,050 INFO misc.py line 117 726] Train: [2/20][151/510] Data 4.777 (3.833) Batch 35.073 (27.984) Remain 74:08:59 loss: 0.2307 loss_seg: 0.1374 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:46:40,757 INFO misc.py line 117 726] Train: [2/20][152/510] Data 3.580 (3.831) Batch 31.707 (28.009) Remain 74:12:29 loss: 0.1791 loss_seg: 0.0949 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:47:09,413 INFO misc.py line 117 726] Train: [2/20][153/510] Data 3.003 (3.826) Batch 28.656 (28.013) Remain 74:12:42 loss: 0.2468 loss_seg: 0.1489 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:47:45,580 INFO misc.py line 117 726] Train: [2/20][154/510] Data 4.930 (3.833) Batch 36.167 (28.067) Remain 74:20:49 loss: 0.2789 loss_seg: 0.1768 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:48:07,629 INFO misc.py line 117 726] Train: [2/20][155/510] Data 3.156 (3.828) Batch 22.049 (28.028) Remain 74:14:04 loss: 0.1825 loss_seg: 0.0962 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:48:28,021 INFO misc.py line 117 726] Train: [2/20][156/510] Data 2.590 (3.820) Batch 20.392 (27.978) Remain 74:05:40 loss: 0.2338 loss_seg: 0.1385 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:48:52,603 INFO misc.py line 117 726] Train: [2/20][157/510] Data 3.273 (3.817) Batch 24.581 (27.956) Remain 74:01:41 loss: 0.2927 loss_seg: 0.1933 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:49:13,448 INFO misc.py line 117 726] Train: [2/20][158/510] Data 2.249 (3.807) Batch 20.846 (27.910) Remain 73:53:56 loss: 0.2463 loss_seg: 0.1497 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:49:31,965 INFO misc.py line 117 726] Train: [2/20][159/510] Data 1.780 (3.794) Batch 18.517 (27.850) Remain 73:43:54 loss: 0.2864 loss_seg: 0.1839 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:50:06,019 INFO misc.py line 117 726] Train: [2/20][160/510] Data 8.032 (3.821) Batch 34.054 (27.889) Remain 73:49:43 loss: 0.2310 loss_seg: 0.1424 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:50:25,805 INFO misc.py line 117 726] Train: [2/20][161/510] Data 2.766 (3.814) Batch 19.786 (27.838) Remain 73:41:07 loss: 0.2195 loss_seg: 0.1259 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:50:50,487 INFO misc.py line 117 726] Train: [2/20][162/510] Data 3.123 (3.810) Batch 24.682 (27.818) Remain 73:37:30 loss: 0.2628 loss_seg: 0.1635 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:51:14,812 INFO misc.py line 117 726] Train: [2/20][163/510] Data 3.426 (3.807) Batch 24.325 (27.796) Remain 73:33:34 loss: 0.2383 loss_seg: 0.1471 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:51:49,616 INFO misc.py line 117 726] Train: [2/20][164/510] Data 9.633 (3.843) Batch 34.803 (27.840) Remain 73:40:01 loss: 0.2089 loss_seg: 0.1150 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0431 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:52:18,645 INFO misc.py line 117 726] Train: [2/20][165/510] Data 3.430 (3.841) Batch 29.029 (27.847) Remain 73:40:43 loss: 0.2648 loss_seg: 0.1746 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:52:34,704 INFO misc.py line 117 726] Train: [2/20][166/510] Data 1.621 (3.827) Batch 16.059 (27.775) Remain 73:28:46 loss: 0.2467 loss_seg: 0.1506 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:52:58,511 INFO misc.py line 117 726] Train: [2/20][167/510] Data 2.580 (3.820) Batch 23.807 (27.751) Remain 73:24:28 loss: 0.2113 loss_seg: 0.1206 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:53:21,164 INFO misc.py line 117 726] Train: [2/20][168/510] Data 2.572 (3.812) Batch 22.652 (27.720) Remain 73:19:06 loss: 0.2009 loss_seg: 0.1147 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:53:46,054 INFO misc.py line 117 726] Train: [2/20][169/510] Data 3.229 (3.809) Batch 24.891 (27.703) Remain 73:15:56 loss: 0.1733 loss_seg: 0.0920 loss_superpoint_edge: 0.0146 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:54:11,561 INFO misc.py line 117 726] Train: [2/20][170/510] Data 3.630 (3.808) Batch 25.506 (27.689) Remain 73:13:23 loss: 0.2827 loss_seg: 0.1809 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:54:38,396 INFO misc.py line 117 726] Train: [2/20][171/510] Data 2.750 (3.801) Batch 26.835 (27.684) Remain 73:12:07 loss: 0.2478 loss_seg: 0.1507 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:55:02,494 INFO misc.py line 117 726] Train: [2/20][172/510] Data 2.514 (3.794) Batch 24.098 (27.663) Remain 73:08:17 loss: 0.2370 loss_seg: 0.1444 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:55:42,323 INFO misc.py line 117 726] Train: [2/20][173/510] Data 7.533 (3.816) Batch 39.829 (27.735) Remain 73:19:11 loss: 0.3660 loss_seg: 0.2735 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:56:14,555 INFO misc.py line 117 726] Train: [2/20][174/510] Data 3.498 (3.814) Batch 32.233 (27.761) Remain 73:22:53 loss: 0.2290 loss_seg: 0.1351 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:56:47,102 INFO misc.py line 117 726] Train: [2/20][175/510] Data 3.215 (3.810) Batch 32.546 (27.789) Remain 73:26:50 loss: 0.2382 loss_seg: 0.1455 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:57:11,171 INFO misc.py line 117 726] Train: [2/20][176/510] Data 2.626 (3.803) Batch 24.069 (27.767) Remain 73:22:58 loss: 0.3279 loss_seg: 0.2259 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:57:39,706 INFO misc.py line 117 726] Train: [2/20][177/510] Data 3.497 (3.802) Batch 28.536 (27.772) Remain 73:23:12 loss: 0.2558 loss_seg: 0.1558 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:58:13,492 INFO misc.py line 117 726] Train: [2/20][178/510] Data 4.067 (3.803) Batch 33.785 (27.806) Remain 73:28:11 loss: 0.2283 loss_seg: 0.1362 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:58:45,667 INFO misc.py line 117 726] Train: [2/20][179/510] Data 5.533 (3.813) Batch 32.175 (27.831) Remain 73:31:40 loss: 0.2345 loss_seg: 0.1395 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:59:13,807 INFO misc.py line 117 726] Train: [2/20][180/510] Data 3.078 (3.809) Batch 28.140 (27.833) Remain 73:31:28 loss: 0.2588 loss_seg: 0.1566 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 19:59:34,571 INFO misc.py line 117 726] Train: [2/20][181/510] Data 2.039 (3.799) Batch 20.764 (27.793) Remain 73:24:43 loss: 0.2623 loss_seg: 0.1675 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:00:02,681 INFO misc.py line 117 726] Train: [2/20][182/510] Data 2.988 (3.794) Batch 28.110 (27.795) Remain 73:24:32 loss: 0.2157 loss_seg: 0.1266 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:00:26,551 INFO misc.py line 117 726] Train: [2/20][183/510] Data 3.063 (3.790) Batch 23.871 (27.773) Remain 73:20:37 loss: 0.2784 loss_seg: 0.1790 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:00:59,812 INFO misc.py line 117 726] Train: [2/20][184/510] Data 10.947 (3.830) Batch 33.261 (27.803) Remain 73:24:57 loss: 0.3741 loss_seg: 0.2628 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:01:35,202 INFO misc.py line 117 726] Train: [2/20][185/510] Data 4.255 (3.832) Batch 35.390 (27.845) Remain 73:31:06 loss: 0.2371 loss_seg: 0.1516 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:02:11,035 INFO misc.py line 117 726] Train: [2/20][186/510] Data 5.617 (3.842) Batch 35.833 (27.889) Remain 73:37:33 loss: 0.2466 loss_seg: 0.1558 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:02:37,246 INFO misc.py line 117 726] Train: [2/20][187/510] Data 3.299 (3.839) Batch 26.211 (27.879) Remain 73:35:38 loss: 0.3230 loss_seg: 0.2075 loss_superpoint_edge: 0.0450 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:02:54,050 INFO misc.py line 117 726] Train: [2/20][188/510] Data 2.278 (3.831) Batch 16.804 (27.820) Remain 73:25:42 loss: 0.3495 loss_seg: 0.2314 loss_superpoint_edge: 0.0454 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:03:16,903 INFO misc.py line 117 726] Train: [2/20][189/510] Data 3.540 (3.829) Batch 22.853 (27.793) Remain 73:21:00 loss: 0.2301 loss_seg: 0.1386 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:03:44,456 INFO misc.py line 117 726] Train: [2/20][190/510] Data 4.261 (3.831) Batch 27.553 (27.792) Remain 73:20:20 loss: 0.2510 loss_seg: 0.1545 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:04:16,228 INFO misc.py line 117 726] Train: [2/20][191/510] Data 3.244 (3.828) Batch 31.772 (27.813) Remain 73:23:13 loss: 0.2844 loss_seg: 0.1816 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:04:39,131 INFO misc.py line 117 726] Train: [2/20][192/510] Data 2.420 (3.821) Batch 22.902 (27.787) Remain 73:18:39 loss: 0.2890 loss_seg: 0.1831 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:05:06,729 INFO misc.py line 117 726] Train: [2/20][193/510] Data 4.085 (3.822) Batch 27.598 (27.786) Remain 73:18:02 loss: 0.2292 loss_seg: 0.1343 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:05:38,241 INFO misc.py line 117 726] Train: [2/20][194/510] Data 3.424 (3.820) Batch 31.512 (27.805) Remain 73:20:39 loss: 0.2888 loss_seg: 0.1945 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:06:07,661 INFO misc.py line 117 726] Train: [2/20][195/510] Data 3.435 (3.818) Batch 29.420 (27.814) Remain 73:21:31 loss: 0.2018 loss_seg: 0.1133 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:06:39,315 INFO misc.py line 117 726] Train: [2/20][196/510] Data 4.775 (3.823) Batch 31.654 (27.834) Remain 73:24:12 loss: 0.2645 loss_seg: 0.1674 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:07:05,381 INFO misc.py line 117 726] Train: [2/20][197/510] Data 4.539 (3.827) Batch 26.066 (27.825) Remain 73:22:18 loss: 0.3494 loss_seg: 0.2448 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:07:29,257 INFO misc.py line 117 726] Train: [2/20][198/510] Data 2.239 (3.819) Batch 23.876 (27.804) Remain 73:18:38 loss: 0.2516 loss_seg: 0.1581 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:07:55,369 INFO misc.py line 117 726] Train: [2/20][199/510] Data 3.010 (3.814) Batch 26.112 (27.796) Remain 73:16:48 loss: 0.3171 loss_seg: 0.2084 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0341 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:08:21,647 INFO misc.py line 117 726] Train: [2/20][200/510] Data 8.548 (3.838) Batch 26.278 (27.788) Remain 73:15:07 loss: 0.3154 loss_seg: 0.2114 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0451 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:08:21,647 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 20:08:45,585 INFO misc.py line 117 726] Train: [2/20][201/510] Data 3.214 (3.835) Batch 23.939 (27.769) Remain 73:11:35 loss: 0.2641 loss_seg: 0.1645 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:09:16,502 INFO misc.py line 117 726] Train: [2/20][202/510] Data 4.325 (3.838) Batch 30.917 (27.784) Remain 73:13:37 loss: 0.2511 loss_seg: 0.1527 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:09:52,598 INFO misc.py line 117 726] Train: [2/20][203/510] Data 5.641 (3.847) Batch 36.096 (27.826) Remain 73:19:44 loss: 0.3279 loss_seg: 0.2301 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:10:10,476 INFO misc.py line 117 726] Train: [2/20][204/510] Data 2.087 (3.838) Batch 17.878 (27.776) Remain 73:11:26 loss: 0.2512 loss_seg: 0.1568 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:10:36,449 INFO misc.py line 117 726] Train: [2/20][205/510] Data 5.310 (3.845) Batch 25.972 (27.767) Remain 73:09:34 loss: 0.2160 loss_seg: 0.1266 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:11:05,443 INFO misc.py line 117 726] Train: [2/20][206/510] Data 4.723 (3.850) Batch 28.994 (27.774) Remain 73:10:03 loss: 0.2245 loss_seg: 0.1321 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:11:44,982 INFO misc.py line 117 726] Train: [2/20][207/510] Data 5.616 (3.858) Batch 39.539 (27.831) Remain 73:18:43 loss: 0.2793 loss_seg: 0.1825 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:12:13,926 INFO misc.py line 117 726] Train: [2/20][208/510] Data 3.017 (3.854) Batch 28.944 (27.837) Remain 73:19:06 loss: 0.2236 loss_seg: 0.1293 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:12:48,544 INFO misc.py line 117 726] Train: [2/20][209/510] Data 4.467 (3.857) Batch 34.618 (27.870) Remain 73:23:51 loss: 0.3160 loss_seg: 0.2095 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:13:13,943 INFO misc.py line 117 726] Train: [2/20][210/510] Data 3.459 (3.855) Batch 25.399 (27.858) Remain 73:21:29 loss: 0.2983 loss_seg: 0.1943 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:13:39,123 INFO misc.py line 117 726] Train: [2/20][211/510] Data 2.961 (3.851) Batch 25.180 (27.845) Remain 73:19:00 loss: 0.2514 loss_seg: 0.1563 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:14:13,135 INFO misc.py line 117 726] Train: [2/20][212/510] Data 7.919 (3.870) Batch 34.012 (27.874) Remain 73:23:11 loss: 0.2397 loss_seg: 0.1484 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:14:43,370 INFO misc.py line 117 726] Train: [2/20][213/510] Data 3.299 (3.868) Batch 30.235 (27.885) Remain 73:24:30 loss: 0.2561 loss_seg: 0.1565 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:15:18,182 INFO misc.py line 117 726] Train: [2/20][214/510] Data 2.130 (3.859) Batch 34.812 (27.918) Remain 73:29:13 loss: 0.2678 loss_seg: 0.1651 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:15:55,080 INFO misc.py line 117 726] Train: [2/20][215/510] Data 8.976 (3.884) Batch 36.898 (27.961) Remain 73:35:27 loss: 0.2448 loss_seg: 0.1537 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:16:23,586 INFO misc.py line 117 726] Train: [2/20][216/510] Data 2.595 (3.878) Batch 28.506 (27.963) Remain 73:35:23 loss: 0.1980 loss_seg: 0.1105 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:16:53,992 INFO misc.py line 117 726] Train: [2/20][217/510] Data 4.905 (3.882) Batch 30.406 (27.975) Remain 73:36:43 loss: 0.2059 loss_seg: 0.1190 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:17:27,163 INFO misc.py line 117 726] Train: [2/20][218/510] Data 4.899 (3.887) Batch 33.171 (27.999) Remain 73:40:04 loss: 0.3147 loss_seg: 0.2091 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:17:59,368 INFO misc.py line 117 726] Train: [2/20][219/510] Data 4.267 (3.889) Batch 32.205 (28.018) Remain 73:42:41 loss: 0.2767 loss_seg: 0.1773 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:18:20,847 INFO misc.py line 117 726] Train: [2/20][220/510] Data 2.587 (3.883) Batch 21.479 (27.988) Remain 73:37:27 loss: 0.2476 loss_seg: 0.1484 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:18:59,797 INFO misc.py line 117 726] Train: [2/20][221/510] Data 10.113 (3.911) Batch 38.949 (28.038) Remain 73:44:55 loss: 0.3000 loss_seg: 0.1993 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:19:24,722 INFO misc.py line 117 726] Train: [2/20][222/510] Data 3.183 (3.908) Batch 24.926 (28.024) Remain 73:42:13 loss: 0.2863 loss_seg: 0.1813 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:19:52,663 INFO misc.py line 117 726] Train: [2/20][223/510] Data 4.933 (3.913) Batch 27.940 (28.024) Remain 73:41:41 loss: 0.3426 loss_seg: 0.2326 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:20:21,690 INFO misc.py line 117 726] Train: [2/20][224/510] Data 2.842 (3.908) Batch 29.028 (28.028) Remain 73:41:56 loss: 0.2122 loss_seg: 0.1185 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:20:48,880 INFO misc.py line 117 726] Train: [2/20][225/510] Data 3.696 (3.907) Batch 27.190 (28.025) Remain 73:40:52 loss: 0.2578 loss_seg: 0.1649 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:21:08,441 INFO misc.py line 117 726] Train: [2/20][226/510] Data 2.189 (3.899) Batch 19.561 (27.987) Remain 73:34:25 loss: 0.1690 loss_seg: 0.0792 loss_superpoint_edge: 0.0134 loss_superpoint_contrast: 0.0455 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:21:29,323 INFO misc.py line 117 726] Train: [2/20][227/510] Data 2.335 (3.892) Batch 20.882 (27.955) Remain 73:28:57 loss: 0.2822 loss_seg: 0.1776 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:21:53,372 INFO misc.py line 117 726] Train: [2/20][228/510] Data 3.056 (3.889) Batch 24.049 (27.938) Remain 73:25:45 loss: 0.2569 loss_seg: 0.1604 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:22:25,498 INFO misc.py line 117 726] Train: [2/20][229/510] Data 4.133 (3.890) Batch 32.126 (27.956) Remain 73:28:12 loss: 0.2367 loss_seg: 0.1426 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:22:46,680 INFO misc.py line 117 726] Train: [2/20][230/510] Data 2.064 (3.882) Batch 21.182 (27.926) Remain 73:23:02 loss: 0.1807 loss_seg: 0.0976 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:23:20,612 INFO misc.py line 117 726] Train: [2/20][231/510] Data 3.329 (3.879) Batch 33.932 (27.953) Remain 73:26:43 loss: 0.2493 loss_seg: 0.1513 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:23:47,115 INFO misc.py line 117 726] Train: [2/20][232/510] Data 2.903 (3.875) Batch 26.503 (27.946) Remain 73:25:15 loss: 0.1972 loss_seg: 0.1105 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:24:22,324 INFO misc.py line 117 726] Train: [2/20][233/510] Data 4.866 (3.879) Batch 35.209 (27.978) Remain 73:29:46 loss: 0.2957 loss_seg: 0.1936 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:24:47,275 INFO misc.py line 117 726] Train: [2/20][234/510] Data 4.071 (3.880) Batch 24.950 (27.965) Remain 73:27:14 loss: 0.2924 loss_seg: 0.1914 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:25:10,395 INFO misc.py line 117 726] Train: [2/20][235/510] Data 3.209 (3.877) Batch 23.120 (27.944) Remain 73:23:29 loss: 0.1982 loss_seg: 0.1086 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:25:37,576 INFO misc.py line 117 726] Train: [2/20][236/510] Data 3.220 (3.874) Batch 27.181 (27.941) Remain 73:22:30 loss: 0.2205 loss_seg: 0.1318 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:26:05,881 INFO misc.py line 117 726] Train: [2/20][237/510] Data 3.848 (3.874) Batch 28.305 (27.942) Remain 73:22:17 loss: 0.2451 loss_seg: 0.1512 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:26:24,647 INFO misc.py line 117 726] Train: [2/20][238/510] Data 2.356 (3.868) Batch 18.765 (27.903) Remain 73:15:40 loss: 0.2500 loss_seg: 0.1569 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:26:52,435 INFO misc.py line 117 726] Train: [2/20][239/510] Data 3.217 (3.865) Batch 27.788 (27.903) Remain 73:15:07 loss: 0.2809 loss_seg: 0.1840 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:27:11,499 INFO misc.py line 117 726] Train: [2/20][240/510] Data 2.759 (3.860) Batch 19.065 (27.865) Remain 73:08:47 loss: 0.1806 loss_seg: 0.0943 loss_superpoint_edge: 0.0137 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:27:39,724 INFO misc.py line 117 726] Train: [2/20][241/510] Data 4.437 (3.863) Batch 28.225 (27.867) Remain 73:08:33 loss: 0.2438 loss_seg: 0.1487 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:28:10,930 INFO misc.py line 117 726] Train: [2/20][242/510] Data 2.718 (3.858) Batch 31.206 (27.881) Remain 73:10:17 loss: 0.2475 loss_seg: 0.1481 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:28:44,820 INFO misc.py line 117 726] Train: [2/20][243/510] Data 5.476 (3.865) Batch 33.890 (27.906) Remain 73:13:46 loss: 0.2212 loss_seg: 0.1303 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:29:26,674 INFO misc.py line 117 726] Train: [2/20][244/510] Data 10.750 (3.893) Batch 41.854 (27.964) Remain 73:22:25 loss: 0.2233 loss_seg: 0.1339 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:30:02,980 INFO misc.py line 117 726] Train: [2/20][245/510] Data 5.824 (3.901) Batch 36.306 (27.998) Remain 73:27:22 loss: 0.2351 loss_seg: 0.1411 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:30:37,886 INFO misc.py line 117 726] Train: [2/20][246/510] Data 4.037 (3.902) Batch 34.906 (28.027) Remain 73:31:23 loss: 0.2195 loss_seg: 0.1245 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:30:59,874 INFO misc.py line 117 726] Train: [2/20][247/510] Data 2.328 (3.895) Batch 21.986 (28.002) Remain 73:27:01 loss: 0.2159 loss_seg: 0.1241 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:31:28,805 INFO misc.py line 117 726] Train: [2/20][248/510] Data 3.384 (3.893) Batch 28.933 (28.006) Remain 73:27:09 loss: 0.1960 loss_seg: 0.1103 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:31:52,565 INFO misc.py line 117 726] Train: [2/20][249/510] Data 3.196 (3.890) Batch 23.760 (27.988) Remain 73:23:58 loss: 0.2401 loss_seg: 0.1418 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:32:17,771 INFO misc.py line 117 726] Train: [2/20][250/510] Data 3.272 (3.888) Batch 25.206 (27.977) Remain 73:21:44 loss: 0.1918 loss_seg: 0.1027 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:32:17,773 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 20:32:46,423 INFO misc.py line 117 726] Train: [2/20][251/510] Data 3.125 (3.885) Batch 28.652 (27.980) Remain 73:21:41 loss: 0.2049 loss_seg: 0.1175 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:33:11,481 INFO misc.py line 117 726] Train: [2/20][252/510] Data 2.663 (3.880) Batch 25.058 (27.968) Remain 73:19:23 loss: 0.2586 loss_seg: 0.1605 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:33:50,112 INFO misc.py line 117 726] Train: [2/20][253/510] Data 7.009 (3.892) Batch 38.631 (28.011) Remain 73:25:37 loss: 0.2812 loss_seg: 0.1740 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:34:14,465 INFO misc.py line 117 726] Train: [2/20][254/510] Data 2.515 (3.887) Batch 24.353 (27.996) Remain 73:22:52 loss: 0.2679 loss_seg: 0.1734 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:34:38,362 INFO misc.py line 117 726] Train: [2/20][255/510] Data 2.891 (3.883) Batch 23.897 (27.980) Remain 73:19:50 loss: 0.2284 loss_seg: 0.1364 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:35:07,403 INFO misc.py line 117 726] Train: [2/20][256/510] Data 3.740 (3.882) Batch 29.041 (27.984) Remain 73:20:02 loss: 0.2311 loss_seg: 0.1371 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:35:40,234 INFO misc.py line 117 726] Train: [2/20][257/510] Data 5.243 (3.888) Batch 32.831 (28.003) Remain 73:22:34 loss: 0.2126 loss_seg: 0.1198 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:36:09,842 INFO misc.py line 117 726] Train: [2/20][258/510] Data 3.054 (3.885) Batch 29.608 (28.009) Remain 73:23:05 loss: 0.2206 loss_seg: 0.1281 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:36:36,459 INFO misc.py line 117 726] Train: [2/20][259/510] Data 2.653 (3.880) Batch 26.617 (28.004) Remain 73:21:46 loss: 0.2242 loss_seg: 0.1265 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:37:09,971 INFO misc.py line 117 726] Train: [2/20][260/510] Data 8.023 (3.896) Batch 33.512 (28.025) Remain 73:24:40 loss: 0.2433 loss_seg: 0.1576 loss_superpoint_edge: 0.0134 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:37:35,099 INFO misc.py line 117 726] Train: [2/20][261/510] Data 2.558 (3.891) Batch 25.128 (28.014) Remain 73:22:26 loss: 0.2292 loss_seg: 0.1384 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:38:02,268 INFO misc.py line 117 726] Train: [2/20][262/510] Data 2.921 (3.887) Batch 27.169 (28.011) Remain 73:21:27 loss: 0.2299 loss_seg: 0.1366 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:38:24,944 INFO misc.py line 117 726] Train: [2/20][263/510] Data 2.735 (3.882) Batch 22.676 (27.990) Remain 73:17:46 loss: 0.2789 loss_seg: 0.1755 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:38:52,591 INFO misc.py line 117 726] Train: [2/20][264/510] Data 3.295 (3.880) Batch 27.647 (27.989) Remain 73:17:05 loss: 0.3075 loss_seg: 0.2152 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:39:19,341 INFO misc.py line 117 726] Train: [2/20][265/510] Data 3.115 (3.877) Batch 26.750 (27.984) Remain 73:15:53 loss: 0.2510 loss_seg: 0.1586 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:39:50,029 INFO misc.py line 117 726] Train: [2/20][266/510] Data 5.693 (3.884) Batch 30.688 (27.995) Remain 73:17:02 loss: 0.2623 loss_seg: 0.1642 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:40:19,656 INFO misc.py line 117 726] Train: [2/20][267/510] Data 4.707 (3.887) Batch 29.626 (28.001) Remain 73:17:32 loss: 0.1936 loss_seg: 0.1041 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:40:45,970 INFO misc.py line 117 726] Train: [2/20][268/510] Data 3.618 (3.886) Batch 26.315 (27.995) Remain 73:16:04 loss: 0.2449 loss_seg: 0.1419 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:41:17,652 INFO misc.py line 117 726] Train: [2/20][269/510] Data 3.614 (3.885) Batch 31.682 (28.008) Remain 73:17:47 loss: 0.3135 loss_seg: 0.2113 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:41:54,532 INFO misc.py line 117 726] Train: [2/20][270/510] Data 4.432 (3.887) Batch 36.880 (28.042) Remain 73:22:32 loss: 0.2334 loss_seg: 0.1388 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:42:24,279 INFO misc.py line 117 726] Train: [2/20][271/510] Data 3.551 (3.886) Batch 29.746 (28.048) Remain 73:23:03 loss: 0.2703 loss_seg: 0.1758 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:42:58,243 INFO misc.py line 117 726] Train: [2/20][272/510] Data 6.692 (3.897) Batch 33.964 (28.070) Remain 73:26:02 loss: 0.3873 loss_seg: 0.2846 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:43:25,674 INFO misc.py line 117 726] Train: [2/20][273/510] Data 3.693 (3.896) Batch 27.431 (28.068) Remain 73:25:12 loss: 0.2715 loss_seg: 0.1714 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:43:57,197 INFO misc.py line 117 726] Train: [2/20][274/510] Data 3.115 (3.893) Batch 31.523 (28.080) Remain 73:26:44 loss: 0.2813 loss_seg: 0.1764 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:44:31,785 INFO misc.py line 117 726] Train: [2/20][275/510] Data 4.987 (3.897) Batch 34.588 (28.104) Remain 73:30:01 loss: 0.3681 loss_seg: 0.2619 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:44:49,500 INFO misc.py line 117 726] Train: [2/20][276/510] Data 1.511 (3.888) Batch 17.716 (28.066) Remain 73:23:35 loss: 0.3124 loss_seg: 0.2036 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:45:08,393 INFO misc.py line 117 726] Train: [2/20][277/510] Data 2.099 (3.882) Batch 18.893 (28.033) Remain 73:17:52 loss: 0.3720 loss_seg: 0.2587 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:45:37,543 INFO misc.py line 117 726] Train: [2/20][278/510] Data 3.061 (3.879) Batch 29.149 (28.037) Remain 73:18:02 loss: 0.2837 loss_seg: 0.1811 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:45:59,173 INFO misc.py line 117 726] Train: [2/20][279/510] Data 2.742 (3.875) Batch 21.631 (28.014) Remain 73:13:55 loss: 0.2624 loss_seg: 0.1657 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:46:39,757 INFO misc.py line 117 726] Train: [2/20][280/510] Data 8.969 (3.893) Batch 40.584 (28.059) Remain 73:20:34 loss: 0.2273 loss_seg: 0.1312 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:47:02,382 INFO misc.py line 117 726] Train: [2/20][281/510] Data 1.602 (3.885) Batch 22.625 (28.039) Remain 73:17:02 loss: 0.2416 loss_seg: 0.1423 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:47:32,982 INFO misc.py line 117 726] Train: [2/20][282/510] Data 2.561 (3.880) Batch 30.600 (28.049) Remain 73:18:01 loss: 0.3123 loss_seg: 0.2039 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:48:02,068 INFO misc.py line 117 726] Train: [2/20][283/510] Data 5.177 (3.885) Batch 29.086 (28.052) Remain 73:18:08 loss: 0.3129 loss_seg: 0.2068 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:48:30,897 INFO misc.py line 117 726] Train: [2/20][284/510] Data 4.705 (3.887) Batch 28.829 (28.055) Remain 73:18:06 loss: 0.2255 loss_seg: 0.1283 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:48:53,466 INFO misc.py line 117 726] Train: [2/20][285/510] Data 2.559 (3.883) Batch 22.569 (28.036) Remain 73:14:35 loss: 0.2589 loss_seg: 0.1564 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:49:15,280 INFO misc.py line 117 726] Train: [2/20][286/510] Data 2.926 (3.879) Batch 21.814 (28.014) Remain 73:10:40 loss: 0.2784 loss_seg: 0.1736 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:49:41,658 INFO misc.py line 117 726] Train: [2/20][287/510] Data 2.779 (3.876) Batch 26.378 (28.008) Remain 73:09:18 loss: 0.2062 loss_seg: 0.1188 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:50:10,136 INFO misc.py line 117 726] Train: [2/20][288/510] Data 5.529 (3.881) Batch 28.478 (28.010) Remain 73:09:05 loss: 0.2662 loss_seg: 0.1699 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:50:28,901 INFO misc.py line 117 726] Train: [2/20][289/510] Data 2.147 (3.875) Batch 18.765 (27.977) Remain 73:03:33 loss: 0.2488 loss_seg: 0.1513 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:50:55,472 INFO misc.py line 117 726] Train: [2/20][290/510] Data 4.082 (3.876) Batch 26.571 (27.972) Remain 73:02:19 loss: 0.2250 loss_seg: 0.1278 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:51:12,569 INFO misc.py line 117 726] Train: [2/20][291/510] Data 1.856 (3.869) Batch 17.097 (27.935) Remain 72:55:56 loss: 0.2817 loss_seg: 0.1752 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:51:42,234 INFO misc.py line 117 726] Train: [2/20][292/510] Data 3.552 (3.868) Batch 29.665 (27.941) Remain 72:56:25 loss: 0.2615 loss_seg: 0.1602 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:52:09,412 INFO misc.py line 117 726] Train: [2/20][293/510] Data 2.653 (3.864) Batch 27.178 (27.938) Remain 72:55:32 loss: 0.2726 loss_seg: 0.1724 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:52:46,366 INFO misc.py line 117 726] Train: [2/20][294/510] Data 4.355 (3.865) Batch 36.954 (27.969) Remain 72:59:55 loss: 0.2104 loss_seg: 0.1224 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:53:21,048 INFO misc.py line 117 726] Train: [2/20][295/510] Data 6.771 (3.875) Batch 34.681 (27.992) Remain 73:03:03 loss: 0.2753 loss_seg: 0.1814 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:53:43,643 INFO misc.py line 117 726] Train: [2/20][296/510] Data 2.635 (3.871) Batch 22.595 (27.973) Remain 72:59:42 loss: 0.3216 loss_seg: 0.2107 loss_superpoint_edge: 0.0451 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:54:15,444 INFO misc.py line 117 726] Train: [2/20][297/510] Data 2.989 (3.868) Batch 31.801 (27.986) Remain 73:01:16 loss: 0.2300 loss_seg: 0.1335 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:54:51,161 INFO misc.py line 117 726] Train: [2/20][298/510] Data 5.208 (3.873) Batch 35.717 (28.013) Remain 73:04:55 loss: 0.2557 loss_seg: 0.1616 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:55:23,326 INFO misc.py line 117 726] Train: [2/20][299/510] Data 4.390 (3.874) Batch 32.165 (28.027) Remain 73:06:38 loss: 0.3531 loss_seg: 0.2528 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:56:05,526 INFO misc.py line 117 726] Train: [2/20][300/510] Data 12.058 (3.902) Batch 42.200 (28.074) Remain 73:13:38 loss: 0.2042 loss_seg: 0.1115 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:56:05,527 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 20:56:30,089 INFO misc.py line 117 726] Train: [2/20][301/510] Data 2.956 (3.899) Batch 24.563 (28.063) Remain 73:11:20 loss: 0.2002 loss_seg: 0.1112 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:56:55,579 INFO misc.py line 117 726] Train: [2/20][302/510] Data 2.615 (3.894) Batch 25.490 (28.054) Remain 73:09:31 loss: 0.2248 loss_seg: 0.1322 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:57:24,285 INFO misc.py line 117 726] Train: [2/20][303/510] Data 4.802 (3.897) Batch 28.706 (28.056) Remain 73:09:23 loss: 0.2262 loss_seg: 0.1292 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:57:54,643 INFO misc.py line 117 726] Train: [2/20][304/510] Data 3.329 (3.896) Batch 30.358 (28.064) Remain 73:10:07 loss: 0.2494 loss_seg: 0.1548 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:58:20,849 INFO misc.py line 117 726] Train: [2/20][305/510] Data 2.826 (3.892) Batch 26.206 (28.058) Remain 73:08:41 loss: 0.2076 loss_seg: 0.1183 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:59:05,651 INFO misc.py line 117 726] Train: [2/20][306/510] Data 13.217 (3.923) Batch 44.803 (28.113) Remain 73:16:52 loss: 0.3689 loss_seg: 0.2496 loss_superpoint_edge: 0.0460 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 20:59:32,543 INFO misc.py line 117 726] Train: [2/20][307/510] Data 2.733 (3.919) Batch 26.892 (28.109) Remain 73:15:46 loss: 0.3101 loss_seg: 0.2023 loss_superpoint_edge: 0.0415 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:00:00,363 INFO misc.py line 117 726] Train: [2/20][308/510] Data 2.815 (3.915) Batch 27.820 (28.108) Remain 73:15:09 loss: 0.2696 loss_seg: 0.1757 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:00:33,945 INFO misc.py line 117 726] Train: [2/20][309/510] Data 4.958 (3.919) Batch 33.582 (28.126) Remain 73:17:29 loss: 0.2293 loss_seg: 0.1419 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:00:56,929 INFO misc.py line 117 726] Train: [2/20][310/510] Data 2.611 (3.914) Batch 22.984 (28.109) Remain 73:14:23 loss: 0.1944 loss_seg: 0.1096 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:01:24,128 INFO misc.py line 117 726] Train: [2/20][311/510] Data 3.659 (3.914) Batch 27.199 (28.106) Remain 73:13:27 loss: 0.2341 loss_seg: 0.1404 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:01:54,182 INFO misc.py line 117 726] Train: [2/20][312/510] Data 3.015 (3.911) Batch 30.054 (28.112) Remain 73:13:58 loss: 0.2595 loss_seg: 0.1713 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:02:22,801 INFO misc.py line 117 726] Train: [2/20][313/510] Data 3.566 (3.910) Batch 28.619 (28.114) Remain 73:13:46 loss: 0.2985 loss_seg: 0.1926 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:02:50,066 INFO misc.py line 117 726] Train: [2/20][314/510] Data 2.915 (3.906) Batch 27.265 (28.111) Remain 73:12:52 loss: 0.2234 loss_seg: 0.1320 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:03:05,955 INFO misc.py line 117 726] Train: [2/20][315/510] Data 1.825 (3.900) Batch 15.889 (28.072) Remain 73:06:17 loss: 0.2645 loss_seg: 0.1590 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:03:27,086 INFO misc.py line 117 726] Train: [2/20][316/510] Data 2.682 (3.896) Batch 21.131 (28.050) Remain 73:02:21 loss: 0.2477 loss_seg: 0.1503 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:03:49,832 INFO misc.py line 117 726] Train: [2/20][317/510] Data 2.838 (3.892) Batch 22.746 (28.033) Remain 72:59:14 loss: 0.3355 loss_seg: 0.2311 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0454 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:04:24,548 INFO misc.py line 117 726] Train: [2/20][318/510] Data 4.930 (3.896) Batch 34.715 (28.054) Remain 73:02:05 loss: 0.2801 loss_seg: 0.1804 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:04:54,085 INFO misc.py line 117 726] Train: [2/20][319/510] Data 3.534 (3.895) Batch 29.537 (28.059) Remain 73:02:21 loss: 0.2791 loss_seg: 0.1780 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:05:28,270 INFO misc.py line 117 726] Train: [2/20][320/510] Data 4.542 (3.897) Batch 34.185 (28.078) Remain 73:04:54 loss: 0.3227 loss_seg: 0.2129 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:06:04,490 INFO misc.py line 117 726] Train: [2/20][321/510] Data 6.792 (3.906) Batch 36.220 (28.104) Remain 73:08:26 loss: 0.2856 loss_seg: 0.1785 loss_superpoint_edge: 0.0401 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:06:29,268 INFO misc.py line 117 726] Train: [2/20][322/510] Data 2.622 (3.902) Batch 24.778 (28.094) Remain 73:06:20 loss: 0.2149 loss_seg: 0.1221 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:06:55,348 INFO misc.py line 117 726] Train: [2/20][323/510] Data 2.551 (3.898) Batch 26.080 (28.087) Remain 73:04:53 loss: 0.2070 loss_seg: 0.1164 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:07:30,712 INFO misc.py line 117 726] Train: [2/20][324/510] Data 4.740 (3.900) Batch 35.364 (28.110) Remain 73:07:57 loss: 0.2632 loss_seg: 0.1598 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:08:00,466 INFO misc.py line 117 726] Train: [2/20][325/510] Data 3.159 (3.898) Batch 29.754 (28.115) Remain 73:08:17 loss: 0.3476 loss_seg: 0.2453 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:08:21,084 INFO misc.py line 117 726] Train: [2/20][326/510] Data 1.887 (3.892) Batch 20.618 (28.092) Remain 73:04:11 loss: 0.3119 loss_seg: 0.2152 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:08:52,219 INFO misc.py line 117 726] Train: [2/20][327/510] Data 4.704 (3.894) Batch 31.135 (28.101) Remain 73:05:11 loss: 0.2583 loss_seg: 0.1672 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:09:24,108 INFO misc.py line 117 726] Train: [2/20][328/510] Data 3.769 (3.894) Batch 31.889 (28.113) Remain 73:06:32 loss: 0.1985 loss_seg: 0.1110 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:09:51,040 INFO misc.py line 117 726] Train: [2/20][329/510] Data 2.840 (3.891) Batch 26.932 (28.109) Remain 73:05:30 loss: 0.3218 loss_seg: 0.2156 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:10:21,417 INFO misc.py line 117 726] Train: [2/20][330/510] Data 3.149 (3.888) Batch 30.377 (28.116) Remain 73:06:07 loss: 0.2877 loss_seg: 0.1978 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:10:43,681 INFO misc.py line 117 726] Train: [2/20][331/510] Data 3.027 (3.886) Batch 22.263 (28.098) Remain 73:02:52 loss: 0.3574 loss_seg: 0.2505 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:11:13,982 INFO misc.py line 117 726] Train: [2/20][332/510] Data 4.158 (3.886) Batch 30.301 (28.105) Remain 73:03:27 loss: 0.2802 loss_seg: 0.1758 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:11:41,856 INFO misc.py line 117 726] Train: [2/20][333/510] Data 4.713 (3.889) Batch 27.873 (28.104) Remain 73:02:52 loss: 0.4113 loss_seg: 0.2972 loss_superpoint_edge: 0.0455 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:12:12,764 INFO misc.py line 117 726] Train: [2/20][334/510] Data 4.429 (3.891) Batch 30.908 (28.113) Remain 73:03:43 loss: 0.2081 loss_seg: 0.1167 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:12:44,746 INFO misc.py line 117 726] Train: [2/20][335/510] Data 3.074 (3.888) Batch 31.983 (28.124) Remain 73:05:04 loss: 0.2047 loss_seg: 0.1202 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:13:04,609 INFO misc.py line 117 726] Train: [2/20][336/510] Data 2.341 (3.883) Batch 19.863 (28.100) Remain 73:00:44 loss: 0.2572 loss_seg: 0.1589 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:13:35,982 INFO misc.py line 117 726] Train: [2/20][337/510] Data 4.278 (3.885) Batch 31.373 (28.109) Remain 73:01:47 loss: 0.2129 loss_seg: 0.1241 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:13:50,639 INFO misc.py line 117 726] Train: [2/20][338/510] Data 1.527 (3.878) Batch 14.657 (28.069) Remain 72:55:04 loss: 0.2428 loss_seg: 0.1514 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:14:14,273 INFO misc.py line 117 726] Train: [2/20][339/510] Data 2.142 (3.872) Batch 23.633 (28.056) Remain 72:52:32 loss: 0.2716 loss_seg: 0.1665 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:14:40,715 INFO misc.py line 117 726] Train: [2/20][340/510] Data 3.078 (3.870) Batch 26.443 (28.051) Remain 72:51:19 loss: 0.2504 loss_seg: 0.1507 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:15:06,115 INFO misc.py line 117 726] Train: [2/20][341/510] Data 2.358 (3.866) Batch 25.400 (28.043) Remain 72:49:38 loss: 0.2190 loss_seg: 0.1254 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:15:18,452 INFO misc.py line 117 726] Train: [2/20][342/510] Data 1.457 (3.859) Batch 12.337 (27.997) Remain 72:41:57 loss: 0.2824 loss_seg: 0.1741 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:15:31,885 INFO misc.py line 117 726] Train: [2/20][343/510] Data 1.063 (3.850) Batch 13.433 (27.954) Remain 72:34:48 loss: 0.2424 loss_seg: 0.1487 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:16:00,426 INFO misc.py line 117 726] Train: [2/20][344/510] Data 5.245 (3.854) Batch 28.541 (27.956) Remain 72:34:37 loss: 0.2263 loss_seg: 0.1306 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:16:24,630 INFO misc.py line 117 726] Train: [2/20][345/510] Data 2.339 (3.850) Batch 24.203 (27.945) Remain 72:32:26 loss: 0.2601 loss_seg: 0.1620 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:16:58,420 INFO misc.py line 117 726] Train: [2/20][346/510] Data 3.412 (3.849) Batch 33.791 (27.962) Remain 72:34:37 loss: 0.2351 loss_seg: 0.1431 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:17:28,193 INFO misc.py line 117 726] Train: [2/20][347/510] Data 3.834 (3.849) Batch 29.773 (27.967) Remain 72:34:59 loss: 0.3139 loss_seg: 0.2081 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:17:54,168 INFO misc.py line 117 726] Train: [2/20][348/510] Data 2.584 (3.845) Batch 25.974 (27.962) Remain 72:33:37 loss: 0.2034 loss_seg: 0.1148 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:18:24,999 INFO misc.py line 117 726] Train: [2/20][349/510] Data 3.910 (3.845) Batch 30.832 (27.970) Remain 72:34:26 loss: 0.2689 loss_seg: 0.1703 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:18:49,171 INFO misc.py line 117 726] Train: [2/20][350/510] Data 2.680 (3.842) Batch 24.172 (27.959) Remain 72:32:16 loss: 0.2836 loss_seg: 0.1795 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:18:49,172 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 21:19:14,215 INFO misc.py line 117 726] Train: [2/20][351/510] Data 3.397 (3.841) Batch 25.044 (27.951) Remain 72:30:30 loss: 0.2597 loss_seg: 0.1636 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:19:45,520 INFO misc.py line 117 726] Train: [2/20][352/510] Data 2.963 (3.838) Batch 31.305 (27.960) Remain 72:31:32 loss: 0.2718 loss_seg: 0.1717 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:20:10,650 INFO misc.py line 117 726] Train: [2/20][353/510] Data 2.737 (3.835) Batch 25.130 (27.952) Remain 72:29:48 loss: 0.2729 loss_seg: 0.1748 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:20:39,900 INFO misc.py line 117 726] Train: [2/20][354/510] Data 2.722 (3.832) Batch 29.250 (27.956) Remain 72:29:55 loss: 0.2569 loss_seg: 0.1586 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:21:07,800 INFO misc.py line 117 726] Train: [2/20][355/510] Data 3.416 (3.831) Batch 27.900 (27.956) Remain 72:29:25 loss: 0.2744 loss_seg: 0.1720 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:21:37,539 INFO misc.py line 117 726] Train: [2/20][356/510] Data 3.434 (3.829) Batch 29.739 (27.961) Remain 72:29:44 loss: 0.2572 loss_seg: 0.1546 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:22:00,943 INFO misc.py line 117 726] Train: [2/20][357/510] Data 2.358 (3.825) Batch 23.405 (27.948) Remain 72:27:16 loss: 0.2305 loss_seg: 0.1378 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:22:33,706 INFO misc.py line 117 726] Train: [2/20][358/510] Data 3.595 (3.825) Batch 32.762 (27.961) Remain 72:28:55 loss: 0.3035 loss_seg: 0.1973 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:23:05,414 INFO misc.py line 117 726] Train: [2/20][359/510] Data 3.631 (3.824) Batch 31.708 (27.972) Remain 72:30:05 loss: 0.1918 loss_seg: 0.1040 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:23:29,779 INFO misc.py line 117 726] Train: [2/20][360/510] Data 3.368 (3.823) Batch 24.365 (27.962) Remain 72:28:03 loss: 0.2259 loss_seg: 0.1315 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:24:02,785 INFO misc.py line 117 726] Train: [2/20][361/510] Data 4.392 (3.824) Batch 33.007 (27.976) Remain 72:29:46 loss: 0.3380 loss_seg: 0.2239 loss_superpoint_edge: 0.0492 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:24:31,511 INFO misc.py line 117 726] Train: [2/20][362/510] Data 3.002 (3.822) Batch 28.726 (27.978) Remain 72:29:38 loss: 0.2546 loss_seg: 0.1587 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:24:56,100 INFO misc.py line 117 726] Train: [2/20][363/510] Data 3.121 (3.820) Batch 24.590 (27.969) Remain 72:27:42 loss: 0.2037 loss_seg: 0.1111 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:25:14,539 INFO misc.py line 117 726] Train: [2/20][364/510] Data 2.198 (3.816) Batch 18.438 (27.942) Remain 72:23:08 loss: 0.2372 loss_seg: 0.1398 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:25:45,854 INFO misc.py line 117 726] Train: [2/20][365/510] Data 3.775 (3.816) Batch 31.316 (27.951) Remain 72:24:07 loss: 0.1765 loss_seg: 0.0939 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:26:13,785 INFO misc.py line 117 726] Train: [2/20][366/510] Data 3.328 (3.814) Batch 27.930 (27.951) Remain 72:23:39 loss: 0.2305 loss_seg: 0.1341 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:26:43,444 INFO misc.py line 117 726] Train: [2/20][367/510] Data 3.513 (3.813) Batch 29.659 (27.956) Remain 72:23:54 loss: 0.2143 loss_seg: 0.1231 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:27:09,331 INFO misc.py line 117 726] Train: [2/20][368/510] Data 2.504 (3.810) Batch 25.887 (27.950) Remain 72:22:33 loss: 0.2874 loss_seg: 0.1860 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:27:26,977 INFO misc.py line 117 726] Train: [2/20][369/510] Data 2.192 (3.805) Batch 17.646 (27.922) Remain 72:17:43 loss: 0.2343 loss_seg: 0.1382 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:27:51,299 INFO misc.py line 117 726] Train: [2/20][370/510] Data 3.047 (3.803) Batch 24.323 (27.912) Remain 72:15:44 loss: 0.2348 loss_seg: 0.1412 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:28:16,395 INFO misc.py line 117 726] Train: [2/20][371/510] Data 2.640 (3.800) Batch 25.095 (27.905) Remain 72:14:05 loss: 0.3001 loss_seg: 0.1999 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:28:36,421 INFO misc.py line 117 726] Train: [2/20][372/510] Data 2.107 (3.796) Batch 20.026 (27.883) Remain 72:10:18 loss: 0.2732 loss_seg: 0.1713 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:29:07,874 INFO misc.py line 117 726] Train: [2/20][373/510] Data 3.760 (3.795) Batch 31.453 (27.893) Remain 72:11:20 loss: 0.3203 loss_seg: 0.2142 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:29:34,049 INFO misc.py line 117 726] Train: [2/20][374/510] Data 2.924 (3.793) Batch 26.174 (27.888) Remain 72:10:09 loss: 0.2391 loss_seg: 0.1436 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:30:07,440 INFO misc.py line 117 726] Train: [2/20][375/510] Data 4.643 (3.795) Batch 33.392 (27.903) Remain 72:11:59 loss: 0.4575 loss_seg: 0.3488 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:30:29,600 INFO misc.py line 117 726] Train: [2/20][376/510] Data 1.939 (3.790) Batch 22.160 (27.888) Remain 72:09:07 loss: 0.2078 loss_seg: 0.1165 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:31:07,944 INFO misc.py line 117 726] Train: [2/20][377/510] Data 9.535 (3.806) Batch 38.344 (27.916) Remain 72:13:00 loss: 0.1867 loss_seg: 0.0969 loss_superpoint_edge: 0.0133 loss_superpoint_contrast: 0.0455 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:31:33,071 INFO misc.py line 117 726] Train: [2/20][378/510] Data 2.657 (3.803) Batch 25.127 (27.908) Remain 72:11:23 loss: 0.2840 loss_seg: 0.1804 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:32:01,450 INFO misc.py line 117 726] Train: [2/20][379/510] Data 3.601 (3.802) Batch 28.379 (27.910) Remain 72:11:06 loss: 0.3291 loss_seg: 0.2286 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:32:33,744 INFO misc.py line 117 726] Train: [2/20][380/510] Data 3.556 (3.801) Batch 32.293 (27.921) Remain 72:12:27 loss: 0.2421 loss_seg: 0.1483 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:33:07,392 INFO misc.py line 117 726] Train: [2/20][381/510] Data 3.379 (3.800) Batch 33.648 (27.936) Remain 72:14:20 loss: 0.2122 loss_seg: 0.1197 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:33:31,923 INFO misc.py line 117 726] Train: [2/20][382/510] Data 2.758 (3.798) Batch 24.531 (27.927) Remain 72:12:28 loss: 0.3043 loss_seg: 0.1960 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:34:06,890 INFO misc.py line 117 726] Train: [2/20][383/510] Data 5.056 (3.801) Batch 34.967 (27.946) Remain 72:14:53 loss: 0.3443 loss_seg: 0.2441 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:34:32,104 INFO misc.py line 117 726] Train: [2/20][384/510] Data 3.715 (3.801) Batch 25.214 (27.939) Remain 72:13:18 loss: 0.3372 loss_seg: 0.2352 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:34:56,532 INFO misc.py line 117 726] Train: [2/20][385/510] Data 4.280 (3.802) Batch 24.428 (27.930) Remain 72:11:25 loss: 0.2425 loss_seg: 0.1451 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:35:25,215 INFO misc.py line 117 726] Train: [2/20][386/510] Data 2.710 (3.799) Batch 28.683 (27.932) Remain 72:11:15 loss: 0.2276 loss_seg: 0.1405 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:35:58,129 INFO misc.py line 117 726] Train: [2/20][387/510] Data 3.661 (3.799) Batch 32.914 (27.945) Remain 72:12:48 loss: 0.2382 loss_seg: 0.1460 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:36:26,164 INFO misc.py line 117 726] Train: [2/20][388/510] Data 2.802 (3.796) Batch 28.035 (27.945) Remain 72:12:22 loss: 0.2315 loss_seg: 0.1356 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:36:58,772 INFO misc.py line 117 726] Train: [2/20][389/510] Data 3.757 (3.796) Batch 32.607 (27.957) Remain 72:13:46 loss: 0.1996 loss_seg: 0.1110 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:37:18,076 INFO misc.py line 117 726] Train: [2/20][390/510] Data 2.180 (3.792) Batch 19.304 (27.935) Remain 72:09:50 loss: 0.2988 loss_seg: 0.1928 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:37:44,567 INFO misc.py line 117 726] Train: [2/20][391/510] Data 2.539 (3.789) Batch 26.491 (27.931) Remain 72:08:48 loss: 0.2378 loss_seg: 0.1427 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:38:10,248 INFO misc.py line 117 726] Train: [2/20][392/510] Data 3.131 (3.787) Batch 25.681 (27.925) Remain 72:07:26 loss: 0.2460 loss_seg: 0.1471 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:38:44,802 INFO misc.py line 117 726] Train: [2/20][393/510] Data 4.402 (3.789) Batch 34.554 (27.942) Remain 72:09:36 loss: 0.2069 loss_seg: 0.1172 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:39:10,015 INFO misc.py line 117 726] Train: [2/20][394/510] Data 2.713 (3.786) Batch 25.213 (27.935) Remain 72:08:03 loss: 0.1935 loss_seg: 0.1052 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:39:41,477 INFO misc.py line 117 726] Train: [2/20][395/510] Data 5.040 (3.789) Batch 31.462 (27.944) Remain 72:08:59 loss: 0.2121 loss_seg: 0.1218 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:40:09,698 INFO misc.py line 117 726] Train: [2/20][396/510] Data 2.889 (3.787) Batch 28.222 (27.945) Remain 72:08:38 loss: 0.2781 loss_seg: 0.1783 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:40:32,775 INFO misc.py line 117 726] Train: [2/20][397/510] Data 2.374 (3.783) Batch 23.077 (27.932) Remain 72:06:15 loss: 0.2158 loss_seg: 0.1238 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:41:08,955 INFO misc.py line 117 726] Train: [2/20][398/510] Data 6.145 (3.789) Batch 36.180 (27.953) Remain 72:09:01 loss: 0.2311 loss_seg: 0.1410 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:41:30,815 INFO misc.py line 117 726] Train: [2/20][399/510] Data 2.106 (3.785) Batch 21.860 (27.938) Remain 72:06:10 loss: 0.2066 loss_seg: 0.1199 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:41:53,426 INFO misc.py line 117 726] Train: [2/20][400/510] Data 2.478 (3.782) Batch 22.611 (27.924) Remain 72:03:38 loss: 0.2524 loss_seg: 0.1548 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:41:53,427 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 21:42:25,188 INFO misc.py line 117 726] Train: [2/20][401/510] Data 5.238 (3.785) Batch 31.762 (27.934) Remain 72:04:39 loss: 0.1894 loss_seg: 0.1040 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:42:59,320 INFO misc.py line 117 726] Train: [2/20][402/510] Data 5.594 (3.790) Batch 34.132 (27.950) Remain 72:06:36 loss: 0.2711 loss_seg: 0.1749 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:43:31,563 INFO misc.py line 117 726] Train: [2/20][403/510] Data 6.350 (3.796) Batch 32.243 (27.960) Remain 72:07:47 loss: 0.2609 loss_seg: 0.1631 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:43:56,497 INFO misc.py line 117 726] Train: [2/20][404/510] Data 3.416 (3.795) Batch 24.933 (27.953) Remain 72:06:09 loss: 0.3673 loss_seg: 0.2525 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:44:32,804 INFO misc.py line 117 726] Train: [2/20][405/510] Data 4.313 (3.796) Batch 36.307 (27.974) Remain 72:08:54 loss: 0.2610 loss_seg: 0.1648 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:44:56,901 INFO misc.py line 117 726] Train: [2/20][406/510] Data 2.904 (3.794) Batch 24.097 (27.964) Remain 72:06:57 loss: 0.3256 loss_seg: 0.2266 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:45:21,413 INFO misc.py line 117 726] Train: [2/20][407/510] Data 3.125 (3.793) Batch 24.512 (27.955) Remain 72:05:10 loss: 0.2693 loss_seg: 0.1836 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:45:49,846 INFO misc.py line 117 726] Train: [2/20][408/510] Data 3.425 (3.792) Batch 28.433 (27.957) Remain 72:04:53 loss: 0.2891 loss_seg: 0.1825 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:46:15,605 INFO misc.py line 117 726] Train: [2/20][409/510] Data 3.544 (3.791) Batch 25.759 (27.951) Remain 72:03:35 loss: 0.2181 loss_seg: 0.1229 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:46:53,205 INFO misc.py line 117 726] Train: [2/20][410/510] Data 5.046 (3.794) Batch 37.599 (27.975) Remain 72:06:47 loss: 0.2571 loss_seg: 0.1578 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:47:19,195 INFO misc.py line 117 726] Train: [2/20][411/510] Data 2.581 (3.791) Batch 25.990 (27.970) Remain 72:05:33 loss: 0.2346 loss_seg: 0.1376 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:47:54,318 INFO misc.py line 117 726] Train: [2/20][412/510] Data 4.509 (3.793) Batch 35.123 (27.988) Remain 72:07:48 loss: 0.2328 loss_seg: 0.1385 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:48:23,722 INFO misc.py line 117 726] Train: [2/20][413/510] Data 2.581 (3.790) Batch 29.404 (27.991) Remain 72:07:52 loss: 0.2473 loss_seg: 0.1503 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:49:00,738 INFO misc.py line 117 726] Train: [2/20][414/510] Data 4.482 (3.792) Batch 37.016 (28.013) Remain 72:10:48 loss: 0.2105 loss_seg: 0.1236 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:49:25,056 INFO misc.py line 117 726] Train: [2/20][415/510] Data 2.720 (3.789) Batch 24.318 (28.004) Remain 72:08:56 loss: 0.3050 loss_seg: 0.1997 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:49:50,782 INFO misc.py line 117 726] Train: [2/20][416/510] Data 3.397 (3.788) Batch 25.725 (27.998) Remain 72:07:37 loss: 0.2321 loss_seg: 0.1405 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:50:19,548 INFO misc.py line 117 726] Train: [2/20][417/510] Data 3.762 (3.788) Batch 28.766 (28.000) Remain 72:07:26 loss: 0.2819 loss_seg: 0.1910 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:50:49,293 INFO misc.py line 117 726] Train: [2/20][418/510] Data 4.268 (3.789) Batch 29.745 (28.005) Remain 72:07:37 loss: 0.2648 loss_seg: 0.1745 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:51:22,090 INFO misc.py line 117 726] Train: [2/20][419/510] Data 3.705 (3.789) Batch 32.796 (28.016) Remain 72:08:56 loss: 0.2527 loss_seg: 0.1530 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:52:06,299 INFO misc.py line 117 726] Train: [2/20][420/510] Data 11.298 (3.807) Batch 44.210 (28.055) Remain 72:14:28 loss: 0.2370 loss_seg: 0.1409 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:52:31,806 INFO misc.py line 117 726] Train: [2/20][421/510] Data 2.004 (3.803) Batch 25.507 (28.049) Remain 72:13:04 loss: 0.1990 loss_seg: 0.1056 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:52:58,865 INFO misc.py line 117 726] Train: [2/20][422/510] Data 2.918 (3.801) Batch 27.059 (28.046) Remain 72:12:14 loss: 0.2191 loss_seg: 0.1284 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:53:16,698 INFO misc.py line 117 726] Train: [2/20][423/510] Data 2.168 (3.797) Batch 17.833 (28.022) Remain 72:08:00 loss: 0.3334 loss_seg: 0.2274 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:53:44,035 INFO misc.py line 117 726] Train: [2/20][424/510] Data 4.450 (3.798) Batch 27.337 (28.020) Remain 72:07:17 loss: 0.3617 loss_seg: 0.2572 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:54:17,753 INFO misc.py line 117 726] Train: [2/20][425/510] Data 4.375 (3.800) Batch 33.718 (28.034) Remain 72:08:54 loss: 0.4720 loss_seg: 0.3348 loss_superpoint_edge: 0.0655 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:54:47,148 INFO misc.py line 117 726] Train: [2/20][426/510] Data 3.561 (3.799) Batch 29.394 (28.037) Remain 72:08:56 loss: 0.2146 loss_seg: 0.1229 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:55:04,436 INFO misc.py line 117 726] Train: [2/20][427/510] Data 2.507 (3.796) Batch 17.289 (28.012) Remain 72:04:33 loss: 0.2388 loss_seg: 0.1370 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:55:30,058 INFO misc.py line 117 726] Train: [2/20][428/510] Data 2.603 (3.793) Batch 25.621 (28.006) Remain 72:03:13 loss: 0.2525 loss_seg: 0.1578 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:55:45,477 INFO misc.py line 117 726] Train: [2/20][429/510] Data 2.134 (3.789) Batch 15.420 (27.977) Remain 71:58:11 loss: 0.2354 loss_seg: 0.1441 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:56:20,673 INFO misc.py line 117 726] Train: [2/20][430/510] Data 6.178 (3.795) Batch 35.195 (27.994) Remain 72:00:20 loss: 0.2570 loss_seg: 0.1618 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:56:54,295 INFO misc.py line 117 726] Train: [2/20][431/510] Data 5.362 (3.799) Batch 33.622 (28.007) Remain 72:01:54 loss: 0.2695 loss_seg: 0.1725 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:57:20,286 INFO misc.py line 117 726] Train: [2/20][432/510] Data 3.346 (3.798) Batch 25.990 (28.002) Remain 72:00:42 loss: 0.2780 loss_seg: 0.1722 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:57:42,611 INFO misc.py line 117 726] Train: [2/20][433/510] Data 2.947 (3.796) Batch 22.325 (27.989) Remain 71:58:12 loss: 0.2490 loss_seg: 0.1500 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0436 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:58:06,791 INFO misc.py line 117 726] Train: [2/20][434/510] Data 3.006 (3.794) Batch 24.180 (27.980) Remain 71:56:22 loss: 0.2644 loss_seg: 0.1632 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:58:29,173 INFO misc.py line 117 726] Train: [2/20][435/510] Data 4.770 (3.796) Batch 22.382 (27.967) Remain 71:53:54 loss: 0.3511 loss_seg: 0.2580 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:59:01,133 INFO misc.py line 117 726] Train: [2/20][436/510] Data 3.311 (3.795) Batch 31.960 (27.976) Remain 71:54:52 loss: 0.2400 loss_seg: 0.1431 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:59:22,530 INFO misc.py line 117 726] Train: [2/20][437/510] Data 2.760 (3.792) Batch 21.397 (27.961) Remain 71:52:03 loss: 0.2908 loss_seg: 0.1868 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 21:59:55,760 INFO misc.py line 117 726] Train: [2/20][438/510] Data 5.496 (3.796) Batch 33.230 (27.973) Remain 71:53:27 loss: 0.2971 loss_seg: 0.2015 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:00:22,703 INFO misc.py line 117 726] Train: [2/20][439/510] Data 3.494 (3.796) Batch 26.943 (27.971) Remain 71:52:38 loss: 0.3218 loss_seg: 0.2279 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:00:48,870 INFO misc.py line 117 726] Train: [2/20][440/510] Data 2.902 (3.794) Batch 26.167 (27.967) Remain 71:51:32 loss: 0.2763 loss_seg: 0.1769 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:01:19,676 INFO misc.py line 117 726] Train: [2/20][441/510] Data 3.307 (3.793) Batch 30.806 (27.973) Remain 71:52:03 loss: 0.2426 loss_seg: 0.1445 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:01:47,646 INFO misc.py line 117 726] Train: [2/20][442/510] Data 2.951 (3.791) Batch 27.970 (27.973) Remain 71:51:35 loss: 0.2326 loss_seg: 0.1391 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:02:12,191 INFO misc.py line 117 726] Train: [2/20][443/510] Data 2.820 (3.788) Batch 24.545 (27.965) Remain 71:49:55 loss: 0.2793 loss_seg: 0.1794 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:02:33,223 INFO misc.py line 117 726] Train: [2/20][444/510] Data 2.467 (3.785) Batch 21.032 (27.950) Remain 71:47:02 loss: 0.2309 loss_seg: 0.1328 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:02:59,355 INFO misc.py line 117 726] Train: [2/20][445/510] Data 2.651 (3.783) Batch 26.132 (27.946) Remain 71:45:56 loss: 0.2341 loss_seg: 0.1362 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:03:24,756 INFO misc.py line 117 726] Train: [2/20][446/510] Data 4.248 (3.784) Batch 25.401 (27.940) Remain 71:44:35 loss: 0.2613 loss_seg: 0.1614 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:03:57,320 INFO misc.py line 117 726] Train: [2/20][447/510] Data 4.734 (3.786) Batch 32.564 (27.950) Remain 71:45:43 loss: 0.2240 loss_seg: 0.1315 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:04:29,771 INFO misc.py line 117 726] Train: [2/20][448/510] Data 3.702 (3.786) Batch 32.451 (27.960) Remain 71:46:49 loss: 0.2626 loss_seg: 0.1645 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:05:04,349 INFO misc.py line 117 726] Train: [2/20][449/510] Data 5.199 (3.789) Batch 34.578 (27.975) Remain 71:48:38 loss: 0.2495 loss_seg: 0.1465 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:05:37,250 INFO misc.py line 117 726] Train: [2/20][450/510] Data 6.575 (3.795) Batch 32.900 (27.986) Remain 71:49:52 loss: 0.3585 loss_seg: 0.2524 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:05:37,250 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 22:06:11,152 INFO misc.py line 117 726] Train: [2/20][451/510] Data 4.642 (3.797) Batch 33.902 (27.999) Remain 71:51:26 loss: 0.3018 loss_seg: 0.1960 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:06:38,251 INFO misc.py line 117 726] Train: [2/20][452/510] Data 2.874 (3.795) Batch 27.099 (27.997) Remain 71:50:39 loss: 0.1611 loss_seg: 0.0800 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:07:13,337 INFO misc.py line 117 726] Train: [2/20][453/510] Data 4.541 (3.797) Batch 35.086 (28.013) Remain 71:52:37 loss: 0.2774 loss_seg: 0.1779 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:07:42,501 INFO misc.py line 117 726] Train: [2/20][454/510] Data 3.288 (3.796) Batch 29.163 (28.016) Remain 71:52:32 loss: 0.2580 loss_seg: 0.1588 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:08:14,698 INFO misc.py line 117 726] Train: [2/20][455/510] Data 3.439 (3.795) Batch 32.198 (28.025) Remain 71:53:30 loss: 0.2407 loss_seg: 0.1458 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:08:35,072 INFO misc.py line 117 726] Train: [2/20][456/510] Data 2.283 (3.791) Batch 20.374 (28.008) Remain 71:50:26 loss: 0.2227 loss_seg: 0.1245 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:08:59,360 INFO misc.py line 117 726] Train: [2/20][457/510] Data 2.645 (3.789) Batch 24.287 (28.000) Remain 71:48:42 loss: 0.3161 loss_seg: 0.1996 loss_superpoint_edge: 0.0464 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0340 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:09:28,852 INFO misc.py line 117 726] Train: [2/20][458/510] Data 2.848 (3.787) Batch 29.493 (28.003) Remain 71:48:45 loss: 0.2134 loss_seg: 0.1197 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:09:58,219 INFO misc.py line 117 726] Train: [2/20][459/510] Data 3.290 (3.786) Batch 29.367 (28.006) Remain 71:48:44 loss: 0.2638 loss_seg: 0.1696 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:10:25,864 INFO misc.py line 117 726] Train: [2/20][460/510] Data 3.138 (3.784) Batch 27.645 (28.005) Remain 71:48:09 loss: 0.2522 loss_seg: 0.1540 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:10:56,791 INFO misc.py line 117 726] Train: [2/20][461/510] Data 2.565 (3.782) Batch 30.927 (28.012) Remain 71:48:40 loss: 0.2497 loss_seg: 0.1579 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:11:25,629 INFO misc.py line 117 726] Train: [2/20][462/510] Data 3.305 (3.781) Batch 28.838 (28.014) Remain 71:48:28 loss: 0.2769 loss_seg: 0.1762 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:11:59,148 INFO misc.py line 117 726] Train: [2/20][463/510] Data 4.302 (3.782) Batch 33.519 (28.025) Remain 71:49:51 loss: 0.2392 loss_seg: 0.1433 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:12:31,694 INFO misc.py line 117 726] Train: [2/20][464/510] Data 5.477 (3.786) Batch 32.547 (28.035) Remain 71:50:53 loss: 0.2281 loss_seg: 0.1341 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:13:05,445 INFO misc.py line 117 726] Train: [2/20][465/510] Data 4.915 (3.788) Batch 33.751 (28.048) Remain 71:52:19 loss: 0.2945 loss_seg: 0.1953 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:13:31,975 INFO misc.py line 117 726] Train: [2/20][466/510] Data 2.737 (3.786) Batch 26.530 (28.044) Remain 71:51:21 loss: 0.2412 loss_seg: 0.1480 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:14:07,262 INFO misc.py line 117 726] Train: [2/20][467/510] Data 3.722 (3.786) Batch 35.287 (28.060) Remain 71:53:17 loss: 0.2662 loss_seg: 0.1688 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:14:34,865 INFO misc.py line 117 726] Train: [2/20][468/510] Data 4.450 (3.787) Batch 27.603 (28.059) Remain 71:52:40 loss: 0.1952 loss_seg: 0.1086 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:15:03,828 INFO misc.py line 117 726] Train: [2/20][469/510] Data 3.288 (3.786) Batch 28.963 (28.061) Remain 71:52:30 loss: 0.2332 loss_seg: 0.1392 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:15:34,108 INFO misc.py line 117 726] Train: [2/20][470/510] Data 3.491 (3.785) Batch 30.280 (28.066) Remain 71:52:45 loss: 0.2329 loss_seg: 0.1421 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:16:06,884 INFO misc.py line 117 726] Train: [2/20][471/510] Data 3.093 (3.784) Batch 32.776 (28.076) Remain 71:53:50 loss: 0.2691 loss_seg: 0.1740 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0319 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:16:40,539 INFO misc.py line 117 726] Train: [2/20][472/510] Data 3.251 (3.783) Batch 33.655 (28.088) Remain 71:55:12 loss: 0.2488 loss_seg: 0.1498 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:17:09,755 INFO misc.py line 117 726] Train: [2/20][473/510] Data 7.688 (3.791) Batch 29.216 (28.090) Remain 71:55:06 loss: 0.2286 loss_seg: 0.1427 loss_superpoint_edge: 0.0129 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:17:39,143 INFO misc.py line 117 726] Train: [2/20][474/510] Data 3.095 (3.789) Batch 29.388 (28.093) Remain 71:55:03 loss: 0.2074 loss_seg: 0.1119 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:18:09,609 INFO misc.py line 117 726] Train: [2/20][475/510] Data 3.903 (3.790) Batch 30.465 (28.098) Remain 71:55:21 loss: 0.2844 loss_seg: 0.1827 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:18:37,081 INFO misc.py line 117 726] Train: [2/20][476/510] Data 4.028 (3.790) Batch 27.473 (28.097) Remain 71:54:41 loss: 0.3909 loss_seg: 0.2845 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:19:02,173 INFO misc.py line 117 726] Train: [2/20][477/510] Data 2.707 (3.788) Batch 25.092 (28.090) Remain 71:53:14 loss: 0.2840 loss_seg: 0.1831 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:19:28,936 INFO misc.py line 117 726] Train: [2/20][478/510] Data 2.763 (3.786) Batch 26.763 (28.087) Remain 71:52:21 loss: 0.2894 loss_seg: 0.1867 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:19:55,598 INFO misc.py line 117 726] Train: [2/20][479/510] Data 3.013 (3.784) Batch 26.662 (28.084) Remain 71:51:25 loss: 0.2897 loss_seg: 0.1828 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:20:23,966 INFO misc.py line 117 726] Train: [2/20][480/510] Data 5.424 (3.788) Batch 28.369 (28.085) Remain 71:51:02 loss: 0.3329 loss_seg: 0.2361 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:20:44,521 INFO misc.py line 117 726] Train: [2/20][481/510] Data 2.807 (3.786) Batch 20.555 (28.069) Remain 71:48:09 loss: 0.3468 loss_seg: 0.2463 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:21:15,486 INFO misc.py line 117 726] Train: [2/20][482/510] Data 3.610 (3.785) Batch 30.964 (28.075) Remain 71:48:37 loss: 0.2968 loss_seg: 0.2015 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:21:42,585 INFO misc.py line 117 726] Train: [2/20][483/510] Data 3.800 (3.785) Batch 27.100 (28.073) Remain 71:47:50 loss: 0.2353 loss_seg: 0.1374 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:22:16,836 INFO misc.py line 117 726] Train: [2/20][484/510] Data 3.118 (3.784) Batch 34.251 (28.086) Remain 71:49:20 loss: 0.2684 loss_seg: 0.1672 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:22:51,587 INFO misc.py line 117 726] Train: [2/20][485/510] Data 3.845 (3.784) Batch 34.751 (28.100) Remain 71:50:59 loss: 0.2981 loss_seg: 0.1912 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:23:33,446 INFO misc.py line 117 726] Train: [2/20][486/510] Data 11.397 (3.800) Batch 41.859 (28.128) Remain 71:54:53 loss: 0.2647 loss_seg: 0.1753 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:24:03,456 INFO misc.py line 117 726] Train: [2/20][487/510] Data 3.948 (3.800) Batch 30.009 (28.132) Remain 71:55:01 loss: 0.2293 loss_seg: 0.1326 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:24:29,497 INFO misc.py line 117 726] Train: [2/20][488/510] Data 3.906 (3.800) Batch 26.042 (28.128) Remain 71:53:53 loss: 0.1982 loss_seg: 0.1133 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:25:03,824 INFO misc.py line 117 726] Train: [2/20][489/510] Data 5.286 (3.803) Batch 34.327 (28.141) Remain 71:55:23 loss: 0.2170 loss_seg: 0.1267 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:25:26,350 INFO misc.py line 117 726] Train: [2/20][490/510] Data 2.286 (3.800) Batch 22.526 (28.129) Remain 71:53:08 loss: 0.2354 loss_seg: 0.1445 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:25:54,334 INFO misc.py line 117 726] Train: [2/20][491/510] Data 3.105 (3.799) Batch 27.984 (28.129) Remain 71:52:37 loss: 0.2199 loss_seg: 0.1272 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:26:22,756 INFO misc.py line 117 726] Train: [2/20][492/510] Data 3.498 (3.798) Batch 28.422 (28.130) Remain 71:52:15 loss: 0.2198 loss_seg: 0.1303 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:26:35,700 INFO misc.py line 117 726] Train: [2/20][493/510] Data 1.674 (3.794) Batch 12.944 (28.099) Remain 71:47:02 loss: 0.1706 loss_seg: 0.0844 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:26:59,465 INFO misc.py line 117 726] Train: [2/20][494/510] Data 2.818 (3.792) Batch 23.765 (28.090) Remain 71:45:12 loss: 0.4849 loss_seg: 0.3811 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:27:23,454 INFO misc.py line 117 726] Train: [2/20][495/510] Data 2.697 (3.790) Batch 23.990 (28.081) Remain 71:43:28 loss: 0.2772 loss_seg: 0.1757 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:27:50,570 INFO misc.py line 117 726] Train: [2/20][496/510] Data 3.475 (3.789) Batch 27.115 (28.079) Remain 71:42:42 loss: 0.2728 loss_seg: 0.1753 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:28:18,915 INFO misc.py line 117 726] Train: [2/20][497/510] Data 5.113 (3.792) Batch 28.346 (28.080) Remain 71:42:18 loss: 0.2374 loss_seg: 0.1455 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:28:48,654 INFO misc.py line 117 726] Train: [2/20][498/510] Data 6.333 (3.797) Batch 29.739 (28.083) Remain 71:42:21 loss: 0.2512 loss_seg: 0.1477 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:29:13,047 INFO misc.py line 117 726] Train: [2/20][499/510] Data 2.429 (3.794) Batch 24.394 (28.076) Remain 71:40:45 loss: 0.2336 loss_seg: 0.1394 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:29:39,307 INFO misc.py line 117 726] Train: [2/20][500/510] Data 4.364 (3.795) Batch 26.260 (28.072) Remain 71:39:43 loss: 0.2643 loss_seg: 0.1688 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:29:39,308 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 22:30:06,636 INFO misc.py line 117 726] Train: [2/20][501/510] Data 3.979 (3.796) Batch 27.329 (28.071) Remain 71:39:01 loss: 0.2188 loss_seg: 0.1275 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:30:28,988 INFO misc.py line 117 726] Train: [2/20][502/510] Data 3.213 (3.794) Batch 22.352 (28.059) Remain 71:36:48 loss: 0.2765 loss_seg: 0.1783 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:30:59,014 INFO misc.py line 117 726] Train: [2/20][503/510] Data 3.377 (3.794) Batch 30.026 (28.063) Remain 71:36:56 loss: 0.2501 loss_seg: 0.1520 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:31:17,870 INFO misc.py line 117 726] Train: [2/20][504/510] Data 2.362 (3.791) Batch 18.856 (28.045) Remain 71:33:39 loss: 0.2733 loss_seg: 0.1715 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:31:47,959 INFO misc.py line 117 726] Train: [2/20][505/510] Data 3.321 (3.790) Batch 30.088 (28.049) Remain 71:33:48 loss: 0.2282 loss_seg: 0.1365 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:32:12,769 INFO misc.py line 117 726] Train: [2/20][506/510] Data 4.305 (3.791) Batch 24.810 (28.042) Remain 71:32:21 loss: 0.2190 loss_seg: 0.1281 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:32:39,969 INFO misc.py line 117 726] Train: [2/20][507/510] Data 2.746 (3.789) Batch 27.200 (28.041) Remain 71:31:38 loss: 0.2314 loss_seg: 0.1299 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:33:04,397 INFO misc.py line 117 726] Train: [2/20][508/510] Data 2.399 (3.786) Batch 24.429 (28.034) Remain 71:30:04 loss: 0.3471 loss_seg: 0.2161 loss_superpoint_edge: 0.0648 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:33:28,718 INFO misc.py line 117 726] Train: [2/20][509/510] Data 2.816 (3.784) Batch 24.321 (28.026) Remain 71:28:29 loss: 0.2299 loss_seg: 0.1367 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:33:53,547 INFO misc.py line 117 726] Train: [2/20][510/510] Data 2.848 (3.782) Batch 24.829 (28.020) Remain 71:27:03 loss: 0.2199 loss_seg: 0.1327 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:33:53,548 INFO misc.py line 147 726] Train result: loss: 0.2608 loss_seg: 0.1637 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 [2026-06-09 22:33:53,549 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-09 22:34:09,195 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7432 [2026-06-09 22:34:27,029 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6395 [2026-06-09 22:35:41,080 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 1.0243 [2026-06-09 22:36:22,302 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.1039 [2026-06-09 22:36:41,516 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0373 [2026-06-09 22:37:17,312 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.3181 [2026-06-09 22:38:03,514 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 1.9528 [2026-06-09 22:38:19,218 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2270 [2026-06-09 22:38:37,005 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.8291 [2026-06-09 22:38:55,591 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3992 [2026-06-09 22:39:11,552 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.6309 [2026-06-09 22:39:33,169 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7335 [2026-06-09 22:39:58,895 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8168 [2026-06-09 22:40:10,314 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.5662 [2026-06-09 22:40:41,590 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0664 [2026-06-09 22:41:07,627 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3220 [2026-06-09 22:41:34,340 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3005 [2026-06-09 22:42:16,943 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 3.9307 [2026-06-09 22:42:37,845 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3919 [2026-06-09 22:42:54,240 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.5412 [2026-06-09 22:43:25,118 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.6168 [2026-06-09 22:43:41,406 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.3227 [2026-06-09 22:44:03,325 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2017 [2026-06-09 22:44:24,829 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7907 [2026-06-09 22:44:38,124 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6243 [2026-06-09 22:45:05,659 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.4714 [2026-06-09 22:45:46,846 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0952 [2026-06-09 22:46:03,969 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5538 [2026-06-09 22:46:22,505 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4405 [2026-06-09 22:46:39,252 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4863 [2026-06-09 22:47:04,279 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2246 [2026-06-09 22:47:22,290 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5680 [2026-06-09 22:47:39,728 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9379 [2026-06-09 22:48:04,561 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7933 [2026-06-09 22:48:04,583 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6693/0.7436/0.8948. [2026-06-09 22:48:04,583 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9250/0.9593 [2026-06-09 22:48:04,583 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9762/0.9875 [2026-06-09 22:48:04,583 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8381/0.9680 [2026-06-09 22:48:04,583 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0009/0.0069 [2026-06-09 22:48:04,583 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3259/0.4243 [2026-06-09 22:48:04,583 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.5885/0.6111 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5969/0.6854 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7844/0.9113 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9165/0.9505 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6710/0.7515 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7581/0.8450 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7290/0.8720 [2026-06-09 22:48:04,584 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5901/0.6940 [2026-06-09 22:48:04,584 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-09 22:48:04,585 INFO misc.py line 213 726] Best validation mIoU updated to: 0.6693 [2026-06-09 22:48:04,585 INFO misc.py line 218 726] Currently Best mIoU: 0.6693 [2026-06-09 22:48:04,585 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 22:48:34,818 INFO misc.py line 117 726] Train: [3/20][1/510] Data 3.686 (3.686) Batch 28.190 (28.190) Remain 71:52:35 loss: 0.1754 loss_seg: 0.0899 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:49:00,244 INFO misc.py line 117 726] Train: [3/20][2/510] Data 2.983 (2.983) Batch 25.426 (25.426) Remain 64:49:19 loss: 0.2288 loss_seg: 0.1345 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:49:41,733 INFO misc.py line 117 726] Train: [3/20][3/510] Data 9.784 (9.784) Batch 41.489 (41.489) Remain 105:45:42 loss: 0.2426 loss_seg: 0.1471 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:50:10,747 INFO misc.py line 117 726] Train: [3/20][4/510] Data 3.272 (3.272) Batch 29.014 (29.014) Remain 73:57:15 loss: 0.2484 loss_seg: 0.1447 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:50:30,216 INFO misc.py line 117 726] Train: [3/20][5/510] Data 2.202 (2.737) Batch 19.469 (24.241) Remain 61:46:55 loss: 0.2577 loss_seg: 0.1591 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:50:51,590 INFO misc.py line 117 726] Train: [3/20][6/510] Data 2.796 (2.757) Batch 21.374 (23.286) Remain 59:20:22 loss: 0.2783 loss_seg: 0.1758 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:51:15,796 INFO misc.py line 117 726] Train: [3/20][7/510] Data 3.247 (2.879) Batch 24.206 (23.516) Remain 59:55:09 loss: 0.2724 loss_seg: 0.1837 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:51:31,686 INFO misc.py line 117 726] Train: [3/20][8/510] Data 2.041 (2.712) Batch 15.891 (21.991) Remain 56:01:38 loss: 0.3466 loss_seg: 0.2286 loss_superpoint_edge: 0.0480 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:51:55,460 INFO misc.py line 117 726] Train: [3/20][9/510] Data 3.028 (2.764) Batch 23.774 (22.288) Remain 56:46:42 loss: 0.2437 loss_seg: 0.1482 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:52:16,927 INFO misc.py line 117 726] Train: [3/20][10/510] Data 2.934 (2.789) Batch 21.467 (22.171) Remain 56:28:24 loss: 0.2466 loss_seg: 0.1481 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:52:41,558 INFO misc.py line 117 726] Train: [3/20][11/510] Data 3.263 (2.848) Batch 24.631 (22.478) Remain 57:15:02 loss: 0.2219 loss_seg: 0.1293 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:53:05,769 INFO misc.py line 117 726] Train: [3/20][12/510] Data 2.953 (2.860) Batch 24.211 (22.671) Remain 57:44:04 loss: 0.3804 loss_seg: 0.2578 loss_superpoint_edge: 0.0541 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:53:32,093 INFO misc.py line 117 726] Train: [3/20][13/510] Data 3.396 (2.913) Batch 26.324 (23.036) Remain 58:39:31 loss: 0.2007 loss_seg: 0.1113 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:54:09,447 INFO misc.py line 117 726] Train: [3/20][14/510] Data 5.082 (3.110) Batch 37.354 (24.338) Remain 61:57:58 loss: 0.2830 loss_seg: 0.1767 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:54:32,072 INFO misc.py line 117 726] Train: [3/20][15/510] Data 3.180 (3.116) Batch 22.624 (24.195) Remain 61:35:46 loss: 0.2834 loss_seg: 0.1825 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:55:02,217 INFO misc.py line 117 726] Train: [3/20][16/510] Data 3.912 (3.177) Batch 30.146 (24.653) Remain 62:45:16 loss: 0.2517 loss_seg: 0.1539 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:55:33,659 INFO misc.py line 117 726] Train: [3/20][17/510] Data 3.566 (3.205) Batch 31.442 (25.138) Remain 63:58:55 loss: 0.2351 loss_seg: 0.1461 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:56:08,323 INFO misc.py line 117 726] Train: [3/20][18/510] Data 10.621 (3.700) Batch 34.664 (25.773) Remain 65:35:28 loss: 0.2883 loss_seg: 0.1823 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:56:38,694 INFO misc.py line 117 726] Train: [3/20][19/510] Data 3.748 (3.703) Batch 30.371 (26.060) Remain 66:18:55 loss: 0.2272 loss_seg: 0.1383 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:57:10,967 INFO misc.py line 117 726] Train: [3/20][20/510] Data 5.625 (3.816) Batch 32.273 (26.426) Remain 67:14:17 loss: 0.3224 loss_seg: 0.2135 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:57:36,694 INFO misc.py line 117 726] Train: [3/20][21/510] Data 5.096 (3.887) Batch 25.727 (26.387) Remain 67:07:55 loss: 0.3777 loss_seg: 0.2605 loss_superpoint_edge: 0.0444 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:58:00,978 INFO misc.py line 117 726] Train: [3/20][22/510] Data 2.775 (3.828) Batch 24.284 (26.276) Remain 66:50:35 loss: 0.2623 loss_seg: 0.1633 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:58:18,951 INFO misc.py line 117 726] Train: [3/20][23/510] Data 2.319 (3.753) Batch 17.973 (25.861) Remain 65:46:48 loss: 0.2307 loss_seg: 0.1429 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:58:41,794 INFO misc.py line 117 726] Train: [3/20][24/510] Data 3.051 (3.719) Batch 22.843 (25.717) Remain 65:24:26 loss: 0.3173 loss_seg: 0.2123 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:59:10,416 INFO misc.py line 117 726] Train: [3/20][25/510] Data 4.605 (3.760) Batch 28.622 (25.849) Remain 65:44:09 loss: 0.2681 loss_seg: 0.1781 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 22:59:35,168 INFO misc.py line 117 726] Train: [3/20][26/510] Data 3.591 (3.752) Batch 24.752 (25.801) Remain 65:36:26 loss: 0.2072 loss_seg: 0.1199 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:00:03,786 INFO misc.py line 117 726] Train: [3/20][27/510] Data 3.417 (3.738) Batch 28.619 (25.919) Remain 65:53:55 loss: 0.2048 loss_seg: 0.1142 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:00:21,503 INFO misc.py line 117 726] Train: [3/20][28/510] Data 2.359 (3.683) Batch 17.717 (25.591) Remain 65:03:26 loss: 0.2835 loss_seg: 0.1808 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:00:51,635 INFO misc.py line 117 726] Train: [3/20][29/510] Data 4.511 (3.715) Batch 30.132 (25.765) Remain 65:29:39 loss: 0.3411 loss_seg: 0.2314 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:01:10,779 INFO misc.py line 117 726] Train: [3/20][30/510] Data 2.794 (3.681) Batch 19.145 (25.520) Remain 64:51:50 loss: 0.2843 loss_seg: 0.1831 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:01:47,166 INFO misc.py line 117 726] Train: [3/20][31/510] Data 5.502 (3.746) Batch 36.387 (25.908) Remain 65:50:35 loss: 0.1624 loss_seg: 0.0797 loss_superpoint_edge: 0.0138 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:02:22,499 INFO misc.py line 117 726] Train: [3/20][32/510] Data 9.570 (3.947) Batch 35.333 (26.233) Remain 66:39:42 loss: 0.2944 loss_seg: 0.1983 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:02:50,338 INFO misc.py line 117 726] Train: [3/20][33/510] Data 2.506 (3.899) Batch 27.839 (26.287) Remain 66:47:25 loss: 0.2591 loss_seg: 0.1559 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:03:19,865 INFO misc.py line 117 726] Train: [3/20][34/510] Data 5.473 (3.950) Batch 29.527 (26.391) Remain 67:02:55 loss: 0.3119 loss_seg: 0.2130 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:03:50,115 INFO misc.py line 117 726] Train: [3/20][35/510] Data 5.869 (4.010) Batch 30.249 (26.512) Remain 67:20:51 loss: 0.2540 loss_seg: 0.1569 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:04:26,411 INFO misc.py line 117 726] Train: [3/20][36/510] Data 5.868 (4.066) Batch 36.296 (26.808) Remain 68:05:36 loss: 0.2228 loss_seg: 0.1266 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:04:54,884 INFO misc.py line 117 726] Train: [3/20][37/510] Data 3.053 (4.036) Batch 28.473 (26.857) Remain 68:12:36 loss: 0.2877 loss_seg: 0.1908 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:05:19,190 INFO misc.py line 117 726] Train: [3/20][38/510] Data 2.625 (3.996) Batch 24.306 (26.784) Remain 68:01:03 loss: 0.3519 loss_seg: 0.2472 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:05:45,919 INFO misc.py line 117 726] Train: [3/20][39/510] Data 2.750 (3.961) Batch 26.729 (26.783) Remain 68:00:22 loss: 0.2556 loss_seg: 0.1532 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:06:11,852 INFO misc.py line 117 726] Train: [3/20][40/510] Data 3.130 (3.939) Batch 25.933 (26.760) Remain 67:56:26 loss: 0.2806 loss_seg: 0.1803 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:06:47,129 INFO misc.py line 117 726] Train: [3/20][41/510] Data 5.967 (3.992) Batch 35.277 (26.984) Remain 68:30:07 loss: 0.2491 loss_seg: 0.1467 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:07:26,367 INFO misc.py line 117 726] Train: [3/20][42/510] Data 6.032 (4.044) Batch 39.238 (27.298) Remain 69:17:31 loss: 0.2018 loss_seg: 0.1212 loss_superpoint_edge: 0.0143 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:07:55,091 INFO misc.py line 117 726] Train: [3/20][43/510] Data 2.530 (4.007) Batch 28.724 (27.334) Remain 69:22:30 loss: 0.2370 loss_seg: 0.1436 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:08:24,955 INFO misc.py line 117 726] Train: [3/20][44/510] Data 3.396 (3.992) Batch 29.864 (27.396) Remain 69:31:26 loss: 0.2427 loss_seg: 0.1453 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:08:53,271 INFO misc.py line 117 726] Train: [3/20][45/510] Data 3.137 (3.971) Batch 28.316 (27.418) Remain 69:34:19 loss: 0.2653 loss_seg: 0.1708 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:09:20,388 INFO misc.py line 117 726] Train: [3/20][46/510] Data 2.878 (3.946) Batch 27.117 (27.411) Remain 69:32:48 loss: 0.3158 loss_seg: 0.2076 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:09:37,406 INFO misc.py line 117 726] Train: [3/20][47/510] Data 2.442 (3.912) Batch 17.018 (27.174) Remain 68:56:23 loss: 0.2856 loss_seg: 0.1928 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:10:10,677 INFO misc.py line 117 726] Train: [3/20][48/510] Data 6.536 (3.970) Batch 33.271 (27.310) Remain 69:16:33 loss: 0.2738 loss_seg: 0.1773 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:10:37,817 INFO misc.py line 117 726] Train: [3/20][49/510] Data 3.761 (3.965) Batch 27.140 (27.306) Remain 69:15:32 loss: 0.2307 loss_seg: 0.1368 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:11:03,575 INFO misc.py line 117 726] Train: [3/20][50/510] Data 3.757 (3.961) Batch 25.758 (27.273) Remain 69:10:04 loss: 0.3945 loss_seg: 0.2847 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:11:03,575 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 23:11:19,915 INFO misc.py line 117 726] Train: [3/20][51/510] Data 2.309 (3.927) Batch 16.340 (27.045) Remain 68:34:57 loss: 0.4577 loss_seg: 0.3540 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:11:42,954 INFO misc.py line 117 726] Train: [3/20][52/510] Data 2.690 (3.901) Batch 23.040 (26.964) Remain 68:22:04 loss: 0.4047 loss_seg: 0.3038 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:11:59,355 INFO misc.py line 117 726] Train: [3/20][53/510] Data 1.641 (3.856) Batch 16.401 (26.752) Remain 67:49:29 loss: 0.2521 loss_seg: 0.1577 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:12:27,572 INFO misc.py line 117 726] Train: [3/20][54/510] Data 3.137 (3.842) Batch 28.217 (26.781) Remain 67:53:24 loss: 0.2527 loss_seg: 0.1486 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:12:51,922 INFO misc.py line 117 726] Train: [3/20][55/510] Data 3.511 (3.836) Batch 24.351 (26.734) Remain 67:45:51 loss: 0.2732 loss_seg: 0.1786 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:13:25,819 INFO misc.py line 117 726] Train: [3/20][56/510] Data 3.960 (3.838) Batch 33.896 (26.870) Remain 68:05:57 loss: 0.2635 loss_seg: 0.1612 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:13:43,095 INFO misc.py line 117 726] Train: [3/20][57/510] Data 1.877 (3.802) Batch 17.276 (26.692) Remain 67:38:30 loss: 0.2271 loss_seg: 0.1324 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:14:10,087 INFO misc.py line 117 726] Train: [3/20][58/510] Data 4.949 (3.823) Batch 26.991 (26.697) Remain 67:38:52 loss: 0.2689 loss_seg: 0.1729 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:14:40,067 INFO misc.py line 117 726] Train: [3/20][59/510] Data 3.938 (3.825) Batch 29.980 (26.756) Remain 67:47:21 loss: 0.2355 loss_seg: 0.1433 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:15:14,629 INFO misc.py line 117 726] Train: [3/20][60/510] Data 4.362 (3.834) Batch 34.563 (26.893) Remain 68:07:43 loss: 0.3393 loss_seg: 0.2372 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:15:46,411 INFO misc.py line 117 726] Train: [3/20][61/510] Data 4.105 (3.839) Batch 31.782 (26.977) Remain 68:20:05 loss: 0.2683 loss_seg: 0.1748 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:16:12,063 INFO misc.py line 117 726] Train: [3/20][62/510] Data 3.165 (3.827) Batch 25.651 (26.955) Remain 68:16:13 loss: 0.2625 loss_seg: 0.1619 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:16:48,273 INFO misc.py line 117 726] Train: [3/20][63/510] Data 4.829 (3.844) Batch 36.211 (27.109) Remain 68:39:12 loss: 0.2519 loss_seg: 0.1559 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:17:05,604 INFO misc.py line 117 726] Train: [3/20][64/510] Data 1.699 (3.809) Batch 17.331 (26.949) Remain 68:14:24 loss: 0.2041 loss_seg: 0.1161 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:17:37,988 INFO misc.py line 117 726] Train: [3/20][65/510] Data 3.626 (3.806) Batch 32.384 (27.036) Remain 68:27:16 loss: 0.2203 loss_seg: 0.1311 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:18:08,954 INFO misc.py line 117 726] Train: [3/20][66/510] Data 3.255 (3.797) Batch 30.966 (27.099) Remain 68:36:17 loss: 0.3975 loss_seg: 0.2882 loss_superpoint_edge: 0.0444 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:18:35,134 INFO misc.py line 117 726] Train: [3/20][67/510] Data 4.484 (3.808) Batch 26.180 (27.084) Remain 68:33:40 loss: 0.2572 loss_seg: 0.1527 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:19:09,196 INFO misc.py line 117 726] Train: [3/20][68/510] Data 7.094 (3.858) Batch 34.062 (27.192) Remain 68:49:31 loss: 0.3003 loss_seg: 0.1921 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:19:21,464 INFO misc.py line 117 726] Train: [3/20][69/510] Data 1.701 (3.826) Batch 12.268 (26.966) Remain 68:14:43 loss: 0.2890 loss_seg: 0.1905 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:19:44,781 INFO misc.py line 117 726] Train: [3/20][70/510] Data 3.738 (3.824) Batch 23.317 (26.911) Remain 68:06:00 loss: 0.2904 loss_seg: 0.1936 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:20:19,286 INFO misc.py line 117 726] Train: [3/20][71/510] Data 4.001 (3.827) Batch 34.504 (27.023) Remain 68:22:30 loss: 0.2374 loss_seg: 0.1436 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:20:50,828 INFO misc.py line 117 726] Train: [3/20][72/510] Data 4.076 (3.831) Batch 31.542 (27.088) Remain 68:32:00 loss: 0.2786 loss_seg: 0.1847 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:21:19,615 INFO misc.py line 117 726] Train: [3/20][73/510] Data 3.059 (3.820) Batch 28.787 (27.113) Remain 68:35:14 loss: 0.2146 loss_seg: 0.1226 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:21:49,743 INFO misc.py line 117 726] Train: [3/20][74/510] Data 6.183 (3.853) Batch 30.127 (27.155) Remain 68:41:13 loss: 0.2710 loss_seg: 0.1739 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:22:14,955 INFO misc.py line 117 726] Train: [3/20][75/510] Data 2.282 (3.831) Batch 25.213 (27.128) Remain 68:36:41 loss: 0.2610 loss_seg: 0.1619 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:22:41,276 INFO misc.py line 117 726] Train: [3/20][76/510] Data 2.791 (3.817) Batch 26.320 (27.117) Remain 68:34:33 loss: 0.2678 loss_seg: 0.1638 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:23:02,506 INFO misc.py line 117 726] Train: [3/20][77/510] Data 2.446 (3.798) Batch 21.230 (27.037) Remain 68:22:02 loss: 0.3998 loss_seg: 0.2873 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:23:27,229 INFO misc.py line 117 726] Train: [3/20][78/510] Data 3.169 (3.790) Batch 24.723 (27.007) Remain 68:16:54 loss: 0.2896 loss_seg: 0.1885 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:24:04,762 INFO misc.py line 117 726] Train: [3/20][79/510] Data 4.294 (3.797) Batch 37.533 (27.145) Remain 68:37:27 loss: 0.3460 loss_seg: 0.2424 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:24:34,232 INFO misc.py line 117 726] Train: [3/20][80/510] Data 3.144 (3.788) Batch 29.470 (27.175) Remain 68:41:35 loss: 0.2652 loss_seg: 0.1658 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:25:03,598 INFO misc.py line 117 726] Train: [3/20][81/510] Data 3.142 (3.780) Batch 29.366 (27.203) Remain 68:45:23 loss: 0.2271 loss_seg: 0.1371 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:25:33,729 INFO misc.py line 117 726] Train: [3/20][82/510] Data 4.162 (3.785) Batch 30.131 (27.240) Remain 68:50:33 loss: 0.2678 loss_seg: 0.1731 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:26:12,118 INFO misc.py line 117 726] Train: [3/20][83/510] Data 10.139 (3.864) Batch 38.389 (27.380) Remain 69:11:14 loss: 0.2478 loss_seg: 0.1502 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:26:36,103 INFO misc.py line 117 726] Train: [3/20][84/510] Data 2.344 (3.845) Batch 23.985 (27.338) Remain 69:04:25 loss: 0.2151 loss_seg: 0.1195 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:27:05,891 INFO misc.py line 117 726] Train: [3/20][85/510] Data 3.817 (3.845) Batch 29.789 (27.368) Remain 69:08:29 loss: 0.2462 loss_seg: 0.1509 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:27:28,878 INFO misc.py line 117 726] Train: [3/20][86/510] Data 2.800 (3.832) Batch 22.987 (27.315) Remain 69:00:02 loss: 0.2609 loss_seg: 0.1629 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:28:00,406 INFO misc.py line 117 726] Train: [3/20][87/510] Data 4.264 (3.837) Batch 31.528 (27.365) Remain 69:07:11 loss: 0.3628 loss_seg: 0.2536 loss_superpoint_edge: 0.0431 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:28:28,197 INFO misc.py line 117 726] Train: [3/20][88/510] Data 3.584 (3.835) Batch 27.791 (27.370) Remain 69:07:29 loss: 0.3051 loss_seg: 0.1984 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:28:59,698 INFO misc.py line 117 726] Train: [3/20][89/510] Data 3.334 (3.829) Batch 31.501 (27.418) Remain 69:14:18 loss: 0.2635 loss_seg: 0.1625 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:29:37,668 INFO misc.py line 117 726] Train: [3/20][90/510] Data 6.010 (3.854) Batch 37.970 (27.539) Remain 69:32:13 loss: 0.2671 loss_seg: 0.1718 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:30:06,766 INFO misc.py line 117 726] Train: [3/20][91/510] Data 3.520 (3.850) Batch 29.098 (27.557) Remain 69:34:27 loss: 0.2273 loss_seg: 0.1351 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:30:30,743 INFO misc.py line 117 726] Train: [3/20][92/510] Data 2.205 (3.831) Batch 23.977 (27.517) Remain 69:27:54 loss: 0.2601 loss_seg: 0.1583 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:30:53,052 INFO misc.py line 117 726] Train: [3/20][93/510] Data 3.746 (3.831) Batch 22.309 (27.459) Remain 69:18:40 loss: 0.3770 loss_seg: 0.2736 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:31:21,468 INFO misc.py line 117 726] Train: [3/20][94/510] Data 2.805 (3.819) Batch 28.416 (27.470) Remain 69:19:48 loss: 0.1822 loss_seg: 0.0969 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:31:44,658 INFO misc.py line 117 726] Train: [3/20][95/510] Data 3.162 (3.812) Batch 23.189 (27.423) Remain 69:12:18 loss: 0.1624 loss_seg: 0.0790 loss_superpoint_edge: 0.0132 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0295 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:32:15,310 INFO misc.py line 117 726] Train: [3/20][96/510] Data 3.936 (3.813) Batch 30.652 (27.458) Remain 69:17:06 loss: 0.4415 loss_seg: 0.3158 loss_superpoint_edge: 0.0577 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:32:50,827 INFO misc.py line 117 726] Train: [3/20][97/510] Data 4.187 (3.817) Batch 35.517 (27.544) Remain 69:29:38 loss: 0.2627 loss_seg: 0.1685 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:33:23,347 INFO misc.py line 117 726] Train: [3/20][98/510] Data 2.920 (3.808) Batch 32.520 (27.596) Remain 69:37:06 loss: 0.2767 loss_seg: 0.1756 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:33:46,513 INFO misc.py line 117 726] Train: [3/20][99/510] Data 2.810 (3.798) Batch 23.166 (27.550) Remain 69:29:39 loss: 0.1928 loss_seg: 0.1070 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:34:16,862 INFO misc.py line 117 726] Train: [3/20][100/510] Data 4.276 (3.803) Batch 30.349 (27.579) Remain 69:33:34 loss: 0.2816 loss_seg: 0.1824 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:34:16,862 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 23:34:44,803 INFO misc.py line 117 726] Train: [3/20][101/510] Data 3.657 (3.801) Batch 27.941 (27.582) Remain 69:33:40 loss: 0.3487 loss_seg: 0.2332 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:35:08,674 INFO misc.py line 117 726] Train: [3/20][102/510] Data 2.626 (3.789) Batch 23.871 (27.545) Remain 69:27:32 loss: 0.3959 loss_seg: 0.2845 loss_superpoint_edge: 0.0447 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:35:37,389 INFO misc.py line 117 726] Train: [3/20][103/510] Data 2.679 (3.778) Batch 28.715 (27.557) Remain 69:28:50 loss: 0.2561 loss_seg: 0.1580 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:36:04,921 INFO misc.py line 117 726] Train: [3/20][104/510] Data 2.848 (3.769) Batch 27.531 (27.556) Remain 69:28:21 loss: 0.2458 loss_seg: 0.1563 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:36:39,514 INFO misc.py line 117 726] Train: [3/20][105/510] Data 5.573 (3.787) Batch 34.593 (27.625) Remain 69:38:19 loss: 0.2881 loss_seg: 0.1910 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:37:02,802 INFO misc.py line 117 726] Train: [3/20][106/510] Data 1.945 (3.769) Batch 23.288 (27.583) Remain 69:31:29 loss: 0.2689 loss_seg: 0.1704 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:37:34,058 INFO misc.py line 117 726] Train: [3/20][107/510] Data 3.501 (3.766) Batch 31.257 (27.619) Remain 69:36:22 loss: 0.3381 loss_seg: 0.2252 loss_superpoint_edge: 0.0456 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:38:00,137 INFO misc.py line 117 726] Train: [3/20][108/510] Data 2.931 (3.758) Batch 26.078 (27.604) Remain 69:33:42 loss: 0.2108 loss_seg: 0.1182 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:38:36,340 INFO misc.py line 117 726] Train: [3/20][109/510] Data 8.815 (3.806) Batch 36.204 (27.685) Remain 69:45:30 loss: 0.3025 loss_seg: 0.2030 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:39:01,890 INFO misc.py line 117 726] Train: [3/20][110/510] Data 2.172 (3.791) Batch 25.550 (27.665) Remain 69:42:01 loss: 0.2146 loss_seg: 0.1197 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:39:28,913 INFO misc.py line 117 726] Train: [3/20][111/510] Data 2.924 (3.783) Batch 27.023 (27.659) Remain 69:40:40 loss: 0.1980 loss_seg: 0.1120 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:39:49,853 INFO misc.py line 117 726] Train: [3/20][112/510] Data 2.832 (3.774) Batch 20.941 (27.597) Remain 69:30:53 loss: 0.3236 loss_seg: 0.2101 loss_superpoint_edge: 0.0431 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:40:18,882 INFO misc.py line 117 726] Train: [3/20][113/510] Data 3.537 (3.772) Batch 29.029 (27.610) Remain 69:32:23 loss: 0.2869 loss_seg: 0.1894 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:40:45,273 INFO misc.py line 117 726] Train: [3/20][114/510] Data 3.775 (3.772) Batch 26.391 (27.599) Remain 69:30:16 loss: 0.1923 loss_seg: 0.1022 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:41:05,379 INFO misc.py line 117 726] Train: [3/20][115/510] Data 2.052 (3.756) Batch 20.106 (27.533) Remain 69:19:42 loss: 0.3464 loss_seg: 0.2391 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:41:28,173 INFO misc.py line 117 726] Train: [3/20][116/510] Data 2.619 (3.746) Batch 22.794 (27.491) Remain 69:12:54 loss: 0.2594 loss_seg: 0.1614 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:41:41,273 INFO misc.py line 117 726] Train: [3/20][117/510] Data 1.890 (3.730) Batch 13.100 (27.364) Remain 68:53:23 loss: 0.1726 loss_seg: 0.0874 loss_superpoint_edge: 0.0135 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:42:00,849 INFO misc.py line 117 726] Train: [3/20][118/510] Data 2.543 (3.720) Batch 19.576 (27.297) Remain 68:42:42 loss: 0.2294 loss_seg: 0.1377 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:42:22,244 INFO misc.py line 117 726] Train: [3/20][119/510] Data 2.621 (3.710) Batch 21.396 (27.246) Remain 68:34:34 loss: 0.3885 loss_seg: 0.2607 loss_superpoint_edge: 0.0567 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0340 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:42:49,209 INFO misc.py line 117 726] Train: [3/20][120/510] Data 2.476 (3.700) Batch 26.965 (27.243) Remain 68:33:45 loss: 0.2077 loss_seg: 0.1158 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:43:20,217 INFO misc.py line 117 726] Train: [3/20][121/510] Data 4.199 (3.704) Batch 31.008 (27.275) Remain 68:38:06 loss: 0.2072 loss_seg: 0.1193 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:43:50,632 INFO misc.py line 117 726] Train: [3/20][122/510] Data 3.420 (3.702) Batch 30.414 (27.302) Remain 68:41:38 loss: 0.2397 loss_seg: 0.1440 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:44:19,629 INFO misc.py line 117 726] Train: [3/20][123/510] Data 4.996 (3.712) Batch 28.998 (27.316) Remain 68:43:19 loss: 0.2619 loss_seg: 0.1747 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:44:41,333 INFO misc.py line 117 726] Train: [3/20][124/510] Data 2.501 (3.702) Batch 21.703 (27.269) Remain 68:35:51 loss: 0.1931 loss_seg: 0.1070 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:45:05,058 INFO misc.py line 117 726] Train: [3/20][125/510] Data 4.356 (3.708) Batch 23.726 (27.240) Remain 68:31:01 loss: 0.2198 loss_seg: 0.1308 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:45:29,839 INFO misc.py line 117 726] Train: [3/20][126/510] Data 2.263 (3.696) Batch 24.781 (27.220) Remain 68:27:33 loss: 0.2264 loss_seg: 0.1332 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:45:57,913 INFO misc.py line 117 726] Train: [3/20][127/510] Data 2.769 (3.688) Batch 28.074 (27.227) Remain 68:28:08 loss: 0.2367 loss_seg: 0.1502 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:46:24,757 INFO misc.py line 117 726] Train: [3/20][128/510] Data 2.809 (3.681) Batch 26.844 (27.224) Remain 68:27:13 loss: 0.2178 loss_seg: 0.1307 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:46:59,534 INFO misc.py line 117 726] Train: [3/20][129/510] Data 4.194 (3.685) Batch 34.777 (27.284) Remain 68:35:48 loss: 0.2863 loss_seg: 0.1825 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:47:32,929 INFO misc.py line 117 726] Train: [3/20][130/510] Data 3.692 (3.686) Batch 33.394 (27.332) Remain 68:42:36 loss: 0.2175 loss_seg: 0.1269 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:48:13,348 INFO misc.py line 117 726] Train: [3/20][131/510] Data 9.205 (3.729) Batch 40.420 (27.434) Remain 68:57:34 loss: 0.2625 loss_seg: 0.1692 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:48:50,160 INFO misc.py line 117 726] Train: [3/20][132/510] Data 3.933 (3.730) Batch 36.811 (27.507) Remain 69:08:04 loss: 0.2105 loss_seg: 0.1204 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:49:20,844 INFO misc.py line 117 726] Train: [3/20][133/510] Data 4.351 (3.735) Batch 30.685 (27.532) Remain 69:11:18 loss: 0.2804 loss_seg: 0.1812 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:49:46,802 INFO misc.py line 117 726] Train: [3/20][134/510] Data 3.174 (3.731) Batch 25.957 (27.520) Remain 69:09:02 loss: 0.3031 loss_seg: 0.2097 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:50:15,060 INFO misc.py line 117 726] Train: [3/20][135/510] Data 3.000 (3.725) Batch 28.259 (27.525) Remain 69:09:25 loss: 0.3091 loss_seg: 0.2019 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0342 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:50:41,821 INFO misc.py line 117 726] Train: [3/20][136/510] Data 2.651 (3.717) Batch 26.761 (27.519) Remain 69:08:05 loss: 0.2664 loss_seg: 0.1608 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:51:12,559 INFO misc.py line 117 726] Train: [3/20][137/510] Data 3.262 (3.714) Batch 30.738 (27.543) Remain 69:11:15 loss: 0.2097 loss_seg: 0.1163 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:51:49,013 INFO misc.py line 117 726] Train: [3/20][138/510] Data 4.666 (3.721) Batch 36.454 (27.609) Remain 69:20:44 loss: 0.3168 loss_seg: 0.2141 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:52:19,494 INFO misc.py line 117 726] Train: [3/20][139/510] Data 3.841 (3.722) Batch 30.481 (27.631) Remain 69:23:28 loss: 0.2368 loss_seg: 0.1391 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:52:48,774 INFO misc.py line 117 726] Train: [3/20][140/510] Data 2.650 (3.714) Batch 29.280 (27.643) Remain 69:24:49 loss: 0.2163 loss_seg: 0.1217 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:53:08,442 INFO misc.py line 117 726] Train: [3/20][141/510] Data 2.332 (3.704) Batch 19.668 (27.585) Remain 69:15:39 loss: 0.2921 loss_seg: 0.1891 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:53:42,139 INFO misc.py line 117 726] Train: [3/20][142/510] Data 6.191 (3.722) Batch 33.696 (27.629) Remain 69:21:49 loss: 0.3204 loss_seg: 0.2100 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:54:05,989 INFO misc.py line 117 726] Train: [3/20][143/510] Data 4.067 (3.724) Batch 23.850 (27.602) Remain 69:17:17 loss: 0.3209 loss_seg: 0.2118 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0427 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:54:31,505 INFO misc.py line 117 726] Train: [3/20][144/510] Data 2.761 (3.717) Batch 25.517 (27.587) Remain 69:14:36 loss: 0.1977 loss_seg: 0.1134 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:55:06,851 INFO misc.py line 117 726] Train: [3/20][145/510] Data 7.704 (3.745) Batch 35.345 (27.642) Remain 69:22:22 loss: 0.3258 loss_seg: 0.2234 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:55:38,713 INFO misc.py line 117 726] Train: [3/20][146/510] Data 4.035 (3.747) Batch 31.862 (27.671) Remain 69:26:21 loss: 0.2322 loss_seg: 0.1391 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:56:16,689 INFO misc.py line 117 726] Train: [3/20][147/510] Data 4.609 (3.753) Batch 37.976 (27.743) Remain 69:36:40 loss: 0.2633 loss_seg: 0.1693 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:56:38,926 INFO misc.py line 117 726] Train: [3/20][148/510] Data 3.577 (3.752) Batch 22.238 (27.705) Remain 69:30:29 loss: 0.3485 loss_seg: 0.2496 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:57:23,159 INFO misc.py line 117 726] Train: [3/20][149/510] Data 14.217 (3.824) Batch 44.232 (27.818) Remain 69:47:04 loss: 0.2641 loss_seg: 0.1715 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:57:42,497 INFO misc.py line 117 726] Train: [3/20][150/510] Data 2.025 (3.812) Batch 19.338 (27.760) Remain 69:37:55 loss: 0.2066 loss_seg: 0.1209 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:57:42,497 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-09 23:58:04,679 INFO misc.py line 117 726] Train: [3/20][151/510] Data 2.763 (3.805) Batch 22.182 (27.723) Remain 69:31:47 loss: 0.1919 loss_seg: 0.1034 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:58:44,349 INFO misc.py line 117 726] Train: [3/20][152/510] Data 7.216 (3.827) Batch 39.670 (27.803) Remain 69:43:23 loss: 0.3012 loss_seg: 0.2035 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:59:11,497 INFO misc.py line 117 726] Train: [3/20][153/510] Data 3.034 (3.822) Batch 27.148 (27.798) Remain 69:42:16 loss: 0.2728 loss_seg: 0.1650 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-09 23:59:51,631 INFO misc.py line 117 726] Train: [3/20][154/510] Data 7.286 (3.845) Batch 40.134 (27.880) Remain 69:54:05 loss: 0.3550 loss_seg: 0.2408 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:00:22,244 INFO misc.py line 117 726] Train: [3/20][155/510] Data 4.532 (3.850) Batch 30.613 (27.898) Remain 69:56:20 loss: 0.2774 loss_seg: 0.1815 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:00:56,611 INFO misc.py line 117 726] Train: [3/20][156/510] Data 6.008 (3.864) Batch 34.366 (27.940) Remain 70:02:13 loss: 0.2216 loss_seg: 0.1308 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:01:23,309 INFO misc.py line 117 726] Train: [3/20][157/510] Data 2.249 (3.853) Batch 26.699 (27.932) Remain 70:00:33 loss: 0.2590 loss_seg: 0.1638 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:01:45,456 INFO misc.py line 117 726] Train: [3/20][158/510] Data 2.778 (3.846) Batch 22.146 (27.895) Remain 69:54:28 loss: 0.2424 loss_seg: 0.1488 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:02:11,924 INFO misc.py line 117 726] Train: [3/20][159/510] Data 2.856 (3.840) Batch 26.469 (27.886) Remain 69:52:38 loss: 0.2842 loss_seg: 0.1826 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:02:44,633 INFO misc.py line 117 726] Train: [3/20][160/510] Data 3.692 (3.839) Batch 32.709 (27.917) Remain 69:56:47 loss: 0.2182 loss_seg: 0.1251 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:03:17,434 INFO misc.py line 117 726] Train: [3/20][161/510] Data 5.475 (3.849) Batch 32.800 (27.947) Remain 70:00:58 loss: 0.3373 loss_seg: 0.2301 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:03:43,207 INFO misc.py line 117 726] Train: [3/20][162/510] Data 4.109 (3.851) Batch 25.773 (27.934) Remain 69:58:26 loss: 0.2490 loss_seg: 0.1558 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:04:11,197 INFO misc.py line 117 726] Train: [3/20][163/510] Data 2.982 (3.846) Batch 27.991 (27.934) Remain 69:58:02 loss: 0.2251 loss_seg: 0.1326 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:04:30,990 INFO misc.py line 117 726] Train: [3/20][164/510] Data 2.331 (3.836) Batch 19.793 (27.884) Remain 69:49:58 loss: 0.2243 loss_seg: 0.1302 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:04:52,387 INFO misc.py line 117 726] Train: [3/20][165/510] Data 2.620 (3.829) Batch 21.398 (27.844) Remain 69:43:29 loss: 0.3319 loss_seg: 0.2126 loss_superpoint_edge: 0.0475 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:05:04,188 INFO misc.py line 117 726] Train: [3/20][166/510] Data 1.596 (3.815) Batch 11.800 (27.745) Remain 69:28:14 loss: 0.2660 loss_seg: 0.1696 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:05:30,364 INFO misc.py line 117 726] Train: [3/20][167/510] Data 2.674 (3.808) Batch 26.177 (27.736) Remain 69:26:20 loss: 0.2524 loss_seg: 0.1541 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:06:02,403 INFO misc.py line 117 726] Train: [3/20][168/510] Data 6.532 (3.825) Batch 32.039 (27.762) Remain 69:29:47 loss: 0.3406 loss_seg: 0.2416 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:06:22,285 INFO misc.py line 117 726] Train: [3/20][169/510] Data 1.964 (3.813) Batch 19.882 (27.714) Remain 69:22:12 loss: 0.2031 loss_seg: 0.1146 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:06:48,321 INFO misc.py line 117 726] Train: [3/20][170/510] Data 3.124 (3.809) Batch 26.035 (27.704) Remain 69:20:14 loss: 0.2580 loss_seg: 0.1582 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:07:11,986 INFO misc.py line 117 726] Train: [3/20][171/510] Data 2.172 (3.799) Batch 23.666 (27.680) Remain 69:16:09 loss: 0.2168 loss_seg: 0.1209 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:07:47,089 INFO misc.py line 117 726] Train: [3/20][172/510] Data 5.450 (3.809) Batch 35.102 (27.724) Remain 69:22:17 loss: 0.3404 loss_seg: 0.2331 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:08:16,294 INFO misc.py line 117 726] Train: [3/20][173/510] Data 3.276 (3.806) Batch 29.205 (27.733) Remain 69:23:08 loss: 0.2431 loss_seg: 0.1516 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:08:38,841 INFO misc.py line 117 726] Train: [3/20][174/510] Data 2.763 (3.800) Batch 22.547 (27.702) Remain 69:18:07 loss: 0.2797 loss_seg: 0.1816 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:09:03,917 INFO misc.py line 117 726] Train: [3/20][175/510] Data 2.548 (3.793) Batch 25.076 (27.687) Remain 69:15:22 loss: 0.2255 loss_seg: 0.1333 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:09:29,962 INFO misc.py line 117 726] Train: [3/20][176/510] Data 3.035 (3.788) Batch 26.046 (27.678) Remain 69:13:29 loss: 0.2883 loss_seg: 0.1840 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:09:56,457 INFO misc.py line 117 726] Train: [3/20][177/510] Data 2.855 (3.783) Batch 26.495 (27.671) Remain 69:12:00 loss: 0.3450 loss_seg: 0.2462 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:10:28,237 INFO misc.py line 117 726] Train: [3/20][178/510] Data 6.957 (3.801) Batch 31.780 (27.694) Remain 69:15:04 loss: 0.3021 loss_seg: 0.2060 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:10:50,091 INFO misc.py line 117 726] Train: [3/20][179/510] Data 2.509 (3.794) Batch 21.854 (27.661) Remain 69:09:37 loss: 0.3108 loss_seg: 0.2143 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:11:16,479 INFO misc.py line 117 726] Train: [3/20][180/510] Data 3.071 (3.790) Batch 26.388 (27.654) Remain 69:08:05 loss: 0.1781 loss_seg: 0.0949 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:11:44,207 INFO misc.py line 117 726] Train: [3/20][181/510] Data 4.269 (3.792) Batch 27.728 (27.654) Remain 69:07:41 loss: 0.2702 loss_seg: 0.1671 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0456 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:12:11,183 INFO misc.py line 117 726] Train: [3/20][182/510] Data 2.709 (3.786) Batch 26.976 (27.651) Remain 69:06:39 loss: 0.2077 loss_seg: 0.1166 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:12:37,969 INFO misc.py line 117 726] Train: [3/20][183/510] Data 2.696 (3.780) Batch 26.786 (27.646) Remain 69:05:28 loss: 0.2078 loss_seg: 0.1194 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:13:06,350 INFO misc.py line 117 726] Train: [3/20][184/510] Data 2.992 (3.776) Batch 28.381 (27.650) Remain 69:05:37 loss: 0.2705 loss_seg: 0.1710 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:13:38,670 INFO misc.py line 117 726] Train: [3/20][185/510] Data 3.471 (3.774) Batch 32.320 (27.675) Remain 69:09:00 loss: 0.2580 loss_seg: 0.1579 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:14:04,394 INFO misc.py line 117 726] Train: [3/20][186/510] Data 2.877 (3.769) Batch 25.724 (27.665) Remain 69:06:57 loss: 0.2319 loss_seg: 0.1406 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:14:40,783 INFO misc.py line 117 726] Train: [3/20][187/510] Data 5.092 (3.776) Batch 36.388 (27.712) Remain 69:13:36 loss: 0.2337 loss_seg: 0.1372 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:15:03,330 INFO misc.py line 117 726] Train: [3/20][188/510] Data 2.384 (3.769) Batch 22.548 (27.684) Remain 69:08:57 loss: 0.2026 loss_seg: 0.1151 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:15:27,783 INFO misc.py line 117 726] Train: [3/20][189/510] Data 3.239 (3.766) Batch 24.453 (27.667) Remain 69:05:53 loss: 0.2675 loss_seg: 0.1656 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:15:57,958 INFO misc.py line 117 726] Train: [3/20][190/510] Data 3.885 (3.767) Batch 30.175 (27.680) Remain 69:07:26 loss: 0.2436 loss_seg: 0.1475 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:16:32,691 INFO misc.py line 117 726] Train: [3/20][191/510] Data 2.742 (3.761) Batch 34.733 (27.718) Remain 69:12:35 loss: 0.2202 loss_seg: 0.1263 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:17:01,646 INFO misc.py line 117 726] Train: [3/20][192/510] Data 5.399 (3.770) Batch 28.955 (27.724) Remain 69:13:06 loss: 0.7113 loss_seg: 0.5836 loss_superpoint_edge: 0.0566 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:17:26,511 INFO misc.py line 117 726] Train: [3/20][193/510] Data 2.647 (3.764) Batch 24.865 (27.709) Remain 69:10:23 loss: 0.2299 loss_seg: 0.1368 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:17:59,907 INFO misc.py line 117 726] Train: [3/20][194/510] Data 3.551 (3.763) Batch 33.395 (27.739) Remain 69:14:23 loss: 0.2293 loss_seg: 0.1341 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:18:36,496 INFO misc.py line 117 726] Train: [3/20][195/510] Data 8.806 (3.789) Batch 36.589 (27.785) Remain 69:20:50 loss: 0.2291 loss_seg: 0.1294 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:19:09,513 INFO misc.py line 117 726] Train: [3/20][196/510] Data 3.812 (3.789) Batch 33.017 (27.812) Remain 69:24:25 loss: 0.2184 loss_seg: 0.1278 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:19:31,552 INFO misc.py line 117 726] Train: [3/20][197/510] Data 2.196 (3.781) Batch 22.039 (27.783) Remain 69:19:30 loss: 0.2283 loss_seg: 0.1348 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:20:08,429 INFO misc.py line 117 726] Train: [3/20][198/510] Data 7.297 (3.799) Batch 36.877 (27.829) Remain 69:26:01 loss: 0.3190 loss_seg: 0.2112 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:20:42,821 INFO misc.py line 117 726] Train: [3/20][199/510] Data 3.709 (3.799) Batch 34.392 (27.863) Remain 69:30:34 loss: 0.2420 loss_seg: 0.1473 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:21:07,566 INFO misc.py line 117 726] Train: [3/20][200/510] Data 2.520 (3.792) Batch 24.745 (27.847) Remain 69:27:44 loss: 0.3196 loss_seg: 0.2071 loss_superpoint_edge: 0.0464 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:21:07,566 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 00:21:38,367 INFO misc.py line 117 726] Train: [3/20][201/510] Data 3.173 (3.789) Batch 30.801 (27.862) Remain 69:29:30 loss: 0.2493 loss_seg: 0.1576 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:21:58,074 INFO misc.py line 117 726] Train: [3/20][202/510] Data 2.810 (3.784) Batch 19.706 (27.821) Remain 69:22:55 loss: 0.2140 loss_seg: 0.1220 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:22:29,704 INFO misc.py line 117 726] Train: [3/20][203/510] Data 3.398 (3.782) Batch 31.631 (27.840) Remain 69:25:18 loss: 0.2394 loss_seg: 0.1439 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:23:02,222 INFO misc.py line 117 726] Train: [3/20][204/510] Data 6.784 (3.797) Batch 32.517 (27.863) Remain 69:28:19 loss: 0.3762 loss_seg: 0.2762 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:23:31,752 INFO misc.py line 117 726] Train: [3/20][205/510] Data 5.266 (3.804) Batch 29.530 (27.871) Remain 69:29:05 loss: 0.3816 loss_seg: 0.2790 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:23:52,676 INFO misc.py line 117 726] Train: [3/20][206/510] Data 1.838 (3.795) Batch 20.925 (27.837) Remain 69:23:30 loss: 0.2184 loss_seg: 0.1239 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:24:22,808 INFO misc.py line 117 726] Train: [3/20][207/510] Data 3.897 (3.795) Batch 30.131 (27.848) Remain 69:24:43 loss: 0.2539 loss_seg: 0.1537 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:25:00,139 INFO misc.py line 117 726] Train: [3/20][208/510] Data 4.333 (3.798) Batch 37.332 (27.895) Remain 69:31:10 loss: 0.1918 loss_seg: 0.1072 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:25:23,801 INFO misc.py line 117 726] Train: [3/20][209/510] Data 2.736 (3.793) Batch 23.662 (27.874) Remain 69:27:38 loss: 0.1856 loss_seg: 0.0981 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:25:46,902 INFO misc.py line 117 726] Train: [3/20][210/510] Data 4.581 (3.797) Batch 23.101 (27.851) Remain 69:23:43 loss: 0.2264 loss_seg: 0.1378 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:26:19,651 INFO misc.py line 117 726] Train: [3/20][211/510] Data 6.214 (3.808) Batch 32.749 (27.875) Remain 69:26:47 loss: 0.2873 loss_seg: 0.1829 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:26:51,072 INFO misc.py line 117 726] Train: [3/20][212/510] Data 3.497 (3.807) Batch 31.421 (27.892) Remain 69:28:51 loss: 0.2129 loss_seg: 0.1215 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:27:21,605 INFO misc.py line 117 726] Train: [3/20][213/510] Data 3.511 (3.805) Batch 30.533 (27.904) Remain 69:30:16 loss: 0.2883 loss_seg: 0.2062 loss_superpoint_edge: 0.0134 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:27:54,648 INFO misc.py line 117 726] Train: [3/20][214/510] Data 3.265 (3.803) Batch 33.043 (27.929) Remain 69:33:26 loss: 0.2179 loss_seg: 0.1278 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:28:20,604 INFO misc.py line 117 726] Train: [3/20][215/510] Data 3.083 (3.799) Batch 25.956 (27.919) Remain 69:31:35 loss: 0.2191 loss_seg: 0.1285 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:28:41,200 INFO misc.py line 117 726] Train: [3/20][216/510] Data 2.904 (3.795) Batch 20.596 (27.885) Remain 69:25:59 loss: 0.3480 loss_seg: 0.2334 loss_superpoint_edge: 0.0472 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:29:11,571 INFO misc.py line 117 726] Train: [3/20][217/510] Data 2.629 (3.790) Batch 30.371 (27.896) Remain 69:27:15 loss: 0.2432 loss_seg: 0.1500 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:29:35,417 INFO misc.py line 117 726] Train: [3/20][218/510] Data 2.835 (3.785) Batch 23.846 (27.878) Remain 69:23:59 loss: 0.2350 loss_seg: 0.1405 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:29:58,368 INFO misc.py line 117 726] Train: [3/20][219/510] Data 2.564 (3.780) Batch 22.950 (27.855) Remain 69:20:06 loss: 0.3083 loss_seg: 0.1982 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:30:30,061 INFO misc.py line 117 726] Train: [3/20][220/510] Data 3.046 (3.776) Batch 31.694 (27.872) Remain 69:22:17 loss: 0.2055 loss_seg: 0.1176 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:30:50,629 INFO misc.py line 117 726] Train: [3/20][221/510] Data 2.053 (3.768) Batch 20.568 (27.839) Remain 69:16:49 loss: 0.3237 loss_seg: 0.2296 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:31:22,368 INFO misc.py line 117 726] Train: [3/20][222/510] Data 5.098 (3.774) Batch 31.738 (27.857) Remain 69:19:00 loss: 0.1592 loss_seg: 0.0776 loss_superpoint_edge: 0.0113 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:31:46,108 INFO misc.py line 117 726] Train: [3/20][223/510] Data 3.143 (3.771) Batch 23.741 (27.838) Remain 69:15:45 loss: 0.4742 loss_seg: 0.3592 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:32:22,380 INFO misc.py line 117 726] Train: [3/20][224/510] Data 8.940 (3.795) Batch 36.272 (27.876) Remain 69:20:59 loss: 0.3417 loss_seg: 0.2418 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:33:03,805 INFO misc.py line 117 726] Train: [3/20][225/510] Data 11.133 (3.828) Batch 41.425 (27.937) Remain 69:29:38 loss: 0.2104 loss_seg: 0.1223 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:33:26,596 INFO misc.py line 117 726] Train: [3/20][226/510] Data 2.905 (3.824) Batch 22.791 (27.914) Remain 69:25:43 loss: 0.1993 loss_seg: 0.1100 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:33:52,144 INFO misc.py line 117 726] Train: [3/20][227/510] Data 2.875 (3.819) Batch 25.548 (27.904) Remain 69:23:41 loss: 0.2134 loss_seg: 0.1191 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:34:22,204 INFO misc.py line 117 726] Train: [3/20][228/510] Data 5.026 (3.825) Batch 30.060 (27.913) Remain 69:24:38 loss: 0.2133 loss_seg: 0.1271 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:34:50,147 INFO misc.py line 117 726] Train: [3/20][229/510] Data 6.266 (3.836) Batch 27.943 (27.913) Remain 69:24:12 loss: 0.2852 loss_seg: 0.1849 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:35:08,460 INFO misc.py line 117 726] Train: [3/20][230/510] Data 2.686 (3.831) Batch 18.313 (27.871) Remain 69:17:25 loss: 0.3011 loss_seg: 0.1931 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:35:30,937 INFO misc.py line 117 726] Train: [3/20][231/510] Data 2.841 (3.826) Batch 22.477 (27.847) Remain 69:13:26 loss: 0.2021 loss_seg: 0.1160 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:36:04,404 INFO misc.py line 117 726] Train: [3/20][232/510] Data 4.618 (3.830) Batch 33.467 (27.872) Remain 69:16:37 loss: 0.2658 loss_seg: 0.1705 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:36:39,558 INFO misc.py line 117 726] Train: [3/20][233/510] Data 5.567 (3.837) Batch 35.154 (27.904) Remain 69:20:53 loss: 0.2644 loss_seg: 0.1669 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:37:11,690 INFO misc.py line 117 726] Train: [3/20][234/510] Data 3.417 (3.835) Batch 32.132 (27.922) Remain 69:23:09 loss: 0.3126 loss_seg: 0.2035 loss_superpoint_edge: 0.0416 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:37:32,533 INFO misc.py line 117 726] Train: [3/20][235/510] Data 2.089 (3.828) Batch 20.843 (27.891) Remain 69:18:08 loss: 0.1981 loss_seg: 0.1091 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:37:56,131 INFO misc.py line 117 726] Train: [3/20][236/510] Data 2.883 (3.824) Batch 23.598 (27.873) Remain 69:14:55 loss: 0.1981 loss_seg: 0.1113 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:38:23,372 INFO misc.py line 117 726] Train: [3/20][237/510] Data 3.724 (3.823) Batch 27.242 (27.870) Remain 69:14:03 loss: 0.2746 loss_seg: 0.1725 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:38:40,200 INFO misc.py line 117 726] Train: [3/20][238/510] Data 1.751 (3.815) Batch 16.828 (27.823) Remain 69:06:35 loss: 0.2359 loss_seg: 0.1426 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:39:04,622 INFO misc.py line 117 726] Train: [3/20][239/510] Data 2.381 (3.809) Batch 24.422 (27.809) Remain 69:03:58 loss: 0.2670 loss_seg: 0.1675 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:39:39,569 INFO misc.py line 117 726] Train: [3/20][240/510] Data 7.697 (3.825) Batch 34.946 (27.839) Remain 69:08:00 loss: 0.2951 loss_seg: 0.1931 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:40:06,591 INFO misc.py line 117 726] Train: [3/20][241/510] Data 3.002 (3.821) Batch 27.022 (27.836) Remain 69:07:01 loss: 0.2260 loss_seg: 0.1346 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:40:29,479 INFO misc.py line 117 726] Train: [3/20][242/510] Data 2.358 (3.815) Batch 22.888 (27.815) Remain 69:03:28 loss: 0.2583 loss_seg: 0.1563 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:40:54,549 INFO misc.py line 117 726] Train: [3/20][243/510] Data 4.848 (3.820) Batch 25.069 (27.803) Remain 69:01:18 loss: 0.3001 loss_seg: 0.1974 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:41:23,248 INFO misc.py line 117 726] Train: [3/20][244/510] Data 4.090 (3.821) Batch 28.700 (27.807) Remain 69:01:24 loss: 0.2512 loss_seg: 0.1494 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:41:43,541 INFO misc.py line 117 726] Train: [3/20][245/510] Data 2.137 (3.814) Batch 20.293 (27.776) Remain 68:56:19 loss: 0.2011 loss_seg: 0.1106 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:42:06,832 INFO misc.py line 117 726] Train: [3/20][246/510] Data 2.431 (3.808) Batch 23.291 (27.758) Remain 68:53:06 loss: 0.2249 loss_seg: 0.1301 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:42:39,019 INFO misc.py line 117 726] Train: [3/20][247/510] Data 3.311 (3.806) Batch 32.187 (27.776) Remain 68:55:20 loss: 0.2222 loss_seg: 0.1298 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:43:03,622 INFO misc.py line 117 726] Train: [3/20][248/510] Data 3.262 (3.804) Batch 24.603 (27.763) Remain 68:52:57 loss: 0.2585 loss_seg: 0.1651 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:43:35,447 INFO misc.py line 117 726] Train: [3/20][249/510] Data 3.593 (3.803) Batch 31.825 (27.779) Remain 68:54:57 loss: 0.1741 loss_seg: 0.0923 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:44:03,228 INFO misc.py line 117 726] Train: [3/20][250/510] Data 2.638 (3.798) Batch 27.781 (27.779) Remain 68:54:29 loss: 0.2664 loss_seg: 0.1646 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:44:03,228 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 00:44:28,354 INFO misc.py line 117 726] Train: [3/20][251/510] Data 2.822 (3.794) Batch 25.126 (27.769) Remain 68:52:26 loss: 0.2088 loss_seg: 0.1208 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:44:54,320 INFO misc.py line 117 726] Train: [3/20][252/510] Data 2.850 (3.791) Batch 25.966 (27.761) Remain 68:50:53 loss: 0.2404 loss_seg: 0.1429 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:45:18,711 INFO misc.py line 117 726] Train: [3/20][253/510] Data 3.171 (3.788) Batch 24.391 (27.748) Remain 68:48:25 loss: 0.2654 loss_seg: 0.1722 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:45:49,947 INFO misc.py line 117 726] Train: [3/20][254/510] Data 3.416 (3.787) Batch 31.236 (27.762) Remain 68:50:01 loss: 0.2076 loss_seg: 0.1174 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:46:20,014 INFO misc.py line 117 726] Train: [3/20][255/510] Data 3.105 (3.784) Batch 30.067 (27.771) Remain 68:50:55 loss: 0.2305 loss_seg: 0.1381 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:46:50,116 INFO misc.py line 117 726] Train: [3/20][256/510] Data 3.626 (3.783) Batch 30.101 (27.780) Remain 68:51:50 loss: 0.2428 loss_seg: 0.1510 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:47:12,228 INFO misc.py line 117 726] Train: [3/20][257/510] Data 3.160 (3.781) Batch 22.113 (27.758) Remain 68:48:03 loss: 0.2386 loss_seg: 0.1461 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:47:42,193 INFO misc.py line 117 726] Train: [3/20][258/510] Data 4.334 (3.783) Batch 29.965 (27.767) Remain 68:48:52 loss: 0.2097 loss_seg: 0.1202 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:48:10,403 INFO misc.py line 117 726] Train: [3/20][259/510] Data 3.424 (3.782) Batch 28.209 (27.768) Remain 68:48:40 loss: 0.2325 loss_seg: 0.1393 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:48:30,667 INFO misc.py line 117 726] Train: [3/20][260/510] Data 2.515 (3.777) Batch 20.265 (27.739) Remain 68:43:52 loss: 0.1633 loss_seg: 0.0781 loss_superpoint_edge: 0.0113 loss_superpoint_contrast: 0.0443 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:48:56,129 INFO misc.py line 117 726] Train: [3/20][261/510] Data 2.194 (3.771) Batch 25.461 (27.730) Remain 68:42:05 loss: 0.3304 loss_seg: 0.2221 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:49:19,757 INFO misc.py line 117 726] Train: [3/20][262/510] Data 2.462 (3.765) Batch 23.628 (27.714) Remain 68:39:16 loss: 0.2819 loss_seg: 0.1812 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:49:49,096 INFO misc.py line 117 726] Train: [3/20][263/510] Data 3.351 (3.764) Batch 29.339 (27.721) Remain 68:39:44 loss: 0.2293 loss_seg: 0.1338 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:50:14,962 INFO misc.py line 117 726] Train: [3/20][264/510] Data 4.571 (3.767) Batch 25.866 (27.714) Remain 68:38:13 loss: 0.2211 loss_seg: 0.1252 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:50:43,216 INFO misc.py line 117 726] Train: [3/20][265/510] Data 2.704 (3.763) Batch 28.254 (27.716) Remain 68:38:04 loss: 0.2279 loss_seg: 0.1406 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:51:14,879 INFO misc.py line 117 726] Train: [3/20][266/510] Data 5.051 (3.768) Batch 31.663 (27.731) Remain 68:39:50 loss: 0.2389 loss_seg: 0.1439 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:51:40,226 INFO misc.py line 117 726] Train: [3/20][267/510] Data 3.121 (3.765) Batch 25.347 (27.722) Remain 68:38:02 loss: 0.2177 loss_seg: 0.1251 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:52:09,661 INFO misc.py line 117 726] Train: [3/20][268/510] Data 4.120 (3.767) Batch 29.434 (27.728) Remain 68:38:32 loss: 0.3492 loss_seg: 0.2315 loss_superpoint_edge: 0.0483 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:52:42,278 INFO misc.py line 117 726] Train: [3/20][269/510] Data 3.727 (3.767) Batch 32.618 (27.746) Remain 68:40:48 loss: 0.2886 loss_seg: 0.1924 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:53:09,396 INFO misc.py line 117 726] Train: [3/20][270/510] Data 7.717 (3.781) Batch 27.117 (27.744) Remain 68:39:59 loss: 0.3260 loss_seg: 0.2204 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:53:39,049 INFO misc.py line 117 726] Train: [3/20][271/510] Data 3.183 (3.779) Batch 29.654 (27.751) Remain 68:40:35 loss: 0.3278 loss_seg: 0.2310 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:54:05,769 INFO misc.py line 117 726] Train: [3/20][272/510] Data 2.716 (3.775) Batch 26.720 (27.747) Remain 68:39:33 loss: 0.3393 loss_seg: 0.2306 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:54:33,936 INFO misc.py line 117 726] Train: [3/20][273/510] Data 3.304 (3.773) Batch 28.167 (27.749) Remain 68:39:19 loss: 0.2651 loss_seg: 0.1632 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:55:04,204 INFO misc.py line 117 726] Train: [3/20][274/510] Data 4.606 (3.777) Batch 30.268 (27.758) Remain 68:40:14 loss: 0.2549 loss_seg: 0.1565 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:55:39,573 INFO misc.py line 117 726] Train: [3/20][275/510] Data 9.345 (3.797) Batch 35.369 (27.786) Remain 68:43:55 loss: 0.2521 loss_seg: 0.1519 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:56:03,839 INFO misc.py line 117 726] Train: [3/20][276/510] Data 2.800 (3.793) Batch 24.266 (27.773) Remain 68:41:33 loss: 0.3237 loss_seg: 0.2101 loss_superpoint_edge: 0.0448 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:56:44,744 INFO misc.py line 117 726] Train: [3/20][277/510] Data 10.427 (3.818) Batch 40.905 (27.821) Remain 68:48:12 loss: 0.4413 loss_seg: 0.3503 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:57:22,058 INFO misc.py line 117 726] Train: [3/20][278/510] Data 7.040 (3.829) Batch 37.314 (27.856) Remain 68:52:51 loss: 0.4707 loss_seg: 0.3696 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:57:47,515 INFO misc.py line 117 726] Train: [3/20][279/510] Data 3.126 (3.827) Batch 25.457 (27.847) Remain 68:51:06 loss: 0.2501 loss_seg: 0.1512 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:58:14,044 INFO misc.py line 117 726] Train: [3/20][280/510] Data 2.771 (3.823) Batch 26.530 (27.842) Remain 68:49:56 loss: 0.2806 loss_seg: 0.1820 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:58:42,137 INFO misc.py line 117 726] Train: [3/20][281/510] Data 3.039 (3.820) Batch 28.093 (27.843) Remain 68:49:36 loss: 0.2999 loss_seg: 0.2006 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:59:13,318 INFO misc.py line 117 726] Train: [3/20][282/510] Data 3.477 (3.819) Batch 31.180 (27.855) Remain 68:50:55 loss: 0.2655 loss_seg: 0.1668 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:59:34,616 INFO misc.py line 117 726] Train: [3/20][283/510] Data 2.812 (3.815) Batch 21.299 (27.832) Remain 68:46:58 loss: 0.3407 loss_seg: 0.2283 loss_superpoint_edge: 0.0423 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 00:59:49,053 INFO misc.py line 117 726] Train: [3/20][284/510] Data 1.574 (3.807) Batch 14.437 (27.784) Remain 68:39:26 loss: 0.3413 loss_seg: 0.2236 loss_superpoint_edge: 0.0499 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:00:24,858 INFO misc.py line 117 726] Train: [3/20][285/510] Data 6.213 (3.816) Batch 35.804 (27.812) Remain 68:43:12 loss: 0.2702 loss_seg: 0.1687 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:00:48,310 INFO misc.py line 117 726] Train: [3/20][286/510] Data 2.033 (3.810) Batch 23.452 (27.797) Remain 68:40:27 loss: 0.2043 loss_seg: 0.1188 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:01:08,913 INFO misc.py line 117 726] Train: [3/20][287/510] Data 2.247 (3.804) Batch 20.603 (27.772) Remain 68:36:14 loss: 0.2700 loss_seg: 0.1697 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:01:42,036 INFO misc.py line 117 726] Train: [3/20][288/510] Data 4.131 (3.805) Batch 33.123 (27.791) Remain 68:38:33 loss: 0.5733 loss_seg: 0.4469 loss_superpoint_edge: 0.0546 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:02:14,647 INFO misc.py line 117 726] Train: [3/20][289/510] Data 4.046 (3.806) Batch 32.611 (27.807) Remain 68:40:35 loss: 0.2466 loss_seg: 0.1552 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:02:41,865 INFO misc.py line 117 726] Train: [3/20][290/510] Data 3.099 (3.804) Batch 27.218 (27.805) Remain 68:39:49 loss: 0.2586 loss_seg: 0.1647 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:03:20,500 INFO misc.py line 117 726] Train: [3/20][291/510] Data 7.461 (3.816) Batch 38.635 (27.843) Remain 68:44:55 loss: 0.4457 loss_seg: 0.3190 loss_superpoint_edge: 0.0585 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:03:49,815 INFO misc.py line 117 726] Train: [3/20][292/510] Data 3.315 (3.815) Batch 29.314 (27.848) Remain 68:45:13 loss: 0.2560 loss_seg: 0.1533 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:04:14,349 INFO misc.py line 117 726] Train: [3/20][293/510] Data 2.685 (3.811) Batch 24.535 (27.837) Remain 68:43:03 loss: 0.2263 loss_seg: 0.1333 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:04:48,178 INFO misc.py line 117 726] Train: [3/20][294/510] Data 5.460 (3.816) Batch 33.829 (27.857) Remain 68:45:39 loss: 0.3188 loss_seg: 0.2127 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:05:21,753 INFO misc.py line 117 726] Train: [3/20][295/510] Data 3.121 (3.814) Batch 33.575 (27.877) Remain 68:48:05 loss: 0.2012 loss_seg: 0.1126 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:05:54,775 INFO misc.py line 117 726] Train: [3/20][296/510] Data 3.729 (3.814) Batch 33.022 (27.894) Remain 68:50:13 loss: 0.2811 loss_seg: 0.1813 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:06:23,192 INFO misc.py line 117 726] Train: [3/20][297/510] Data 2.608 (3.810) Batch 28.417 (27.896) Remain 68:50:01 loss: 0.2085 loss_seg: 0.1238 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:06:51,011 INFO misc.py line 117 726] Train: [3/20][298/510] Data 3.417 (3.808) Batch 27.819 (27.896) Remain 68:49:30 loss: 0.2811 loss_seg: 0.1791 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:07:18,280 INFO misc.py line 117 726] Train: [3/20][299/510] Data 5.885 (3.815) Batch 27.269 (27.894) Remain 68:48:44 loss: 0.4864 loss_seg: 0.3924 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:07:47,618 INFO misc.py line 117 726] Train: [3/20][300/510] Data 3.408 (3.814) Batch 29.337 (27.899) Remain 68:48:59 loss: 0.1748 loss_seg: 0.0907 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:07:47,618 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 01:08:17,685 INFO misc.py line 117 726] Train: [3/20][301/510] Data 4.629 (3.817) Batch 30.067 (27.906) Remain 68:49:36 loss: 0.1852 loss_seg: 0.1022 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:08:50,057 INFO misc.py line 117 726] Train: [3/20][302/510] Data 4.726 (3.820) Batch 32.373 (27.921) Remain 68:51:20 loss: 0.3131 loss_seg: 0.2185 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:09:15,357 INFO misc.py line 117 726] Train: [3/20][303/510] Data 3.138 (3.817) Batch 25.299 (27.912) Remain 68:49:35 loss: 0.2860 loss_seg: 0.1891 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:09:38,981 INFO misc.py line 117 726] Train: [3/20][304/510] Data 2.922 (3.814) Batch 23.624 (27.898) Remain 68:47:01 loss: 0.2044 loss_seg: 0.1169 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:10:03,895 INFO misc.py line 117 726] Train: [3/20][305/510] Data 3.236 (3.812) Batch 24.914 (27.888) Remain 68:45:05 loss: 0.2977 loss_seg: 0.1876 loss_superpoint_edge: 0.0405 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:10:25,396 INFO misc.py line 117 726] Train: [3/20][306/510] Data 2.249 (3.807) Batch 21.501 (27.867) Remain 68:41:30 loss: 0.2623 loss_seg: 0.1663 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:10:50,780 INFO misc.py line 117 726] Train: [3/20][307/510] Data 3.361 (3.806) Batch 25.384 (27.859) Remain 68:39:50 loss: 0.2652 loss_seg: 0.1580 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:11:16,109 INFO misc.py line 117 726] Train: [3/20][308/510] Data 3.166 (3.804) Batch 25.330 (27.850) Remain 68:38:08 loss: 0.3282 loss_seg: 0.2139 loss_superpoint_edge: 0.0474 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:11:40,970 INFO misc.py line 117 726] Train: [3/20][309/510] Data 2.521 (3.800) Batch 24.861 (27.841) Remain 68:36:14 loss: 0.2020 loss_seg: 0.1124 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:12:10,373 INFO misc.py line 117 726] Train: [3/20][310/510] Data 3.259 (3.798) Batch 29.403 (27.846) Remain 68:36:31 loss: 0.2313 loss_seg: 0.1372 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:12:40,274 INFO misc.py line 117 726] Train: [3/20][311/510] Data 6.250 (3.806) Batch 29.901 (27.852) Remain 68:37:02 loss: 0.3441 loss_seg: 0.2329 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0344 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:12:59,925 INFO misc.py line 117 726] Train: [3/20][312/510] Data 2.406 (3.801) Batch 19.650 (27.826) Remain 68:32:39 loss: 0.2061 loss_seg: 0.1105 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:13:35,082 INFO misc.py line 117 726] Train: [3/20][313/510] Data 3.927 (3.802) Batch 35.157 (27.850) Remain 68:35:41 loss: 0.2054 loss_seg: 0.1149 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:13:58,108 INFO misc.py line 117 726] Train: [3/20][314/510] Data 2.345 (3.797) Batch 23.026 (27.834) Remain 68:32:56 loss: 0.2828 loss_seg: 0.1951 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:14:31,308 INFO misc.py line 117 726] Train: [3/20][315/510] Data 4.297 (3.799) Batch 33.200 (27.851) Remain 68:35:00 loss: 0.2605 loss_seg: 0.1635 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:15:01,647 INFO misc.py line 117 726] Train: [3/20][316/510] Data 4.495 (3.801) Batch 30.339 (27.859) Remain 68:35:43 loss: 0.2696 loss_seg: 0.1747 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:15:25,599 INFO misc.py line 117 726] Train: [3/20][317/510] Data 2.362 (3.796) Batch 23.953 (27.847) Remain 68:33:25 loss: 0.2497 loss_seg: 0.1504 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:16:08,225 INFO misc.py line 117 726] Train: [3/20][318/510] Data 9.512 (3.814) Batch 42.626 (27.894) Remain 68:39:53 loss: 0.2474 loss_seg: 0.1561 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:16:37,476 INFO misc.py line 117 726] Train: [3/20][319/510] Data 6.701 (3.823) Batch 29.251 (27.898) Remain 68:40:03 loss: 0.2740 loss_seg: 0.1756 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:17:14,715 INFO misc.py line 117 726] Train: [3/20][320/510] Data 5.221 (3.828) Batch 37.239 (27.927) Remain 68:43:56 loss: 0.3696 loss_seg: 0.2783 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:17:42,043 INFO misc.py line 117 726] Train: [3/20][321/510] Data 2.791 (3.825) Batch 27.328 (27.925) Remain 68:43:11 loss: 0.1930 loss_seg: 0.1083 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:18:07,234 INFO misc.py line 117 726] Train: [3/20][322/510] Data 2.739 (3.821) Batch 25.191 (27.917) Remain 68:41:28 loss: 0.2876 loss_seg: 0.1846 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:18:33,168 INFO misc.py line 117 726] Train: [3/20][323/510] Data 3.218 (3.819) Batch 25.934 (27.911) Remain 68:40:05 loss: 0.1954 loss_seg: 0.1119 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:18:57,319 INFO misc.py line 117 726] Train: [3/20][324/510] Data 2.374 (3.815) Batch 24.151 (27.899) Remain 68:37:53 loss: 0.2382 loss_seg: 0.1439 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:19:35,571 INFO misc.py line 117 726] Train: [3/20][325/510] Data 6.091 (3.822) Batch 38.252 (27.931) Remain 68:42:10 loss: 0.2583 loss_seg: 0.1580 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:20:04,303 INFO misc.py line 117 726] Train: [3/20][326/510] Data 2.944 (3.819) Batch 28.732 (27.934) Remain 68:42:04 loss: 0.2685 loss_seg: 0.1757 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:20:40,776 INFO misc.py line 117 726] Train: [3/20][327/510] Data 4.401 (3.821) Batch 36.474 (27.960) Remain 68:45:29 loss: 0.2509 loss_seg: 0.1580 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:21:15,010 INFO misc.py line 117 726] Train: [3/20][328/510] Data 4.998 (3.825) Batch 34.234 (27.979) Remain 68:47:52 loss: 0.2690 loss_seg: 0.1690 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:21:42,888 INFO misc.py line 117 726] Train: [3/20][329/510] Data 2.877 (3.822) Batch 27.878 (27.979) Remain 68:47:22 loss: 0.2853 loss_seg: 0.1827 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:22:06,817 INFO misc.py line 117 726] Train: [3/20][330/510] Data 3.082 (3.819) Batch 23.929 (27.967) Remain 68:45:04 loss: 0.2743 loss_seg: 0.1798 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:22:38,569 INFO misc.py line 117 726] Train: [3/20][331/510] Data 4.454 (3.821) Batch 31.752 (27.978) Remain 68:46:18 loss: 0.2708 loss_seg: 0.1740 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:23:01,653 INFO misc.py line 117 726] Train: [3/20][332/510] Data 2.263 (3.817) Batch 23.084 (27.963) Remain 68:43:39 loss: 0.2940 loss_seg: 0.1824 loss_superpoint_edge: 0.0424 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:23:30,755 INFO misc.py line 117 726] Train: [3/20][333/510] Data 6.499 (3.825) Batch 29.102 (27.967) Remain 68:43:41 loss: 0.2083 loss_seg: 0.1136 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:23:58,064 INFO misc.py line 117 726] Train: [3/20][334/510] Data 2.546 (3.821) Batch 27.309 (27.965) Remain 68:42:56 loss: 0.1887 loss_seg: 0.1017 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:24:30,742 INFO misc.py line 117 726] Train: [3/20][335/510] Data 4.300 (3.822) Batch 32.679 (27.979) Remain 68:44:33 loss: 0.2494 loss_seg: 0.1491 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:25:04,873 INFO misc.py line 117 726] Train: [3/20][336/510] Data 3.879 (3.822) Batch 34.130 (27.997) Remain 68:46:49 loss: 0.1773 loss_seg: 0.0935 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:25:32,628 INFO misc.py line 117 726] Train: [3/20][337/510] Data 2.899 (3.820) Batch 27.755 (27.997) Remain 68:46:14 loss: 0.3037 loss_seg: 0.1980 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:25:55,289 INFO misc.py line 117 726] Train: [3/20][338/510] Data 2.932 (3.817) Batch 22.661 (27.981) Remain 68:43:25 loss: 0.2383 loss_seg: 0.1439 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:26:22,452 INFO misc.py line 117 726] Train: [3/20][339/510] Data 2.983 (3.815) Batch 27.163 (27.978) Remain 68:42:36 loss: 0.2542 loss_seg: 0.1577 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:26:55,248 INFO misc.py line 117 726] Train: [3/20][340/510] Data 3.510 (3.814) Batch 32.796 (27.993) Remain 68:44:14 loss: 0.2106 loss_seg: 0.1231 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:27:24,498 INFO misc.py line 117 726] Train: [3/20][341/510] Data 3.788 (3.814) Batch 29.250 (27.996) Remain 68:44:19 loss: 0.2557 loss_seg: 0.1575 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:27:56,274 INFO misc.py line 117 726] Train: [3/20][342/510] Data 5.739 (3.819) Batch 31.776 (28.007) Remain 68:45:30 loss: 0.3288 loss_seg: 0.2163 loss_superpoint_edge: 0.0430 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:28:25,122 INFO misc.py line 117 726] Train: [3/20][343/510] Data 3.284 (3.818) Batch 28.848 (28.010) Remain 68:45:24 loss: 0.3513 loss_seg: 0.2434 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:28:56,872 INFO misc.py line 117 726] Train: [3/20][344/510] Data 4.927 (3.821) Batch 31.749 (28.021) Remain 68:46:32 loss: 0.2869 loss_seg: 0.1903 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:29:09,934 INFO misc.py line 117 726] Train: [3/20][345/510] Data 1.522 (3.814) Batch 13.062 (27.977) Remain 68:39:38 loss: 0.2952 loss_seg: 0.1921 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:29:35,612 INFO misc.py line 117 726] Train: [3/20][346/510] Data 2.888 (3.812) Batch 25.679 (27.970) Remain 68:38:11 loss: 0.2061 loss_seg: 0.1177 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:30:12,910 INFO misc.py line 117 726] Train: [3/20][347/510] Data 9.759 (3.829) Batch 37.297 (27.998) Remain 68:41:42 loss: 0.2738 loss_seg: 0.1754 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0441 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:30:35,695 INFO misc.py line 117 726] Train: [3/20][348/510] Data 3.263 (3.827) Batch 22.786 (27.982) Remain 68:39:01 loss: 0.2720 loss_seg: 0.1711 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:31:02,484 INFO misc.py line 117 726] Train: [3/20][349/510] Data 3.106 (3.825) Batch 26.789 (27.979) Remain 68:38:02 loss: 0.2496 loss_seg: 0.1503 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:31:26,256 INFO misc.py line 117 726] Train: [3/20][350/510] Data 5.401 (3.830) Batch 23.772 (27.967) Remain 68:35:47 loss: 0.2752 loss_seg: 0.1790 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:31:26,257 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 01:31:54,451 INFO misc.py line 117 726] Train: [3/20][351/510] Data 5.265 (3.834) Batch 28.195 (27.968) Remain 68:35:25 loss: 0.2468 loss_seg: 0.1505 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:32:19,106 INFO misc.py line 117 726] Train: [3/20][352/510] Data 2.667 (3.830) Batch 24.655 (27.958) Remain 68:33:33 loss: 0.2183 loss_seg: 0.1237 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:32:45,611 INFO misc.py line 117 726] Train: [3/20][353/510] Data 3.653 (3.830) Batch 26.505 (27.954) Remain 68:32:29 loss: 0.3654 loss_seg: 0.2555 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:33:12,315 INFO misc.py line 117 726] Train: [3/20][354/510] Data 3.072 (3.828) Batch 26.703 (27.950) Remain 68:31:29 loss: 0.3064 loss_seg: 0.2128 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:33:45,769 INFO misc.py line 117 726] Train: [3/20][355/510] Data 4.908 (3.831) Batch 33.454 (27.966) Remain 68:33:20 loss: 0.1904 loss_seg: 0.1060 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:34:12,523 INFO misc.py line 117 726] Train: [3/20][356/510] Data 3.863 (3.831) Batch 26.754 (27.963) Remain 68:32:21 loss: 0.2057 loss_seg: 0.1162 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:34:29,147 INFO misc.py line 117 726] Train: [3/20][357/510] Data 2.105 (3.826) Batch 16.624 (27.931) Remain 68:27:11 loss: 0.2484 loss_seg: 0.1478 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:35:00,160 INFO misc.py line 117 726] Train: [3/20][358/510] Data 4.220 (3.827) Batch 31.013 (27.939) Remain 68:27:59 loss: 0.2699 loss_seg: 0.1754 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:35:22,599 INFO misc.py line 117 726] Train: [3/20][359/510] Data 3.001 (3.825) Batch 22.439 (27.924) Remain 68:25:15 loss: 0.2735 loss_seg: 0.1763 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:35:44,391 INFO misc.py line 117 726] Train: [3/20][360/510] Data 2.965 (3.822) Batch 21.792 (27.907) Remain 68:22:16 loss: 0.3265 loss_seg: 0.2116 loss_superpoint_edge: 0.0441 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:36:04,237 INFO misc.py line 117 726] Train: [3/20][361/510] Data 2.826 (3.820) Batch 19.846 (27.884) Remain 68:18:29 loss: 0.1817 loss_seg: 0.0932 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:36:30,354 INFO misc.py line 117 726] Train: [3/20][362/510] Data 3.754 (3.819) Batch 26.117 (27.879) Remain 68:17:18 loss: 0.2709 loss_seg: 0.1693 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:36:51,726 INFO misc.py line 117 726] Train: [3/20][363/510] Data 2.509 (3.816) Batch 21.372 (27.861) Remain 68:14:11 loss: 0.3736 loss_seg: 0.2684 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:37:11,218 INFO misc.py line 117 726] Train: [3/20][364/510] Data 2.300 (3.812) Batch 19.493 (27.838) Remain 68:10:18 loss: 0.3152 loss_seg: 0.2086 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:37:49,773 INFO misc.py line 117 726] Train: [3/20][365/510] Data 6.824 (3.820) Batch 38.555 (27.868) Remain 68:14:12 loss: 0.2432 loss_seg: 0.1488 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:38:23,994 INFO misc.py line 117 726] Train: [3/20][366/510] Data 4.412 (3.822) Batch 34.221 (27.885) Remain 68:16:18 loss: 0.3064 loss_seg: 0.1999 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:38:43,178 INFO misc.py line 117 726] Train: [3/20][367/510] Data 2.219 (3.817) Batch 19.185 (27.861) Remain 68:12:19 loss: 0.2358 loss_seg: 0.1369 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:39:13,823 INFO misc.py line 117 726] Train: [3/20][368/510] Data 4.494 (3.819) Batch 30.644 (27.869) Remain 68:12:59 loss: 0.2403 loss_seg: 0.1402 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:39:38,637 INFO misc.py line 117 726] Train: [3/20][369/510] Data 2.792 (3.816) Batch 24.815 (27.860) Remain 68:11:17 loss: 0.2488 loss_seg: 0.1467 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:40:09,406 INFO misc.py line 117 726] Train: [3/20][370/510] Data 3.919 (3.816) Batch 30.768 (27.868) Remain 68:11:59 loss: 0.2589 loss_seg: 0.1590 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:40:35,202 INFO misc.py line 117 726] Train: [3/20][371/510] Data 2.854 (3.814) Batch 25.796 (27.863) Remain 68:10:42 loss: 0.2424 loss_seg: 0.1438 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:41:06,375 INFO misc.py line 117 726] Train: [3/20][372/510] Data 5.049 (3.817) Batch 31.174 (27.872) Remain 68:11:33 loss: 0.1985 loss_seg: 0.1107 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:41:39,291 INFO misc.py line 117 726] Train: [3/20][373/510] Data 4.372 (3.819) Batch 32.916 (27.885) Remain 68:13:05 loss: 0.2497 loss_seg: 0.1571 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:42:02,361 INFO misc.py line 117 726] Train: [3/20][374/510] Data 2.437 (3.815) Batch 23.070 (27.872) Remain 68:10:43 loss: 0.2354 loss_seg: 0.1404 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:42:25,134 INFO misc.py line 117 726] Train: [3/20][375/510] Data 2.993 (3.813) Batch 22.773 (27.859) Remain 68:08:14 loss: 0.2081 loss_seg: 0.1171 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:42:57,578 INFO misc.py line 117 726] Train: [3/20][376/510] Data 3.880 (3.813) Batch 32.443 (27.871) Remain 68:09:35 loss: 0.3928 loss_seg: 0.2825 loss_superpoint_edge: 0.0433 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:43:29,206 INFO misc.py line 117 726] Train: [3/20][377/510] Data 5.116 (3.816) Batch 31.629 (27.881) Remain 68:10:35 loss: 0.2425 loss_seg: 0.1522 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:43:59,249 INFO misc.py line 117 726] Train: [3/20][378/510] Data 3.213 (3.815) Batch 30.042 (27.887) Remain 68:10:58 loss: 0.2305 loss_seg: 0.1379 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:44:22,618 INFO misc.py line 117 726] Train: [3/20][379/510] Data 4.030 (3.815) Batch 23.370 (27.875) Remain 68:08:45 loss: 0.2147 loss_seg: 0.1213 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:44:55,729 INFO misc.py line 117 726] Train: [3/20][380/510] Data 6.015 (3.821) Batch 33.111 (27.889) Remain 68:10:19 loss: 0.2641 loss_seg: 0.1712 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:45:25,652 INFO misc.py line 117 726] Train: [3/20][381/510] Data 3.445 (3.820) Batch 29.923 (27.894) Remain 68:10:38 loss: 0.2330 loss_seg: 0.1414 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:45:51,423 INFO misc.py line 117 726] Train: [3/20][382/510] Data 2.952 (3.818) Batch 25.770 (27.888) Remain 68:09:21 loss: 0.2762 loss_seg: 0.1749 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:46:21,061 INFO misc.py line 117 726] Train: [3/20][383/510] Data 3.138 (3.816) Batch 29.639 (27.893) Remain 68:09:34 loss: 0.2681 loss_seg: 0.1726 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:46:46,316 INFO misc.py line 117 726] Train: [3/20][384/510] Data 2.984 (3.814) Batch 25.254 (27.886) Remain 68:08:05 loss: 0.1900 loss_seg: 0.1001 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:47:10,274 INFO misc.py line 117 726] Train: [3/20][385/510] Data 3.017 (3.812) Batch 23.958 (27.876) Remain 68:06:07 loss: 0.3002 loss_seg: 0.1928 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:47:34,630 INFO misc.py line 117 726] Train: [3/20][386/510] Data 2.649 (3.809) Batch 24.356 (27.867) Remain 68:04:18 loss: 0.2811 loss_seg: 0.1780 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:47:50,523 INFO misc.py line 117 726] Train: [3/20][387/510] Data 2.499 (3.805) Batch 15.893 (27.835) Remain 67:59:16 loss: 0.2497 loss_seg: 0.1483 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:48:27,784 INFO misc.py line 117 726] Train: [3/20][388/510] Data 4.836 (3.808) Batch 37.261 (27.860) Remain 68:02:23 loss: 0.2960 loss_seg: 0.1975 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:48:53,950 INFO misc.py line 117 726] Train: [3/20][389/510] Data 3.065 (3.806) Batch 26.167 (27.855) Remain 68:01:17 loss: 0.3724 loss_seg: 0.2689 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:49:24,795 INFO misc.py line 117 726] Train: [3/20][390/510] Data 3.601 (3.806) Batch 30.844 (27.863) Remain 68:01:57 loss: 0.2490 loss_seg: 0.1534 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:49:44,802 INFO misc.py line 117 726] Train: [3/20][391/510] Data 2.506 (3.802) Batch 20.008 (27.843) Remain 67:58:31 loss: 0.2355 loss_seg: 0.1393 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:50:07,661 INFO misc.py line 117 726] Train: [3/20][392/510] Data 2.776 (3.800) Batch 22.859 (27.830) Remain 67:56:11 loss: 0.2568 loss_seg: 0.1534 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:50:45,230 INFO misc.py line 117 726] Train: [3/20][393/510] Data 6.386 (3.806) Batch 37.568 (27.855) Remain 67:59:22 loss: 0.2397 loss_seg: 0.1482 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:51:03,047 INFO misc.py line 117 726] Train: [3/20][394/510] Data 1.860 (3.801) Batch 17.817 (27.829) Remain 67:55:09 loss: 0.2917 loss_seg: 0.1834 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:51:31,969 INFO misc.py line 117 726] Train: [3/20][395/510] Data 4.935 (3.804) Batch 28.923 (27.832) Remain 67:55:06 loss: 0.2226 loss_seg: 0.1305 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:51:59,120 INFO misc.py line 117 726] Train: [3/20][396/510] Data 2.697 (3.801) Batch 27.151 (27.830) Remain 67:54:23 loss: 0.2402 loss_seg: 0.1483 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:52:32,501 INFO misc.py line 117 726] Train: [3/20][397/510] Data 4.028 (3.802) Batch 33.381 (27.845) Remain 67:55:58 loss: 0.2671 loss_seg: 0.1741 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:53:00,838 INFO misc.py line 117 726] Train: [3/20][398/510] Data 3.583 (3.801) Batch 28.337 (27.846) Remain 67:55:42 loss: 0.3053 loss_seg: 0.2027 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:53:28,512 INFO misc.py line 117 726] Train: [3/20][399/510] Data 5.277 (3.805) Batch 27.674 (27.845) Remain 67:55:10 loss: 0.1948 loss_seg: 0.1041 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:54:08,129 INFO misc.py line 117 726] Train: [3/20][400/510] Data 9.614 (3.820) Batch 39.617 (27.875) Remain 67:59:02 loss: 0.3330 loss_seg: 0.2421 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:54:08,129 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 01:54:47,792 INFO misc.py line 117 726] Train: [3/20][401/510] Data 9.307 (3.834) Batch 39.664 (27.905) Remain 68:02:55 loss: 0.4062 loss_seg: 0.2802 loss_superpoint_edge: 0.0510 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:55:23,330 INFO misc.py line 117 726] Train: [3/20][402/510] Data 3.829 (3.834) Batch 35.538 (27.924) Remain 68:05:15 loss: 0.2981 loss_seg: 0.1852 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:56:01,628 INFO misc.py line 117 726] Train: [3/20][403/510] Data 6.386 (3.840) Batch 38.298 (27.950) Remain 68:08:34 loss: 0.3109 loss_seg: 0.2097 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:56:28,815 INFO misc.py line 117 726] Train: [3/20][404/510] Data 5.012 (3.843) Batch 27.187 (27.948) Remain 68:07:50 loss: 0.1804 loss_seg: 0.0925 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:57:06,943 INFO misc.py line 117 726] Train: [3/20][405/510] Data 5.548 (3.847) Batch 38.128 (27.973) Remain 68:11:04 loss: 0.2486 loss_seg: 0.1569 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:57:36,404 INFO misc.py line 117 726] Train: [3/20][406/510] Data 3.249 (3.846) Batch 29.462 (27.977) Remain 68:11:08 loss: 0.3269 loss_seg: 0.2218 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:58:11,376 INFO misc.py line 117 726] Train: [3/20][407/510] Data 3.978 (3.846) Batch 34.972 (27.994) Remain 68:13:12 loss: 0.2574 loss_seg: 0.1632 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:58:42,458 INFO misc.py line 117 726] Train: [3/20][408/510] Data 2.921 (3.844) Batch 31.082 (28.002) Remain 68:13:51 loss: 0.2129 loss_seg: 0.1185 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:59:26,345 INFO misc.py line 117 726] Train: [3/20][409/510] Data 12.219 (3.864) Batch 43.886 (28.041) Remain 68:19:06 loss: 0.2734 loss_seg: 0.1821 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 01:59:56,599 INFO misc.py line 117 726] Train: [3/20][410/510] Data 4.831 (3.867) Batch 30.254 (28.046) Remain 68:19:26 loss: 0.2815 loss_seg: 0.1807 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:00:14,876 INFO misc.py line 117 726] Train: [3/20][411/510] Data 2.110 (3.862) Batch 18.278 (28.022) Remain 68:15:28 loss: 0.1781 loss_seg: 0.0928 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:00:39,289 INFO misc.py line 117 726] Train: [3/20][412/510] Data 2.724 (3.860) Batch 24.412 (28.014) Remain 68:13:43 loss: 0.2386 loss_seg: 0.1440 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:01:07,956 INFO misc.py line 117 726] Train: [3/20][413/510] Data 3.732 (3.859) Batch 28.668 (28.015) Remain 68:13:29 loss: 0.3092 loss_seg: 0.2111 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:01:32,067 INFO misc.py line 117 726] Train: [3/20][414/510] Data 2.728 (3.857) Batch 24.111 (28.006) Remain 68:11:37 loss: 0.1655 loss_seg: 0.0800 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:01:58,777 INFO misc.py line 117 726] Train: [3/20][415/510] Data 2.123 (3.852) Batch 26.710 (28.003) Remain 68:10:42 loss: 0.2533 loss_seg: 0.1520 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:02:34,119 INFO misc.py line 117 726] Train: [3/20][416/510] Data 5.261 (3.856) Batch 35.342 (28.020) Remain 68:12:49 loss: 0.3077 loss_seg: 0.2050 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:03:01,763 INFO misc.py line 117 726] Train: [3/20][417/510] Data 3.135 (3.854) Batch 27.643 (28.019) Remain 68:12:13 loss: 0.3564 loss_seg: 0.2504 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:03:24,802 INFO misc.py line 117 726] Train: [3/20][418/510] Data 2.012 (3.850) Batch 23.039 (28.007) Remain 68:10:00 loss: 0.2792 loss_seg: 0.1869 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:03:44,497 INFO misc.py line 117 726] Train: [3/20][419/510] Data 1.990 (3.845) Batch 19.695 (27.987) Remain 68:06:37 loss: 0.2509 loss_seg: 0.1554 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:04:11,860 INFO misc.py line 117 726] Train: [3/20][420/510] Data 4.468 (3.847) Batch 27.364 (27.986) Remain 68:05:56 loss: 0.3311 loss_seg: 0.2236 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:04:37,033 INFO misc.py line 117 726] Train: [3/20][421/510] Data 2.399 (3.843) Batch 25.173 (27.979) Remain 68:04:29 loss: 0.2421 loss_seg: 0.1416 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:05:04,044 INFO misc.py line 117 726] Train: [3/20][422/510] Data 5.364 (3.847) Batch 27.010 (27.977) Remain 68:03:41 loss: 0.2790 loss_seg: 0.1802 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:05:21,586 INFO misc.py line 117 726] Train: [3/20][423/510] Data 1.426 (3.841) Batch 17.542 (27.952) Remain 67:59:35 loss: 0.2363 loss_seg: 0.1461 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:05:50,131 INFO misc.py line 117 726] Train: [3/20][424/510] Data 5.300 (3.844) Batch 28.545 (27.953) Remain 67:59:20 loss: 0.2357 loss_seg: 0.1434 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:06:18,295 INFO misc.py line 117 726] Train: [3/20][425/510] Data 3.184 (3.843) Batch 28.164 (27.954) Remain 67:58:56 loss: 0.2210 loss_seg: 0.1283 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:06:52,077 INFO misc.py line 117 726] Train: [3/20][426/510] Data 4.028 (3.843) Batch 33.782 (27.968) Remain 68:00:29 loss: 0.2453 loss_seg: 0.1502 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:07:21,433 INFO misc.py line 117 726] Train: [3/20][427/510] Data 3.246 (3.842) Batch 29.356 (27.971) Remain 68:00:30 loss: 0.2561 loss_seg: 0.1598 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:07:38,544 INFO misc.py line 117 726] Train: [3/20][428/510] Data 1.705 (3.837) Batch 17.111 (27.945) Remain 67:56:18 loss: 0.2451 loss_seg: 0.1521 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:08:03,554 INFO misc.py line 117 726] Train: [3/20][429/510] Data 2.607 (3.834) Batch 25.010 (27.939) Remain 67:54:50 loss: 0.1809 loss_seg: 0.0951 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:08:22,908 INFO misc.py line 117 726] Train: [3/20][430/510] Data 1.991 (3.830) Batch 19.354 (27.918) Remain 67:51:26 loss: 0.2333 loss_seg: 0.1381 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:08:48,477 INFO misc.py line 117 726] Train: [3/20][431/510] Data 3.426 (3.829) Batch 25.569 (27.913) Remain 67:50:10 loss: 0.2130 loss_seg: 0.1198 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:09:19,291 INFO misc.py line 117 726] Train: [3/20][432/510] Data 4.331 (3.830) Batch 30.814 (27.920) Remain 67:50:41 loss: 0.3156 loss_seg: 0.2040 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0437 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:09:37,827 INFO misc.py line 117 726] Train: [3/20][433/510] Data 2.176 (3.826) Batch 18.536 (27.898) Remain 67:47:02 loss: 0.3040 loss_seg: 0.2005 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:10:09,102 INFO misc.py line 117 726] Train: [3/20][434/510] Data 5.371 (3.830) Batch 31.275 (27.906) Remain 67:47:43 loss: 0.4313 loss_seg: 0.3264 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:10:35,918 INFO misc.py line 117 726] Train: [3/20][435/510] Data 3.325 (3.828) Batch 26.815 (27.903) Remain 67:46:53 loss: 0.2651 loss_seg: 0.1650 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:11:07,233 INFO misc.py line 117 726] Train: [3/20][436/510] Data 4.525 (3.830) Batch 31.315 (27.911) Remain 67:47:34 loss: 0.3080 loss_seg: 0.2053 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:11:32,016 INFO misc.py line 117 726] Train: [3/20][437/510] Data 2.941 (3.828) Batch 24.783 (27.904) Remain 67:46:03 loss: 0.1617 loss_seg: 0.0804 loss_superpoint_edge: 0.0114 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:12:02,229 INFO misc.py line 117 726] Train: [3/20][438/510] Data 3.588 (3.827) Batch 30.213 (27.909) Remain 67:46:22 loss: 0.2452 loss_seg: 0.1498 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:12:20,081 INFO misc.py line 117 726] Train: [3/20][439/510] Data 2.970 (3.826) Batch 17.852 (27.886) Remain 67:42:32 loss: 0.2256 loss_seg: 0.1292 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:12:41,147 INFO misc.py line 117 726] Train: [3/20][440/510] Data 2.189 (3.822) Batch 21.066 (27.871) Remain 67:39:48 loss: 0.2219 loss_seg: 0.1261 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:13:12,319 INFO misc.py line 117 726] Train: [3/20][441/510] Data 3.032 (3.820) Batch 31.173 (27.878) Remain 67:40:26 loss: 0.2942 loss_seg: 0.1895 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:13:36,104 INFO misc.py line 117 726] Train: [3/20][442/510] Data 1.999 (3.816) Batch 23.784 (27.869) Remain 67:38:36 loss: 0.2616 loss_seg: 0.1623 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:13:57,873 INFO misc.py line 117 726] Train: [3/20][443/510] Data 2.791 (3.813) Batch 21.769 (27.855) Remain 67:36:07 loss: 0.2880 loss_seg: 0.1879 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:14:32,313 INFO misc.py line 117 726] Train: [3/20][444/510] Data 5.487 (3.817) Batch 34.439 (27.870) Remain 67:37:50 loss: 0.2768 loss_seg: 0.1834 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:15:06,736 INFO misc.py line 117 726] Train: [3/20][445/510] Data 3.926 (3.818) Batch 34.423 (27.885) Remain 67:39:32 loss: 0.3229 loss_seg: 0.2199 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:15:35,130 INFO misc.py line 117 726] Train: [3/20][446/510] Data 3.145 (3.816) Batch 28.394 (27.886) Remain 67:39:14 loss: 0.2371 loss_seg: 0.1413 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:16:00,083 INFO misc.py line 117 726] Train: [3/20][447/510] Data 2.122 (3.812) Batch 24.953 (27.879) Remain 67:37:48 loss: 0.2348 loss_seg: 0.1361 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:16:29,166 INFO misc.py line 117 726] Train: [3/20][448/510] Data 3.269 (3.811) Batch 29.083 (27.882) Remain 67:37:44 loss: 0.2230 loss_seg: 0.1309 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:16:59,666 INFO misc.py line 117 726] Train: [3/20][449/510] Data 3.036 (3.809) Batch 30.500 (27.888) Remain 67:38:07 loss: 0.2083 loss_seg: 0.1174 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:17:29,188 INFO misc.py line 117 726] Train: [3/20][450/510] Data 3.568 (3.809) Batch 29.522 (27.891) Remain 67:38:11 loss: 0.2857 loss_seg: 0.1790 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:17:29,188 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 02:18:04,257 INFO misc.py line 117 726] Train: [3/20][451/510] Data 5.182 (3.812) Batch 35.070 (27.907) Remain 67:40:03 loss: 0.2611 loss_seg: 0.1640 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:18:40,836 INFO misc.py line 117 726] Train: [3/20][452/510] Data 4.000 (3.812) Batch 36.578 (27.927) Remain 67:42:24 loss: 0.2141 loss_seg: 0.1242 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:19:09,349 INFO misc.py line 117 726] Train: [3/20][453/510] Data 3.716 (3.812) Batch 28.513 (27.928) Remain 67:42:07 loss: 0.2291 loss_seg: 0.1368 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:19:38,544 INFO misc.py line 117 726] Train: [3/20][454/510] Data 3.753 (3.812) Batch 29.195 (27.931) Remain 67:42:04 loss: 0.2092 loss_seg: 0.1179 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:19:59,992 INFO misc.py line 117 726] Train: [3/20][455/510] Data 2.787 (3.810) Batch 21.448 (27.916) Remain 67:39:31 loss: 0.2612 loss_seg: 0.1626 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:20:29,466 INFO misc.py line 117 726] Train: [3/20][456/510] Data 3.459 (3.809) Batch 29.474 (27.920) Remain 67:39:33 loss: 0.2278 loss_seg: 0.1361 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:20:54,683 INFO misc.py line 117 726] Train: [3/20][457/510] Data 3.138 (3.807) Batch 25.218 (27.914) Remain 67:38:13 loss: 0.2971 loss_seg: 0.1915 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:21:25,518 INFO misc.py line 117 726] Train: [3/20][458/510] Data 3.754 (3.807) Batch 30.834 (27.920) Remain 67:38:41 loss: 0.1853 loss_seg: 0.1026 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:21:49,574 INFO misc.py line 117 726] Train: [3/20][459/510] Data 3.772 (3.807) Batch 24.057 (27.912) Remain 67:36:59 loss: 0.2964 loss_seg: 0.1983 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:22:09,193 INFO misc.py line 117 726] Train: [3/20][460/510] Data 1.968 (3.803) Batch 19.619 (27.894) Remain 67:33:53 loss: 0.2962 loss_seg: 0.1922 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:22:41,250 INFO misc.py line 117 726] Train: [3/20][461/510] Data 3.484 (3.802) Batch 32.058 (27.903) Remain 67:34:45 loss: 0.2253 loss_seg: 0.1321 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:23:21,900 INFO misc.py line 117 726] Train: [3/20][462/510] Data 8.300 (3.812) Batch 40.650 (27.931) Remain 67:38:19 loss: 0.2936 loss_seg: 0.1890 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:23:44,004 INFO misc.py line 117 726] Train: [3/20][463/510] Data 1.986 (3.808) Batch 22.104 (27.918) Remain 67:36:01 loss: 0.2332 loss_seg: 0.1401 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:24:17,624 INFO misc.py line 117 726] Train: [3/20][464/510] Data 5.344 (3.812) Batch 33.620 (27.930) Remain 67:37:20 loss: 0.2328 loss_seg: 0.1413 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:24:41,011 INFO misc.py line 117 726] Train: [3/20][465/510] Data 2.579 (3.809) Batch 23.387 (27.921) Remain 67:35:27 loss: 0.2673 loss_seg: 0.1667 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:25:06,849 INFO misc.py line 117 726] Train: [3/20][466/510] Data 2.621 (3.806) Batch 25.838 (27.916) Remain 67:34:20 loss: 0.2096 loss_seg: 0.1210 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:25:23,534 INFO misc.py line 117 726] Train: [3/20][467/510] Data 2.335 (3.803) Batch 16.685 (27.892) Remain 67:30:21 loss: 0.2163 loss_seg: 0.1270 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:25:57,000 INFO misc.py line 117 726] Train: [3/20][468/510] Data 3.443 (3.802) Batch 33.466 (27.904) Remain 67:31:37 loss: 0.2415 loss_seg: 0.1451 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:26:28,574 INFO misc.py line 117 726] Train: [3/20][469/510] Data 3.207 (3.801) Batch 31.575 (27.912) Remain 67:32:18 loss: 0.2878 loss_seg: 0.1841 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:26:53,951 INFO misc.py line 117 726] Train: [3/20][470/510] Data 2.256 (3.798) Batch 25.376 (27.906) Remain 67:31:03 loss: 0.2288 loss_seg: 0.1312 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:27:15,333 INFO misc.py line 117 726] Train: [3/20][471/510] Data 2.685 (3.795) Batch 21.383 (27.892) Remain 67:28:34 loss: 0.2866 loss_seg: 0.1851 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:27:48,715 INFO misc.py line 117 726] Train: [3/20][472/510] Data 5.653 (3.799) Batch 33.381 (27.904) Remain 67:29:48 loss: 0.2143 loss_seg: 0.1245 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:28:19,553 INFO misc.py line 117 726] Train: [3/20][473/510] Data 3.172 (3.798) Batch 30.838 (27.910) Remain 67:30:14 loss: 0.2361 loss_seg: 0.1403 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:28:49,575 INFO misc.py line 117 726] Train: [3/20][474/510] Data 3.231 (3.797) Batch 30.022 (27.915) Remain 67:30:25 loss: 0.2619 loss_seg: 0.1680 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:29:23,240 INFO misc.py line 117 726] Train: [3/20][475/510] Data 3.907 (3.797) Batch 33.665 (27.927) Remain 67:31:43 loss: 0.3388 loss_seg: 0.2268 loss_superpoint_edge: 0.0434 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:29:49,323 INFO misc.py line 117 726] Train: [3/20][476/510] Data 2.842 (3.795) Batch 26.083 (27.923) Remain 67:30:41 loss: 0.3347 loss_seg: 0.2258 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:30:10,867 INFO misc.py line 117 726] Train: [3/20][477/510] Data 2.265 (3.792) Batch 21.545 (27.910) Remain 67:28:16 loss: 0.2226 loss_seg: 0.1282 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:30:41,752 INFO misc.py line 117 726] Train: [3/20][478/510] Data 3.707 (3.792) Batch 30.884 (27.916) Remain 67:28:43 loss: 0.2598 loss_seg: 0.1678 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:31:10,345 INFO misc.py line 117 726] Train: [3/20][479/510] Data 2.728 (3.789) Batch 28.594 (27.917) Remain 67:28:27 loss: 0.2125 loss_seg: 0.1244 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:31:41,128 INFO misc.py line 117 726] Train: [3/20][480/510] Data 4.087 (3.790) Batch 30.783 (27.923) Remain 67:28:52 loss: 0.2595 loss_seg: 0.1610 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:32:04,905 INFO misc.py line 117 726] Train: [3/20][481/510] Data 2.202 (3.787) Batch 23.777 (27.915) Remain 67:27:08 loss: 0.1903 loss_seg: 0.1046 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:32:33,673 INFO misc.py line 117 726] Train: [3/20][482/510] Data 3.142 (3.785) Batch 28.767 (27.916) Remain 67:26:56 loss: 0.2796 loss_seg: 0.1816 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:33:02,848 INFO misc.py line 117 726] Train: [3/20][483/510] Data 3.097 (3.784) Batch 29.175 (27.919) Remain 67:26:51 loss: 0.2032 loss_seg: 0.1139 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:33:27,036 INFO misc.py line 117 726] Train: [3/20][484/510] Data 3.625 (3.784) Batch 24.188 (27.911) Remain 67:25:16 loss: 0.2549 loss_seg: 0.1595 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:34:04,221 INFO misc.py line 117 726] Train: [3/20][485/510] Data 4.597 (3.785) Batch 37.185 (27.930) Remain 67:27:35 loss: 0.1724 loss_seg: 0.0890 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:34:38,738 INFO misc.py line 117 726] Train: [3/20][486/510] Data 4.663 (3.787) Batch 34.517 (27.944) Remain 67:29:06 loss: 0.2951 loss_seg: 0.1953 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:35:07,422 INFO misc.py line 117 726] Train: [3/20][487/510] Data 2.626 (3.785) Batch 28.684 (27.946) Remain 67:28:51 loss: 0.2273 loss_seg: 0.1383 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:35:33,435 INFO misc.py line 117 726] Train: [3/20][488/510] Data 3.129 (3.783) Batch 26.013 (27.942) Remain 67:27:48 loss: 0.1976 loss_seg: 0.1109 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:35:56,964 INFO misc.py line 117 726] Train: [3/20][489/510] Data 3.332 (3.782) Batch 23.529 (27.933) Remain 67:26:01 loss: 0.2243 loss_seg: 0.1333 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:36:22,481 INFO misc.py line 117 726] Train: [3/20][490/510] Data 3.453 (3.782) Batch 25.517 (27.928) Remain 67:24:50 loss: 0.2708 loss_seg: 0.1718 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:36:53,416 INFO misc.py line 117 726] Train: [3/20][491/510] Data 2.523 (3.779) Batch 30.935 (27.934) Remain 67:25:16 loss: 0.2070 loss_seg: 0.1173 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:37:20,940 INFO misc.py line 117 726] Train: [3/20][492/510] Data 5.325 (3.782) Batch 27.524 (27.933) Remain 67:24:41 loss: 0.2183 loss_seg: 0.1258 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:37:47,251 INFO misc.py line 117 726] Train: [3/20][493/510] Data 3.091 (3.781) Batch 26.310 (27.930) Remain 67:23:44 loss: 0.3121 loss_seg: 0.2079 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:38:14,964 INFO misc.py line 117 726] Train: [3/20][494/510] Data 2.970 (3.779) Batch 27.714 (27.929) Remain 67:23:12 loss: 0.2504 loss_seg: 0.1553 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:38:46,616 INFO misc.py line 117 726] Train: [3/20][495/510] Data 6.175 (3.784) Batch 31.652 (27.937) Remain 67:23:50 loss: 0.2879 loss_seg: 0.1945 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:39:15,797 INFO misc.py line 117 726] Train: [3/20][496/510] Data 3.912 (3.784) Batch 29.181 (27.939) Remain 67:23:44 loss: 0.2413 loss_seg: 0.1452 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:39:41,000 INFO misc.py line 117 726] Train: [3/20][497/510] Data 2.351 (3.782) Batch 25.203 (27.934) Remain 67:22:28 loss: 0.2485 loss_seg: 0.1565 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:40:15,004 INFO misc.py line 117 726] Train: [3/20][498/510] Data 3.699 (3.781) Batch 34.004 (27.946) Remain 67:23:47 loss: 0.2599 loss_seg: 0.1662 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:40:34,584 INFO misc.py line 117 726] Train: [3/20][499/510] Data 2.482 (3.779) Batch 19.580 (27.929) Remain 67:20:52 loss: 0.1965 loss_seg: 0.1019 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:41:14,123 INFO misc.py line 117 726] Train: [3/20][500/510] Data 6.008 (3.783) Batch 39.540 (27.952) Remain 67:23:47 loss: 0.3297 loss_seg: 0.2250 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:41:14,124 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 02:41:47,305 INFO misc.py line 117 726] Train: [3/20][501/510] Data 3.810 (3.783) Batch 33.182 (27.963) Remain 67:24:50 loss: 0.2228 loss_seg: 0.1330 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:42:17,448 INFO misc.py line 117 726] Train: [3/20][502/510] Data 5.918 (3.788) Batch 30.143 (27.967) Remain 67:25:00 loss: 0.4493 loss_seg: 0.3453 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:42:39,161 INFO misc.py line 117 726] Train: [3/20][503/510] Data 2.267 (3.785) Batch 21.713 (27.955) Remain 67:22:44 loss: 0.1706 loss_seg: 0.0878 loss_superpoint_edge: 0.0145 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:43:09,247 INFO misc.py line 117 726] Train: [3/20][504/510] Data 3.188 (3.783) Batch 30.087 (27.959) Remain 67:22:53 loss: 0.2610 loss_seg: 0.1666 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:43:29,881 INFO misc.py line 117 726] Train: [3/20][505/510] Data 2.464 (3.781) Batch 20.634 (27.945) Remain 67:20:18 loss: 0.2562 loss_seg: 0.1583 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:43:46,767 INFO misc.py line 117 726] Train: [3/20][506/510] Data 2.723 (3.779) Batch 16.886 (27.923) Remain 67:16:40 loss: 0.3322 loss_seg: 0.2128 loss_superpoint_edge: 0.0498 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0339 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:44:20,653 INFO misc.py line 117 726] Train: [3/20][507/510] Data 6.217 (3.783) Batch 33.886 (27.934) Remain 67:17:54 loss: 0.2825 loss_seg: 0.1852 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:44:56,880 INFO misc.py line 117 726] Train: [3/20][508/510] Data 4.870 (3.786) Batch 36.227 (27.951) Remain 67:19:49 loss: 0.2317 loss_seg: 0.1370 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:45:23,156 INFO misc.py line 117 726] Train: [3/20][509/510] Data 2.964 (3.784) Batch 26.276 (27.947) Remain 67:18:52 loss: 0.2587 loss_seg: 0.1657 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:45:51,666 INFO misc.py line 117 726] Train: [3/20][510/510] Data 4.422 (3.785) Batch 28.510 (27.949) Remain 67:18:34 loss: 0.2714 loss_seg: 0.1737 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 02:45:51,667 INFO misc.py line 147 726] Train result: loss: 0.2648 loss_seg: 0.1675 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 [2026-06-10 02:45:51,668 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-10 02:46:07,238 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7322 [2026-06-10 02:46:23,140 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6663 [2026-06-10 02:47:37,326 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 1.0323 [2026-06-10 02:48:17,210 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0388 [2026-06-10 02:48:36,424 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9691 [2026-06-10 02:49:12,194 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.1480 [2026-06-10 02:49:58,502 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1396 [2026-06-10 02:50:14,019 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2425 [2026-06-10 02:50:31,576 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.8543 [2026-06-10 02:50:50,131 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.5086 [2026-06-10 02:51:05,828 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5101 [2026-06-10 02:51:27,118 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.8196 [2026-06-10 02:51:52,800 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9181 [2026-06-10 02:52:04,215 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6997 [2026-06-10 02:52:35,223 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0521 [2026-06-10 02:53:00,948 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3480 [2026-06-10 02:53:27,302 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.4023 [2026-06-10 02:54:09,811 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.2286 [2026-06-10 02:54:30,673 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3772 [2026-06-10 02:54:47,018 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.7895 [2026-06-10 02:55:17,960 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.8417 [2026-06-10 02:55:34,101 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.5392 [2026-06-10 02:55:55,772 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3258 [2026-06-10 02:56:17,360 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7836 [2026-06-10 02:56:30,678 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.7237 [2026-06-10 02:56:58,375 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5107 [2026-06-10 02:57:39,627 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1873 [2026-06-10 02:57:56,917 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5493 [2026-06-10 02:58:15,515 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4091 [2026-06-10 02:58:32,203 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3881 [2026-06-10 02:58:57,026 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2757 [2026-06-10 02:59:15,058 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6018 [2026-06-10 02:59:32,487 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9423 [2026-06-10 02:59:56,707 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.8335 [2026-06-10 02:59:56,721 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6688/0.7411/0.8948. [2026-06-10 02:59:56,721 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9191/0.9541 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9759/0.9881 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8360/0.9718 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0008/0.0055 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3140/0.3651 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6036/0.6331 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6062/0.6877 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7942/0.9018 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9185/0.9581 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6712/0.7730 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7573/0.8428 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7058/0.8527 [2026-06-10 02:59:56,722 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5917/0.7009 [2026-06-10 02:59:56,722 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-10 02:59:56,723 INFO misc.py line 218 726] Currently Best mIoU: 0.6693 [2026-06-10 02:59:56,723 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 03:00:24,557 INFO misc.py line 117 726] Train: [4/20][1/510] Data 2.862 (2.862) Batch 26.297 (26.297) Remain 63:19:27 loss: 0.3259 loss_seg: 0.2198 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:00:53,035 INFO misc.py line 117 726] Train: [4/20][2/510] Data 3.660 (3.660) Batch 28.478 (28.478) Remain 68:34:06 loss: 0.2127 loss_seg: 0.1240 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:01:25,635 INFO misc.py line 117 726] Train: [4/20][3/510] Data 3.243 (3.243) Batch 32.600 (32.600) Remain 78:29:01 loss: 0.2396 loss_seg: 0.1419 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:01:48,625 INFO misc.py line 117 726] Train: [4/20][4/510] Data 3.887 (3.887) Batch 22.990 (22.990) Remain 55:20:33 loss: 0.3077 loss_seg: 0.2137 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:02:20,336 INFO misc.py line 117 726] Train: [4/20][5/510] Data 4.262 (4.075) Batch 31.711 (27.351) Remain 65:49:53 loss: 0.1831 loss_seg: 0.1002 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:02:49,299 INFO misc.py line 117 726] Train: [4/20][6/510] Data 5.166 (4.438) Batch 28.963 (27.888) Remain 67:07:01 loss: 0.2506 loss_seg: 0.1543 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:03:12,841 INFO misc.py line 117 726] Train: [4/20][7/510] Data 2.916 (4.058) Batch 23.542 (26.802) Remain 64:29:41 loss: 0.2210 loss_seg: 0.1262 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:03:35,003 INFO misc.py line 117 726] Train: [4/20][8/510] Data 1.897 (3.626) Batch 22.163 (25.874) Remain 62:15:18 loss: 0.2443 loss_seg: 0.1470 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:04:07,364 INFO misc.py line 117 726] Train: [4/20][9/510] Data 3.257 (3.564) Batch 32.361 (26.955) Remain 64:50:56 loss: 0.2461 loss_seg: 0.1497 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:04:37,773 INFO misc.py line 117 726] Train: [4/20][10/510] Data 5.910 (3.899) Batch 30.409 (27.448) Remain 66:01:42 loss: 0.2315 loss_seg: 0.1348 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:05:11,863 INFO misc.py line 117 726] Train: [4/20][11/510] Data 4.015 (3.914) Batch 34.090 (28.279) Remain 68:01:03 loss: 0.3113 loss_seg: 0.2031 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:05:48,849 INFO misc.py line 117 726] Train: [4/20][12/510] Data 6.054 (4.152) Batch 36.986 (29.246) Remain 70:20:12 loss: 0.2868 loss_seg: 0.1917 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:06:17,155 INFO misc.py line 117 726] Train: [4/20][13/510] Data 2.910 (4.028) Batch 28.306 (29.152) Remain 70:06:09 loss: 0.2330 loss_seg: 0.1386 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:06:47,949 INFO misc.py line 117 726] Train: [4/20][14/510] Data 3.773 (4.004) Batch 30.794 (29.301) Remain 70:27:12 loss: 0.2408 loss_seg: 0.1457 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:07:11,127 INFO misc.py line 117 726] Train: [4/20][15/510] Data 2.579 (3.886) Batch 23.178 (28.791) Remain 69:13:06 loss: 0.2201 loss_seg: 0.1295 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:07:44,335 INFO misc.py line 117 726] Train: [4/20][16/510] Data 4.443 (3.929) Batch 33.208 (29.131) Remain 70:01:37 loss: 0.2332 loss_seg: 0.1444 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:08:12,858 INFO misc.py line 117 726] Train: [4/20][17/510] Data 3.136 (3.872) Batch 28.523 (29.087) Remain 69:54:52 loss: 0.6495 loss_seg: 0.5260 loss_superpoint_edge: 0.0557 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:08:36,657 INFO misc.py line 117 726] Train: [4/20][18/510] Data 2.758 (3.798) Batch 23.799 (28.735) Remain 69:03:33 loss: 0.2597 loss_seg: 0.1596 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:09:01,218 INFO misc.py line 117 726] Train: [4/20][19/510] Data 2.678 (3.728) Batch 24.561 (28.474) Remain 68:25:28 loss: 0.2703 loss_seg: 0.1687 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:09:31,026 INFO misc.py line 117 726] Train: [4/20][20/510] Data 3.557 (3.718) Batch 29.808 (28.552) Remain 68:36:18 loss: 0.2108 loss_seg: 0.1202 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:09:53,931 INFO misc.py line 117 726] Train: [4/20][21/510] Data 2.511 (3.651) Batch 22.905 (28.239) Remain 67:50:36 loss: 0.2387 loss_seg: 0.1422 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:10:22,907 INFO misc.py line 117 726] Train: [4/20][22/510] Data 3.448 (3.640) Batch 28.975 (28.277) Remain 67:55:43 loss: 0.2895 loss_seg: 0.1893 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:10:43,515 INFO misc.py line 117 726] Train: [4/20][23/510] Data 1.849 (3.550) Batch 20.608 (27.894) Remain 66:59:59 loss: 0.2485 loss_seg: 0.1474 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:11:20,512 INFO misc.py line 117 726] Train: [4/20][24/510] Data 7.037 (3.716) Batch 36.996 (28.327) Remain 68:01:59 loss: 0.2527 loss_seg: 0.1607 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:11:54,810 INFO misc.py line 117 726] Train: [4/20][25/510] Data 6.287 (3.833) Batch 34.299 (28.599) Remain 68:40:37 loss: 0.2612 loss_seg: 0.1649 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:12:13,673 INFO misc.py line 117 726] Train: [4/20][26/510] Data 1.753 (3.743) Batch 18.863 (28.176) Remain 67:39:09 loss: 0.2009 loss_seg: 0.1143 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:12:40,790 INFO misc.py line 117 726] Train: [4/20][27/510] Data 3.254 (3.722) Batch 27.117 (28.131) Remain 67:32:20 loss: 0.2507 loss_seg: 0.1557 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:13:07,201 INFO misc.py line 117 726] Train: [4/20][28/510] Data 3.998 (3.734) Batch 26.411 (28.063) Remain 67:21:57 loss: 0.2745 loss_seg: 0.1831 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:13:32,351 INFO misc.py line 117 726] Train: [4/20][29/510] Data 3.486 (3.724) Batch 25.149 (27.951) Remain 67:05:21 loss: 0.2799 loss_seg: 0.1791 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:13:58,481 INFO misc.py line 117 726] Train: [4/20][30/510] Data 2.508 (3.679) Batch 26.130 (27.883) Remain 66:55:10 loss: 0.2675 loss_seg: 0.1718 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:14:28,039 INFO misc.py line 117 726] Train: [4/20][31/510] Data 2.955 (3.653) Batch 29.559 (27.943) Remain 67:03:19 loss: 0.2243 loss_seg: 0.1319 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:14:57,664 INFO misc.py line 117 726] Train: [4/20][32/510] Data 5.909 (3.731) Batch 29.624 (28.001) Remain 67:11:12 loss: 0.2371 loss_seg: 0.1428 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:15:22,382 INFO misc.py line 117 726] Train: [4/20][33/510] Data 2.513 (3.690) Batch 24.718 (27.892) Remain 66:54:59 loss: 0.2202 loss_seg: 0.1284 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:15:51,918 INFO misc.py line 117 726] Train: [4/20][34/510] Data 3.909 (3.697) Batch 29.536 (27.945) Remain 67:02:09 loss: 0.3512 loss_seg: 0.2353 loss_superpoint_edge: 0.0489 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:16:15,601 INFO misc.py line 117 726] Train: [4/20][35/510] Data 2.589 (3.663) Batch 23.683 (27.811) Remain 66:42:31 loss: 0.2404 loss_seg: 0.1421 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:16:43,526 INFO misc.py line 117 726] Train: [4/20][36/510] Data 4.914 (3.701) Batch 27.924 (27.815) Remain 66:42:33 loss: 0.2350 loss_seg: 0.1384 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:17:15,639 INFO misc.py line 117 726] Train: [4/20][37/510] Data 4.011 (3.710) Batch 32.113 (27.941) Remain 67:00:17 loss: 0.1934 loss_seg: 0.1064 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:18:00,272 INFO misc.py line 117 726] Train: [4/20][38/510] Data 14.837 (4.028) Batch 44.633 (28.418) Remain 68:08:25 loss: 0.2053 loss_seg: 0.1195 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:18:22,633 INFO misc.py line 117 726] Train: [4/20][39/510] Data 2.244 (3.978) Batch 22.361 (28.250) Remain 67:43:45 loss: 0.2341 loss_seg: 0.1370 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:18:44,383 INFO misc.py line 117 726] Train: [4/20][40/510] Data 2.058 (3.926) Batch 21.751 (28.074) Remain 67:18:01 loss: 0.2417 loss_seg: 0.1453 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:19:06,142 INFO misc.py line 117 726] Train: [4/20][41/510] Data 3.223 (3.908) Batch 21.758 (27.908) Remain 66:53:38 loss: 0.2118 loss_seg: 0.1232 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:19:36,289 INFO misc.py line 117 726] Train: [4/20][42/510] Data 3.243 (3.891) Batch 30.147 (27.965) Remain 67:01:26 loss: 0.2902 loss_seg: 0.1912 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:20:03,250 INFO misc.py line 117 726] Train: [4/20][43/510] Data 2.940 (3.867) Batch 26.961 (27.940) Remain 66:57:21 loss: 0.2935 loss_seg: 0.1888 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:20:30,274 INFO misc.py line 117 726] Train: [4/20][44/510] Data 2.937 (3.844) Batch 27.025 (27.918) Remain 66:53:41 loss: 0.3155 loss_seg: 0.2115 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:20:56,741 INFO misc.py line 117 726] Train: [4/20][45/510] Data 3.018 (3.825) Batch 26.467 (27.883) Remain 66:48:15 loss: 0.2442 loss_seg: 0.1415 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:21:28,715 INFO misc.py line 117 726] Train: [4/20][46/510] Data 4.277 (3.835) Batch 31.974 (27.979) Remain 67:01:27 loss: 0.2474 loss_seg: 0.1562 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:21:46,471 INFO misc.py line 117 726] Train: [4/20][47/510] Data 1.820 (3.789) Batch 17.756 (27.746) Remain 66:27:36 loss: 0.1949 loss_seg: 0.1010 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:22:14,218 INFO misc.py line 117 726] Train: [4/20][48/510] Data 3.743 (3.788) Batch 27.747 (27.746) Remain 66:27:08 loss: 0.4350 loss_seg: 0.3361 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:22:41,751 INFO misc.py line 117 726] Train: [4/20][49/510] Data 3.469 (3.781) Batch 27.533 (27.742) Remain 66:26:00 loss: 0.2083 loss_seg: 0.1186 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:23:15,535 INFO misc.py line 117 726] Train: [4/20][50/510] Data 4.484 (3.796) Batch 33.784 (27.870) Remain 66:44:01 loss: 0.3255 loss_seg: 0.2128 loss_superpoint_edge: 0.0450 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:23:15,535 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 03:23:47,167 INFO misc.py line 117 726] Train: [4/20][51/510] Data 3.639 (3.793) Batch 31.632 (27.949) Remain 66:54:48 loss: 0.1968 loss_seg: 0.1138 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:24:10,707 INFO misc.py line 117 726] Train: [4/20][52/510] Data 2.862 (3.774) Batch 23.540 (27.859) Remain 66:41:25 loss: 0.1958 loss_seg: 0.1056 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:24:45,555 INFO misc.py line 117 726] Train: [4/20][53/510] Data 3.159 (3.762) Batch 34.849 (27.998) Remain 67:01:02 loss: 0.2607 loss_seg: 0.1592 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:25:14,690 INFO misc.py line 117 726] Train: [4/20][54/510] Data 3.019 (3.747) Batch 29.135 (28.021) Remain 67:03:46 loss: 0.2850 loss_seg: 0.1835 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:25:43,511 INFO misc.py line 117 726] Train: [4/20][55/510] Data 4.698 (3.765) Batch 28.821 (28.036) Remain 67:05:30 loss: 0.3480 loss_seg: 0.2457 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:26:14,680 INFO misc.py line 117 726] Train: [4/20][56/510] Data 3.446 (3.759) Batch 31.169 (28.095) Remain 67:13:32 loss: 0.2240 loss_seg: 0.1293 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:26:45,534 INFO misc.py line 117 726] Train: [4/20][57/510] Data 3.403 (3.753) Batch 30.854 (28.146) Remain 67:20:23 loss: 0.2263 loss_seg: 0.1303 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:27:15,019 INFO misc.py line 117 726] Train: [4/20][58/510] Data 3.202 (3.743) Batch 29.485 (28.171) Remain 67:23:25 loss: 0.1983 loss_seg: 0.1104 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:27:45,144 INFO misc.py line 117 726] Train: [4/20][59/510] Data 3.327 (3.735) Batch 30.125 (28.206) Remain 67:27:57 loss: 0.3312 loss_seg: 0.2224 loss_superpoint_edge: 0.0404 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:28:14,259 INFO misc.py line 117 726] Train: [4/20][60/510] Data 2.917 (3.721) Batch 29.115 (28.221) Remain 67:29:46 loss: 0.2727 loss_seg: 0.1744 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:28:44,001 INFO misc.py line 117 726] Train: [4/20][61/510] Data 3.611 (3.719) Batch 29.742 (28.248) Remain 67:33:04 loss: 0.2574 loss_seg: 0.1592 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:29:12,638 INFO misc.py line 117 726] Train: [4/20][62/510] Data 5.261 (3.745) Batch 28.637 (28.254) Remain 67:33:32 loss: 0.2991 loss_seg: 0.2057 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:29:40,212 INFO misc.py line 117 726] Train: [4/20][63/510] Data 2.602 (3.726) Batch 27.574 (28.243) Remain 67:31:27 loss: 0.2518 loss_seg: 0.1549 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:30:12,029 INFO misc.py line 117 726] Train: [4/20][64/510] Data 4.142 (3.733) Batch 31.816 (28.302) Remain 67:39:22 loss: 0.2568 loss_seg: 0.1590 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:30:46,946 INFO misc.py line 117 726] Train: [4/20][65/510] Data 5.722 (3.765) Batch 34.917 (28.408) Remain 67:54:12 loss: 0.1908 loss_seg: 0.1079 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:31:13,118 INFO misc.py line 117 726] Train: [4/20][66/510] Data 2.843 (3.750) Batch 26.173 (28.373) Remain 67:48:39 loss: 0.2727 loss_seg: 0.1689 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:31:44,163 INFO misc.py line 117 726] Train: [4/20][67/510] Data 3.259 (3.743) Batch 31.044 (28.414) Remain 67:54:09 loss: 0.2444 loss_seg: 0.1519 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:32:12,410 INFO misc.py line 117 726] Train: [4/20][68/510] Data 3.592 (3.740) Batch 28.247 (28.412) Remain 67:53:19 loss: 0.2387 loss_seg: 0.1410 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:32:50,029 INFO misc.py line 117 726] Train: [4/20][69/510] Data 8.725 (3.816) Batch 37.619 (28.551) Remain 68:12:50 loss: 0.2551 loss_seg: 0.1571 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:33:24,217 INFO misc.py line 117 726] Train: [4/20][70/510] Data 5.294 (3.838) Batch 34.188 (28.636) Remain 68:24:25 loss: 0.3063 loss_seg: 0.1985 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0340 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:33:50,205 INFO misc.py line 117 726] Train: [4/20][71/510] Data 2.449 (3.818) Batch 25.987 (28.597) Remain 68:18:22 loss: 0.2792 loss_seg: 0.1786 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:34:13,183 INFO misc.py line 117 726] Train: [4/20][72/510] Data 2.411 (3.797) Batch 22.979 (28.515) Remain 68:06:13 loss: 0.2844 loss_seg: 0.1843 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:34:48,469 INFO misc.py line 117 726] Train: [4/20][73/510] Data 5.529 (3.822) Batch 35.285 (28.612) Remain 68:19:36 loss: 0.2622 loss_seg: 0.1661 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:35:19,764 INFO misc.py line 117 726] Train: [4/20][74/510] Data 3.114 (3.812) Batch 31.296 (28.650) Remain 68:24:32 loss: 0.2437 loss_seg: 0.1527 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:35:50,886 INFO misc.py line 117 726] Train: [4/20][75/510] Data 8.271 (3.874) Batch 31.122 (28.684) Remain 68:28:59 loss: 0.2241 loss_seg: 0.1285 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:36:27,505 INFO misc.py line 117 726] Train: [4/20][76/510] Data 5.829 (3.901) Batch 36.619 (28.793) Remain 68:44:04 loss: 0.2896 loss_seg: 0.2006 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:36:36,080 INFO misc.py line 117 726] Train: [4/20][77/510] Data 1.295 (3.866) Batch 8.575 (28.520) Remain 68:04:28 loss: 0.3056 loss_seg: 0.1967 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0430 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:37:15,236 INFO misc.py line 117 726] Train: [4/20][78/510] Data 6.054 (3.895) Batch 39.156 (28.661) Remain 68:24:18 loss: 0.2058 loss_seg: 0.1160 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:37:37,256 INFO misc.py line 117 726] Train: [4/20][79/510] Data 2.696 (3.879) Batch 22.020 (28.574) Remain 68:11:18 loss: 0.2059 loss_seg: 0.1146 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:38:08,619 INFO misc.py line 117 726] Train: [4/20][80/510] Data 4.449 (3.886) Batch 31.363 (28.610) Remain 68:16:01 loss: 0.2923 loss_seg: 0.1923 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:38:43,955 INFO misc.py line 117 726] Train: [4/20][81/510] Data 6.624 (3.921) Batch 35.336 (28.696) Remain 68:27:53 loss: 0.2411 loss_seg: 0.1476 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:39:14,121 INFO misc.py line 117 726] Train: [4/20][82/510] Data 5.950 (3.947) Batch 30.166 (28.715) Remain 68:30:04 loss: 0.4276 loss_seg: 0.3282 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:39:40,495 INFO misc.py line 117 726] Train: [4/20][83/510] Data 4.262 (3.951) Batch 26.374 (28.686) Remain 68:25:24 loss: 0.3298 loss_seg: 0.2325 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:40:12,174 INFO misc.py line 117 726] Train: [4/20][84/510] Data 4.536 (3.958) Batch 31.679 (28.723) Remain 68:30:13 loss: 0.2915 loss_seg: 0.1872 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:40:34,807 INFO misc.py line 117 726] Train: [4/20][85/510] Data 2.465 (3.940) Batch 22.633 (28.648) Remain 68:19:06 loss: 0.2466 loss_seg: 0.1506 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:41:06,231 INFO misc.py line 117 726] Train: [4/20][86/510] Data 5.343 (3.957) Batch 31.424 (28.682) Remain 68:23:25 loss: 0.2164 loss_seg: 0.1272 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:41:38,755 INFO misc.py line 117 726] Train: [4/20][87/510] Data 3.318 (3.949) Batch 32.524 (28.728) Remain 68:29:29 loss: 0.2566 loss_seg: 0.1588 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:42:11,895 INFO misc.py line 117 726] Train: [4/20][88/510] Data 5.061 (3.962) Batch 33.140 (28.780) Remain 68:36:25 loss: 0.2166 loss_seg: 0.1265 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:42:46,805 INFO misc.py line 117 726] Train: [4/20][89/510] Data 3.606 (3.958) Batch 34.910 (28.851) Remain 68:46:08 loss: 0.2127 loss_seg: 0.1201 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:43:18,805 INFO misc.py line 117 726] Train: [4/20][90/510] Data 3.507 (3.953) Batch 32.000 (28.887) Remain 68:50:50 loss: 0.3263 loss_seg: 0.2144 loss_superpoint_edge: 0.0448 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:43:58,281 INFO misc.py line 117 726] Train: [4/20][91/510] Data 5.240 (3.968) Batch 39.476 (29.007) Remain 69:07:34 loss: 0.2519 loss_seg: 0.1574 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:44:35,330 INFO misc.py line 117 726] Train: [4/20][92/510] Data 5.485 (3.985) Batch 37.048 (29.098) Remain 69:20:00 loss: 0.2639 loss_seg: 0.1588 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:44:58,234 INFO misc.py line 117 726] Train: [4/20][93/510] Data 2.637 (3.970) Batch 22.904 (29.029) Remain 69:09:40 loss: 0.2345 loss_seg: 0.1385 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:45:15,728 INFO misc.py line 117 726] Train: [4/20][94/510] Data 1.550 (3.943) Batch 17.495 (28.902) Remain 68:51:04 loss: 0.2119 loss_seg: 0.1228 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:45:44,951 INFO misc.py line 117 726] Train: [4/20][95/510] Data 3.676 (3.940) Batch 29.223 (28.906) Remain 68:51:05 loss: 0.3153 loss_seg: 0.2194 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:46:11,142 INFO misc.py line 117 726] Train: [4/20][96/510] Data 5.879 (3.961) Batch 26.190 (28.876) Remain 68:46:26 loss: 0.2812 loss_seg: 0.1795 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:46:34,412 INFO misc.py line 117 726] Train: [4/20][97/510] Data 3.334 (3.954) Batch 23.270 (28.817) Remain 68:37:26 loss: 0.3398 loss_seg: 0.2313 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:46:53,951 INFO misc.py line 117 726] Train: [4/20][98/510] Data 2.238 (3.936) Batch 19.540 (28.719) Remain 68:23:00 loss: 0.2117 loss_seg: 0.1209 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:47:19,189 INFO misc.py line 117 726] Train: [4/20][99/510] Data 2.940 (3.926) Batch 25.238 (28.683) Remain 68:17:20 loss: 0.3519 loss_seg: 0.2526 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:47:52,588 INFO misc.py line 117 726] Train: [4/20][100/510] Data 4.803 (3.935) Batch 33.399 (28.731) Remain 68:23:48 loss: 0.2707 loss_seg: 0.1678 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:47:52,589 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 03:48:16,994 INFO misc.py line 117 726] Train: [4/20][101/510] Data 5.602 (3.952) Batch 24.406 (28.687) Remain 68:17:01 loss: 0.2543 loss_seg: 0.1548 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:48:43,600 INFO misc.py line 117 726] Train: [4/20][102/510] Data 2.918 (3.942) Batch 26.606 (28.666) Remain 68:13:33 loss: 0.3126 loss_seg: 0.2008 loss_superpoint_edge: 0.0451 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:49:07,265 INFO misc.py line 117 726] Train: [4/20][103/510] Data 2.863 (3.931) Batch 23.664 (28.616) Remain 68:05:55 loss: 0.1949 loss_seg: 0.1030 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:49:46,470 INFO misc.py line 117 726] Train: [4/20][104/510] Data 6.439 (3.956) Batch 39.205 (28.721) Remain 68:20:25 loss: 0.2670 loss_seg: 0.1757 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:50:17,313 INFO misc.py line 117 726] Train: [4/20][105/510] Data 2.724 (3.944) Batch 30.843 (28.742) Remain 68:22:54 loss: 0.3045 loss_seg: 0.1912 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:50:38,028 INFO misc.py line 117 726] Train: [4/20][106/510] Data 2.616 (3.931) Batch 20.715 (28.664) Remain 68:11:18 loss: 0.2544 loss_seg: 0.1571 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:51:04,086 INFO misc.py line 117 726] Train: [4/20][107/510] Data 3.133 (3.923) Batch 26.057 (28.639) Remain 68:07:15 loss: 0.2414 loss_seg: 0.1440 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:51:33,622 INFO misc.py line 117 726] Train: [4/20][108/510] Data 2.601 (3.910) Batch 29.537 (28.647) Remain 68:07:59 loss: 0.3097 loss_seg: 0.2062 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:51:57,297 INFO misc.py line 117 726] Train: [4/20][109/510] Data 3.734 (3.909) Batch 23.675 (28.601) Remain 68:00:49 loss: 0.3429 loss_seg: 0.2236 loss_superpoint_edge: 0.0505 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:52:33,347 INFO misc.py line 117 726] Train: [4/20][110/510] Data 5.447 (3.923) Batch 36.049 (28.670) Remain 68:10:16 loss: 0.1847 loss_seg: 0.0995 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:53:02,653 INFO misc.py line 117 726] Train: [4/20][111/510] Data 3.348 (3.918) Batch 29.306 (28.676) Remain 68:10:38 loss: 0.2019 loss_seg: 0.1148 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:53:31,270 INFO misc.py line 117 726] Train: [4/20][112/510] Data 3.522 (3.914) Batch 28.617 (28.676) Remain 68:10:05 loss: 0.2326 loss_seg: 0.1392 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:53:59,452 INFO misc.py line 117 726] Train: [4/20][113/510] Data 3.009 (3.906) Batch 28.182 (28.671) Remain 68:08:58 loss: 0.2135 loss_seg: 0.1251 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:54:34,137 INFO misc.py line 117 726] Train: [4/20][114/510] Data 9.839 (3.959) Batch 34.685 (28.725) Remain 68:16:13 loss: 0.3149 loss_seg: 0.2102 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:55:05,554 INFO misc.py line 117 726] Train: [4/20][115/510] Data 3.369 (3.954) Batch 31.417 (28.749) Remain 68:19:10 loss: 0.2461 loss_seg: 0.1521 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:55:21,893 INFO misc.py line 117 726] Train: [4/20][116/510] Data 1.745 (3.935) Batch 16.339 (28.639) Remain 68:03:01 loss: 0.2025 loss_seg: 0.1121 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:55:51,477 INFO misc.py line 117 726] Train: [4/20][117/510] Data 4.289 (3.938) Batch 29.583 (28.648) Remain 68:03:44 loss: 0.2331 loss_seg: 0.1422 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:56:17,736 INFO misc.py line 117 726] Train: [4/20][118/510] Data 2.910 (3.929) Batch 26.260 (28.627) Remain 68:00:17 loss: 0.2649 loss_seg: 0.1648 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:56:52,837 INFO misc.py line 117 726] Train: [4/20][119/510] Data 4.521 (3.934) Batch 35.101 (28.683) Remain 68:07:46 loss: 0.3061 loss_seg: 0.1962 loss_superpoint_edge: 0.0427 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:57:13,352 INFO misc.py line 117 726] Train: [4/20][120/510] Data 2.153 (3.919) Batch 20.515 (28.613) Remain 67:57:20 loss: 0.2052 loss_seg: 0.1172 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:57:35,912 INFO misc.py line 117 726] Train: [4/20][121/510] Data 2.635 (3.908) Batch 22.560 (28.562) Remain 67:49:33 loss: 0.2289 loss_seg: 0.1369 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:58:00,823 INFO misc.py line 117 726] Train: [4/20][122/510] Data 2.694 (3.898) Batch 24.911 (28.531) Remain 67:44:42 loss: 0.2860 loss_seg: 0.1823 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:58:30,265 INFO misc.py line 117 726] Train: [4/20][123/510] Data 3.287 (3.892) Batch 29.442 (28.539) Remain 67:45:19 loss: 0.3080 loss_seg: 0.2061 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:58:49,818 INFO misc.py line 117 726] Train: [4/20][124/510] Data 2.966 (3.885) Batch 19.553 (28.464) Remain 67:34:16 loss: 0.2492 loss_seg: 0.1514 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:59:20,536 INFO misc.py line 117 726] Train: [4/20][125/510] Data 3.972 (3.886) Batch 30.718 (28.483) Remain 67:36:25 loss: 0.2299 loss_seg: 0.1459 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 03:59:53,131 INFO misc.py line 117 726] Train: [4/20][126/510] Data 2.818 (3.877) Batch 32.595 (28.516) Remain 67:40:42 loss: 0.2212 loss_seg: 0.1300 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:00:15,347 INFO misc.py line 117 726] Train: [4/20][127/510] Data 2.481 (3.866) Batch 22.216 (28.465) Remain 67:33:00 loss: 0.3653 loss_seg: 0.2650 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:00:34,881 INFO misc.py line 117 726] Train: [4/20][128/510] Data 1.955 (3.850) Batch 19.534 (28.394) Remain 67:22:21 loss: 0.2736 loss_seg: 0.1723 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:01:04,446 INFO misc.py line 117 726] Train: [4/20][129/510] Data 4.500 (3.856) Batch 29.565 (28.403) Remain 67:23:12 loss: 0.2480 loss_seg: 0.1579 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:01:27,107 INFO misc.py line 117 726] Train: [4/20][130/510] Data 3.516 (3.853) Batch 22.661 (28.358) Remain 67:16:17 loss: 0.3011 loss_seg: 0.1987 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:02:00,803 INFO misc.py line 117 726] Train: [4/20][131/510] Data 3.876 (3.853) Batch 33.696 (28.400) Remain 67:21:45 loss: 0.2398 loss_seg: 0.1461 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:02:18,307 INFO misc.py line 117 726] Train: [4/20][132/510] Data 1.560 (3.835) Batch 17.504 (28.315) Remain 67:09:15 loss: 0.2660 loss_seg: 0.1673 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:02:44,074 INFO misc.py line 117 726] Train: [4/20][133/510] Data 2.770 (3.827) Batch 25.767 (28.296) Remain 67:06:00 loss: 0.2553 loss_seg: 0.1579 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:03:09,398 INFO misc.py line 117 726] Train: [4/20][134/510] Data 2.806 (3.819) Batch 25.324 (28.273) Remain 67:02:18 loss: 0.2053 loss_seg: 0.1172 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:03:47,496 INFO misc.py line 117 726] Train: [4/20][135/510] Data 6.522 (3.840) Batch 38.098 (28.347) Remain 67:12:25 loss: 0.3047 loss_seg: 0.1961 loss_superpoint_edge: 0.0424 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:04:26,535 INFO misc.py line 117 726] Train: [4/20][136/510] Data 13.330 (3.911) Batch 39.039 (28.428) Remain 67:23:22 loss: 0.1786 loss_seg: 0.0944 loss_superpoint_edge: 0.0114 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:05:04,208 INFO misc.py line 117 726] Train: [4/20][137/510] Data 6.524 (3.931) Batch 37.674 (28.497) Remain 67:32:43 loss: 0.2682 loss_seg: 0.1684 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:05:34,546 INFO misc.py line 117 726] Train: [4/20][138/510] Data 6.100 (3.947) Batch 30.338 (28.510) Remain 67:34:11 loss: 0.2415 loss_seg: 0.1482 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:06:03,540 INFO misc.py line 117 726] Train: [4/20][139/510] Data 4.883 (3.954) Batch 28.994 (28.514) Remain 67:34:12 loss: 0.2728 loss_seg: 0.1821 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:06:31,144 INFO misc.py line 117 726] Train: [4/20][140/510] Data 2.812 (3.945) Batch 27.604 (28.507) Remain 67:32:47 loss: 0.2598 loss_seg: 0.1609 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:06:59,762 INFO misc.py line 117 726] Train: [4/20][141/510] Data 2.783 (3.937) Batch 28.618 (28.508) Remain 67:32:26 loss: 0.2346 loss_seg: 0.1452 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:07:18,446 INFO misc.py line 117 726] Train: [4/20][142/510] Data 2.707 (3.928) Batch 18.685 (28.437) Remain 67:21:54 loss: 0.3046 loss_seg: 0.1973 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:07:47,870 INFO misc.py line 117 726] Train: [4/20][143/510] Data 4.644 (3.933) Batch 29.424 (28.445) Remain 67:22:26 loss: 0.2679 loss_seg: 0.1738 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:08:05,940 INFO misc.py line 117 726] Train: [4/20][144/510] Data 2.507 (3.923) Batch 18.069 (28.371) Remain 67:11:30 loss: 0.3094 loss_seg: 0.2026 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:08:44,076 INFO misc.py line 117 726] Train: [4/20][145/510] Data 5.745 (3.936) Batch 38.136 (28.440) Remain 67:20:48 loss: 0.3004 loss_seg: 0.1944 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:09:10,827 INFO misc.py line 117 726] Train: [4/20][146/510] Data 3.714 (3.934) Batch 26.751 (28.428) Remain 67:18:39 loss: 0.2386 loss_seg: 0.1459 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:09:42,154 INFO misc.py line 117 726] Train: [4/20][147/510] Data 3.579 (3.932) Batch 31.327 (28.448) Remain 67:21:02 loss: 0.2010 loss_seg: 0.1119 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:10:05,014 INFO misc.py line 117 726] Train: [4/20][148/510] Data 2.303 (3.921) Batch 22.861 (28.410) Remain 67:15:05 loss: 0.4249 loss_seg: 0.3090 loss_superpoint_edge: 0.0482 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:10:30,294 INFO misc.py line 117 726] Train: [4/20][149/510] Data 2.487 (3.911) Batch 25.280 (28.388) Remain 67:11:34 loss: 0.3241 loss_seg: 0.2245 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:11:03,294 INFO misc.py line 117 726] Train: [4/20][150/510] Data 4.946 (3.918) Batch 33.000 (28.419) Remain 67:15:33 loss: 0.2143 loss_seg: 0.1256 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:11:03,295 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 04:11:36,994 INFO misc.py line 117 726] Train: [4/20][151/510] Data 4.082 (3.919) Batch 33.700 (28.455) Remain 67:20:09 loss: 0.2128 loss_seg: 0.1212 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:12:09,751 INFO misc.py line 117 726] Train: [4/20][152/510] Data 5.889 (3.932) Batch 32.757 (28.484) Remain 67:23:46 loss: 0.3031 loss_seg: 0.2008 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:12:33,484 INFO misc.py line 117 726] Train: [4/20][153/510] Data 2.972 (3.926) Batch 23.734 (28.452) Remain 67:18:48 loss: 0.2473 loss_seg: 0.1497 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:13:07,263 INFO misc.py line 117 726] Train: [4/20][154/510] Data 4.301 (3.928) Batch 33.778 (28.488) Remain 67:23:20 loss: 0.3220 loss_seg: 0.2180 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:13:43,505 INFO misc.py line 117 726] Train: [4/20][155/510] Data 7.162 (3.949) Batch 36.242 (28.539) Remain 67:30:06 loss: 0.2137 loss_seg: 0.1221 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:14:08,619 INFO misc.py line 117 726] Train: [4/20][156/510] Data 2.797 (3.942) Batch 25.115 (28.516) Remain 67:26:27 loss: 0.2093 loss_seg: 0.1168 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:14:37,711 INFO misc.py line 117 726] Train: [4/20][157/510] Data 3.942 (3.942) Batch 29.091 (28.520) Remain 67:26:30 loss: 0.2199 loss_seg: 0.1302 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:14:54,284 INFO misc.py line 117 726] Train: [4/20][158/510] Data 2.000 (3.929) Batch 16.573 (28.443) Remain 67:15:05 loss: 0.2194 loss_seg: 0.1299 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:15:19,189 INFO misc.py line 117 726] Train: [4/20][159/510] Data 2.717 (3.922) Batch 24.906 (28.420) Remain 67:11:24 loss: 0.3591 loss_seg: 0.2597 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:15:57,448 INFO misc.py line 117 726] Train: [4/20][160/510] Data 4.091 (3.923) Batch 38.259 (28.483) Remain 67:19:49 loss: 0.2566 loss_seg: 0.1593 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:16:16,641 INFO misc.py line 117 726] Train: [4/20][161/510] Data 2.238 (3.912) Batch 19.194 (28.424) Remain 67:11:00 loss: 0.2767 loss_seg: 0.1721 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:16:42,867 INFO misc.py line 117 726] Train: [4/20][162/510] Data 3.067 (3.907) Batch 26.226 (28.410) Remain 67:08:34 loss: 0.2324 loss_seg: 0.1396 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:17:14,275 INFO misc.py line 117 726] Train: [4/20][163/510] Data 4.052 (3.908) Batch 31.408 (28.429) Remain 67:10:45 loss: 0.2824 loss_seg: 0.1767 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:17:47,814 INFO misc.py line 117 726] Train: [4/20][164/510] Data 3.958 (3.908) Batch 33.538 (28.461) Remain 67:14:47 loss: 0.2166 loss_seg: 0.1266 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:18:21,284 INFO misc.py line 117 726] Train: [4/20][165/510] Data 5.075 (3.915) Batch 33.470 (28.492) Remain 67:18:41 loss: 0.2648 loss_seg: 0.1674 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:18:48,075 INFO misc.py line 117 726] Train: [4/20][166/510] Data 2.675 (3.908) Batch 26.791 (28.481) Remain 67:16:44 loss: 0.2108 loss_seg: 0.1219 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:19:12,738 INFO misc.py line 117 726] Train: [4/20][167/510] Data 3.056 (3.902) Batch 24.663 (28.458) Remain 67:12:57 loss: 0.2922 loss_seg: 0.1882 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:19:42,608 INFO misc.py line 117 726] Train: [4/20][168/510] Data 5.416 (3.911) Batch 29.870 (28.467) Remain 67:13:42 loss: 0.2327 loss_seg: 0.1414 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:20:06,029 INFO misc.py line 117 726] Train: [4/20][169/510] Data 2.074 (3.900) Batch 23.421 (28.436) Remain 67:08:55 loss: 0.2727 loss_seg: 0.1702 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:20:24,954 INFO misc.py line 117 726] Train: [4/20][170/510] Data 1.910 (3.889) Batch 18.924 (28.379) Remain 67:00:22 loss: 0.2425 loss_seg: 0.1460 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:20:52,569 INFO misc.py line 117 726] Train: [4/20][171/510] Data 2.512 (3.880) Batch 27.615 (28.375) Remain 66:59:15 loss: 0.2276 loss_seg: 0.1338 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:21:24,131 INFO misc.py line 117 726] Train: [4/20][172/510] Data 3.305 (3.877) Batch 31.562 (28.393) Remain 67:01:27 loss: 0.2182 loss_seg: 0.1262 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:21:56,492 INFO misc.py line 117 726] Train: [4/20][173/510] Data 3.047 (3.872) Batch 32.361 (28.417) Remain 67:04:17 loss: 0.2178 loss_seg: 0.1273 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:22:22,877 INFO misc.py line 117 726] Train: [4/20][174/510] Data 4.303 (3.875) Batch 26.385 (28.405) Remain 67:02:08 loss: 0.3168 loss_seg: 0.2134 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:22:50,707 INFO misc.py line 117 726] Train: [4/20][175/510] Data 2.992 (3.869) Batch 27.829 (28.402) Remain 67:01:11 loss: 0.2448 loss_seg: 0.1496 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:23:25,709 INFO misc.py line 117 726] Train: [4/20][176/510] Data 5.423 (3.878) Batch 35.003 (28.440) Remain 67:06:07 loss: 0.2569 loss_seg: 0.1571 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:24:01,631 INFO misc.py line 117 726] Train: [4/20][177/510] Data 4.955 (3.885) Batch 35.922 (28.483) Remain 67:11:43 loss: 0.2347 loss_seg: 0.1504 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:24:25,057 INFO misc.py line 117 726] Train: [4/20][178/510] Data 2.245 (3.875) Batch 23.425 (28.454) Remain 67:07:09 loss: 0.2762 loss_seg: 0.1757 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:24:46,156 INFO misc.py line 117 726] Train: [4/20][179/510] Data 2.662 (3.868) Batch 21.099 (28.412) Remain 67:00:46 loss: 0.2593 loss_seg: 0.1622 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:25:12,299 INFO misc.py line 117 726] Train: [4/20][180/510] Data 3.493 (3.866) Batch 26.143 (28.399) Remain 66:58:29 loss: 0.2090 loss_seg: 0.1173 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:25:45,885 INFO misc.py line 117 726] Train: [4/20][181/510] Data 3.274 (3.863) Batch 33.585 (28.428) Remain 67:02:08 loss: 0.2162 loss_seg: 0.1256 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:26:08,990 INFO misc.py line 117 726] Train: [4/20][182/510] Data 2.083 (3.853) Batch 23.106 (28.399) Remain 66:57:27 loss: 0.2150 loss_seg: 0.1188 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:26:40,527 INFO misc.py line 117 726] Train: [4/20][183/510] Data 3.585 (3.851) Batch 31.537 (28.416) Remain 66:59:27 loss: 0.2418 loss_seg: 0.1463 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:27:13,389 INFO misc.py line 117 726] Train: [4/20][184/510] Data 3.190 (3.848) Batch 32.862 (28.441) Remain 67:02:27 loss: 0.2377 loss_seg: 0.1454 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:27:46,291 INFO misc.py line 117 726] Train: [4/20][185/510] Data 3.238 (3.844) Batch 32.902 (28.465) Remain 67:05:26 loss: 0.2762 loss_seg: 0.1753 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:28:06,202 INFO misc.py line 117 726] Train: [4/20][186/510] Data 2.472 (3.837) Batch 19.910 (28.418) Remain 66:58:21 loss: 0.2014 loss_seg: 0.1130 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:28:44,455 INFO misc.py line 117 726] Train: [4/20][187/510] Data 5.184 (3.844) Batch 38.253 (28.472) Remain 67:05:26 loss: 0.3110 loss_seg: 0.2166 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:29:14,428 INFO misc.py line 117 726] Train: [4/20][188/510] Data 3.256 (3.841) Batch 29.973 (28.480) Remain 67:06:07 loss: 0.2518 loss_seg: 0.1505 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:29:37,663 INFO misc.py line 117 726] Train: [4/20][189/510] Data 2.162 (3.832) Batch 23.235 (28.452) Remain 67:01:39 loss: 0.2395 loss_seg: 0.1417 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:30:05,080 INFO misc.py line 117 726] Train: [4/20][190/510] Data 3.041 (3.828) Batch 27.417 (28.446) Remain 67:00:24 loss: 0.2217 loss_seg: 0.1299 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:30:27,785 INFO misc.py line 117 726] Train: [4/20][191/510] Data 2.519 (3.821) Batch 22.705 (28.416) Remain 66:55:36 loss: 0.2122 loss_seg: 0.1190 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:30:58,960 INFO misc.py line 117 726] Train: [4/20][192/510] Data 5.525 (3.830) Batch 31.175 (28.430) Remain 66:57:12 loss: 0.3466 loss_seg: 0.2460 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:31:24,880 INFO misc.py line 117 726] Train: [4/20][193/510] Data 2.950 (3.825) Batch 25.919 (28.417) Remain 66:54:51 loss: 0.2823 loss_seg: 0.1806 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:31:54,364 INFO misc.py line 117 726] Train: [4/20][194/510] Data 5.730 (3.835) Batch 29.485 (28.423) Remain 66:55:10 loss: 0.3215 loss_seg: 0.2236 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:32:11,609 INFO misc.py line 117 726] Train: [4/20][195/510] Data 1.932 (3.825) Batch 17.244 (28.364) Remain 66:46:28 loss: 0.3221 loss_seg: 0.2219 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:32:41,921 INFO misc.py line 117 726] Train: [4/20][196/510] Data 2.225 (3.817) Batch 30.312 (28.375) Remain 66:47:25 loss: 0.1966 loss_seg: 0.1090 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:33:15,231 INFO misc.py line 117 726] Train: [4/20][197/510] Data 6.499 (3.831) Batch 33.310 (28.400) Remain 66:50:32 loss: 0.2673 loss_seg: 0.1649 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:33:48,125 INFO misc.py line 117 726] Train: [4/20][198/510] Data 3.851 (3.831) Batch 32.895 (28.423) Remain 66:53:19 loss: 0.2628 loss_seg: 0.1647 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:34:18,613 INFO misc.py line 117 726] Train: [4/20][199/510] Data 3.499 (3.829) Batch 30.487 (28.434) Remain 66:54:20 loss: 0.2654 loss_seg: 0.1655 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:34:44,511 INFO misc.py line 117 726] Train: [4/20][200/510] Data 2.731 (3.824) Batch 25.899 (28.421) Remain 66:52:03 loss: 0.2333 loss_seg: 0.1368 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:34:44,512 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 04:35:16,522 INFO misc.py line 117 726] Train: [4/20][201/510] Data 3.387 (3.821) Batch 32.010 (28.439) Remain 66:54:08 loss: 0.2019 loss_seg: 0.1107 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:35:41,406 INFO misc.py line 117 726] Train: [4/20][202/510] Data 2.607 (3.815) Batch 24.885 (28.421) Remain 66:51:08 loss: 0.2497 loss_seg: 0.1532 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:36:11,135 INFO misc.py line 117 726] Train: [4/20][203/510] Data 3.414 (3.813) Batch 29.729 (28.427) Remain 66:51:35 loss: 0.1927 loss_seg: 0.1068 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:36:49,583 INFO misc.py line 117 726] Train: [4/20][204/510] Data 7.355 (3.831) Batch 38.448 (28.477) Remain 66:58:09 loss: 0.3007 loss_seg: 0.2017 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:37:12,437 INFO misc.py line 117 726] Train: [4/20][205/510] Data 2.680 (3.825) Batch 22.855 (28.450) Remain 66:53:45 loss: 0.2918 loss_seg: 0.1880 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:37:46,868 INFO misc.py line 117 726] Train: [4/20][206/510] Data 6.553 (3.839) Batch 34.430 (28.479) Remain 66:57:26 loss: 0.3876 loss_seg: 0.2825 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:38:13,322 INFO misc.py line 117 726] Train: [4/20][207/510] Data 2.735 (3.833) Batch 26.455 (28.469) Remain 66:55:33 loss: 0.2258 loss_seg: 0.1346 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:38:44,986 INFO misc.py line 117 726] Train: [4/20][208/510] Data 2.821 (3.828) Batch 31.663 (28.485) Remain 66:57:16 loss: 0.2315 loss_seg: 0.1398 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:39:13,619 INFO misc.py line 117 726] Train: [4/20][209/510] Data 3.848 (3.828) Batch 28.633 (28.485) Remain 66:56:54 loss: 0.2419 loss_seg: 0.1420 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:39:44,559 INFO misc.py line 117 726] Train: [4/20][210/510] Data 4.612 (3.832) Batch 30.940 (28.497) Remain 66:58:06 loss: 0.1779 loss_seg: 0.0924 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:40:07,458 INFO misc.py line 117 726] Train: [4/20][211/510] Data 2.787 (3.827) Batch 22.899 (28.470) Remain 66:53:50 loss: 0.2137 loss_seg: 0.1217 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:40:32,666 INFO misc.py line 117 726] Train: [4/20][212/510] Data 5.639 (3.836) Batch 25.208 (28.455) Remain 66:51:09 loss: 0.3230 loss_seg: 0.2225 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:40:53,080 INFO misc.py line 117 726] Train: [4/20][213/510] Data 3.059 (3.832) Batch 20.414 (28.416) Remain 66:45:17 loss: 0.2147 loss_seg: 0.1226 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:41:20,155 INFO misc.py line 117 726] Train: [4/20][214/510] Data 2.329 (3.825) Batch 27.075 (28.410) Remain 66:43:55 loss: 0.1979 loss_seg: 0.1096 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:41:50,495 INFO misc.py line 117 726] Train: [4/20][215/510] Data 2.776 (3.820) Batch 30.340 (28.419) Remain 66:44:43 loss: 0.2306 loss_seg: 0.1319 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:42:25,154 INFO misc.py line 117 726] Train: [4/20][216/510] Data 4.302 (3.822) Batch 34.659 (28.448) Remain 66:48:23 loss: 0.2378 loss_seg: 0.1442 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:42:53,805 INFO misc.py line 117 726] Train: [4/20][217/510] Data 2.802 (3.818) Batch 28.650 (28.449) Remain 66:48:02 loss: 0.2555 loss_seg: 0.1586 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:43:16,797 INFO misc.py line 117 726] Train: [4/20][218/510] Data 3.095 (3.814) Batch 22.992 (28.424) Remain 66:43:59 loss: 0.2094 loss_seg: 0.1162 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:43:52,009 INFO misc.py line 117 726] Train: [4/20][219/510] Data 4.605 (3.818) Batch 35.213 (28.455) Remain 66:47:56 loss: 0.2070 loss_seg: 0.1194 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:44:24,328 INFO misc.py line 117 726] Train: [4/20][220/510] Data 3.953 (3.819) Batch 32.319 (28.473) Remain 66:49:58 loss: 0.2047 loss_seg: 0.1160 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:44:41,034 INFO misc.py line 117 726] Train: [4/20][221/510] Data 2.068 (3.811) Batch 16.706 (28.419) Remain 66:41:54 loss: 0.2414 loss_seg: 0.1403 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:45:04,691 INFO misc.py line 117 726] Train: [4/20][222/510] Data 3.063 (3.807) Batch 23.658 (28.398) Remain 66:38:22 loss: 0.3127 loss_seg: 0.2076 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:45:27,120 INFO misc.py line 117 726] Train: [4/20][223/510] Data 3.502 (3.806) Batch 22.428 (28.370) Remain 66:34:04 loss: 0.2447 loss_seg: 0.1498 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:45:58,775 INFO misc.py line 117 726] Train: [4/20][224/510] Data 3.425 (3.804) Batch 31.655 (28.385) Remain 66:35:41 loss: 0.2857 loss_seg: 0.1903 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:46:26,393 INFO misc.py line 117 726] Train: [4/20][225/510] Data 6.510 (3.816) Batch 27.618 (28.382) Remain 66:34:44 loss: 0.2919 loss_seg: 0.2010 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0450 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:46:53,108 INFO misc.py line 117 726] Train: [4/20][226/510] Data 2.444 (3.810) Batch 26.716 (28.374) Remain 66:33:12 loss: 0.2030 loss_seg: 0.1133 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:47:25,601 INFO misc.py line 117 726] Train: [4/20][227/510] Data 3.077 (3.807) Batch 32.493 (28.393) Remain 66:35:19 loss: 0.1722 loss_seg: 0.0885 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:47:55,286 INFO misc.py line 117 726] Train: [4/20][228/510] Data 3.149 (3.804) Batch 29.685 (28.398) Remain 66:35:39 loss: 0.3607 loss_seg: 0.2570 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:48:27,415 INFO misc.py line 117 726] Train: [4/20][229/510] Data 4.681 (3.808) Batch 32.129 (28.415) Remain 66:37:30 loss: 0.2018 loss_seg: 0.1144 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:48:59,171 INFO misc.py line 117 726] Train: [4/20][230/510] Data 4.823 (3.812) Batch 31.756 (28.430) Remain 66:39:06 loss: 0.2183 loss_seg: 0.1286 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:49:35,702 INFO misc.py line 117 726] Train: [4/20][231/510] Data 4.316 (3.814) Batch 36.531 (28.465) Remain 66:43:37 loss: 0.2378 loss_seg: 0.1459 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:50:01,518 INFO misc.py line 117 726] Train: [4/20][232/510] Data 2.174 (3.807) Batch 25.816 (28.454) Remain 66:41:31 loss: 0.3060 loss_seg: 0.1971 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:50:20,169 INFO misc.py line 117 726] Train: [4/20][233/510] Data 2.589 (3.802) Batch 18.651 (28.411) Remain 66:35:03 loss: 0.2645 loss_seg: 0.1646 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:50:51,684 INFO misc.py line 117 726] Train: [4/20][234/510] Data 4.810 (3.806) Batch 31.516 (28.424) Remain 66:36:28 loss: 0.2647 loss_seg: 0.1684 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:51:20,092 INFO misc.py line 117 726] Train: [4/20][235/510] Data 3.140 (3.803) Batch 28.407 (28.424) Remain 66:35:59 loss: 0.2063 loss_seg: 0.1183 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:51:44,293 INFO misc.py line 117 726] Train: [4/20][236/510] Data 3.468 (3.802) Batch 24.201 (28.406) Remain 66:32:58 loss: 0.2465 loss_seg: 0.1533 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:52:10,426 INFO misc.py line 117 726] Train: [4/20][237/510] Data 4.904 (3.807) Batch 26.133 (28.397) Remain 66:31:08 loss: 0.3596 loss_seg: 0.2596 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:52:39,903 INFO misc.py line 117 726] Train: [4/20][238/510] Data 3.702 (3.806) Batch 29.477 (28.401) Remain 66:31:18 loss: 0.2784 loss_seg: 0.1791 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:53:11,314 INFO misc.py line 117 726] Train: [4/20][239/510] Data 4.897 (3.811) Batch 31.411 (28.414) Remain 66:32:37 loss: 0.2172 loss_seg: 0.1277 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:53:44,980 INFO misc.py line 117 726] Train: [4/20][240/510] Data 5.892 (3.820) Batch 33.666 (28.436) Remain 66:35:15 loss: 0.2755 loss_seg: 0.1792 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:54:17,523 INFO misc.py line 117 726] Train: [4/20][241/510] Data 3.816 (3.820) Batch 32.543 (28.453) Remain 66:37:12 loss: 0.2608 loss_seg: 0.1687 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:54:56,050 INFO misc.py line 117 726] Train: [4/20][242/510] Data 9.785 (3.845) Batch 38.527 (28.495) Remain 66:42:39 loss: 0.1971 loss_seg: 0.1029 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:55:33,662 INFO misc.py line 117 726] Train: [4/20][243/510] Data 10.634 (3.873) Batch 37.612 (28.533) Remain 66:47:31 loss: 0.2032 loss_seg: 0.1141 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:56:00,025 INFO misc.py line 117 726] Train: [4/20][244/510] Data 3.671 (3.872) Batch 26.363 (28.524) Remain 66:45:46 loss: 0.2121 loss_seg: 0.1259 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:56:31,039 INFO misc.py line 117 726] Train: [4/20][245/510] Data 4.976 (3.877) Batch 31.014 (28.535) Remain 66:46:45 loss: 0.2653 loss_seg: 0.1709 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:56:56,347 INFO misc.py line 117 726] Train: [4/20][246/510] Data 3.253 (3.874) Batch 25.307 (28.521) Remain 66:44:24 loss: 0.2062 loss_seg: 0.1123 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:57:29,217 INFO misc.py line 117 726] Train: [4/20][247/510] Data 3.800 (3.874) Batch 32.871 (28.539) Remain 66:46:26 loss: 0.2054 loss_seg: 0.1153 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:58:07,843 INFO misc.py line 117 726] Train: [4/20][248/510] Data 7.934 (3.890) Batch 38.626 (28.580) Remain 66:51:44 loss: 0.2103 loss_seg: 0.1214 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:58:32,346 INFO misc.py line 117 726] Train: [4/20][249/510] Data 3.122 (3.887) Batch 24.503 (28.564) Remain 66:48:56 loss: 0.2733 loss_seg: 0.1757 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:59:02,326 INFO misc.py line 117 726] Train: [4/20][250/510] Data 4.124 (3.888) Batch 29.980 (28.570) Remain 66:49:16 loss: 0.2799 loss_seg: 0.1872 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 04:59:02,327 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 04:59:33,656 INFO misc.py line 117 726] Train: [4/20][251/510] Data 4.139 (3.889) Batch 31.329 (28.581) Remain 66:50:21 loss: 0.1864 loss_seg: 0.1012 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:00:03,758 INFO misc.py line 117 726] Train: [4/20][252/510] Data 3.915 (3.889) Batch 30.102 (28.587) Remain 66:50:43 loss: 0.2190 loss_seg: 0.1257 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:00:28,123 INFO misc.py line 117 726] Train: [4/20][253/510] Data 2.527 (3.884) Batch 24.366 (28.570) Remain 66:47:53 loss: 0.2537 loss_seg: 0.1552 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:00:56,514 INFO misc.py line 117 726] Train: [4/20][254/510] Data 3.012 (3.880) Batch 28.390 (28.569) Remain 66:47:18 loss: 0.2157 loss_seg: 0.1223 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:01:24,212 INFO misc.py line 117 726] Train: [4/20][255/510] Data 3.175 (3.878) Batch 27.698 (28.566) Remain 66:46:21 loss: 0.1882 loss_seg: 0.1029 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:01:57,147 INFO misc.py line 117 726] Train: [4/20][256/510] Data 3.254 (3.875) Batch 32.935 (28.583) Remain 66:48:17 loss: 0.2335 loss_seg: 0.1422 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:02:24,012 INFO misc.py line 117 726] Train: [4/20][257/510] Data 3.026 (3.872) Batch 26.866 (28.576) Remain 66:46:52 loss: 0.3038 loss_seg: 0.2051 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:02:59,658 INFO misc.py line 117 726] Train: [4/20][258/510] Data 4.651 (3.875) Batch 35.646 (28.604) Remain 66:50:16 loss: 0.2547 loss_seg: 0.1581 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:03:29,213 INFO misc.py line 117 726] Train: [4/20][259/510] Data 4.732 (3.878) Batch 29.555 (28.608) Remain 66:50:19 loss: 0.3122 loss_seg: 0.2085 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:03:59,024 INFO misc.py line 117 726] Train: [4/20][260/510] Data 2.897 (3.874) Batch 29.810 (28.612) Remain 66:50:30 loss: 0.2336 loss_seg: 0.1371 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:04:23,495 INFO misc.py line 117 726] Train: [4/20][261/510] Data 3.259 (3.872) Batch 24.471 (28.596) Remain 66:47:46 loss: 0.3347 loss_seg: 0.2367 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:04:54,924 INFO misc.py line 117 726] Train: [4/20][262/510] Data 3.860 (3.872) Batch 31.429 (28.607) Remain 66:48:50 loss: 0.3067 loss_seg: 0.2073 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:05:21,409 INFO misc.py line 117 726] Train: [4/20][263/510] Data 4.066 (3.873) Batch 26.486 (28.599) Remain 66:47:12 loss: 0.2988 loss_seg: 0.1968 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:05:47,324 INFO misc.py line 117 726] Train: [4/20][264/510] Data 3.204 (3.870) Batch 25.914 (28.589) Remain 66:45:17 loss: 0.3024 loss_seg: 0.1958 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:06:05,057 INFO misc.py line 117 726] Train: [4/20][265/510] Data 2.231 (3.864) Batch 17.734 (28.547) Remain 66:39:00 loss: 0.2550 loss_seg: 0.1559 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:06:24,438 INFO misc.py line 117 726] Train: [4/20][266/510] Data 2.407 (3.858) Batch 19.380 (28.513) Remain 66:33:39 loss: 0.1921 loss_seg: 0.1034 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:06:45,760 INFO misc.py line 117 726] Train: [4/20][267/510] Data 2.288 (3.852) Batch 21.322 (28.485) Remain 66:29:22 loss: 0.2467 loss_seg: 0.1532 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:07:04,545 INFO misc.py line 117 726] Train: [4/20][268/510] Data 1.681 (3.844) Batch 18.785 (28.449) Remain 66:23:46 loss: 0.2891 loss_seg: 0.1870 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:07:31,507 INFO misc.py line 117 726] Train: [4/20][269/510] Data 2.796 (3.840) Batch 26.962 (28.443) Remain 66:22:30 loss: 0.2965 loss_seg: 0.1892 loss_superpoint_edge: 0.0419 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:08:03,933 INFO misc.py line 117 726] Train: [4/20][270/510] Data 4.578 (3.843) Batch 32.426 (28.458) Remain 66:24:07 loss: 0.2812 loss_seg: 0.1796 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:08:33,518 INFO misc.py line 117 726] Train: [4/20][271/510] Data 3.285 (3.841) Batch 29.585 (28.462) Remain 66:24:14 loss: 0.2567 loss_seg: 0.1590 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:08:59,588 INFO misc.py line 117 726] Train: [4/20][272/510] Data 3.089 (3.838) Batch 26.069 (28.453) Remain 66:22:31 loss: 0.2310 loss_seg: 0.1348 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:09:27,713 INFO misc.py line 117 726] Train: [4/20][273/510] Data 3.023 (3.835) Batch 28.125 (28.452) Remain 66:21:52 loss: 0.2538 loss_seg: 0.1575 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:09:51,287 INFO misc.py line 117 726] Train: [4/20][274/510] Data 4.415 (3.837) Batch 23.574 (28.434) Remain 66:18:53 loss: 0.2627 loss_seg: 0.1629 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:10:29,769 INFO misc.py line 117 726] Train: [4/20][275/510] Data 11.887 (3.867) Batch 38.482 (28.471) Remain 66:23:34 loss: 0.2693 loss_seg: 0.1676 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:10:53,194 INFO misc.py line 117 726] Train: [4/20][276/510] Data 2.815 (3.863) Batch 23.425 (28.453) Remain 66:20:31 loss: 0.2432 loss_seg: 0.1429 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0445 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:11:24,386 INFO misc.py line 117 726] Train: [4/20][277/510] Data 3.695 (3.862) Batch 31.192 (28.463) Remain 66:21:26 loss: 0.3507 loss_seg: 0.2319 loss_superpoint_edge: 0.0526 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:11:55,181 INFO misc.py line 117 726] Train: [4/20][278/510] Data 4.702 (3.865) Batch 30.795 (28.471) Remain 66:22:09 loss: 0.3622 loss_seg: 0.2390 loss_superpoint_edge: 0.0548 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:12:23,585 INFO misc.py line 117 726] Train: [4/20][279/510] Data 2.363 (3.860) Batch 28.403 (28.471) Remain 66:21:38 loss: 0.2186 loss_seg: 0.1267 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:12:48,148 INFO misc.py line 117 726] Train: [4/20][280/510] Data 2.738 (3.856) Batch 24.563 (28.457) Remain 66:19:11 loss: 0.3308 loss_seg: 0.2261 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:13:12,840 INFO misc.py line 117 726] Train: [4/20][281/510] Data 1.988 (3.849) Batch 24.692 (28.443) Remain 66:16:49 loss: 0.2679 loss_seg: 0.1678 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:13:43,464 INFO misc.py line 117 726] Train: [4/20][282/510] Data 3.644 (3.848) Batch 30.623 (28.451) Remain 66:17:26 loss: 0.2061 loss_seg: 0.1190 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:14:10,783 INFO misc.py line 117 726] Train: [4/20][283/510] Data 2.655 (3.844) Batch 27.320 (28.447) Remain 66:16:24 loss: 0.2425 loss_seg: 0.1525 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:14:36,058 INFO misc.py line 117 726] Train: [4/20][284/510] Data 2.359 (3.839) Batch 25.275 (28.436) Remain 66:14:21 loss: 0.2756 loss_seg: 0.1739 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:15:19,752 INFO misc.py line 117 726] Train: [4/20][285/510] Data 11.784 (3.867) Batch 43.694 (28.490) Remain 66:21:26 loss: 0.2233 loss_seg: 0.1291 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:15:46,743 INFO misc.py line 117 726] Train: [4/20][286/510] Data 3.435 (3.866) Batch 26.990 (28.484) Remain 66:20:13 loss: 0.2200 loss_seg: 0.1269 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:16:12,401 INFO misc.py line 117 726] Train: [4/20][287/510] Data 3.185 (3.863) Batch 25.658 (28.475) Remain 66:18:21 loss: 0.2126 loss_seg: 0.1234 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:16:39,442 INFO misc.py line 117 726] Train: [4/20][288/510] Data 2.797 (3.859) Batch 27.041 (28.469) Remain 66:17:11 loss: 0.2499 loss_seg: 0.1479 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:17:07,923 INFO misc.py line 117 726] Train: [4/20][289/510] Data 3.369 (3.858) Batch 28.481 (28.470) Remain 66:16:43 loss: 0.1854 loss_seg: 0.0936 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:17:38,663 INFO misc.py line 117 726] Train: [4/20][290/510] Data 3.611 (3.857) Batch 30.740 (28.477) Remain 66:17:20 loss: 0.2411 loss_seg: 0.1491 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:18:06,583 INFO misc.py line 117 726] Train: [4/20][291/510] Data 3.371 (3.855) Batch 27.920 (28.476) Remain 66:16:36 loss: 0.2663 loss_seg: 0.1665 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:18:41,199 INFO misc.py line 117 726] Train: [4/20][292/510] Data 4.917 (3.859) Batch 34.616 (28.497) Remain 66:19:05 loss: 0.2746 loss_seg: 0.1759 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:19:02,657 INFO misc.py line 117 726] Train: [4/20][293/510] Data 2.343 (3.854) Batch 21.458 (28.472) Remain 66:15:14 loss: 0.2336 loss_seg: 0.1365 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:19:30,491 INFO misc.py line 117 726] Train: [4/20][294/510] Data 2.840 (3.850) Batch 27.834 (28.470) Remain 66:14:27 loss: 0.2822 loss_seg: 0.1952 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:19:55,342 INFO misc.py line 117 726] Train: [4/20][295/510] Data 2.738 (3.846) Batch 24.851 (28.458) Remain 66:12:14 loss: 0.2324 loss_seg: 0.1399 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:20:31,172 INFO misc.py line 117 726] Train: [4/20][296/510] Data 4.946 (3.850) Batch 35.830 (28.483) Remain 66:15:17 loss: 0.3061 loss_seg: 0.2028 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:20:59,472 INFO misc.py line 117 726] Train: [4/20][297/510] Data 3.994 (3.851) Batch 28.301 (28.482) Remain 66:14:43 loss: 0.1808 loss_seg: 0.0951 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:21:22,898 INFO misc.py line 117 726] Train: [4/20][298/510] Data 2.141 (3.845) Batch 23.425 (28.465) Remain 66:11:51 loss: 0.2231 loss_seg: 0.1268 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:21:49,223 INFO misc.py line 117 726] Train: [4/20][299/510] Data 3.523 (3.844) Batch 26.325 (28.458) Remain 66:10:22 loss: 0.2303 loss_seg: 0.1343 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:22:10,960 INFO misc.py line 117 726] Train: [4/20][300/510] Data 2.734 (3.840) Batch 21.738 (28.435) Remain 66:06:44 loss: 0.2675 loss_seg: 0.1663 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:22:10,962 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 05:22:40,068 INFO misc.py line 117 726] Train: [4/20][301/510] Data 3.289 (3.838) Batch 29.108 (28.438) Remain 66:06:35 loss: 0.2093 loss_seg: 0.1190 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:23:05,051 INFO misc.py line 117 726] Train: [4/20][302/510] Data 3.104 (3.836) Batch 24.983 (28.426) Remain 66:04:29 loss: 0.2710 loss_seg: 0.1728 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:23:29,358 INFO misc.py line 117 726] Train: [4/20][303/510] Data 2.432 (3.831) Batch 24.307 (28.412) Remain 66:02:06 loss: 0.1788 loss_seg: 0.0921 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:23:47,408 INFO misc.py line 117 726] Train: [4/20][304/510] Data 1.786 (3.824) Batch 18.050 (28.378) Remain 65:56:50 loss: 0.2631 loss_seg: 0.1624 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:24:09,390 INFO misc.py line 117 726] Train: [4/20][305/510] Data 2.021 (3.818) Batch 21.982 (28.357) Remain 65:53:24 loss: 0.1785 loss_seg: 0.0941 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:24:38,525 INFO misc.py line 117 726] Train: [4/20][306/510] Data 3.004 (3.815) Batch 29.134 (28.359) Remain 65:53:17 loss: 0.2559 loss_seg: 0.1556 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:25:05,196 INFO misc.py line 117 726] Train: [4/20][307/510] Data 2.902 (3.812) Batch 26.671 (28.354) Remain 65:52:02 loss: 0.2247 loss_seg: 0.1335 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:25:30,609 INFO misc.py line 117 726] Train: [4/20][308/510] Data 3.293 (3.811) Batch 25.413 (28.344) Remain 65:50:13 loss: 0.2284 loss_seg: 0.1303 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:25:48,074 INFO misc.py line 117 726] Train: [4/20][309/510] Data 2.365 (3.806) Batch 17.465 (28.309) Remain 65:44:48 loss: 0.2996 loss_seg: 0.1927 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:26:19,677 INFO misc.py line 117 726] Train: [4/20][310/510] Data 4.613 (3.809) Batch 31.603 (28.319) Remain 65:45:49 loss: 0.3927 loss_seg: 0.2897 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:26:34,599 INFO misc.py line 117 726] Train: [4/20][311/510] Data 2.137 (3.803) Batch 14.922 (28.276) Remain 65:39:17 loss: 0.3028 loss_seg: 0.2055 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:27:07,716 INFO misc.py line 117 726] Train: [4/20][312/510] Data 3.884 (3.804) Batch 33.117 (28.292) Remain 65:41:00 loss: 0.2976 loss_seg: 0.1992 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:27:39,531 INFO misc.py line 117 726] Train: [4/20][313/510] Data 4.148 (3.805) Batch 31.814 (28.303) Remain 65:42:07 loss: 0.4704 loss_seg: 0.3378 loss_superpoint_edge: 0.0646 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:28:05,673 INFO misc.py line 117 726] Train: [4/20][314/510] Data 5.115 (3.809) Batch 26.142 (28.296) Remain 65:40:40 loss: 0.2139 loss_seg: 0.1184 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:28:39,012 INFO misc.py line 117 726] Train: [4/20][315/510] Data 4.353 (3.811) Batch 33.339 (28.312) Remain 65:42:27 loss: 0.2554 loss_seg: 0.1586 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:29:07,946 INFO misc.py line 117 726] Train: [4/20][316/510] Data 3.529 (3.810) Batch 28.934 (28.314) Remain 65:42:15 loss: 0.2637 loss_seg: 0.1653 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:29:44,856 INFO misc.py line 117 726] Train: [4/20][317/510] Data 4.637 (3.812) Batch 36.910 (28.341) Remain 65:45:36 loss: 0.2360 loss_seg: 0.1399 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:30:11,470 INFO misc.py line 117 726] Train: [4/20][318/510] Data 3.487 (3.811) Batch 26.614 (28.336) Remain 65:44:22 loss: 0.2435 loss_seg: 0.1487 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:30:42,581 INFO misc.py line 117 726] Train: [4/20][319/510] Data 3.138 (3.809) Batch 31.111 (28.345) Remain 65:45:07 loss: 0.2217 loss_seg: 0.1273 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:31:08,116 INFO misc.py line 117 726] Train: [4/20][320/510] Data 3.226 (3.807) Batch 25.535 (28.336) Remain 65:43:24 loss: 0.4289 loss_seg: 0.3265 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:31:36,838 INFO misc.py line 117 726] Train: [4/20][321/510] Data 3.461 (3.806) Batch 28.721 (28.337) Remain 65:43:06 loss: 0.2972 loss_seg: 0.1933 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:31:58,803 INFO misc.py line 117 726] Train: [4/20][322/510] Data 1.763 (3.800) Batch 21.965 (28.317) Remain 65:39:51 loss: 0.3644 loss_seg: 0.2534 loss_superpoint_edge: 0.0419 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:32:25,180 INFO misc.py line 117 726] Train: [4/20][323/510] Data 2.936 (3.797) Batch 26.378 (28.311) Remain 65:38:32 loss: 0.2142 loss_seg: 0.1246 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:33:01,964 INFO misc.py line 117 726] Train: [4/20][324/510] Data 11.733 (3.822) Batch 36.784 (28.337) Remain 65:41:44 loss: 0.2120 loss_seg: 0.1222 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:33:32,948 INFO misc.py line 117 726] Train: [4/20][325/510] Data 3.299 (3.820) Batch 30.984 (28.346) Remain 65:42:24 loss: 0.2112 loss_seg: 0.1225 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:34:07,352 INFO misc.py line 117 726] Train: [4/20][326/510] Data 8.143 (3.834) Batch 34.404 (28.364) Remain 65:44:32 loss: 0.2056 loss_seg: 0.1163 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:34:35,159 INFO misc.py line 117 726] Train: [4/20][327/510] Data 2.996 (3.831) Batch 27.807 (28.363) Remain 65:43:50 loss: 0.3145 loss_seg: 0.2201 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:35:01,502 INFO misc.py line 117 726] Train: [4/20][328/510] Data 3.098 (3.829) Batch 26.343 (28.357) Remain 65:42:30 loss: 0.2659 loss_seg: 0.1660 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:35:27,918 INFO misc.py line 117 726] Train: [4/20][329/510] Data 2.610 (3.825) Batch 26.416 (28.351) Remain 65:41:12 loss: 0.2753 loss_seg: 0.1701 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:35:42,467 INFO misc.py line 117 726] Train: [4/20][330/510] Data 1.934 (3.819) Batch 14.549 (28.308) Remain 65:34:51 loss: 0.2838 loss_seg: 0.1824 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:36:18,267 INFO misc.py line 117 726] Train: [4/20][331/510] Data 4.469 (3.821) Batch 35.800 (28.331) Remain 65:37:33 loss: 0.2202 loss_seg: 0.1271 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:36:43,488 INFO misc.py line 117 726] Train: [4/20][332/510] Data 3.053 (3.819) Batch 25.221 (28.322) Remain 65:35:46 loss: 0.2000 loss_seg: 0.1070 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:37:09,076 INFO misc.py line 117 726] Train: [4/20][333/510] Data 2.599 (3.815) Batch 25.588 (28.313) Remain 65:34:09 loss: 0.2663 loss_seg: 0.1704 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:37:36,180 INFO misc.py line 117 726] Train: [4/20][334/510] Data 3.044 (3.813) Batch 27.105 (28.310) Remain 65:33:10 loss: 0.2923 loss_seg: 0.1906 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:37:58,101 INFO misc.py line 117 726] Train: [4/20][335/510] Data 2.742 (3.810) Batch 21.920 (28.291) Remain 65:30:01 loss: 0.2472 loss_seg: 0.1507 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:38:28,818 INFO misc.py line 117 726] Train: [4/20][336/510] Data 3.519 (3.809) Batch 30.718 (28.298) Remain 65:30:34 loss: 0.2625 loss_seg: 0.1620 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:38:56,514 INFO misc.py line 117 726] Train: [4/20][337/510] Data 2.625 (3.805) Batch 27.696 (28.296) Remain 65:29:50 loss: 0.2398 loss_seg: 0.1430 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:39:18,482 INFO misc.py line 117 726] Train: [4/20][338/510] Data 2.545 (3.801) Batch 21.968 (28.277) Remain 65:26:45 loss: 0.2752 loss_seg: 0.1746 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:39:48,833 INFO misc.py line 117 726] Train: [4/20][339/510] Data 4.574 (3.804) Batch 30.352 (28.283) Remain 65:27:08 loss: 0.2355 loss_seg: 0.1397 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:40:20,217 INFO misc.py line 117 726] Train: [4/20][340/510] Data 4.585 (3.806) Batch 31.384 (28.293) Remain 65:27:56 loss: 0.3551 loss_seg: 0.2481 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:40:48,290 INFO misc.py line 117 726] Train: [4/20][341/510] Data 3.391 (3.805) Batch 28.073 (28.292) Remain 65:27:23 loss: 0.2927 loss_seg: 0.2005 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:41:12,370 INFO misc.py line 117 726] Train: [4/20][342/510] Data 2.346 (3.801) Batch 24.080 (28.279) Remain 65:25:11 loss: 0.1744 loss_seg: 0.0903 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:41:55,634 INFO misc.py line 117 726] Train: [4/20][343/510] Data 10.723 (3.821) Batch 43.264 (28.324) Remain 65:30:49 loss: 0.2057 loss_seg: 0.1142 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:42:28,482 INFO misc.py line 117 726] Train: [4/20][344/510] Data 3.584 (3.820) Batch 32.848 (28.337) Remain 65:32:12 loss: 0.1646 loss_seg: 0.0825 loss_superpoint_edge: 0.0136 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:42:49,359 INFO misc.py line 117 726] Train: [4/20][345/510] Data 2.100 (3.815) Batch 20.877 (28.315) Remain 65:28:42 loss: 0.2660 loss_seg: 0.1646 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:43:13,660 INFO misc.py line 117 726] Train: [4/20][346/510] Data 3.510 (3.814) Batch 24.301 (28.303) Remain 65:26:36 loss: 0.2249 loss_seg: 0.1316 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:43:43,669 INFO misc.py line 117 726] Train: [4/20][347/510] Data 3.711 (3.814) Batch 30.009 (28.308) Remain 65:26:49 loss: 0.3058 loss_seg: 0.2061 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:44:05,501 INFO misc.py line 117 726] Train: [4/20][348/510] Data 2.415 (3.810) Batch 21.831 (28.289) Remain 65:23:44 loss: 0.1891 loss_seg: 0.0989 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:44:41,304 INFO misc.py line 117 726] Train: [4/20][349/510] Data 6.675 (3.818) Batch 35.803 (28.311) Remain 65:26:17 loss: 0.3296 loss_seg: 0.2315 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:45:10,615 INFO misc.py line 117 726] Train: [4/20][350/510] Data 3.117 (3.816) Batch 29.311 (28.314) Remain 65:26:12 loss: 0.2378 loss_seg: 0.1421 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:45:10,616 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 05:45:44,361 INFO misc.py line 117 726] Train: [4/20][351/510] Data 4.818 (3.819) Batch 33.747 (28.330) Remain 65:27:54 loss: 0.3045 loss_seg: 0.2070 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:46:11,014 INFO misc.py line 117 726] Train: [4/20][352/510] Data 2.361 (3.815) Batch 26.652 (28.325) Remain 65:26:46 loss: 0.1969 loss_seg: 0.1078 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:46:31,428 INFO misc.py line 117 726] Train: [4/20][353/510] Data 4.129 (3.816) Batch 20.414 (28.302) Remain 65:23:09 loss: 0.5021 loss_seg: 0.3884 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0351 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:47:07,963 INFO misc.py line 117 726] Train: [4/20][354/510] Data 6.308 (3.823) Batch 36.535 (28.326) Remain 65:25:56 loss: 0.3988 loss_seg: 0.2839 loss_superpoint_edge: 0.0435 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:47:35,147 INFO misc.py line 117 726] Train: [4/20][355/510] Data 3.193 (3.821) Batch 27.184 (28.322) Remain 65:25:01 loss: 0.1795 loss_seg: 0.0950 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:47:56,527 INFO misc.py line 117 726] Train: [4/20][356/510] Data 3.763 (3.821) Batch 21.380 (28.303) Remain 65:21:49 loss: 0.3337 loss_seg: 0.2357 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:48:29,118 INFO misc.py line 117 726] Train: [4/20][357/510] Data 5.287 (3.825) Batch 32.591 (28.315) Remain 65:23:01 loss: 0.2407 loss_seg: 0.1420 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:48:59,507 INFO misc.py line 117 726] Train: [4/20][358/510] Data 4.251 (3.826) Batch 30.388 (28.321) Remain 65:23:22 loss: 0.2529 loss_seg: 0.1652 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:49:19,855 INFO misc.py line 117 726] Train: [4/20][359/510] Data 2.923 (3.824) Batch 20.349 (28.298) Remain 65:19:47 loss: 0.2542 loss_seg: 0.1597 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:49:45,672 INFO misc.py line 117 726] Train: [4/20][360/510] Data 3.883 (3.824) Batch 25.817 (28.291) Remain 65:18:21 loss: 0.2276 loss_seg: 0.1369 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:50:10,246 INFO misc.py line 117 726] Train: [4/20][361/510] Data 2.355 (3.820) Batch 24.573 (28.281) Remain 65:16:27 loss: 0.2636 loss_seg: 0.1689 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:50:32,950 INFO misc.py line 117 726] Train: [4/20][362/510] Data 2.117 (3.815) Batch 22.704 (28.265) Remain 65:13:49 loss: 0.2258 loss_seg: 0.1326 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:51:02,078 INFO misc.py line 117 726] Train: [4/20][363/510] Data 5.244 (3.819) Batch 29.128 (28.268) Remain 65:13:41 loss: 0.3508 loss_seg: 0.2395 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:51:30,065 INFO misc.py line 117 726] Train: [4/20][364/510] Data 2.613 (3.816) Batch 27.987 (28.267) Remain 65:13:06 loss: 0.3451 loss_seg: 0.2456 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:52:01,150 INFO misc.py line 117 726] Train: [4/20][365/510] Data 2.854 (3.813) Batch 31.085 (28.275) Remain 65:13:43 loss: 0.2874 loss_seg: 0.1861 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:52:37,819 INFO misc.py line 117 726] Train: [4/20][366/510] Data 6.443 (3.820) Batch 36.669 (28.298) Remain 65:16:26 loss: 0.1798 loss_seg: 0.0947 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:53:11,938 INFO misc.py line 117 726] Train: [4/20][367/510] Data 5.488 (3.825) Batch 34.119 (28.314) Remain 65:18:11 loss: 0.3212 loss_seg: 0.2179 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:53:42,527 INFO misc.py line 117 726] Train: [4/20][368/510] Data 3.104 (3.823) Batch 30.589 (28.320) Remain 65:18:34 loss: 0.2590 loss_seg: 0.1602 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:54:19,269 INFO misc.py line 117 726] Train: [4/20][369/510] Data 6.091 (3.829) Batch 36.741 (28.343) Remain 65:21:17 loss: 0.2994 loss_seg: 0.1985 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:54:44,638 INFO misc.py line 117 726] Train: [4/20][370/510] Data 2.938 (3.827) Batch 25.369 (28.335) Remain 65:19:41 loss: 0.2700 loss_seg: 0.1718 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:55:07,148 INFO misc.py line 117 726] Train: [4/20][371/510] Data 4.318 (3.828) Batch 22.510 (28.319) Remain 65:17:02 loss: 0.2336 loss_seg: 0.1317 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:55:38,122 INFO misc.py line 117 726] Train: [4/20][372/510] Data 3.435 (3.827) Batch 30.974 (28.327) Remain 65:17:33 loss: 0.2081 loss_seg: 0.1163 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:56:11,517 INFO misc.py line 117 726] Train: [4/20][373/510] Data 5.587 (3.832) Batch 33.394 (28.340) Remain 65:18:58 loss: 0.2275 loss_seg: 0.1322 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:56:36,985 INFO misc.py line 117 726] Train: [4/20][374/510] Data 2.478 (3.828) Batch 25.469 (28.332) Remain 65:17:26 loss: 0.2435 loss_seg: 0.1532 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:56:54,148 INFO misc.py line 117 726] Train: [4/20][375/510] Data 2.432 (3.824) Batch 17.163 (28.302) Remain 65:12:48 loss: 0.2758 loss_seg: 0.1749 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:57:17,429 INFO misc.py line 117 726] Train: [4/20][376/510] Data 2.658 (3.821) Batch 23.280 (28.289) Remain 65:10:28 loss: 0.3135 loss_seg: 0.2070 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:57:47,621 INFO misc.py line 117 726] Train: [4/20][377/510] Data 5.180 (3.825) Batch 30.192 (28.294) Remain 65:10:42 loss: 0.2411 loss_seg: 0.1470 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:58:14,906 INFO misc.py line 117 726] Train: [4/20][378/510] Data 4.161 (3.826) Batch 27.286 (28.291) Remain 65:09:52 loss: 0.2306 loss_seg: 0.1340 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:58:54,713 INFO misc.py line 117 726] Train: [4/20][379/510] Data 6.834 (3.834) Batch 39.807 (28.322) Remain 65:13:37 loss: 0.2326 loss_seg: 0.1390 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:59:14,828 INFO misc.py line 117 726] Train: [4/20][380/510] Data 3.146 (3.832) Batch 20.115 (28.300) Remain 65:10:09 loss: 0.2001 loss_seg: 0.1111 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:59:32,000 INFO misc.py line 117 726] Train: [4/20][381/510] Data 2.027 (3.827) Batch 17.172 (28.271) Remain 65:05:36 loss: 0.4312 loss_seg: 0.3241 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 05:59:55,066 INFO misc.py line 117 726] Train: [4/20][382/510] Data 3.790 (3.827) Batch 23.066 (28.257) Remain 65:03:14 loss: 0.1862 loss_seg: 0.0981 loss_superpoint_edge: 0.0139 loss_superpoint_contrast: 0.0431 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:00:16,330 INFO misc.py line 117 726] Train: [4/20][383/510] Data 1.979 (3.822) Batch 21.264 (28.239) Remain 65:00:13 loss: 0.2147 loss_seg: 0.1237 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:00:41,302 INFO misc.py line 117 726] Train: [4/20][384/510] Data 3.055 (3.820) Batch 24.972 (28.230) Remain 64:58:34 loss: 0.2538 loss_seg: 0.1618 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:01:01,219 INFO misc.py line 117 726] Train: [4/20][385/510] Data 2.151 (3.816) Batch 19.918 (28.208) Remain 64:55:06 loss: 0.3327 loss_seg: 0.2232 loss_superpoint_edge: 0.0416 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:01:29,954 INFO misc.py line 117 726] Train: [4/20][386/510] Data 2.905 (3.813) Batch 28.735 (28.210) Remain 64:54:49 loss: 0.2070 loss_seg: 0.1177 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:02:06,340 INFO misc.py line 117 726] Train: [4/20][387/510] Data 5.539 (3.818) Batch 36.386 (28.231) Remain 64:57:17 loss: 0.3241 loss_seg: 0.2209 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:02:25,505 INFO misc.py line 117 726] Train: [4/20][388/510] Data 2.407 (3.814) Batch 19.166 (28.207) Remain 64:53:34 loss: 0.1950 loss_seg: 0.1069 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:03:06,077 INFO misc.py line 117 726] Train: [4/20][389/510] Data 10.481 (3.831) Batch 40.571 (28.239) Remain 64:57:31 loss: 0.2791 loss_seg: 0.1750 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:03:32,124 INFO misc.py line 117 726] Train: [4/20][390/510] Data 2.737 (3.829) Batch 26.047 (28.234) Remain 64:56:16 loss: 0.2729 loss_seg: 0.1720 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:04:05,867 INFO misc.py line 117 726] Train: [4/20][391/510] Data 3.474 (3.828) Batch 33.743 (28.248) Remain 64:57:45 loss: 0.2344 loss_seg: 0.1435 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:04:31,083 INFO misc.py line 117 726] Train: [4/20][392/510] Data 2.710 (3.825) Batch 25.216 (28.240) Remain 64:56:12 loss: 0.1970 loss_seg: 0.1079 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:05:04,298 INFO misc.py line 117 726] Train: [4/20][393/510] Data 6.199 (3.831) Batch 33.215 (28.253) Remain 64:57:29 loss: 0.2356 loss_seg: 0.1444 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:05:25,344 INFO misc.py line 117 726] Train: [4/20][394/510] Data 2.736 (3.828) Batch 21.046 (28.235) Remain 64:54:29 loss: 0.2448 loss_seg: 0.1492 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:05:51,315 INFO misc.py line 117 726] Train: [4/20][395/510] Data 2.307 (3.824) Batch 25.971 (28.229) Remain 64:53:13 loss: 0.2641 loss_seg: 0.1630 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:06:16,705 INFO misc.py line 117 726] Train: [4/20][396/510] Data 2.552 (3.821) Batch 25.390 (28.222) Remain 64:51:45 loss: 0.2027 loss_seg: 0.1122 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:06:50,107 INFO misc.py line 117 726] Train: [4/20][397/510] Data 5.082 (3.824) Batch 33.402 (28.235) Remain 64:53:05 loss: 0.2173 loss_seg: 0.1269 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:07:14,168 INFO misc.py line 117 726] Train: [4/20][398/510] Data 2.751 (3.821) Batch 24.061 (28.224) Remain 64:51:09 loss: 0.3574 loss_seg: 0.2624 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:07:40,971 INFO misc.py line 117 726] Train: [4/20][399/510] Data 1.893 (3.817) Batch 26.803 (28.221) Remain 64:50:12 loss: 0.2856 loss_seg: 0.1790 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:08:17,209 INFO misc.py line 117 726] Train: [4/20][400/510] Data 3.726 (3.816) Batch 36.238 (28.241) Remain 64:52:30 loss: 0.2363 loss_seg: 0.1411 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:08:17,210 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 06:08:43,778 INFO misc.py line 117 726] Train: [4/20][401/510] Data 3.277 (3.815) Batch 26.569 (28.237) Remain 64:51:27 loss: 0.1833 loss_seg: 0.0968 loss_superpoint_edge: 0.0147 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:09:05,531 INFO misc.py line 117 726] Train: [4/20][402/510] Data 2.387 (3.811) Batch 21.752 (28.220) Remain 64:48:45 loss: 0.3499 loss_seg: 0.2304 loss_superpoint_edge: 0.0495 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:09:28,576 INFO misc.py line 117 726] Train: [4/20][403/510] Data 4.576 (3.813) Batch 23.046 (28.207) Remain 64:46:30 loss: 0.6315 loss_seg: 0.5051 loss_superpoint_edge: 0.0543 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:10:05,456 INFO misc.py line 117 726] Train: [4/20][404/510] Data 4.610 (3.815) Batch 36.880 (28.229) Remain 64:49:00 loss: 0.2214 loss_seg: 0.1274 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:10:34,761 INFO misc.py line 117 726] Train: [4/20][405/510] Data 3.563 (3.815) Batch 29.304 (28.232) Remain 64:48:54 loss: 0.2588 loss_seg: 0.1593 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:10:59,558 INFO misc.py line 117 726] Train: [4/20][406/510] Data 3.010 (3.813) Batch 24.797 (28.223) Remain 64:47:15 loss: 0.2200 loss_seg: 0.1290 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:11:21,015 INFO misc.py line 117 726] Train: [4/20][407/510] Data 2.487 (3.809) Batch 21.457 (28.206) Remain 64:44:29 loss: 0.2116 loss_seg: 0.1220 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:11:49,346 INFO misc.py line 117 726] Train: [4/20][408/510] Data 3.001 (3.807) Batch 28.332 (28.207) Remain 64:44:03 loss: 0.2135 loss_seg: 0.1220 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:12:23,551 INFO misc.py line 117 726] Train: [4/20][409/510] Data 3.550 (3.807) Batch 34.204 (28.221) Remain 64:45:37 loss: 0.1972 loss_seg: 0.1098 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:12:51,725 INFO misc.py line 117 726] Train: [4/20][410/510] Data 5.234 (3.810) Batch 28.174 (28.221) Remain 64:45:08 loss: 0.2671 loss_seg: 0.1658 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:13:20,954 INFO misc.py line 117 726] Train: [4/20][411/510] Data 3.423 (3.809) Batch 29.228 (28.224) Remain 64:45:00 loss: 0.2615 loss_seg: 0.1598 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:13:49,557 INFO misc.py line 117 726] Train: [4/20][412/510] Data 4.410 (3.811) Batch 28.604 (28.225) Remain 64:44:39 loss: 0.2794 loss_seg: 0.1773 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:14:17,666 INFO misc.py line 117 726] Train: [4/20][413/510] Data 3.354 (3.810) Batch 28.108 (28.224) Remain 64:44:09 loss: 0.2238 loss_seg: 0.1329 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:14:45,269 INFO misc.py line 117 726] Train: [4/20][414/510] Data 5.079 (3.813) Batch 27.603 (28.223) Remain 64:43:28 loss: 0.2822 loss_seg: 0.1788 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:15:23,181 INFO misc.py line 117 726] Train: [4/20][415/510] Data 4.254 (3.814) Batch 37.912 (28.246) Remain 64:46:14 loss: 0.2487 loss_seg: 0.1553 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:15:54,385 INFO misc.py line 117 726] Train: [4/20][416/510] Data 3.722 (3.814) Batch 31.203 (28.254) Remain 64:46:45 loss: 0.2414 loss_seg: 0.1456 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:16:22,813 INFO misc.py line 117 726] Train: [4/20][417/510] Data 3.288 (3.812) Batch 28.429 (28.254) Remain 64:46:20 loss: 0.2210 loss_seg: 0.1293 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:16:59,443 INFO misc.py line 117 726] Train: [4/20][418/510] Data 4.978 (3.815) Batch 36.629 (28.274) Remain 64:48:38 loss: 0.2265 loss_seg: 0.1343 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:17:27,435 INFO misc.py line 117 726] Train: [4/20][419/510] Data 2.813 (3.813) Batch 27.992 (28.274) Remain 64:48:05 loss: 0.2487 loss_seg: 0.1525 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:17:56,653 INFO misc.py line 117 726] Train: [4/20][420/510] Data 3.474 (3.812) Batch 29.217 (28.276) Remain 64:47:55 loss: 0.2405 loss_seg: 0.1461 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:18:25,307 INFO misc.py line 117 726] Train: [4/20][421/510] Data 2.870 (3.810) Batch 28.655 (28.277) Remain 64:47:34 loss: 0.2402 loss_seg: 0.1483 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:18:42,464 INFO misc.py line 117 726] Train: [4/20][422/510] Data 2.697 (3.807) Batch 17.157 (28.250) Remain 64:43:27 loss: 0.2531 loss_seg: 0.1602 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:19:10,972 INFO misc.py line 117 726] Train: [4/20][423/510] Data 3.450 (3.806) Batch 28.508 (28.251) Remain 64:43:04 loss: 0.2704 loss_seg: 0.1688 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:19:46,571 INFO misc.py line 117 726] Train: [4/20][424/510] Data 3.370 (3.805) Batch 35.599 (28.268) Remain 64:45:00 loss: 0.2416 loss_seg: 0.1434 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:20:17,297 INFO misc.py line 117 726] Train: [4/20][425/510] Data 3.698 (3.805) Batch 30.726 (28.274) Remain 64:45:19 loss: 0.2247 loss_seg: 0.1297 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:20:48,450 INFO misc.py line 117 726] Train: [4/20][426/510] Data 3.702 (3.805) Batch 31.153 (28.281) Remain 64:45:47 loss: 0.2928 loss_seg: 0.2037 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:21:04,247 INFO misc.py line 117 726] Train: [4/20][427/510] Data 2.105 (3.801) Batch 15.797 (28.251) Remain 64:41:16 loss: 0.3124 loss_seg: 0.2062 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:21:36,673 INFO misc.py line 117 726] Train: [4/20][428/510] Data 4.215 (3.802) Batch 32.426 (28.261) Remain 64:42:09 loss: 0.2482 loss_seg: 0.1486 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:22:01,408 INFO misc.py line 117 726] Train: [4/20][429/510] Data 2.633 (3.799) Batch 24.735 (28.253) Remain 64:40:32 loss: 0.2908 loss_seg: 0.1903 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:22:30,105 INFO misc.py line 117 726] Train: [4/20][430/510] Data 2.985 (3.797) Batch 28.697 (28.254) Remain 64:40:13 loss: 0.2002 loss_seg: 0.1135 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:23:15,479 INFO misc.py line 117 726] Train: [4/20][431/510] Data 12.874 (3.818) Batch 45.373 (28.294) Remain 64:45:14 loss: 0.3135 loss_seg: 0.2123 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:23:45,489 INFO misc.py line 117 726] Train: [4/20][432/510] Data 2.964 (3.816) Batch 30.010 (28.298) Remain 64:45:19 loss: 0.2155 loss_seg: 0.1197 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:24:14,230 INFO misc.py line 117 726] Train: [4/20][433/510] Data 3.886 (3.816) Batch 28.741 (28.299) Remain 64:44:59 loss: 0.3189 loss_seg: 0.2084 loss_superpoint_edge: 0.0447 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:24:49,397 INFO misc.py line 117 726] Train: [4/20][434/510] Data 8.246 (3.827) Batch 35.167 (28.315) Remain 64:46:42 loss: 0.2732 loss_seg: 0.1752 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:25:09,248 INFO misc.py line 117 726] Train: [4/20][435/510] Data 2.381 (3.823) Batch 19.852 (28.295) Remain 64:43:32 loss: 0.3278 loss_seg: 0.2297 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:25:38,632 INFO misc.py line 117 726] Train: [4/20][436/510] Data 2.920 (3.821) Batch 29.384 (28.298) Remain 64:43:25 loss: 0.2249 loss_seg: 0.1321 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:26:07,895 INFO misc.py line 117 726] Train: [4/20][437/510] Data 4.137 (3.822) Batch 29.263 (28.300) Remain 64:43:15 loss: 0.1890 loss_seg: 0.1021 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:26:38,872 INFO misc.py line 117 726] Train: [4/20][438/510] Data 3.887 (3.822) Batch 30.977 (28.306) Remain 64:43:37 loss: 0.2315 loss_seg: 0.1373 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:27:05,107 INFO misc.py line 117 726] Train: [4/20][439/510] Data 3.334 (3.821) Batch 26.235 (28.302) Remain 64:42:29 loss: 0.2496 loss_seg: 0.1563 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:27:33,324 INFO misc.py line 117 726] Train: [4/20][440/510] Data 3.046 (3.819) Batch 28.217 (28.301) Remain 64:42:00 loss: 0.2549 loss_seg: 0.1577 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:28:07,895 INFO misc.py line 117 726] Train: [4/20][441/510] Data 7.059 (3.827) Batch 34.571 (28.316) Remain 64:43:29 loss: 0.3164 loss_seg: 0.2122 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:28:37,481 INFO misc.py line 117 726] Train: [4/20][442/510] Data 3.693 (3.826) Batch 29.586 (28.319) Remain 64:43:25 loss: 0.2989 loss_seg: 0.1963 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:28:59,732 INFO misc.py line 117 726] Train: [4/20][443/510] Data 1.678 (3.821) Batch 22.251 (28.305) Remain 64:41:03 loss: 0.2352 loss_seg: 0.1419 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:29:27,500 INFO misc.py line 117 726] Train: [4/20][444/510] Data 2.479 (3.818) Batch 27.768 (28.304) Remain 64:40:24 loss: 0.2456 loss_seg: 0.1442 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:29:54,958 INFO misc.py line 117 726] Train: [4/20][445/510] Data 3.127 (3.817) Batch 27.457 (28.302) Remain 64:39:40 loss: 0.3026 loss_seg: 0.1924 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:30:24,215 INFO misc.py line 117 726] Train: [4/20][446/510] Data 5.238 (3.820) Batch 29.257 (28.304) Remain 64:39:30 loss: 0.2563 loss_seg: 0.1621 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:30:42,350 INFO misc.py line 117 726] Train: [4/20][447/510] Data 2.152 (3.816) Batch 18.135 (28.281) Remain 64:35:53 loss: 0.2648 loss_seg: 0.1642 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:31:10,140 INFO misc.py line 117 726] Train: [4/20][448/510] Data 2.795 (3.814) Batch 27.790 (28.280) Remain 64:35:16 loss: 0.2328 loss_seg: 0.1416 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:31:25,664 INFO misc.py line 117 726] Train: [4/20][449/510] Data 2.135 (3.810) Batch 15.524 (28.251) Remain 64:30:52 loss: 0.2600 loss_seg: 0.1585 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:31:55,638 INFO misc.py line 117 726] Train: [4/20][450/510] Data 3.292 (3.809) Batch 29.973 (28.255) Remain 64:30:56 loss: 0.2445 loss_seg: 0.1475 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:31:55,638 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 06:32:29,373 INFO misc.py line 117 726] Train: [4/20][451/510] Data 3.560 (3.809) Batch 33.735 (28.267) Remain 64:32:08 loss: 0.2110 loss_seg: 0.1181 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:33:03,626 INFO misc.py line 117 726] Train: [4/20][452/510] Data 5.474 (3.812) Batch 34.253 (28.281) Remain 64:33:29 loss: 0.2470 loss_seg: 0.1513 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:33:27,334 INFO misc.py line 117 726] Train: [4/20][453/510] Data 2.536 (3.809) Batch 23.708 (28.270) Remain 64:31:38 loss: 0.2532 loss_seg: 0.1523 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:33:50,912 INFO misc.py line 117 726] Train: [4/20][454/510] Data 2.853 (3.807) Batch 23.579 (28.260) Remain 64:29:44 loss: 0.2174 loss_seg: 0.1273 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:34:22,834 INFO misc.py line 117 726] Train: [4/20][455/510] Data 3.676 (3.807) Batch 31.921 (28.268) Remain 64:30:22 loss: 0.2881 loss_seg: 0.1891 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:34:54,846 INFO misc.py line 117 726] Train: [4/20][456/510] Data 3.749 (3.807) Batch 32.012 (28.276) Remain 64:31:02 loss: 0.2231 loss_seg: 0.1271 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:35:23,111 INFO misc.py line 117 726] Train: [4/20][457/510] Data 3.803 (3.807) Batch 28.265 (28.276) Remain 64:30:33 loss: 0.2696 loss_seg: 0.1753 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:35:49,582 INFO misc.py line 117 726] Train: [4/20][458/510] Data 4.253 (3.808) Batch 26.471 (28.272) Remain 64:29:32 loss: 0.2058 loss_seg: 0.1172 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:36:23,824 INFO misc.py line 117 726] Train: [4/20][459/510] Data 6.434 (3.814) Batch 34.242 (28.285) Remain 64:30:52 loss: 0.3042 loss_seg: 0.1958 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:36:49,047 INFO misc.py line 117 726] Train: [4/20][460/510] Data 2.358 (3.810) Batch 25.223 (28.279) Remain 64:29:28 loss: 0.1821 loss_seg: 0.0992 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:37:26,642 INFO misc.py line 117 726] Train: [4/20][461/510] Data 6.444 (3.816) Batch 37.595 (28.299) Remain 64:31:47 loss: 0.2781 loss_seg: 0.1812 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:37:57,788 INFO misc.py line 117 726] Train: [4/20][462/510] Data 3.635 (3.816) Batch 31.146 (28.305) Remain 64:32:10 loss: 0.2712 loss_seg: 0.1755 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:38:34,247 INFO misc.py line 117 726] Train: [4/20][463/510] Data 5.320 (3.819) Batch 36.459 (28.323) Remain 64:34:07 loss: 0.3308 loss_seg: 0.2304 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:38:51,927 INFO misc.py line 117 726] Train: [4/20][464/510] Data 1.792 (3.815) Batch 17.680 (28.300) Remain 64:30:29 loss: 0.2167 loss_seg: 0.1251 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:39:21,661 INFO misc.py line 117 726] Train: [4/20][465/510] Data 3.370 (3.814) Batch 29.734 (28.303) Remain 64:30:26 loss: 0.3047 loss_seg: 0.1973 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:39:42,938 INFO misc.py line 117 726] Train: [4/20][466/510] Data 2.943 (3.812) Batch 21.277 (28.288) Remain 64:27:54 loss: 0.2398 loss_seg: 0.1499 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:40:01,804 INFO misc.py line 117 726] Train: [4/20][467/510] Data 2.194 (3.808) Batch 18.866 (28.268) Remain 64:24:39 loss: 0.2346 loss_seg: 0.1376 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:40:26,266 INFO misc.py line 117 726] Train: [4/20][468/510] Data 2.896 (3.806) Batch 24.462 (28.259) Remain 64:23:03 loss: 0.2853 loss_seg: 0.1812 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:41:00,752 INFO misc.py line 117 726] Train: [4/20][469/510] Data 6.116 (3.811) Batch 34.486 (28.273) Remain 64:24:25 loss: 0.3268 loss_seg: 0.2197 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:41:22,469 INFO misc.py line 117 726] Train: [4/20][470/510] Data 2.743 (3.809) Batch 21.717 (28.259) Remain 64:22:01 loss: 0.2662 loss_seg: 0.1764 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0431 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:41:44,786 INFO misc.py line 117 726] Train: [4/20][471/510] Data 2.526 (3.806) Batch 22.316 (28.246) Remain 64:19:49 loss: 0.3009 loss_seg: 0.1992 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:42:16,825 INFO misc.py line 117 726] Train: [4/20][472/510] Data 6.310 (3.812) Batch 32.039 (28.254) Remain 64:20:27 loss: 0.2564 loss_seg: 0.1594 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:42:42,948 INFO misc.py line 117 726] Train: [4/20][473/510] Data 2.671 (3.809) Batch 26.123 (28.250) Remain 64:19:21 loss: 0.2571 loss_seg: 0.1622 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:43:21,432 INFO misc.py line 117 726] Train: [4/20][474/510] Data 5.240 (3.812) Batch 38.484 (28.271) Remain 64:21:51 loss: 0.2685 loss_seg: 0.1725 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:43:47,168 INFO misc.py line 117 726] Train: [4/20][475/510] Data 3.105 (3.811) Batch 25.736 (28.266) Remain 64:20:39 loss: 0.1971 loss_seg: 0.1090 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:44:08,676 INFO misc.py line 117 726] Train: [4/20][476/510] Data 1.960 (3.807) Batch 21.508 (28.252) Remain 64:18:14 loss: 0.1868 loss_seg: 0.0980 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:44:32,131 INFO misc.py line 117 726] Train: [4/20][477/510] Data 3.042 (3.805) Batch 23.455 (28.242) Remain 64:16:23 loss: 0.2610 loss_seg: 0.1575 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:44:54,463 INFO misc.py line 117 726] Train: [4/20][478/510] Data 2.625 (3.803) Batch 22.331 (28.229) Remain 64:14:12 loss: 0.2732 loss_seg: 0.1719 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:45:22,109 INFO misc.py line 117 726] Train: [4/20][479/510] Data 5.068 (3.805) Batch 27.646 (28.228) Remain 64:13:34 loss: 0.2137 loss_seg: 0.1215 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:45:49,708 INFO misc.py line 117 726] Train: [4/20][480/510] Data 4.095 (3.806) Batch 27.598 (28.227) Remain 64:12:55 loss: 0.2116 loss_seg: 0.1220 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:46:03,964 INFO misc.py line 117 726] Train: [4/20][481/510] Data 1.536 (3.801) Batch 14.257 (28.197) Remain 64:08:28 loss: 0.2389 loss_seg: 0.1508 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:46:29,511 INFO misc.py line 117 726] Train: [4/20][482/510] Data 3.682 (3.801) Batch 25.547 (28.192) Remain 64:07:14 loss: 0.2043 loss_seg: 0.1179 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:46:53,809 INFO misc.py line 117 726] Train: [4/20][483/510] Data 4.052 (3.801) Batch 24.297 (28.184) Remain 64:05:39 loss: 0.2292 loss_seg: 0.1382 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:47:22,730 INFO misc.py line 117 726] Train: [4/20][484/510] Data 5.585 (3.805) Batch 28.921 (28.185) Remain 64:05:24 loss: 0.2799 loss_seg: 0.1854 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:47:48,153 INFO misc.py line 117 726] Train: [4/20][485/510] Data 2.553 (3.803) Batch 25.422 (28.179) Remain 64:04:09 loss: 0.1904 loss_seg: 0.1024 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:48:14,191 INFO misc.py line 117 726] Train: [4/20][486/510] Data 2.930 (3.801) Batch 26.039 (28.175) Remain 64:03:04 loss: 0.2989 loss_seg: 0.1980 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:48:44,528 INFO misc.py line 117 726] Train: [4/20][487/510] Data 3.862 (3.801) Batch 30.337 (28.180) Remain 64:03:13 loss: 0.2988 loss_seg: 0.1966 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:49:03,666 INFO misc.py line 117 726] Train: [4/20][488/510] Data 2.039 (3.797) Batch 19.137 (28.161) Remain 64:00:12 loss: 0.3620 loss_seg: 0.2495 loss_superpoint_edge: 0.0445 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:49:26,845 INFO misc.py line 117 726] Train: [4/20][489/510] Data 4.826 (3.799) Batch 23.180 (28.151) Remain 63:58:20 loss: 0.2037 loss_seg: 0.1170 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:49:58,557 INFO misc.py line 117 726] Train: [4/20][490/510] Data 5.234 (3.802) Batch 31.712 (28.158) Remain 63:58:52 loss: 0.2350 loss_seg: 0.1412 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:50:14,263 INFO misc.py line 117 726] Train: [4/20][491/510] Data 2.013 (3.799) Batch 15.706 (28.132) Remain 63:54:55 loss: 0.3012 loss_seg: 0.2010 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:50:37,278 INFO misc.py line 117 726] Train: [4/20][492/510] Data 1.913 (3.795) Batch 23.015 (28.122) Remain 63:53:01 loss: 0.2529 loss_seg: 0.1554 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:50:59,886 INFO misc.py line 117 726] Train: [4/20][493/510] Data 2.345 (3.792) Batch 22.606 (28.111) Remain 63:51:01 loss: 0.2632 loss_seg: 0.1639 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:51:23,296 INFO misc.py line 117 726] Train: [4/20][494/510] Data 2.800 (3.790) Batch 23.412 (28.101) Remain 63:49:14 loss: 0.1841 loss_seg: 0.0991 loss_superpoint_edge: 0.0148 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:52:01,732 INFO misc.py line 117 726] Train: [4/20][495/510] Data 5.392 (3.793) Batch 38.436 (28.122) Remain 63:51:38 loss: 0.3587 loss_seg: 0.2576 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:52:30,890 INFO misc.py line 117 726] Train: [4/20][496/510] Data 2.882 (3.791) Batch 29.157 (28.124) Remain 63:51:27 loss: 0.2224 loss_seg: 0.1303 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:52:57,457 INFO misc.py line 117 726] Train: [4/20][497/510] Data 2.797 (3.789) Batch 26.567 (28.121) Remain 63:50:33 loss: 0.2614 loss_seg: 0.1630 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:53:22,497 INFO misc.py line 117 726] Train: [4/20][498/510] Data 2.778 (3.787) Batch 25.040 (28.115) Remain 63:49:14 loss: 0.3183 loss_seg: 0.2198 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:53:45,822 INFO misc.py line 117 726] Train: [4/20][499/510] Data 3.040 (3.786) Batch 23.325 (28.105) Remain 63:47:27 loss: 0.2567 loss_seg: 0.1588 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:54:16,502 INFO misc.py line 117 726] Train: [4/20][500/510] Data 3.667 (3.785) Batch 30.680 (28.110) Remain 63:47:41 loss: 0.2129 loss_seg: 0.1231 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:54:16,503 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 06:54:50,722 INFO misc.py line 117 726] Train: [4/20][501/510] Data 8.601 (3.795) Batch 34.220 (28.123) Remain 63:48:54 loss: 0.2812 loss_seg: 0.1952 loss_superpoint_edge: 0.0105 loss_superpoint_contrast: 0.0448 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:55:26,490 INFO misc.py line 117 726] Train: [4/20][502/510] Data 4.981 (3.797) Batch 35.767 (28.138) Remain 63:50:31 loss: 0.2954 loss_seg: 0.1910 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:55:53,785 INFO misc.py line 117 726] Train: [4/20][503/510] Data 4.102 (3.798) Batch 27.295 (28.136) Remain 63:49:49 loss: 0.2445 loss_seg: 0.1475 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:56:17,616 INFO misc.py line 117 726] Train: [4/20][504/510] Data 3.230 (3.797) Batch 23.831 (28.128) Remain 63:48:10 loss: 0.2113 loss_seg: 0.1222 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:56:49,395 INFO misc.py line 117 726] Train: [4/20][505/510] Data 3.589 (3.797) Batch 31.779 (28.135) Remain 63:48:42 loss: 0.2295 loss_seg: 0.1375 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:57:30,247 INFO misc.py line 117 726] Train: [4/20][506/510] Data 9.675 (3.808) Batch 40.852 (28.160) Remain 63:51:40 loss: 0.3856 loss_seg: 0.2630 loss_superpoint_edge: 0.0548 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:58:05,557 INFO misc.py line 117 726] Train: [4/20][507/510] Data 4.362 (3.809) Batch 35.310 (28.174) Remain 63:53:07 loss: 0.2291 loss_seg: 0.1326 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:58:27,743 INFO misc.py line 117 726] Train: [4/20][508/510] Data 1.997 (3.806) Batch 22.186 (28.163) Remain 63:51:03 loss: 0.2858 loss_seg: 0.1809 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:58:49,349 INFO misc.py line 117 726] Train: [4/20][509/510] Data 2.340 (3.803) Batch 21.606 (28.150) Remain 63:48:49 loss: 0.2242 loss_seg: 0.1286 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:59:08,994 INFO misc.py line 117 726] Train: [4/20][510/510] Data 2.430 (3.800) Batch 19.645 (28.133) Remain 63:46:04 loss: 0.1737 loss_seg: 0.0906 loss_superpoint_edge: 0.0125 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 06:59:08,995 INFO misc.py line 147 726] Train result: loss: 0.2586 loss_seg: 0.1620 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-10 06:59:08,996 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-10 06:59:24,616 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7907 [2026-06-10 06:59:40,613 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6799 [2026-06-10 07:00:55,151 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9715 [2026-06-10 07:01:35,304 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9824 [2026-06-10 07:01:54,460 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0031 [2026-06-10 07:02:31,052 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.0294 [2026-06-10 07:03:17,603 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1178 [2026-06-10 07:03:33,045 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3814 [2026-06-10 07:03:50,996 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9928 [2026-06-10 07:04:09,831 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3608 [2026-06-10 07:04:25,585 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4103 [2026-06-10 07:04:47,297 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7720 [2026-06-10 07:05:13,463 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8170 [2026-06-10 07:05:24,968 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7918 [2026-06-10 07:05:56,511 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0498 [2026-06-10 07:06:22,579 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.1889 [2026-06-10 07:06:49,268 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.1639 [2026-06-10 07:07:32,101 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.3197 [2026-06-10 07:07:53,013 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3764 [2026-06-10 07:08:09,706 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.7092 [2026-06-10 07:08:41,009 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.6332 [2026-06-10 07:08:57,283 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4311 [2026-06-10 07:09:19,221 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2348 [2026-06-10 07:09:41,032 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7859 [2026-06-10 07:09:54,434 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6316 [2026-06-10 07:10:21,936 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5038 [2026-06-10 07:11:03,424 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0939 [2026-06-10 07:11:20,639 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5338 [2026-06-10 07:11:39,291 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4424 [2026-06-10 07:11:56,491 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3200 [2026-06-10 07:12:21,613 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1732 [2026-06-10 07:12:39,915 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5520 [2026-06-10 07:12:57,459 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.0750 [2026-06-10 07:13:21,884 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7997 [2026-06-10 07:13:21,898 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6740/0.7473/0.8960. [2026-06-10 07:13:21,898 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9217/0.9541 [2026-06-10 07:13:21,898 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9762/0.9880 [2026-06-10 07:13:21,898 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8374/0.9692 [2026-06-10 07:13:21,898 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0004/0.0031 [2026-06-10 07:13:21,898 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3548/0.4175 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.5898/0.6189 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6191/0.6995 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7861/0.9068 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9172/0.9584 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6820/0.7691 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7571/0.8388 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7222/0.8783 [2026-06-10 07:13:21,899 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5982/0.7130 [2026-06-10 07:13:21,899 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-10 07:13:21,900 INFO misc.py line 213 726] Best validation mIoU updated to: 0.6740 [2026-06-10 07:13:21,900 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-10 07:13:21,900 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 07:14:08,834 INFO misc.py line 117 726] Train: [5/20][1/510] Data 11.489 (11.489) Batch 44.859 (44.859) Remain 101:40:01 loss: 0.2256 loss_seg: 0.1286 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:14:36,982 INFO misc.py line 117 726] Train: [5/20][2/510] Data 3.459 (3.459) Batch 28.148 (28.148) Remain 63:47:08 loss: 0.2281 loss_seg: 0.1323 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:15:10,958 INFO misc.py line 117 726] Train: [5/20][3/510] Data 4.479 (4.479) Batch 33.976 (33.976) Remain 76:59:03 loss: 0.3434 loss_seg: 0.2409 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:15:46,215 INFO misc.py line 117 726] Train: [5/20][4/510] Data 4.308 (4.308) Batch 35.256 (35.256) Remain 79:52:31 loss: 0.2356 loss_seg: 0.1453 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0322 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:16:04,888 INFO misc.py line 117 726] Train: [5/20][5/510] Data 2.145 (3.226) Batch 18.674 (26.965) Remain 61:05:00 loss: 0.2396 loss_seg: 0.1448 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:16:35,381 INFO misc.py line 117 726] Train: [5/20][6/510] Data 6.703 (4.385) Batch 30.493 (28.141) Remain 63:44:21 loss: 0.4730 loss_seg: 0.3666 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:17:03,972 INFO misc.py line 117 726] Train: [5/20][7/510] Data 2.982 (4.034) Batch 28.591 (28.253) Remain 63:59:10 loss: 0.1898 loss_seg: 0.1038 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:17:27,986 INFO misc.py line 117 726] Train: [5/20][8/510] Data 2.838 (3.795) Batch 24.014 (27.406) Remain 62:03:31 loss: 0.1911 loss_seg: 0.1052 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:17:53,652 INFO misc.py line 117 726] Train: [5/20][9/510] Data 2.595 (3.595) Batch 25.665 (27.116) Remain 61:23:39 loss: 0.2412 loss_seg: 0.1461 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:18:26,455 INFO misc.py line 117 726] Train: [5/20][10/510] Data 3.725 (3.614) Batch 32.803 (27.928) Remain 63:13:34 loss: 0.2768 loss_seg: 0.1748 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:18:52,902 INFO misc.py line 117 726] Train: [5/20][11/510] Data 4.736 (3.754) Batch 26.447 (27.743) Remain 62:47:57 loss: 0.2055 loss_seg: 0.1179 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:19:10,267 INFO misc.py line 117 726] Train: [5/20][12/510] Data 1.868 (3.544) Batch 17.365 (26.590) Remain 60:10:54 loss: 0.2509 loss_seg: 0.1531 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:19:42,138 INFO misc.py line 117 726] Train: [5/20][13/510] Data 4.477 (3.638) Batch 31.870 (27.118) Remain 61:22:09 loss: 0.2859 loss_seg: 0.1863 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:20:05,256 INFO misc.py line 117 726] Train: [5/20][14/510] Data 2.019 (3.491) Batch 23.118 (26.754) Remain 60:32:20 loss: 0.2548 loss_seg: 0.1589 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:20:35,639 INFO misc.py line 117 726] Train: [5/20][15/510] Data 3.870 (3.522) Batch 30.383 (27.057) Remain 61:12:57 loss: 0.2538 loss_seg: 0.1594 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:21:05,048 INFO misc.py line 117 726] Train: [5/20][16/510] Data 3.370 (3.510) Batch 29.409 (27.238) Remain 61:37:03 loss: 0.1829 loss_seg: 0.0967 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:21:32,619 INFO misc.py line 117 726] Train: [5/20][17/510] Data 2.944 (3.470) Batch 27.571 (27.261) Remain 61:39:50 loss: 0.2178 loss_seg: 0.1264 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:21:57,751 INFO misc.py line 117 726] Train: [5/20][18/510] Data 2.546 (3.408) Batch 25.132 (27.120) Remain 61:20:07 loss: 0.2219 loss_seg: 0.1330 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:22:23,152 INFO misc.py line 117 726] Train: [5/20][19/510] Data 3.286 (3.401) Batch 25.401 (27.012) Remain 61:05:05 loss: 0.2016 loss_seg: 0.1124 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:22:49,224 INFO misc.py line 117 726] Train: [5/20][20/510] Data 2.949 (3.374) Batch 26.072 (26.957) Remain 60:57:08 loss: 0.2476 loss_seg: 0.1491 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:23:28,317 INFO misc.py line 117 726] Train: [5/20][21/510] Data 10.077 (3.746) Batch 39.093 (27.631) Remain 62:28:08 loss: 0.2074 loss_seg: 0.1139 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0443 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:24:04,373 INFO misc.py line 117 726] Train: [5/20][22/510] Data 4.791 (3.801) Batch 36.056 (28.074) Remain 63:27:49 loss: 0.2541 loss_seg: 0.1549 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:24:36,440 INFO misc.py line 117 726] Train: [5/20][23/510] Data 4.231 (3.823) Batch 32.067 (28.274) Remain 63:54:26 loss: 0.2291 loss_seg: 0.1390 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:25:13,916 INFO misc.py line 117 726] Train: [5/20][24/510] Data 4.767 (3.868) Batch 37.476 (28.712) Remain 64:53:23 loss: 0.2405 loss_seg: 0.1446 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:25:34,026 INFO misc.py line 117 726] Train: [5/20][25/510] Data 1.930 (3.780) Batch 20.110 (28.321) Remain 63:59:53 loss: 0.2170 loss_seg: 0.1264 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:25:59,014 INFO misc.py line 117 726] Train: [5/20][26/510] Data 3.384 (3.763) Batch 24.988 (28.176) Remain 63:39:46 loss: 0.2048 loss_seg: 0.1148 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:26:25,987 INFO misc.py line 117 726] Train: [5/20][27/510] Data 2.484 (3.709) Batch 26.973 (28.126) Remain 63:32:30 loss: 0.2681 loss_seg: 0.1715 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:26:59,690 INFO misc.py line 117 726] Train: [5/20][28/510] Data 4.096 (3.725) Batch 33.703 (28.349) Remain 64:02:16 loss: 0.2242 loss_seg: 0.1325 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:27:18,353 INFO misc.py line 117 726] Train: [5/20][29/510] Data 1.843 (3.652) Batch 18.663 (27.977) Remain 63:11:18 loss: 0.2860 loss_seg: 0.1925 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:27:47,774 INFO misc.py line 117 726] Train: [5/20][30/510] Data 3.416 (3.644) Batch 29.421 (28.030) Remain 63:18:05 loss: 0.2652 loss_seg: 0.1661 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:28:12,931 INFO misc.py line 117 726] Train: [5/20][31/510] Data 2.405 (3.599) Batch 25.157 (27.928) Remain 63:03:43 loss: 0.2170 loss_seg: 0.1265 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:28:46,818 INFO misc.py line 117 726] Train: [5/20][32/510] Data 3.495 (3.596) Batch 33.887 (28.133) Remain 63:31:05 loss: 0.2147 loss_seg: 0.1265 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:29:10,856 INFO misc.py line 117 726] Train: [5/20][33/510] Data 2.108 (3.546) Batch 24.038 (27.997) Remain 63:12:08 loss: 0.2868 loss_seg: 0.1801 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:29:45,418 INFO misc.py line 117 726] Train: [5/20][34/510] Data 6.189 (3.632) Batch 34.562 (28.208) Remain 63:40:21 loss: 0.2592 loss_seg: 0.1681 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:30:14,082 INFO misc.py line 117 726] Train: [5/20][35/510] Data 4.532 (3.660) Batch 28.664 (28.223) Remain 63:41:48 loss: 0.2009 loss_seg: 0.1105 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:30:44,058 INFO misc.py line 117 726] Train: [5/20][36/510] Data 3.723 (3.662) Batch 29.976 (28.276) Remain 63:48:32 loss: 0.3173 loss_seg: 0.2033 loss_superpoint_edge: 0.0473 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:31:10,612 INFO misc.py line 117 726] Train: [5/20][37/510] Data 2.830 (3.637) Batch 26.554 (28.225) Remain 63:41:12 loss: 0.2167 loss_seg: 0.1280 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:31:39,250 INFO misc.py line 117 726] Train: [5/20][38/510] Data 2.897 (3.616) Batch 28.638 (28.237) Remain 63:42:20 loss: 0.2507 loss_seg: 0.1526 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:32:11,199 INFO misc.py line 117 726] Train: [5/20][39/510] Data 5.222 (3.661) Batch 31.949 (28.340) Remain 63:55:49 loss: 0.2098 loss_seg: 0.1257 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:32:42,270 INFO misc.py line 117 726] Train: [5/20][40/510] Data 3.292 (3.651) Batch 31.071 (28.414) Remain 64:05:20 loss: 0.2193 loss_seg: 0.1276 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:33:08,560 INFO misc.py line 117 726] Train: [5/20][41/510] Data 3.004 (3.634) Batch 26.290 (28.358) Remain 63:57:18 loss: 0.1759 loss_seg: 0.0930 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:33:43,990 INFO misc.py line 117 726] Train: [5/20][42/510] Data 5.081 (3.671) Batch 35.430 (28.539) Remain 64:21:21 loss: 0.2340 loss_seg: 0.1372 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:34:08,005 INFO misc.py line 117 726] Train: [5/20][43/510] Data 2.965 (3.653) Batch 24.014 (28.426) Remain 64:05:35 loss: 0.2185 loss_seg: 0.1297 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:34:29,868 INFO misc.py line 117 726] Train: [5/20][44/510] Data 2.686 (3.630) Batch 21.863 (28.266) Remain 63:43:27 loss: 0.2131 loss_seg: 0.1190 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:34:49,958 INFO misc.py line 117 726] Train: [5/20][45/510] Data 1.636 (3.582) Batch 20.090 (28.071) Remain 63:16:39 loss: 0.2056 loss_seg: 0.1174 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:35:03,061 INFO misc.py line 117 726] Train: [5/20][46/510] Data 1.687 (3.538) Batch 13.103 (27.723) Remain 62:29:06 loss: 0.1894 loss_seg: 0.1019 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:35:32,698 INFO misc.py line 117 726] Train: [5/20][47/510] Data 3.796 (3.544) Batch 29.637 (27.767) Remain 62:34:32 loss: 0.2250 loss_seg: 0.1342 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:35:49,004 INFO misc.py line 117 726] Train: [5/20][48/510] Data 1.986 (3.509) Batch 16.306 (27.512) Remain 61:59:38 loss: 0.3048 loss_seg: 0.2023 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:36:19,682 INFO misc.py line 117 726] Train: [5/20][49/510] Data 4.698 (3.535) Batch 30.678 (27.581) Remain 62:08:29 loss: 0.4174 loss_seg: 0.3048 loss_superpoint_edge: 0.0423 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:36:48,155 INFO misc.py line 117 726] Train: [5/20][50/510] Data 3.680 (3.538) Batch 28.473 (27.600) Remain 62:10:35 loss: 0.2706 loss_seg: 0.1690 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:36:48,156 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 07:37:17,258 INFO misc.py line 117 726] Train: [5/20][51/510] Data 3.994 (3.548) Batch 29.103 (27.631) Remain 62:14:21 loss: 0.2860 loss_seg: 0.1890 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:37:39,013 INFO misc.py line 117 726] Train: [5/20][52/510] Data 2.311 (3.522) Batch 21.755 (27.511) Remain 61:57:41 loss: 0.2519 loss_seg: 0.1478 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:38:04,744 INFO misc.py line 117 726] Train: [5/20][53/510] Data 3.940 (3.531) Batch 25.731 (27.476) Remain 61:52:25 loss: 0.2904 loss_seg: 0.1910 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:38:33,851 INFO misc.py line 117 726] Train: [5/20][54/510] Data 3.710 (3.534) Batch 29.107 (27.508) Remain 61:56:17 loss: 0.2429 loss_seg: 0.1525 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:39:05,608 INFO misc.py line 117 726] Train: [5/20][55/510] Data 3.926 (3.542) Batch 31.758 (27.589) Remain 62:06:52 loss: 0.2237 loss_seg: 0.1330 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:39:37,333 INFO misc.py line 117 726] Train: [5/20][56/510] Data 4.650 (3.563) Batch 31.725 (27.667) Remain 62:16:57 loss: 0.2593 loss_seg: 0.1633 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:40:01,730 INFO misc.py line 117 726] Train: [5/20][57/510] Data 2.683 (3.546) Batch 24.397 (27.607) Remain 62:08:18 loss: 0.2426 loss_seg: 0.1499 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:40:34,520 INFO misc.py line 117 726] Train: [5/20][58/510] Data 5.215 (3.577) Batch 32.790 (27.701) Remain 62:20:34 loss: 0.3828 loss_seg: 0.2735 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:41:04,644 INFO misc.py line 117 726] Train: [5/20][59/510] Data 3.174 (3.570) Batch 30.125 (27.744) Remain 62:25:57 loss: 0.2313 loss_seg: 0.1365 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:41:30,434 INFO misc.py line 117 726] Train: [5/20][60/510] Data 2.977 (3.559) Batch 25.790 (27.710) Remain 62:20:51 loss: 0.2837 loss_seg: 0.1754 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:41:52,223 INFO misc.py line 117 726] Train: [5/20][61/510] Data 2.093 (3.534) Batch 21.789 (27.608) Remain 62:06:37 loss: 0.2367 loss_seg: 0.1401 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:42:25,119 INFO misc.py line 117 726] Train: [5/20][62/510] Data 4.322 (3.547) Batch 32.896 (27.698) Remain 62:18:15 loss: 0.2545 loss_seg: 0.1579 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:42:46,116 INFO misc.py line 117 726] Train: [5/20][63/510] Data 4.177 (3.558) Batch 20.997 (27.586) Remain 62:02:43 loss: 0.2456 loss_seg: 0.1497 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:43:23,637 INFO misc.py line 117 726] Train: [5/20][64/510] Data 11.271 (3.684) Batch 37.521 (27.749) Remain 62:24:14 loss: 0.1888 loss_seg: 0.1032 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:44:02,509 INFO misc.py line 117 726] Train: [5/20][65/510] Data 5.582 (3.715) Batch 38.872 (27.928) Remain 62:47:59 loss: 0.2112 loss_seg: 0.1245 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:44:40,257 INFO misc.py line 117 726] Train: [5/20][66/510] Data 5.960 (3.750) Batch 37.748 (28.084) Remain 63:08:32 loss: 0.2444 loss_seg: 0.1548 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:45:18,287 INFO misc.py line 117 726] Train: [5/20][67/510] Data 7.696 (3.812) Batch 38.030 (28.240) Remain 63:29:02 loss: 0.1963 loss_seg: 0.1081 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:45:46,474 INFO misc.py line 117 726] Train: [5/20][68/510] Data 3.238 (3.803) Batch 28.186 (28.239) Remain 63:28:27 loss: 0.2518 loss_seg: 0.1500 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:46:16,817 INFO misc.py line 117 726] Train: [5/20][69/510] Data 5.169 (3.824) Batch 30.343 (28.271) Remain 63:32:17 loss: 0.2742 loss_seg: 0.1836 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:46:46,016 INFO misc.py line 117 726] Train: [5/20][70/510] Data 5.719 (3.852) Batch 29.199 (28.284) Remain 63:33:41 loss: 0.2013 loss_seg: 0.1072 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:47:31,793 INFO misc.py line 117 726] Train: [5/20][71/510] Data 12.195 (3.975) Batch 45.776 (28.542) Remain 64:07:53 loss: 0.2857 loss_seg: 0.1868 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:47:58,827 INFO misc.py line 117 726] Train: [5/20][72/510] Data 3.247 (3.964) Batch 27.034 (28.520) Remain 64:04:28 loss: 0.2309 loss_seg: 0.1365 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:48:31,035 INFO misc.py line 117 726] Train: [5/20][73/510] Data 4.266 (3.969) Batch 32.208 (28.573) Remain 64:11:05 loss: 0.2290 loss_seg: 0.1408 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:48:59,628 INFO misc.py line 117 726] Train: [5/20][74/510] Data 2.502 (3.948) Batch 28.593 (28.573) Remain 64:10:39 loss: 0.2865 loss_seg: 0.1944 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:49:23,509 INFO misc.py line 117 726] Train: [5/20][75/510] Data 2.128 (3.923) Batch 23.881 (28.508) Remain 64:01:24 loss: 0.2452 loss_seg: 0.1465 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:49:47,164 INFO misc.py line 117 726] Train: [5/20][76/510] Data 4.498 (3.931) Batch 23.655 (28.441) Remain 63:51:58 loss: 0.3999 loss_seg: 0.3093 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:50:14,337 INFO misc.py line 117 726] Train: [5/20][77/510] Data 2.624 (3.913) Batch 27.173 (28.424) Remain 63:49:11 loss: 0.3023 loss_seg: 0.1982 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:50:37,700 INFO misc.py line 117 726] Train: [5/20][78/510] Data 2.648 (3.896) Batch 23.364 (28.357) Remain 63:39:37 loss: 0.2013 loss_seg: 0.1121 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:51:11,245 INFO misc.py line 117 726] Train: [5/20][79/510] Data 3.870 (3.896) Batch 33.544 (28.425) Remain 63:48:20 loss: 0.1858 loss_seg: 0.1011 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:51:49,313 INFO misc.py line 117 726] Train: [5/20][80/510] Data 5.307 (3.914) Batch 38.068 (28.550) Remain 64:04:44 loss: 0.2488 loss_seg: 0.1549 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:52:22,331 INFO misc.py line 117 726] Train: [5/20][81/510] Data 3.717 (3.912) Batch 33.018 (28.607) Remain 64:11:58 loss: 0.1572 loss_seg: 0.0784 loss_superpoint_edge: 0.0118 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:52:55,475 INFO misc.py line 117 726] Train: [5/20][82/510] Data 4.196 (3.915) Batch 33.144 (28.665) Remain 64:19:13 loss: 0.2794 loss_seg: 0.1781 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:53:27,899 INFO misc.py line 117 726] Train: [5/20][83/510] Data 4.614 (3.924) Batch 32.424 (28.712) Remain 64:25:04 loss: 0.2341 loss_seg: 0.1411 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:53:56,446 INFO misc.py line 117 726] Train: [5/20][84/510] Data 3.616 (3.920) Batch 28.547 (28.710) Remain 64:24:19 loss: 0.2460 loss_seg: 0.1494 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:54:28,796 INFO misc.py line 117 726] Train: [5/20][85/510] Data 4.050 (3.922) Batch 32.350 (28.754) Remain 64:29:49 loss: 0.2402 loss_seg: 0.1420 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:54:49,894 INFO misc.py line 117 726] Train: [5/20][86/510] Data 2.857 (3.909) Batch 21.098 (28.662) Remain 64:16:55 loss: 0.2776 loss_seg: 0.1794 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:55:28,417 INFO misc.py line 117 726] Train: [5/20][87/510] Data 5.282 (3.925) Batch 38.523 (28.779) Remain 64:32:15 loss: 0.2530 loss_seg: 0.1557 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:55:57,789 INFO misc.py line 117 726] Train: [5/20][88/510] Data 3.693 (3.922) Batch 29.372 (28.786) Remain 64:32:42 loss: 0.2604 loss_seg: 0.1664 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:56:26,509 INFO misc.py line 117 726] Train: [5/20][89/510] Data 2.999 (3.912) Batch 28.720 (28.785) Remain 64:32:07 loss: 0.2366 loss_seg: 0.1388 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:56:58,173 INFO misc.py line 117 726] Train: [5/20][90/510] Data 2.866 (3.900) Batch 31.664 (28.819) Remain 64:36:05 loss: 0.2365 loss_seg: 0.1459 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:57:31,056 INFO misc.py line 117 726] Train: [5/20][91/510] Data 3.444 (3.894) Batch 32.883 (28.865) Remain 64:41:49 loss: 0.4013 loss_seg: 0.2772 loss_superpoint_edge: 0.0594 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:58:02,199 INFO misc.py line 117 726] Train: [5/20][92/510] Data 3.127 (3.886) Batch 31.143 (28.890) Remain 64:44:47 loss: 0.2318 loss_seg: 0.1367 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:58:28,902 INFO misc.py line 117 726] Train: [5/20][93/510] Data 2.304 (3.868) Batch 26.702 (28.866) Remain 64:41:02 loss: 0.2799 loss_seg: 0.1756 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:58:52,044 INFO misc.py line 117 726] Train: [5/20][94/510] Data 2.346 (3.852) Batch 23.143 (28.803) Remain 64:32:06 loss: 0.2341 loss_seg: 0.1398 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:59:21,348 INFO misc.py line 117 726] Train: [5/20][95/510] Data 3.608 (3.849) Batch 29.303 (28.809) Remain 64:32:21 loss: 0.2699 loss_seg: 0.1687 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 07:59:48,366 INFO misc.py line 117 726] Train: [5/20][96/510] Data 4.958 (3.861) Batch 27.018 (28.789) Remain 64:29:17 loss: 0.3532 loss_seg: 0.2584 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:00:07,642 INFO misc.py line 117 726] Train: [5/20][97/510] Data 2.159 (3.843) Batch 19.277 (28.688) Remain 64:15:12 loss: 0.1816 loss_seg: 0.0978 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:00:34,879 INFO misc.py line 117 726] Train: [5/20][98/510] Data 2.810 (3.832) Batch 27.236 (28.673) Remain 64:12:40 loss: 0.2241 loss_seg: 0.1301 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:00:54,673 INFO misc.py line 117 726] Train: [5/20][99/510] Data 4.136 (3.835) Batch 19.795 (28.580) Remain 63:59:46 loss: 0.2589 loss_seg: 0.1644 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:01:33,189 INFO misc.py line 117 726] Train: [5/20][100/510] Data 8.132 (3.879) Batch 38.515 (28.683) Remain 64:13:03 loss: 0.2629 loss_seg: 0.1642 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0450 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:01:33,190 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 08:02:09,862 INFO misc.py line 117 726] Train: [5/20][101/510] Data 4.205 (3.883) Batch 36.674 (28.764) Remain 64:23:31 loss: 0.2165 loss_seg: 0.1265 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:02:49,506 INFO misc.py line 117 726] Train: [5/20][102/510] Data 8.867 (3.933) Batch 39.643 (28.874) Remain 64:37:48 loss: 0.2430 loss_seg: 0.1555 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:03:14,440 INFO misc.py line 117 726] Train: [5/20][103/510] Data 3.122 (3.925) Batch 24.934 (28.835) Remain 64:32:02 loss: 0.2395 loss_seg: 0.1506 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:03:46,236 INFO misc.py line 117 726] Train: [5/20][104/510] Data 2.912 (3.915) Batch 31.796 (28.864) Remain 64:35:29 loss: 0.3036 loss_seg: 0.1958 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:04:17,301 INFO misc.py line 117 726] Train: [5/20][105/510] Data 3.290 (3.909) Batch 31.065 (28.886) Remain 64:37:54 loss: 0.3429 loss_seg: 0.2273 loss_superpoint_edge: 0.0430 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:04:45,774 INFO misc.py line 117 726] Train: [5/20][106/510] Data 5.311 (3.922) Batch 28.473 (28.882) Remain 64:36:53 loss: 0.2555 loss_seg: 0.1585 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:05:14,437 INFO misc.py line 117 726] Train: [5/20][107/510] Data 3.976 (3.923) Batch 28.664 (28.880) Remain 64:36:07 loss: 0.2257 loss_seg: 0.1322 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:05:44,419 INFO misc.py line 117 726] Train: [5/20][108/510] Data 4.445 (3.928) Batch 29.982 (28.890) Remain 64:37:03 loss: 0.2564 loss_seg: 0.1642 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:06:12,543 INFO misc.py line 117 726] Train: [5/20][109/510] Data 3.195 (3.921) Batch 28.124 (28.883) Remain 64:35:36 loss: 0.2396 loss_seg: 0.1427 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:06:36,660 INFO misc.py line 117 726] Train: [5/20][110/510] Data 2.805 (3.910) Batch 24.116 (28.838) Remain 64:29:08 loss: 0.2257 loss_seg: 0.1317 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:07:08,138 INFO misc.py line 117 726] Train: [5/20][111/510] Data 6.045 (3.930) Batch 31.479 (28.863) Remain 64:31:56 loss: 0.3312 loss_seg: 0.2195 loss_superpoint_edge: 0.0436 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:07:43,863 INFO misc.py line 117 726] Train: [5/20][112/510] Data 3.987 (3.931) Batch 35.724 (28.926) Remain 64:39:54 loss: 0.2048 loss_seg: 0.1117 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0429 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:08:13,648 INFO misc.py line 117 726] Train: [5/20][113/510] Data 3.676 (3.928) Batch 29.785 (28.934) Remain 64:40:28 loss: 0.2286 loss_seg: 0.1379 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:08:46,105 INFO misc.py line 117 726] Train: [5/20][114/510] Data 5.032 (3.938) Batch 32.457 (28.965) Remain 64:44:14 loss: 0.2081 loss_seg: 0.1153 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:09:12,530 INFO misc.py line 117 726] Train: [5/20][115/510] Data 2.960 (3.930) Batch 26.425 (28.943) Remain 64:40:43 loss: 0.2651 loss_seg: 0.1658 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:09:41,684 INFO misc.py line 117 726] Train: [5/20][116/510] Data 5.767 (3.946) Batch 29.154 (28.944) Remain 64:40:29 loss: 0.2390 loss_seg: 0.1495 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:10:06,819 INFO misc.py line 117 726] Train: [5/20][117/510] Data 3.457 (3.942) Batch 25.134 (28.911) Remain 64:35:31 loss: 0.2289 loss_seg: 0.1417 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:10:28,645 INFO misc.py line 117 726] Train: [5/20][118/510] Data 2.078 (3.925) Batch 21.826 (28.849) Remain 64:26:47 loss: 0.2616 loss_seg: 0.1565 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:10:57,567 INFO misc.py line 117 726] Train: [5/20][119/510] Data 3.237 (3.919) Batch 28.923 (28.850) Remain 64:26:23 loss: 0.2253 loss_seg: 0.1328 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:11:23,132 INFO misc.py line 117 726] Train: [5/20][120/510] Data 2.397 (3.906) Batch 25.565 (28.822) Remain 64:22:08 loss: 0.2957 loss_seg: 0.1923 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:11:58,620 INFO misc.py line 117 726] Train: [5/20][121/510] Data 3.030 (3.899) Batch 35.487 (28.878) Remain 64:29:14 loss: 0.2128 loss_seg: 0.1216 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:12:18,171 INFO misc.py line 117 726] Train: [5/20][122/510] Data 1.795 (3.881) Batch 19.551 (28.800) Remain 64:18:15 loss: 0.3090 loss_seg: 0.2018 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:12:43,264 INFO misc.py line 117 726] Train: [5/20][123/510] Data 2.776 (3.872) Batch 25.093 (28.769) Remain 64:13:38 loss: 0.2412 loss_seg: 0.1446 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:13:07,208 INFO misc.py line 117 726] Train: [5/20][124/510] Data 3.671 (3.870) Batch 23.944 (28.729) Remain 64:07:48 loss: 0.1956 loss_seg: 0.1118 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:13:37,665 INFO misc.py line 117 726] Train: [5/20][125/510] Data 2.613 (3.860) Batch 30.456 (28.743) Remain 64:09:13 loss: 0.2384 loss_seg: 0.1429 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:13:58,568 INFO misc.py line 117 726] Train: [5/20][126/510] Data 2.331 (3.848) Batch 20.904 (28.680) Remain 64:00:13 loss: 0.2156 loss_seg: 0.1268 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:14:33,921 INFO misc.py line 117 726] Train: [5/20][127/510] Data 4.866 (3.856) Batch 35.353 (28.734) Remain 64:06:56 loss: 0.2792 loss_seg: 0.1824 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:15:07,529 INFO misc.py line 117 726] Train: [5/20][128/510] Data 5.040 (3.865) Batch 33.609 (28.773) Remain 64:11:41 loss: 0.2084 loss_seg: 0.1181 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:15:30,229 INFO misc.py line 117 726] Train: [5/20][129/510] Data 3.132 (3.860) Batch 22.700 (28.724) Remain 64:04:45 loss: 0.2181 loss_seg: 0.1279 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:15:57,577 INFO misc.py line 117 726] Train: [5/20][130/510] Data 3.181 (3.854) Batch 27.348 (28.714) Remain 64:02:49 loss: 0.3503 loss_seg: 0.2567 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:16:22,336 INFO misc.py line 117 726] Train: [5/20][131/510] Data 2.664 (3.845) Batch 24.759 (28.683) Remain 63:58:12 loss: 0.2248 loss_seg: 0.1309 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:16:43,872 INFO misc.py line 117 726] Train: [5/20][132/510] Data 2.841 (3.837) Batch 21.537 (28.627) Remain 63:50:19 loss: 0.2151 loss_seg: 0.1216 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:17:14,824 INFO misc.py line 117 726] Train: [5/20][133/510] Data 2.897 (3.830) Batch 30.951 (28.645) Remain 63:52:14 loss: 0.2900 loss_seg: 0.1872 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:17:50,800 INFO misc.py line 117 726] Train: [5/20][134/510] Data 4.818 (3.838) Batch 35.976 (28.701) Remain 63:59:14 loss: 0.2638 loss_seg: 0.1656 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:18:16,464 INFO misc.py line 117 726] Train: [5/20][135/510] Data 2.733 (3.829) Batch 25.664 (28.678) Remain 63:55:41 loss: 0.1911 loss_seg: 0.1042 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:18:50,981 INFO misc.py line 117 726] Train: [5/20][136/510] Data 4.072 (3.831) Batch 34.517 (28.722) Remain 64:01:05 loss: 0.2210 loss_seg: 0.1335 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:19:27,374 INFO misc.py line 117 726] Train: [5/20][137/510] Data 4.074 (3.833) Batch 36.393 (28.779) Remain 64:08:15 loss: 0.2666 loss_seg: 0.1688 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:19:58,754 INFO misc.py line 117 726] Train: [5/20][138/510] Data 4.625 (3.839) Batch 31.380 (28.798) Remain 64:10:21 loss: 0.2023 loss_seg: 0.1137 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:20:27,459 INFO misc.py line 117 726] Train: [5/20][139/510] Data 3.546 (3.836) Batch 28.705 (28.798) Remain 64:09:47 loss: 0.2182 loss_seg: 0.1291 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:20:47,922 INFO misc.py line 117 726] Train: [5/20][140/510] Data 2.289 (3.825) Batch 20.462 (28.737) Remain 64:01:10 loss: 0.2449 loss_seg: 0.1501 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:21:14,704 INFO misc.py line 117 726] Train: [5/20][141/510] Data 2.985 (3.819) Batch 26.782 (28.723) Remain 63:58:48 loss: 0.2519 loss_seg: 0.1540 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:21:36,989 INFO misc.py line 117 726] Train: [5/20][142/510] Data 2.886 (3.812) Batch 22.285 (28.676) Remain 63:52:08 loss: 0.2851 loss_seg: 0.1771 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:22:08,689 INFO misc.py line 117 726] Train: [5/20][143/510] Data 3.557 (3.811) Batch 31.700 (28.698) Remain 63:54:32 loss: 0.2242 loss_seg: 0.1323 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:22:38,287 INFO misc.py line 117 726] Train: [5/20][144/510] Data 3.609 (3.809) Batch 29.598 (28.704) Remain 63:54:54 loss: 0.2262 loss_seg: 0.1300 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:23:01,458 INFO misc.py line 117 726] Train: [5/20][145/510] Data 2.565 (3.800) Batch 23.170 (28.665) Remain 63:49:13 loss: 0.2710 loss_seg: 0.1837 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:23:31,573 INFO misc.py line 117 726] Train: [5/20][146/510] Data 3.139 (3.796) Batch 30.115 (28.676) Remain 63:50:06 loss: 0.2864 loss_seg: 0.1823 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:23:52,857 INFO misc.py line 117 726] Train: [5/20][147/510] Data 2.616 (3.788) Batch 21.284 (28.624) Remain 63:42:46 loss: 0.2938 loss_seg: 0.1943 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:24:17,888 INFO misc.py line 117 726] Train: [5/20][148/510] Data 2.784 (3.781) Batch 25.031 (28.600) Remain 63:38:59 loss: 0.2240 loss_seg: 0.1293 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:24:41,387 INFO misc.py line 117 726] Train: [5/20][149/510] Data 2.539 (3.772) Batch 23.499 (28.565) Remain 63:33:50 loss: 0.2351 loss_seg: 0.1368 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:25:03,129 INFO misc.py line 117 726] Train: [5/20][150/510] Data 2.332 (3.762) Batch 21.741 (28.518) Remain 63:27:10 loss: 0.2668 loss_seg: 0.1656 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:25:03,129 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 08:25:30,832 INFO misc.py line 117 726] Train: [5/20][151/510] Data 4.346 (3.766) Batch 27.704 (28.513) Remain 63:25:57 loss: 0.2102 loss_seg: 0.1197 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:25:58,873 INFO misc.py line 117 726] Train: [5/20][152/510] Data 4.288 (3.770) Batch 28.040 (28.509) Remain 63:25:03 loss: 0.2945 loss_seg: 0.1963 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:26:25,775 INFO misc.py line 117 726] Train: [5/20][153/510] Data 2.899 (3.764) Batch 26.902 (28.499) Remain 63:23:09 loss: 0.2717 loss_seg: 0.1745 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:26:56,619 INFO misc.py line 117 726] Train: [5/20][154/510] Data 3.240 (3.761) Batch 30.843 (28.514) Remain 63:24:45 loss: 0.2283 loss_seg: 0.1339 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:27:27,046 INFO misc.py line 117 726] Train: [5/20][155/510] Data 8.781 (3.794) Batch 30.428 (28.527) Remain 63:25:57 loss: 0.1959 loss_seg: 0.1040 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:27:54,384 INFO misc.py line 117 726] Train: [5/20][156/510] Data 2.850 (3.787) Batch 27.337 (28.519) Remain 63:24:26 loss: 0.2868 loss_seg: 0.1871 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:28:21,342 INFO misc.py line 117 726] Train: [5/20][157/510] Data 2.786 (3.781) Batch 26.958 (28.509) Remain 63:22:37 loss: 0.2537 loss_seg: 0.1524 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:28:42,996 INFO misc.py line 117 726] Train: [5/20][158/510] Data 2.608 (3.773) Batch 21.655 (28.465) Remain 63:16:14 loss: 0.2913 loss_seg: 0.1904 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:29:14,968 INFO misc.py line 117 726] Train: [5/20][159/510] Data 3.376 (3.771) Batch 31.972 (28.487) Remain 63:18:46 loss: 0.2218 loss_seg: 0.1281 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:29:40,962 INFO misc.py line 117 726] Train: [5/20][160/510] Data 2.369 (3.762) Batch 25.992 (28.471) Remain 63:16:10 loss: 0.2299 loss_seg: 0.1340 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:30:13,339 INFO misc.py line 117 726] Train: [5/20][161/510] Data 4.495 (3.766) Batch 32.378 (28.496) Remain 63:19:00 loss: 0.2521 loss_seg: 0.1557 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:30:41,531 INFO misc.py line 117 726] Train: [5/20][162/510] Data 3.131 (3.762) Batch 28.192 (28.494) Remain 63:18:16 loss: 0.2585 loss_seg: 0.1577 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:31:19,857 INFO misc.py line 117 726] Train: [5/20][163/510] Data 4.419 (3.767) Batch 38.325 (28.556) Remain 63:25:59 loss: 0.2779 loss_seg: 0.1775 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:31:40,193 INFO misc.py line 117 726] Train: [5/20][164/510] Data 2.102 (3.756) Batch 20.336 (28.505) Remain 63:18:42 loss: 0.1972 loss_seg: 0.1086 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:32:10,435 INFO misc.py line 117 726] Train: [5/20][165/510] Data 2.738 (3.750) Batch 30.242 (28.515) Remain 63:19:39 loss: 0.2348 loss_seg: 0.1351 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:32:43,090 INFO misc.py line 117 726] Train: [5/20][166/510] Data 4.229 (3.753) Batch 32.655 (28.541) Remain 63:22:34 loss: 0.2306 loss_seg: 0.1391 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:33:16,063 INFO misc.py line 117 726] Train: [5/20][167/510] Data 4.966 (3.760) Batch 32.973 (28.568) Remain 63:25:41 loss: 0.2914 loss_seg: 0.1909 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:33:30,302 INFO misc.py line 117 726] Train: [5/20][168/510] Data 2.079 (3.750) Batch 14.239 (28.481) Remain 63:13:39 loss: 0.3706 loss_seg: 0.2746 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:33:54,898 INFO misc.py line 117 726] Train: [5/20][169/510] Data 2.934 (3.745) Batch 24.595 (28.457) Remain 63:10:03 loss: 0.2676 loss_seg: 0.1690 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:34:23,727 INFO misc.py line 117 726] Train: [5/20][170/510] Data 4.267 (3.748) Batch 28.830 (28.460) Remain 63:09:52 loss: 0.2695 loss_seg: 0.1794 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:34:42,170 INFO misc.py line 117 726] Train: [5/20][171/510] Data 1.855 (3.737) Batch 18.443 (28.400) Remain 63:01:28 loss: 0.2031 loss_seg: 0.1166 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:35:16,010 INFO misc.py line 117 726] Train: [5/20][172/510] Data 4.344 (3.741) Batch 33.840 (28.432) Remain 63:05:16 loss: 0.3058 loss_seg: 0.2042 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:35:40,863 INFO misc.py line 117 726] Train: [5/20][173/510] Data 2.172 (3.731) Batch 24.853 (28.411) Remain 63:02:00 loss: 0.2244 loss_seg: 0.1315 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:36:00,946 INFO misc.py line 117 726] Train: [5/20][174/510] Data 1.825 (3.720) Batch 20.083 (28.362) Remain 62:55:02 loss: 0.2453 loss_seg: 0.1519 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:36:28,121 INFO misc.py line 117 726] Train: [5/20][175/510] Data 2.362 (3.712) Batch 27.174 (28.356) Remain 62:53:39 loss: 0.1858 loss_seg: 0.1012 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:37:00,692 INFO misc.py line 117 726] Train: [5/20][176/510] Data 4.805 (3.719) Batch 32.571 (28.380) Remain 62:56:25 loss: 0.2447 loss_seg: 0.1492 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:37:32,627 INFO misc.py line 117 726] Train: [5/20][177/510] Data 5.926 (3.731) Batch 31.935 (28.400) Remain 62:58:40 loss: 0.2360 loss_seg: 0.1432 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:38:05,349 INFO misc.py line 117 726] Train: [5/20][178/510] Data 4.678 (3.737) Batch 32.722 (28.425) Remain 63:01:29 loss: 0.2540 loss_seg: 0.1529 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:38:32,474 INFO misc.py line 117 726] Train: [5/20][179/510] Data 2.521 (3.730) Batch 27.125 (28.418) Remain 63:00:01 loss: 0.2327 loss_seg: 0.1370 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:39:03,235 INFO misc.py line 117 726] Train: [5/20][180/510] Data 3.519 (3.729) Batch 30.761 (28.431) Remain 63:01:18 loss: 0.2465 loss_seg: 0.1547 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:39:29,900 INFO misc.py line 117 726] Train: [5/20][181/510] Data 3.314 (3.726) Batch 26.665 (28.421) Remain 62:59:31 loss: 0.2869 loss_seg: 0.1868 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:39:45,607 INFO misc.py line 117 726] Train: [5/20][182/510] Data 1.737 (3.715) Batch 15.707 (28.350) Remain 62:49:36 loss: 0.3712 loss_seg: 0.2556 loss_superpoint_edge: 0.0456 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:40:21,029 INFO misc.py line 117 726] Train: [5/20][183/510] Data 3.932 (3.716) Batch 35.422 (28.389) Remain 62:54:21 loss: 0.2246 loss_seg: 0.1312 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:40:47,203 INFO misc.py line 117 726] Train: [5/20][184/510] Data 2.967 (3.712) Batch 26.174 (28.377) Remain 62:52:15 loss: 0.2420 loss_seg: 0.1451 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:41:22,236 INFO misc.py line 117 726] Train: [5/20][185/510] Data 3.592 (3.712) Batch 35.032 (28.414) Remain 62:56:38 loss: 0.2543 loss_seg: 0.1570 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:41:39,567 INFO misc.py line 117 726] Train: [5/20][186/510] Data 2.011 (3.702) Batch 17.331 (28.353) Remain 62:48:07 loss: 0.2450 loss_seg: 0.1521 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:42:10,376 INFO misc.py line 117 726] Train: [5/20][187/510] Data 3.853 (3.703) Batch 30.808 (28.366) Remain 62:49:25 loss: 0.3146 loss_seg: 0.2155 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:42:45,099 INFO misc.py line 117 726] Train: [5/20][188/510] Data 6.006 (3.716) Batch 34.723 (28.401) Remain 62:53:30 loss: 0.2385 loss_seg: 0.1415 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:43:28,602 INFO misc.py line 117 726] Train: [5/20][189/510] Data 10.730 (3.753) Batch 43.503 (28.482) Remain 63:03:49 loss: 0.2244 loss_seg: 0.1346 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:43:52,944 INFO misc.py line 117 726] Train: [5/20][190/510] Data 2.881 (3.749) Batch 24.342 (28.460) Remain 63:00:24 loss: 0.1821 loss_seg: 0.0994 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:44:32,903 INFO misc.py line 117 726] Train: [5/20][191/510] Data 8.979 (3.776) Batch 39.959 (28.521) Remain 63:08:03 loss: 0.2972 loss_seg: 0.1930 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:44:56,594 INFO misc.py line 117 726] Train: [5/20][192/510] Data 2.544 (3.770) Batch 23.692 (28.495) Remain 63:04:11 loss: 0.2058 loss_seg: 0.1151 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:45:21,187 INFO misc.py line 117 726] Train: [5/20][193/510] Data 3.370 (3.768) Batch 24.593 (28.475) Remain 63:00:59 loss: 0.3445 loss_seg: 0.2468 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:45:47,498 INFO misc.py line 117 726] Train: [5/20][194/510] Data 3.216 (3.765) Batch 26.311 (28.464) Remain 62:59:00 loss: 0.2565 loss_seg: 0.1565 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:46:24,704 INFO misc.py line 117 726] Train: [5/20][195/510] Data 6.174 (3.778) Batch 37.206 (28.509) Remain 63:04:34 loss: 0.3011 loss_seg: 0.2044 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:46:45,939 INFO misc.py line 117 726] Train: [5/20][196/510] Data 2.247 (3.770) Batch 21.235 (28.471) Remain 62:59:06 loss: 0.2691 loss_seg: 0.1675 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:47:09,741 INFO misc.py line 117 726] Train: [5/20][197/510] Data 2.256 (3.762) Batch 23.802 (28.447) Remain 62:55:26 loss: 0.2127 loss_seg: 0.1215 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:47:40,455 INFO misc.py line 117 726] Train: [5/20][198/510] Data 4.145 (3.764) Batch 30.714 (28.459) Remain 62:56:30 loss: 0.2837 loss_seg: 0.1825 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:48:07,592 INFO misc.py line 117 726] Train: [5/20][199/510] Data 2.964 (3.760) Batch 27.138 (28.452) Remain 62:55:08 loss: 0.2465 loss_seg: 0.1462 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:48:36,399 INFO misc.py line 117 726] Train: [5/20][200/510] Data 3.511 (3.758) Batch 28.807 (28.454) Remain 62:54:53 loss: 0.2334 loss_seg: 0.1377 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:48:36,400 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 08:48:58,389 INFO misc.py line 117 726] Train: [5/20][201/510] Data 2.833 (3.754) Batch 21.989 (28.421) Remain 62:50:05 loss: 0.1729 loss_seg: 0.0901 loss_superpoint_edge: 0.0145 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:49:25,373 INFO misc.py line 117 726] Train: [5/20][202/510] Data 3.094 (3.750) Batch 26.984 (28.414) Remain 62:48:39 loss: 0.2591 loss_seg: 0.1624 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:49:49,549 INFO misc.py line 117 726] Train: [5/20][203/510] Data 2.813 (3.746) Batch 24.177 (28.393) Remain 62:45:22 loss: 0.3111 loss_seg: 0.2185 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:50:25,646 INFO misc.py line 117 726] Train: [5/20][204/510] Data 3.789 (3.746) Batch 36.097 (28.431) Remain 62:49:59 loss: 0.2976 loss_seg: 0.2041 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:50:49,660 INFO misc.py line 117 726] Train: [5/20][205/510] Data 3.107 (3.743) Batch 24.014 (28.409) Remain 62:46:36 loss: 0.2799 loss_seg: 0.1727 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:51:13,458 INFO misc.py line 117 726] Train: [5/20][206/510] Data 4.246 (3.745) Batch 23.798 (28.387) Remain 62:43:07 loss: 0.2511 loss_seg: 0.1564 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:51:33,869 INFO misc.py line 117 726] Train: [5/20][207/510] Data 2.235 (3.738) Batch 20.411 (28.348) Remain 62:37:28 loss: 0.2814 loss_seg: 0.1772 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:51:58,814 INFO misc.py line 117 726] Train: [5/20][208/510] Data 3.156 (3.735) Batch 24.945 (28.331) Remain 62:34:48 loss: 0.2790 loss_seg: 0.1768 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:52:22,600 INFO misc.py line 117 726] Train: [5/20][209/510] Data 2.701 (3.730) Batch 23.786 (28.309) Remain 62:31:24 loss: 0.1899 loss_seg: 0.1020 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:52:54,070 INFO misc.py line 117 726] Train: [5/20][210/510] Data 4.931 (3.736) Batch 31.470 (28.324) Remain 62:32:57 loss: 0.2370 loss_seg: 0.1429 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:53:26,091 INFO misc.py line 117 726] Train: [5/20][211/510] Data 4.154 (3.738) Batch 32.021 (28.342) Remain 62:34:50 loss: 0.2565 loss_seg: 0.1591 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:54:01,386 INFO misc.py line 117 726] Train: [5/20][212/510] Data 5.961 (3.748) Batch 35.295 (28.375) Remain 62:38:46 loss: 0.2505 loss_seg: 0.1528 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:54:41,707 INFO misc.py line 117 726] Train: [5/20][213/510] Data 9.243 (3.775) Batch 40.321 (28.432) Remain 62:45:50 loss: 0.3336 loss_seg: 0.2370 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:55:07,341 INFO misc.py line 117 726] Train: [5/20][214/510] Data 4.467 (3.778) Batch 25.634 (28.419) Remain 62:43:36 loss: 0.2937 loss_seg: 0.1949 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:55:39,452 INFO misc.py line 117 726] Train: [5/20][215/510] Data 5.342 (3.785) Batch 32.111 (28.436) Remain 62:45:26 loss: 0.3304 loss_seg: 0.2310 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:56:08,514 INFO misc.py line 117 726] Train: [5/20][216/510] Data 3.179 (3.782) Batch 29.062 (28.439) Remain 62:45:21 loss: 0.2386 loss_seg: 0.1432 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:56:31,494 INFO misc.py line 117 726] Train: [5/20][217/510] Data 2.349 (3.776) Batch 22.980 (28.414) Remain 62:41:30 loss: 0.1994 loss_seg: 0.1097 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:56:56,355 INFO misc.py line 117 726] Train: [5/20][218/510] Data 5.530 (3.784) Batch 24.860 (28.397) Remain 62:38:50 loss: 0.2249 loss_seg: 0.1295 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:57:15,049 INFO misc.py line 117 726] Train: [5/20][219/510] Data 2.000 (3.776) Batch 18.694 (28.352) Remain 62:32:25 loss: 0.2365 loss_seg: 0.1439 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:57:42,766 INFO misc.py line 117 726] Train: [5/20][220/510] Data 3.010 (3.772) Batch 27.717 (28.349) Remain 62:31:33 loss: 0.2450 loss_seg: 0.1517 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:58:09,492 INFO misc.py line 117 726] Train: [5/20][221/510] Data 3.234 (3.770) Batch 26.727 (28.342) Remain 62:30:06 loss: 0.2734 loss_seg: 0.1752 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:58:34,016 INFO misc.py line 117 726] Train: [5/20][222/510] Data 2.628 (3.764) Batch 24.523 (28.324) Remain 62:27:19 loss: 0.2458 loss_seg: 0.1450 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:59:03,185 INFO misc.py line 117 726] Train: [5/20][223/510] Data 3.497 (3.763) Batch 29.169 (28.328) Remain 62:27:21 loss: 0.2573 loss_seg: 0.1633 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 08:59:32,543 INFO misc.py line 117 726] Train: [5/20][224/510] Data 2.562 (3.758) Batch 29.358 (28.333) Remain 62:27:30 loss: 0.2569 loss_seg: 0.1536 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:00:02,917 INFO misc.py line 117 726] Train: [5/20][225/510] Data 3.045 (3.755) Batch 30.374 (28.342) Remain 62:28:14 loss: 0.2073 loss_seg: 0.1186 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:00:29,305 INFO misc.py line 117 726] Train: [5/20][226/510] Data 4.313 (3.757) Batch 26.387 (28.333) Remain 62:26:37 loss: 0.2202 loss_seg: 0.1296 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:00:58,756 INFO misc.py line 117 726] Train: [5/20][227/510] Data 3.110 (3.754) Batch 29.452 (28.338) Remain 62:26:48 loss: 0.2068 loss_seg: 0.1166 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:01:31,385 INFO misc.py line 117 726] Train: [5/20][228/510] Data 3.694 (3.754) Batch 32.628 (28.357) Remain 62:28:51 loss: 0.2284 loss_seg: 0.1359 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:01:56,266 INFO misc.py line 117 726] Train: [5/20][229/510] Data 2.577 (3.749) Batch 24.881 (28.342) Remain 62:26:20 loss: 0.2937 loss_seg: 0.1823 loss_superpoint_edge: 0.0436 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:02:24,296 INFO misc.py line 117 726] Train: [5/20][230/510] Data 4.079 (3.750) Batch 28.030 (28.341) Remain 62:25:41 loss: 0.2416 loss_seg: 0.1445 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:02:48,184 INFO misc.py line 117 726] Train: [5/20][231/510] Data 3.098 (3.747) Batch 23.888 (28.321) Remain 62:22:38 loss: 0.2578 loss_seg: 0.1608 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:03:12,502 INFO misc.py line 117 726] Train: [5/20][232/510] Data 2.509 (3.742) Batch 24.318 (28.304) Remain 62:19:51 loss: 0.2740 loss_seg: 0.1732 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:03:32,653 INFO misc.py line 117 726] Train: [5/20][233/510] Data 2.569 (3.737) Batch 20.151 (28.268) Remain 62:14:42 loss: 0.3012 loss_seg: 0.1989 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:04:04,793 INFO misc.py line 117 726] Train: [5/20][234/510] Data 3.616 (3.736) Batch 32.140 (28.285) Remain 62:16:26 loss: 0.2928 loss_seg: 0.1859 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:04:38,466 INFO misc.py line 117 726] Train: [5/20][235/510] Data 3.459 (3.735) Batch 33.673 (28.308) Remain 62:19:02 loss: 0.2208 loss_seg: 0.1287 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:05:00,371 INFO misc.py line 117 726] Train: [5/20][236/510] Data 2.712 (3.731) Batch 21.906 (28.281) Remain 62:14:56 loss: 0.2532 loss_seg: 0.1552 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0468 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:05:29,120 INFO misc.py line 117 726] Train: [5/20][237/510] Data 2.981 (3.727) Batch 28.748 (28.283) Remain 62:14:44 loss: 0.2211 loss_seg: 0.1326 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:06:02,763 INFO misc.py line 117 726] Train: [5/20][238/510] Data 2.879 (3.724) Batch 33.644 (28.306) Remain 62:17:16 loss: 0.3645 loss_seg: 0.2628 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:06:23,605 INFO misc.py line 117 726] Train: [5/20][239/510] Data 2.531 (3.719) Batch 20.841 (28.274) Remain 62:12:37 loss: 0.2175 loss_seg: 0.1300 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:06:44,698 INFO misc.py line 117 726] Train: [5/20][240/510] Data 1.880 (3.711) Batch 21.093 (28.244) Remain 62:08:09 loss: 0.1954 loss_seg: 0.1054 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:07:08,735 INFO misc.py line 117 726] Train: [5/20][241/510] Data 2.007 (3.704) Batch 24.038 (28.226) Remain 62:05:21 loss: 0.2537 loss_seg: 0.1565 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:07:37,285 INFO misc.py line 117 726] Train: [5/20][242/510] Data 3.769 (3.704) Batch 28.550 (28.227) Remain 62:05:03 loss: 0.2558 loss_seg: 0.1522 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:08:12,614 INFO misc.py line 117 726] Train: [5/20][243/510] Data 5.898 (3.713) Batch 35.329 (28.257) Remain 62:08:29 loss: 0.2437 loss_seg: 0.1472 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:08:37,502 INFO misc.py line 117 726] Train: [5/20][244/510] Data 2.283 (3.707) Batch 24.888 (28.243) Remain 62:06:10 loss: 0.2508 loss_seg: 0.1496 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:09:09,279 INFO misc.py line 117 726] Train: [5/20][245/510] Data 3.142 (3.705) Batch 31.777 (28.258) Remain 62:07:38 loss: 0.2673 loss_seg: 0.1700 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:09:32,414 INFO misc.py line 117 726] Train: [5/20][246/510] Data 2.212 (3.699) Batch 23.135 (28.236) Remain 62:04:23 loss: 0.2647 loss_seg: 0.1610 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:10:03,350 INFO misc.py line 117 726] Train: [5/20][247/510] Data 3.216 (3.697) Batch 30.936 (28.248) Remain 62:05:22 loss: 0.2579 loss_seg: 0.1632 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:10:33,237 INFO misc.py line 117 726] Train: [5/20][248/510] Data 4.766 (3.701) Batch 29.887 (28.254) Remain 62:05:47 loss: 0.2274 loss_seg: 0.1348 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:10:50,544 INFO misc.py line 117 726] Train: [5/20][249/510] Data 2.273 (3.695) Batch 17.307 (28.210) Remain 61:59:26 loss: 0.2893 loss_seg: 0.1803 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:11:27,030 INFO misc.py line 117 726] Train: [5/20][250/510] Data 6.421 (3.707) Batch 36.487 (28.243) Remain 62:03:23 loss: 0.2405 loss_seg: 0.1452 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:11:27,031 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 09:11:46,392 INFO misc.py line 117 726] Train: [5/20][251/510] Data 2.765 (3.703) Batch 19.361 (28.207) Remain 61:58:12 loss: 0.2973 loss_seg: 0.1953 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:12:16,153 INFO misc.py line 117 726] Train: [5/20][252/510] Data 3.424 (3.702) Batch 29.761 (28.214) Remain 61:58:33 loss: 0.1930 loss_seg: 0.1056 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:12:51,021 INFO misc.py line 117 726] Train: [5/20][253/510] Data 4.245 (3.704) Batch 34.868 (28.240) Remain 62:01:35 loss: 0.2014 loss_seg: 0.1165 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:13:20,786 INFO misc.py line 117 726] Train: [5/20][254/510] Data 3.535 (3.703) Batch 29.765 (28.246) Remain 62:01:55 loss: 0.2736 loss_seg: 0.1747 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:13:44,309 INFO misc.py line 117 726] Train: [5/20][255/510] Data 2.677 (3.699) Batch 23.523 (28.228) Remain 61:58:59 loss: 0.3068 loss_seg: 0.1993 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:14:16,557 INFO misc.py line 117 726] Train: [5/20][256/510] Data 5.631 (3.707) Batch 32.248 (28.243) Remain 62:00:36 loss: 0.2102 loss_seg: 0.1173 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:14:35,653 INFO misc.py line 117 726] Train: [5/20][257/510] Data 2.285 (3.701) Batch 19.096 (28.207) Remain 61:55:23 loss: 0.2499 loss_seg: 0.1547 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:14:58,602 INFO misc.py line 117 726] Train: [5/20][258/510] Data 2.780 (3.697) Batch 22.949 (28.187) Remain 61:52:12 loss: 0.2417 loss_seg: 0.1433 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:15:28,448 INFO misc.py line 117 726] Train: [5/20][259/510] Data 3.406 (3.696) Batch 29.845 (28.193) Remain 61:52:35 loss: 0.2193 loss_seg: 0.1334 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:16:06,390 INFO misc.py line 117 726] Train: [5/20][260/510] Data 6.104 (3.706) Batch 37.943 (28.231) Remain 61:57:06 loss: 0.2099 loss_seg: 0.1209 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:16:31,791 INFO misc.py line 117 726] Train: [5/20][261/510] Data 2.862 (3.702) Batch 25.400 (28.220) Remain 61:55:11 loss: 0.1901 loss_seg: 0.1018 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:16:49,437 INFO misc.py line 117 726] Train: [5/20][262/510] Data 2.188 (3.697) Batch 17.646 (28.179) Remain 61:49:21 loss: 0.2205 loss_seg: 0.1298 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:17:19,870 INFO misc.py line 117 726] Train: [5/20][263/510] Data 4.485 (3.700) Batch 30.433 (28.188) Remain 61:50:01 loss: 0.2213 loss_seg: 0.1276 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:17:40,662 INFO misc.py line 117 726] Train: [5/20][264/510] Data 2.878 (3.696) Batch 20.792 (28.160) Remain 61:45:49 loss: 0.2268 loss_seg: 0.1370 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:18:11,520 INFO misc.py line 117 726] Train: [5/20][265/510] Data 6.202 (3.706) Batch 30.858 (28.170) Remain 61:46:42 loss: 0.2493 loss_seg: 0.1535 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:18:45,854 INFO misc.py line 117 726] Train: [5/20][266/510] Data 9.072 (3.726) Batch 34.334 (28.194) Remain 61:49:19 loss: 0.1803 loss_seg: 0.0914 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:19:11,678 INFO misc.py line 117 726] Train: [5/20][267/510] Data 3.958 (3.727) Batch 25.824 (28.185) Remain 61:47:40 loss: 0.2270 loss_seg: 0.1321 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:19:37,630 INFO misc.py line 117 726] Train: [5/20][268/510] Data 3.060 (3.725) Batch 25.952 (28.176) Remain 61:46:05 loss: 0.2191 loss_seg: 0.1255 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:20:06,079 INFO misc.py line 117 726] Train: [5/20][269/510] Data 2.884 (3.722) Batch 28.449 (28.177) Remain 61:45:45 loss: 0.2742 loss_seg: 0.1756 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:20:35,877 INFO misc.py line 117 726] Train: [5/20][270/510] Data 3.808 (3.722) Batch 29.797 (28.183) Remain 61:46:05 loss: 0.2457 loss_seg: 0.1558 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:21:04,049 INFO misc.py line 117 726] Train: [5/20][271/510] Data 3.241 (3.720) Batch 28.172 (28.183) Remain 61:45:37 loss: 0.2770 loss_seg: 0.1801 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:21:27,493 INFO misc.py line 117 726] Train: [5/20][272/510] Data 2.825 (3.717) Batch 23.444 (28.166) Remain 61:42:49 loss: 0.1998 loss_seg: 0.1097 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:21:57,917 INFO misc.py line 117 726] Train: [5/20][273/510] Data 3.691 (3.717) Batch 30.424 (28.174) Remain 61:43:27 loss: 0.2713 loss_seg: 0.1719 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:22:25,320 INFO misc.py line 117 726] Train: [5/20][274/510] Data 2.346 (3.712) Batch 27.403 (28.171) Remain 61:42:37 loss: 0.2903 loss_seg: 0.1924 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:22:56,520 INFO misc.py line 117 726] Train: [5/20][275/510] Data 3.121 (3.709) Batch 31.201 (28.182) Remain 61:43:36 loss: 0.2599 loss_seg: 0.1613 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:23:27,252 INFO misc.py line 117 726] Train: [5/20][276/510] Data 3.345 (3.708) Batch 30.732 (28.192) Remain 61:44:22 loss: 0.3501 loss_seg: 0.2387 loss_superpoint_edge: 0.0450 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:24:00,133 INFO misc.py line 117 726] Train: [5/20][277/510] Data 4.455 (3.711) Batch 32.881 (28.209) Remain 61:46:08 loss: 0.2105 loss_seg: 0.1176 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:24:31,283 INFO misc.py line 117 726] Train: [5/20][278/510] Data 4.386 (3.713) Batch 31.150 (28.219) Remain 61:47:04 loss: 0.2145 loss_seg: 0.1214 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:25:03,129 INFO misc.py line 117 726] Train: [5/20][279/510] Data 4.145 (3.715) Batch 31.847 (28.232) Remain 61:48:20 loss: 0.3003 loss_seg: 0.1892 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:25:29,504 INFO misc.py line 117 726] Train: [5/20][280/510] Data 2.612 (3.711) Batch 26.375 (28.226) Remain 61:46:59 loss: 0.2075 loss_seg: 0.1170 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:25:59,829 INFO misc.py line 117 726] Train: [5/20][281/510] Data 2.955 (3.708) Batch 30.325 (28.233) Remain 61:47:30 loss: 0.2150 loss_seg: 0.1250 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:26:23,780 INFO misc.py line 117 726] Train: [5/20][282/510] Data 2.409 (3.704) Batch 23.951 (28.218) Remain 61:45:01 loss: 0.2591 loss_seg: 0.1575 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:26:58,123 INFO misc.py line 117 726] Train: [5/20][283/510] Data 5.239 (3.709) Batch 34.343 (28.240) Remain 61:47:25 loss: 0.2275 loss_seg: 0.1289 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:27:24,886 INFO misc.py line 117 726] Train: [5/20][284/510] Data 2.707 (3.705) Batch 26.763 (28.235) Remain 61:46:15 loss: 0.2152 loss_seg: 0.1160 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:27:57,219 INFO misc.py line 117 726] Train: [5/20][285/510] Data 3.713 (3.705) Batch 32.333 (28.249) Remain 61:47:42 loss: 0.2289 loss_seg: 0.1397 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:28:30,047 INFO misc.py line 117 726] Train: [5/20][286/510] Data 7.968 (3.721) Batch 32.828 (28.265) Remain 61:49:21 loss: 0.3479 loss_seg: 0.2242 loss_superpoint_edge: 0.0503 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:29:01,443 INFO misc.py line 117 726] Train: [5/20][287/510] Data 4.358 (3.723) Batch 31.395 (28.276) Remain 61:50:19 loss: 0.1684 loss_seg: 0.0867 loss_superpoint_edge: 0.0117 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:29:32,765 INFO misc.py line 117 726] Train: [5/20][288/510] Data 3.043 (3.720) Batch 31.322 (28.287) Remain 61:51:15 loss: 0.2204 loss_seg: 0.1298 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:29:52,584 INFO misc.py line 117 726] Train: [5/20][289/510] Data 2.071 (3.715) Batch 19.819 (28.257) Remain 61:46:54 loss: 0.2823 loss_seg: 0.1772 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:30:30,378 INFO misc.py line 117 726] Train: [5/20][290/510] Data 4.798 (3.718) Batch 37.795 (28.291) Remain 61:50:47 loss: 0.1946 loss_seg: 0.1067 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:31:01,329 INFO misc.py line 117 726] Train: [5/20][291/510] Data 3.163 (3.716) Batch 30.950 (28.300) Remain 61:51:31 loss: 0.2526 loss_seg: 0.1543 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:31:25,978 INFO misc.py line 117 726] Train: [5/20][292/510] Data 2.918 (3.714) Batch 24.650 (28.287) Remain 61:49:24 loss: 0.2852 loss_seg: 0.1853 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:32:06,284 INFO misc.py line 117 726] Train: [5/20][293/510] Data 11.338 (3.740) Batch 40.306 (28.329) Remain 61:54:21 loss: 0.2559 loss_seg: 0.1627 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:32:34,607 INFO misc.py line 117 726] Train: [5/20][294/510] Data 4.103 (3.741) Batch 28.323 (28.329) Remain 61:53:53 loss: 0.2340 loss_seg: 0.1410 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:33:01,830 INFO misc.py line 117 726] Train: [5/20][295/510] Data 2.860 (3.738) Batch 27.223 (28.325) Remain 61:52:55 loss: 0.2125 loss_seg: 0.1209 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:33:39,903 INFO misc.py line 117 726] Train: [5/20][296/510] Data 5.265 (3.743) Batch 38.072 (28.358) Remain 61:56:48 loss: 0.3225 loss_seg: 0.2184 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:34:08,395 INFO misc.py line 117 726] Train: [5/20][297/510] Data 4.488 (3.746) Batch 28.492 (28.359) Remain 61:56:23 loss: 0.3527 loss_seg: 0.2481 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:34:40,962 INFO misc.py line 117 726] Train: [5/20][298/510] Data 3.884 (3.746) Batch 32.568 (28.373) Remain 61:57:47 loss: 0.2326 loss_seg: 0.1391 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:35:11,813 INFO misc.py line 117 726] Train: [5/20][299/510] Data 4.820 (3.750) Batch 30.850 (28.381) Remain 61:58:25 loss: 0.1907 loss_seg: 0.1028 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:35:31,379 INFO misc.py line 117 726] Train: [5/20][300/510] Data 2.241 (3.745) Batch 19.566 (28.352) Remain 61:54:03 loss: 0.2938 loss_seg: 0.1908 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:35:31,380 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 09:35:53,823 INFO misc.py line 117 726] Train: [5/20][301/510] Data 2.692 (3.741) Batch 22.444 (28.332) Remain 61:50:59 loss: 0.2925 loss_seg: 0.1926 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:36:24,633 INFO misc.py line 117 726] Train: [5/20][302/510] Data 3.680 (3.741) Batch 30.809 (28.340) Remain 61:51:36 loss: 0.2398 loss_seg: 0.1434 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:36:43,468 INFO misc.py line 117 726] Train: [5/20][303/510] Data 2.757 (3.738) Batch 18.835 (28.308) Remain 61:46:58 loss: 0.2501 loss_seg: 0.1551 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:37:32,484 INFO misc.py line 117 726] Train: [5/20][304/510] Data 14.497 (3.774) Batch 49.015 (28.377) Remain 61:55:30 loss: 0.3702 loss_seg: 0.2703 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:37:59,521 INFO misc.py line 117 726] Train: [5/20][305/510] Data 3.682 (3.773) Batch 27.037 (28.373) Remain 61:54:27 loss: 0.2902 loss_seg: 0.1833 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:38:33,158 INFO misc.py line 117 726] Train: [5/20][306/510] Data 4.611 (3.776) Batch 33.637 (28.390) Remain 61:56:15 loss: 0.2045 loss_seg: 0.1141 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:39:05,439 INFO misc.py line 117 726] Train: [5/20][307/510] Data 6.042 (3.784) Batch 32.281 (28.403) Remain 61:57:27 loss: 0.2404 loss_seg: 0.1480 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:39:38,200 INFO misc.py line 117 726] Train: [5/20][308/510] Data 5.548 (3.789) Batch 32.761 (28.417) Remain 61:58:51 loss: 0.3039 loss_seg: 0.2013 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:40:04,294 INFO misc.py line 117 726] Train: [5/20][309/510] Data 3.502 (3.788) Batch 26.094 (28.410) Remain 61:57:23 loss: 0.2766 loss_seg: 0.1705 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:40:25,548 INFO misc.py line 117 726] Train: [5/20][310/510] Data 2.333 (3.784) Batch 21.253 (28.386) Remain 61:53:52 loss: 0.2063 loss_seg: 0.1175 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:40:53,800 INFO misc.py line 117 726] Train: [5/20][311/510] Data 3.013 (3.781) Batch 28.253 (28.386) Remain 61:53:20 loss: 0.2729 loss_seg: 0.1741 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:41:19,316 INFO misc.py line 117 726] Train: [5/20][312/510] Data 2.466 (3.777) Batch 25.516 (28.377) Remain 61:51:39 loss: 0.2248 loss_seg: 0.1275 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:41:46,770 INFO misc.py line 117 726] Train: [5/20][313/510] Data 3.539 (3.776) Batch 27.454 (28.374) Remain 61:50:47 loss: 0.2037 loss_seg: 0.1139 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:42:22,515 INFO misc.py line 117 726] Train: [5/20][314/510] Data 3.956 (3.777) Batch 35.745 (28.397) Remain 61:53:25 loss: 0.2825 loss_seg: 0.1880 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:42:43,149 INFO misc.py line 117 726] Train: [5/20][315/510] Data 2.116 (3.771) Batch 20.633 (28.372) Remain 61:49:41 loss: 0.3304 loss_seg: 0.2183 loss_superpoint_edge: 0.0419 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:43:06,731 INFO misc.py line 117 726] Train: [5/20][316/510] Data 2.560 (3.768) Batch 23.583 (28.357) Remain 61:47:13 loss: 0.2988 loss_seg: 0.1938 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:43:24,351 INFO misc.py line 117 726] Train: [5/20][317/510] Data 2.258 (3.763) Batch 17.619 (28.323) Remain 61:42:16 loss: 0.2311 loss_seg: 0.1323 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:43:55,608 INFO misc.py line 117 726] Train: [5/20][318/510] Data 4.047 (3.764) Batch 31.257 (28.332) Remain 61:43:01 loss: 0.2498 loss_seg: 0.1556 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:44:09,388 INFO misc.py line 117 726] Train: [5/20][319/510] Data 2.505 (3.760) Batch 13.780 (28.286) Remain 61:36:31 loss: 0.2695 loss_seg: 0.1817 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:44:39,261 INFO misc.py line 117 726] Train: [5/20][320/510] Data 3.149 (3.758) Batch 29.873 (28.291) Remain 61:36:42 loss: 0.4167 loss_seg: 0.3149 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:45:05,207 INFO misc.py line 117 726] Train: [5/20][321/510] Data 2.897 (3.755) Batch 25.946 (28.284) Remain 61:35:16 loss: 0.1804 loss_seg: 0.0923 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:45:34,998 INFO misc.py line 117 726] Train: [5/20][322/510] Data 3.171 (3.753) Batch 29.791 (28.289) Remain 61:35:25 loss: 0.2622 loss_seg: 0.1603 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:45:56,027 INFO misc.py line 117 726] Train: [5/20][323/510] Data 2.608 (3.750) Batch 21.029 (28.266) Remain 61:31:59 loss: 0.3626 loss_seg: 0.2461 loss_superpoint_edge: 0.0493 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:46:29,367 INFO misc.py line 117 726] Train: [5/20][324/510] Data 4.322 (3.751) Batch 33.339 (28.282) Remain 61:33:34 loss: 0.1814 loss_seg: 0.0961 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:47:00,486 INFO misc.py line 117 726] Train: [5/20][325/510] Data 4.697 (3.754) Batch 31.119 (28.290) Remain 61:34:15 loss: 0.2575 loss_seg: 0.1612 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:47:31,175 INFO misc.py line 117 726] Train: [5/20][326/510] Data 5.635 (3.760) Batch 30.689 (28.298) Remain 61:34:45 loss: 0.2011 loss_seg: 0.1143 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:47:56,542 INFO misc.py line 117 726] Train: [5/20][327/510] Data 2.708 (3.757) Batch 25.368 (28.289) Remain 61:33:06 loss: 0.3770 loss_seg: 0.2717 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:48:14,277 INFO misc.py line 117 726] Train: [5/20][328/510] Data 2.183 (3.752) Batch 17.735 (28.256) Remain 61:28:23 loss: 0.2022 loss_seg: 0.1088 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:48:35,488 INFO misc.py line 117 726] Train: [5/20][329/510] Data 2.498 (3.748) Batch 21.211 (28.235) Remain 61:25:06 loss: 0.3957 loss_seg: 0.2761 loss_superpoint_edge: 0.0498 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:49:05,354 INFO misc.py line 117 726] Train: [5/20][330/510] Data 2.794 (3.745) Batch 29.865 (28.240) Remain 61:25:17 loss: 0.3409 loss_seg: 0.2316 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:49:40,179 INFO misc.py line 117 726] Train: [5/20][331/510] Data 5.833 (3.752) Batch 34.825 (28.260) Remain 61:27:26 loss: 0.2053 loss_seg: 0.1173 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:50:26,086 INFO misc.py line 117 726] Train: [5/20][332/510] Data 14.704 (3.785) Batch 45.907 (28.313) Remain 61:33:57 loss: 0.2824 loss_seg: 0.1939 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:50:50,949 INFO misc.py line 117 726] Train: [5/20][333/510] Data 2.510 (3.781) Batch 24.863 (28.303) Remain 61:32:07 loss: 0.1721 loss_seg: 0.0897 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:51:07,318 INFO misc.py line 117 726] Train: [5/20][334/510] Data 4.858 (3.784) Batch 16.369 (28.267) Remain 61:26:57 loss: 0.2798 loss_seg: 0.1730 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0535 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:51:41,418 INFO misc.py line 117 726] Train: [5/20][335/510] Data 2.933 (3.782) Batch 34.100 (28.285) Remain 61:28:46 loss: 0.2070 loss_seg: 0.1177 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:52:09,543 INFO misc.py line 117 726] Train: [5/20][336/510] Data 3.319 (3.780) Batch 28.125 (28.284) Remain 61:28:14 loss: 0.2275 loss_seg: 0.1329 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:52:46,272 INFO misc.py line 117 726] Train: [5/20][337/510] Data 5.958 (3.787) Batch 36.729 (28.309) Remain 61:31:03 loss: 0.2151 loss_seg: 0.1257 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:53:07,240 INFO misc.py line 117 726] Train: [5/20][338/510] Data 2.585 (3.783) Batch 20.968 (28.287) Remain 61:27:44 loss: 0.2660 loss_seg: 0.1676 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:53:34,183 INFO misc.py line 117 726] Train: [5/20][339/510] Data 3.006 (3.781) Batch 26.943 (28.283) Remain 61:26:44 loss: 0.2004 loss_seg: 0.1112 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:54:02,121 INFO misc.py line 117 726] Train: [5/20][340/510] Data 4.049 (3.782) Batch 27.938 (28.282) Remain 61:26:08 loss: 0.2421 loss_seg: 0.1539 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:54:25,085 INFO misc.py line 117 726] Train: [5/20][341/510] Data 2.155 (3.777) Batch 22.964 (28.267) Remain 61:23:36 loss: 0.2793 loss_seg: 0.1751 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:54:52,311 INFO misc.py line 117 726] Train: [5/20][342/510] Data 2.675 (3.774) Batch 27.226 (28.264) Remain 61:22:44 loss: 0.1737 loss_seg: 0.0880 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:55:16,453 INFO misc.py line 117 726] Train: [5/20][343/510] Data 2.521 (3.770) Batch 24.142 (28.251) Remain 61:20:41 loss: 0.1951 loss_seg: 0.1050 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:55:32,983 INFO misc.py line 117 726] Train: [5/20][344/510] Data 2.055 (3.765) Batch 16.530 (28.217) Remain 61:15:44 loss: 0.2005 loss_seg: 0.1068 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:55:59,467 INFO misc.py line 117 726] Train: [5/20][345/510] Data 6.046 (3.772) Batch 26.484 (28.212) Remain 61:14:36 loss: 0.2503 loss_seg: 0.1585 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:56:24,969 INFO misc.py line 117 726] Train: [5/20][346/510] Data 2.360 (3.768) Batch 25.502 (28.204) Remain 61:13:06 loss: 0.2550 loss_seg: 0.1574 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:56:57,325 INFO misc.py line 117 726] Train: [5/20][347/510] Data 3.658 (3.767) Batch 32.356 (28.216) Remain 61:14:12 loss: 0.2415 loss_seg: 0.1467 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:57:26,199 INFO misc.py line 117 726] Train: [5/20][348/510] Data 2.994 (3.765) Batch 28.875 (28.218) Remain 61:13:59 loss: 0.2308 loss_seg: 0.1298 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:57:48,469 INFO misc.py line 117 726] Train: [5/20][349/510] Data 2.641 (3.762) Batch 22.269 (28.201) Remain 61:11:17 loss: 0.1733 loss_seg: 0.0901 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:58:24,049 INFO misc.py line 117 726] Train: [5/20][350/510] Data 5.333 (3.766) Batch 35.580 (28.222) Remain 61:13:35 loss: 0.2462 loss_seg: 0.1493 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:58:24,050 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 09:58:51,582 INFO misc.py line 117 726] Train: [5/20][351/510] Data 2.878 (3.764) Batch 27.533 (28.220) Remain 61:12:51 loss: 0.2160 loss_seg: 0.1230 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:59:18,544 INFO misc.py line 117 726] Train: [5/20][352/510] Data 2.866 (3.761) Batch 26.962 (28.217) Remain 61:11:55 loss: 0.2968 loss_seg: 0.1961 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 09:59:38,791 INFO misc.py line 117 726] Train: [5/20][353/510] Data 2.458 (3.757) Batch 20.247 (28.194) Remain 61:08:29 loss: 0.3395 loss_seg: 0.2332 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:00:16,981 INFO misc.py line 117 726] Train: [5/20][354/510] Data 10.792 (3.778) Batch 38.190 (28.222) Remain 61:11:43 loss: 0.2039 loss_seg: 0.1201 loss_superpoint_edge: 0.0142 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:00:54,208 INFO misc.py line 117 726] Train: [5/20][355/510] Data 8.502 (3.791) Batch 37.227 (28.248) Remain 61:14:34 loss: 0.2571 loss_seg: 0.1569 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:01:31,966 INFO misc.py line 117 726] Train: [5/20][356/510] Data 4.537 (3.793) Batch 37.758 (28.275) Remain 61:17:36 loss: 0.2505 loss_seg: 0.1588 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:01:58,611 INFO misc.py line 117 726] Train: [5/20][357/510] Data 2.466 (3.789) Batch 26.645 (28.270) Remain 61:16:32 loss: 0.2432 loss_seg: 0.1497 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:02:26,386 INFO misc.py line 117 726] Train: [5/20][358/510] Data 3.769 (3.789) Batch 27.775 (28.269) Remain 61:15:53 loss: 0.1957 loss_seg: 0.1086 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:03:01,526 INFO misc.py line 117 726] Train: [5/20][359/510] Data 4.408 (3.791) Batch 35.140 (28.288) Remain 61:17:55 loss: 0.2378 loss_seg: 0.1447 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:03:24,705 INFO misc.py line 117 726] Train: [5/20][360/510] Data 3.753 (3.791) Batch 23.179 (28.274) Remain 61:15:35 loss: 0.3044 loss_seg: 0.1958 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:03:55,044 INFO misc.py line 117 726] Train: [5/20][361/510] Data 4.203 (3.792) Batch 30.339 (28.280) Remain 61:15:52 loss: 0.2549 loss_seg: 0.1571 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:04:25,227 INFO misc.py line 117 726] Train: [5/20][362/510] Data 3.485 (3.791) Batch 30.183 (28.285) Remain 61:16:05 loss: 0.2539 loss_seg: 0.1554 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:04:49,695 INFO misc.py line 117 726] Train: [5/20][363/510] Data 4.465 (3.793) Batch 24.469 (28.274) Remain 61:14:14 loss: 0.2068 loss_seg: 0.1161 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:05:11,554 INFO misc.py line 117 726] Train: [5/20][364/510] Data 3.095 (3.791) Batch 21.859 (28.256) Remain 61:11:27 loss: 0.2115 loss_seg: 0.1220 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:05:37,600 INFO misc.py line 117 726] Train: [5/20][365/510] Data 2.767 (3.788) Batch 26.045 (28.250) Remain 61:10:11 loss: 0.2380 loss_seg: 0.1431 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:06:05,346 INFO misc.py line 117 726] Train: [5/20][366/510] Data 4.121 (3.789) Batch 27.746 (28.249) Remain 61:09:32 loss: 0.2673 loss_seg: 0.1663 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:06:31,599 INFO misc.py line 117 726] Train: [5/20][367/510] Data 2.824 (3.787) Batch 26.253 (28.244) Remain 61:08:21 loss: 0.2487 loss_seg: 0.1513 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:07:09,663 INFO misc.py line 117 726] Train: [5/20][368/510] Data 5.771 (3.792) Batch 38.064 (28.270) Remain 61:11:23 loss: 0.2682 loss_seg: 0.1722 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:07:45,764 INFO misc.py line 117 726] Train: [5/20][369/510] Data 10.665 (3.811) Batch 36.101 (28.292) Remain 61:13:41 loss: 0.2089 loss_seg: 0.1156 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:08:14,839 INFO misc.py line 117 726] Train: [5/20][370/510] Data 3.150 (3.809) Batch 29.075 (28.294) Remain 61:13:29 loss: 0.2140 loss_seg: 0.1264 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:08:33,401 INFO misc.py line 117 726] Train: [5/20][371/510] Data 1.811 (3.804) Batch 18.562 (28.268) Remain 61:09:35 loss: 0.2283 loss_seg: 0.1369 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:08:51,695 INFO misc.py line 117 726] Train: [5/20][372/510] Data 2.914 (3.801) Batch 18.294 (28.240) Remain 61:05:36 loss: 0.3100 loss_seg: 0.2009 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:09:22,691 INFO misc.py line 117 726] Train: [5/20][373/510] Data 3.556 (3.800) Batch 30.996 (28.248) Remain 61:06:06 loss: 0.2729 loss_seg: 0.1729 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:09:47,721 INFO misc.py line 117 726] Train: [5/20][374/510] Data 3.946 (3.801) Batch 25.029 (28.239) Remain 61:04:30 loss: 0.2673 loss_seg: 0.1720 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:10:11,564 INFO misc.py line 117 726] Train: [5/20][375/510] Data 3.773 (3.801) Batch 23.843 (28.227) Remain 61:02:30 loss: 0.3742 loss_seg: 0.2624 loss_superpoint_edge: 0.0425 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:10:49,402 INFO misc.py line 117 726] Train: [5/20][376/510] Data 4.693 (3.803) Batch 37.838 (28.253) Remain 61:05:22 loss: 0.2813 loss_seg: 0.1814 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:11:11,051 INFO misc.py line 117 726] Train: [5/20][377/510] Data 2.798 (3.801) Batch 21.649 (28.236) Remain 61:02:37 loss: 0.2947 loss_seg: 0.1871 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:11:42,240 INFO misc.py line 117 726] Train: [5/20][378/510] Data 4.343 (3.802) Batch 31.189 (28.243) Remain 61:03:10 loss: 0.2070 loss_seg: 0.1178 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:12:12,061 INFO misc.py line 117 726] Train: [5/20][379/510] Data 3.224 (3.800) Batch 29.821 (28.248) Remain 61:03:14 loss: 0.2553 loss_seg: 0.1534 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:12:34,310 INFO misc.py line 117 726] Train: [5/20][380/510] Data 2.240 (3.796) Batch 22.249 (28.232) Remain 61:00:42 loss: 0.2254 loss_seg: 0.1341 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:12:58,636 INFO misc.py line 117 726] Train: [5/20][381/510] Data 3.393 (3.795) Batch 24.327 (28.221) Remain 60:58:54 loss: 0.1956 loss_seg: 0.1104 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:13:31,266 INFO misc.py line 117 726] Train: [5/20][382/510] Data 3.394 (3.794) Batch 32.630 (28.233) Remain 60:59:56 loss: 0.2384 loss_seg: 0.1437 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:14:01,288 INFO misc.py line 117 726] Train: [5/20][383/510] Data 4.591 (3.796) Batch 30.022 (28.238) Remain 61:00:04 loss: 0.2775 loss_seg: 0.1791 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:14:35,662 INFO misc.py line 117 726] Train: [5/20][384/510] Data 7.348 (3.806) Batch 34.374 (28.254) Remain 61:01:41 loss: 0.2169 loss_seg: 0.1279 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:15:04,769 INFO misc.py line 117 726] Train: [5/20][385/510] Data 3.275 (3.804) Batch 29.107 (28.256) Remain 61:01:30 loss: 0.3320 loss_seg: 0.2291 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:15:24,863 INFO misc.py line 117 726] Train: [5/20][386/510] Data 1.724 (3.799) Batch 20.094 (28.235) Remain 60:58:16 loss: 0.2079 loss_seg: 0.1195 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:16:01,422 INFO misc.py line 117 726] Train: [5/20][387/510] Data 5.182 (3.802) Batch 36.559 (28.256) Remain 61:00:37 loss: 0.4603 loss_seg: 0.3409 loss_superpoint_edge: 0.0505 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:16:29,468 INFO misc.py line 117 726] Train: [5/20][388/510] Data 2.802 (3.800) Batch 28.046 (28.256) Remain 61:00:04 loss: 0.1952 loss_seg: 0.1062 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:16:54,764 INFO misc.py line 117 726] Train: [5/20][389/510] Data 4.654 (3.802) Batch 25.296 (28.248) Remain 60:58:36 loss: 0.2221 loss_seg: 0.1323 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:17:29,344 INFO misc.py line 117 726] Train: [5/20][390/510] Data 6.228 (3.808) Batch 34.580 (28.265) Remain 61:00:15 loss: 0.2848 loss_seg: 0.1860 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:17:54,999 INFO misc.py line 117 726] Train: [5/20][391/510] Data 2.644 (3.805) Batch 25.654 (28.258) Remain 60:58:55 loss: 0.2234 loss_seg: 0.1324 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:18:19,828 INFO misc.py line 117 726] Train: [5/20][392/510] Data 4.296 (3.806) Batch 24.829 (28.249) Remain 60:57:18 loss: 0.2203 loss_seg: 0.1299 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:18:56,080 INFO misc.py line 117 726] Train: [5/20][393/510] Data 3.701 (3.806) Batch 36.252 (28.270) Remain 60:59:29 loss: 0.2083 loss_seg: 0.1162 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:19:29,238 INFO misc.py line 117 726] Train: [5/20][394/510] Data 5.512 (3.811) Batch 33.157 (28.282) Remain 61:00:38 loss: 0.2326 loss_seg: 0.1406 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:19:56,969 INFO misc.py line 117 726] Train: [5/20][395/510] Data 2.912 (3.808) Batch 27.732 (28.281) Remain 60:59:59 loss: 0.2565 loss_seg: 0.1539 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:20:21,912 INFO misc.py line 117 726] Train: [5/20][396/510] Data 2.599 (3.805) Batch 24.943 (28.272) Remain 60:58:24 loss: 0.2630 loss_seg: 0.1648 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:20:39,859 INFO misc.py line 117 726] Train: [5/20][397/510] Data 2.341 (3.802) Batch 17.947 (28.246) Remain 60:54:33 loss: 0.3122 loss_seg: 0.2068 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:20:59,276 INFO misc.py line 117 726] Train: [5/20][398/510] Data 2.269 (3.798) Batch 19.416 (28.224) Remain 60:51:11 loss: 0.2411 loss_seg: 0.1457 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:21:29,839 INFO misc.py line 117 726] Train: [5/20][399/510] Data 4.398 (3.799) Batch 30.564 (28.229) Remain 60:51:29 loss: 0.3167 loss_seg: 0.2088 loss_superpoint_edge: 0.0412 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:21:58,585 INFO misc.py line 117 726] Train: [5/20][400/510] Data 4.949 (3.802) Batch 28.745 (28.231) Remain 60:51:10 loss: 0.2794 loss_seg: 0.1836 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:21:58,585 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 10:22:32,436 INFO misc.py line 117 726] Train: [5/20][401/510] Data 6.836 (3.810) Batch 33.851 (28.245) Remain 60:52:32 loss: 0.3011 loss_seg: 0.1991 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:23:02,209 INFO misc.py line 117 726] Train: [5/20][402/510] Data 3.804 (3.810) Batch 29.773 (28.249) Remain 60:52:33 loss: 0.3280 loss_seg: 0.2222 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:23:34,061 INFO misc.py line 117 726] Train: [5/20][403/510] Data 3.500 (3.809) Batch 31.852 (28.258) Remain 60:53:15 loss: 0.1864 loss_seg: 0.1000 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:23:53,380 INFO misc.py line 117 726] Train: [5/20][404/510] Data 3.098 (3.807) Batch 19.319 (28.235) Remain 60:49:54 loss: 0.2154 loss_seg: 0.1211 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:24:23,024 INFO misc.py line 117 726] Train: [5/20][405/510] Data 3.579 (3.807) Batch 29.643 (28.239) Remain 60:49:53 loss: 0.2145 loss_seg: 0.1200 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:24:48,204 INFO misc.py line 117 726] Train: [5/20][406/510] Data 2.614 (3.804) Batch 25.180 (28.231) Remain 60:48:26 loss: 0.2957 loss_seg: 0.1999 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:25:15,732 INFO misc.py line 117 726] Train: [5/20][407/510] Data 5.044 (3.807) Batch 27.528 (28.230) Remain 60:47:44 loss: 0.2517 loss_seg: 0.1554 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:25:47,032 INFO misc.py line 117 726] Train: [5/20][408/510] Data 3.459 (3.806) Batch 31.300 (28.237) Remain 60:48:14 loss: 0.2573 loss_seg: 0.1579 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:26:05,226 INFO misc.py line 117 726] Train: [5/20][409/510] Data 2.065 (3.801) Batch 18.194 (28.212) Remain 60:44:34 loss: 0.3350 loss_seg: 0.2231 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:26:37,180 INFO misc.py line 117 726] Train: [5/20][410/510] Data 6.447 (3.808) Batch 31.954 (28.222) Remain 60:45:17 loss: 0.2644 loss_seg: 0.1722 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:27:07,853 INFO misc.py line 117 726] Train: [5/20][411/510] Data 3.474 (3.807) Batch 30.674 (28.228) Remain 60:45:36 loss: 0.2033 loss_seg: 0.1117 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:27:48,161 INFO misc.py line 117 726] Train: [5/20][412/510] Data 11.729 (3.827) Batch 40.307 (28.257) Remain 60:48:56 loss: 0.3716 loss_seg: 0.2707 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:28:18,395 INFO misc.py line 117 726] Train: [5/20][413/510] Data 3.058 (3.825) Batch 30.235 (28.262) Remain 60:49:06 loss: 0.2274 loss_seg: 0.1373 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:28:45,511 INFO misc.py line 117 726] Train: [5/20][414/510] Data 2.571 (3.822) Batch 27.116 (28.259) Remain 60:48:16 loss: 0.2707 loss_seg: 0.1800 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:29:08,314 INFO misc.py line 117 726] Train: [5/20][415/510] Data 2.492 (3.818) Batch 22.803 (28.246) Remain 60:46:05 loss: 0.2502 loss_seg: 0.1512 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:29:39,223 INFO misc.py line 117 726] Train: [5/20][416/510] Data 3.093 (3.817) Batch 30.908 (28.252) Remain 60:46:26 loss: 0.2720 loss_seg: 0.1650 loss_superpoint_edge: 0.0404 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:30:13,644 INFO misc.py line 117 726] Train: [5/20][417/510] Data 3.566 (3.816) Batch 34.421 (28.267) Remain 60:47:54 loss: 0.2023 loss_seg: 0.1164 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:30:45,093 INFO misc.py line 117 726] Train: [5/20][418/510] Data 3.760 (3.816) Batch 31.449 (28.275) Remain 60:48:25 loss: 0.2046 loss_seg: 0.1187 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:31:10,236 INFO misc.py line 117 726] Train: [5/20][419/510] Data 1.977 (3.811) Batch 25.143 (28.267) Remain 60:46:58 loss: 0.2536 loss_seg: 0.1518 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:31:36,261 INFO misc.py line 117 726] Train: [5/20][420/510] Data 2.995 (3.810) Batch 26.026 (28.262) Remain 60:45:48 loss: 0.2563 loss_seg: 0.1560 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:31:56,887 INFO misc.py line 117 726] Train: [5/20][421/510] Data 2.994 (3.808) Batch 20.626 (28.244) Remain 60:42:59 loss: 0.2301 loss_seg: 0.1383 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:32:28,264 INFO misc.py line 117 726] Train: [5/20][422/510] Data 5.119 (3.811) Batch 31.377 (28.251) Remain 60:43:28 loss: 0.2318 loss_seg: 0.1338 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:32:56,806 INFO misc.py line 117 726] Train: [5/20][423/510] Data 6.645 (3.817) Batch 28.541 (28.252) Remain 60:43:05 loss: 0.2201 loss_seg: 0.1262 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:33:39,581 INFO misc.py line 117 726] Train: [5/20][424/510] Data 8.719 (3.829) Batch 42.777 (28.287) Remain 60:47:04 loss: 0.3214 loss_seg: 0.2174 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:34:13,090 INFO misc.py line 117 726] Train: [5/20][425/510] Data 3.696 (3.829) Batch 33.508 (28.299) Remain 60:48:11 loss: 0.1974 loss_seg: 0.1136 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:34:43,915 INFO misc.py line 117 726] Train: [5/20][426/510] Data 4.682 (3.831) Batch 30.825 (28.305) Remain 60:48:29 loss: 0.2268 loss_seg: 0.1339 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:35:20,173 INFO misc.py line 117 726] Train: [5/20][427/510] Data 5.544 (3.835) Batch 36.258 (28.324) Remain 60:50:26 loss: 0.2239 loss_seg: 0.1292 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:35:51,341 INFO misc.py line 117 726] Train: [5/20][428/510] Data 7.915 (3.844) Batch 31.168 (28.330) Remain 60:50:49 loss: 0.1918 loss_seg: 0.1041 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:36:18,478 INFO misc.py line 117 726] Train: [5/20][429/510] Data 4.090 (3.845) Batch 27.137 (28.328) Remain 60:49:59 loss: 0.2643 loss_seg: 0.1613 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0340 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:36:35,807 INFO misc.py line 117 726] Train: [5/20][430/510] Data 2.267 (3.841) Batch 17.329 (28.302) Remain 60:46:12 loss: 0.2286 loss_seg: 0.1367 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:37:09,605 INFO misc.py line 117 726] Train: [5/20][431/510] Data 3.513 (3.841) Batch 33.797 (28.315) Remain 60:47:23 loss: 0.2995 loss_seg: 0.2004 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:37:29,780 INFO misc.py line 117 726] Train: [5/20][432/510] Data 3.250 (3.839) Batch 20.176 (28.296) Remain 60:44:28 loss: 0.3343 loss_seg: 0.2396 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:37:58,999 INFO misc.py line 117 726] Train: [5/20][433/510] Data 3.553 (3.839) Batch 29.219 (28.298) Remain 60:44:16 loss: 0.2147 loss_seg: 0.1269 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:38:27,355 INFO misc.py line 117 726] Train: [5/20][434/510] Data 2.857 (3.836) Batch 28.356 (28.298) Remain 60:43:49 loss: 0.2768 loss_seg: 0.1695 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:38:53,505 INFO misc.py line 117 726] Train: [5/20][435/510] Data 2.299 (3.833) Batch 26.150 (28.293) Remain 60:42:42 loss: 0.2851 loss_seg: 0.1843 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:39:19,014 INFO misc.py line 117 726] Train: [5/20][436/510] Data 3.261 (3.831) Batch 25.509 (28.286) Remain 60:41:24 loss: 0.2256 loss_seg: 0.1326 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:39:41,312 INFO misc.py line 117 726] Train: [5/20][437/510] Data 2.468 (3.828) Batch 22.297 (28.273) Remain 60:39:10 loss: 0.2287 loss_seg: 0.1321 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:40:06,523 INFO misc.py line 117 726] Train: [5/20][438/510] Data 5.110 (3.831) Batch 25.211 (28.266) Remain 60:37:47 loss: 0.1902 loss_seg: 0.1045 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:40:40,316 INFO misc.py line 117 726] Train: [5/20][439/510] Data 4.389 (3.832) Batch 33.793 (28.278) Remain 60:38:57 loss: 0.2010 loss_seg: 0.1158 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:41:05,409 INFO misc.py line 117 726] Train: [5/20][440/510] Data 2.589 (3.830) Batch 25.093 (28.271) Remain 60:37:32 loss: 0.2354 loss_seg: 0.1430 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:41:27,876 INFO misc.py line 117 726] Train: [5/20][441/510] Data 2.889 (3.827) Batch 22.467 (28.258) Remain 60:35:21 loss: 0.2524 loss_seg: 0.1573 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:41:48,783 INFO misc.py line 117 726] Train: [5/20][442/510] Data 2.494 (3.824) Batch 20.907 (28.241) Remain 60:32:44 loss: 0.2021 loss_seg: 0.1119 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:42:20,168 INFO misc.py line 117 726] Train: [5/20][443/510] Data 3.297 (3.823) Batch 31.386 (28.248) Remain 60:33:11 loss: 0.1956 loss_seg: 0.1115 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:42:52,104 INFO misc.py line 117 726] Train: [5/20][444/510] Data 3.466 (3.822) Batch 31.936 (28.257) Remain 60:33:47 loss: 0.1932 loss_seg: 0.1053 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:43:26,053 INFO misc.py line 117 726] Train: [5/20][445/510] Data 4.614 (3.824) Batch 33.949 (28.269) Remain 60:34:58 loss: 0.2976 loss_seg: 0.1942 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:43:57,320 INFO misc.py line 117 726] Train: [5/20][446/510] Data 4.565 (3.826) Batch 31.267 (28.276) Remain 60:35:22 loss: 0.2949 loss_seg: 0.1903 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:44:12,369 INFO misc.py line 117 726] Train: [5/20][447/510] Data 1.216 (3.820) Batch 15.049 (28.246) Remain 60:31:04 loss: 0.2529 loss_seg: 0.1579 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:44:36,659 INFO misc.py line 117 726] Train: [5/20][448/510] Data 2.436 (3.817) Batch 24.290 (28.238) Remain 60:29:27 loss: 0.2061 loss_seg: 0.1197 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:45:03,185 INFO misc.py line 117 726] Train: [5/20][449/510] Data 3.003 (3.815) Batch 26.526 (28.234) Remain 60:28:29 loss: 0.2335 loss_seg: 0.1382 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:45:22,857 INFO misc.py line 117 726] Train: [5/20][450/510] Data 2.592 (3.812) Batch 19.671 (28.215) Remain 60:25:34 loss: 0.2125 loss_seg: 0.1232 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:45:22,857 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 10:45:49,434 INFO misc.py line 117 726] Train: [5/20][451/510] Data 4.465 (3.814) Batch 26.577 (28.211) Remain 60:24:37 loss: 0.1988 loss_seg: 0.1061 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:46:21,408 INFO misc.py line 117 726] Train: [5/20][452/510] Data 4.256 (3.815) Batch 31.974 (28.219) Remain 60:25:14 loss: 0.2369 loss_seg: 0.1513 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:46:54,005 INFO misc.py line 117 726] Train: [5/20][453/510] Data 4.039 (3.815) Batch 32.597 (28.229) Remain 60:26:00 loss: 0.1909 loss_seg: 0.1015 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:47:17,857 INFO misc.py line 117 726] Train: [5/20][454/510] Data 2.845 (3.813) Batch 23.852 (28.219) Remain 60:24:17 loss: 0.2360 loss_seg: 0.1430 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:47:44,508 INFO misc.py line 117 726] Train: [5/20][455/510] Data 2.097 (3.809) Batch 26.651 (28.216) Remain 60:23:22 loss: 0.2230 loss_seg: 0.1281 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:48:11,780 INFO misc.py line 117 726] Train: [5/20][456/510] Data 3.190 (3.808) Batch 27.272 (28.214) Remain 60:22:38 loss: 0.2621 loss_seg: 0.1623 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:48:44,881 INFO misc.py line 117 726] Train: [5/20][457/510] Data 5.924 (3.813) Batch 33.100 (28.224) Remain 60:23:33 loss: 0.5722 loss_seg: 0.4645 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:49:12,778 INFO misc.py line 117 726] Train: [5/20][458/510] Data 3.503 (3.812) Batch 27.898 (28.224) Remain 60:22:59 loss: 0.2208 loss_seg: 0.1271 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:49:41,546 INFO misc.py line 117 726] Train: [5/20][459/510] Data 3.747 (3.812) Batch 28.768 (28.225) Remain 60:22:40 loss: 0.2228 loss_seg: 0.1317 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:50:15,357 INFO misc.py line 117 726] Train: [5/20][460/510] Data 3.588 (3.811) Batch 33.811 (28.237) Remain 60:23:46 loss: 0.2531 loss_seg: 0.1520 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:50:45,197 INFO misc.py line 117 726] Train: [5/20][461/510] Data 3.830 (3.811) Batch 29.839 (28.241) Remain 60:23:45 loss: 0.2509 loss_seg: 0.1581 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:51:13,565 INFO misc.py line 117 726] Train: [5/20][462/510] Data 3.166 (3.810) Batch 28.368 (28.241) Remain 60:23:18 loss: 0.3158 loss_seg: 0.2040 loss_superpoint_edge: 0.0465 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:51:48,449 INFO misc.py line 117 726] Train: [5/20][463/510] Data 3.343 (3.809) Batch 34.884 (28.255) Remain 60:24:41 loss: 0.2383 loss_seg: 0.1412 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:52:16,641 INFO misc.py line 117 726] Train: [5/20][464/510] Data 3.974 (3.809) Batch 28.192 (28.255) Remain 60:24:12 loss: 0.2204 loss_seg: 0.1305 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:52:38,609 INFO misc.py line 117 726] Train: [5/20][465/510] Data 2.966 (3.807) Batch 21.968 (28.242) Remain 60:21:59 loss: 0.2035 loss_seg: 0.1166 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:53:04,868 INFO misc.py line 117 726] Train: [5/20][466/510] Data 2.897 (3.805) Batch 26.259 (28.237) Remain 60:20:58 loss: 0.2374 loss_seg: 0.1404 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:53:41,936 INFO misc.py line 117 726] Train: [5/20][467/510] Data 6.923 (3.812) Batch 37.069 (28.256) Remain 60:22:56 loss: 0.2632 loss_seg: 0.1664 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:54:11,483 INFO misc.py line 117 726] Train: [5/20][468/510] Data 4.419 (3.813) Batch 29.546 (28.259) Remain 60:22:49 loss: 0.2722 loss_seg: 0.1754 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:54:43,525 INFO misc.py line 117 726] Train: [5/20][469/510] Data 4.266 (3.814) Batch 32.042 (28.267) Remain 60:23:23 loss: 0.2277 loss_seg: 0.1304 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:55:21,831 INFO misc.py line 117 726] Train: [5/20][470/510] Data 9.496 (3.827) Batch 38.306 (28.289) Remain 60:25:40 loss: 0.3048 loss_seg: 0.1966 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:55:57,800 INFO misc.py line 117 726] Train: [5/20][471/510] Data 3.688 (3.826) Batch 35.970 (28.305) Remain 60:27:18 loss: 0.2803 loss_seg: 0.1770 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:56:13,289 INFO misc.py line 117 726] Train: [5/20][472/510] Data 1.952 (3.822) Batch 15.489 (28.278) Remain 60:23:20 loss: 0.3454 loss_seg: 0.2322 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:56:38,779 INFO misc.py line 117 726] Train: [5/20][473/510] Data 2.990 (3.821) Batch 25.490 (28.272) Remain 60:22:06 loss: 0.2298 loss_seg: 0.1312 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0450 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:57:08,851 INFO misc.py line 117 726] Train: [5/20][474/510] Data 2.627 (3.818) Batch 30.071 (28.276) Remain 60:22:07 loss: 0.2106 loss_seg: 0.1228 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:57:36,039 INFO misc.py line 117 726] Train: [5/20][475/510] Data 4.679 (3.820) Batch 27.188 (28.273) Remain 60:21:21 loss: 0.2187 loss_seg: 0.1249 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:58:00,505 INFO misc.py line 117 726] Train: [5/20][476/510] Data 3.554 (3.819) Batch 24.466 (28.265) Remain 60:19:51 loss: 0.3043 loss_seg: 0.2020 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:58:25,301 INFO misc.py line 117 726] Train: [5/20][477/510] Data 2.880 (3.817) Batch 24.795 (28.258) Remain 60:18:26 loss: 0.2490 loss_seg: 0.1530 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:59:01,677 INFO misc.py line 117 726] Train: [5/20][478/510] Data 6.711 (3.823) Batch 36.376 (28.275) Remain 60:20:10 loss: 0.2344 loss_seg: 0.1398 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:59:19,027 INFO misc.py line 117 726] Train: [5/20][479/510] Data 2.508 (3.821) Batch 17.351 (28.252) Remain 60:16:45 loss: 0.2644 loss_seg: 0.1566 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 10:59:42,004 INFO misc.py line 117 726] Train: [5/20][480/510] Data 2.821 (3.819) Batch 22.977 (28.241) Remain 60:14:52 loss: 0.2222 loss_seg: 0.1307 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:00:04,669 INFO misc.py line 117 726] Train: [5/20][481/510] Data 2.478 (3.816) Batch 22.665 (28.230) Remain 60:12:54 loss: 0.3828 loss_seg: 0.2661 loss_superpoint_edge: 0.0448 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:00:22,265 INFO misc.py line 117 726] Train: [5/20][482/510] Data 1.928 (3.812) Batch 17.596 (28.207) Remain 60:09:35 loss: 0.2149 loss_seg: 0.1226 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:00:50,140 INFO misc.py line 117 726] Train: [5/20][483/510] Data 2.869 (3.810) Batch 27.875 (28.207) Remain 60:09:02 loss: 0.2413 loss_seg: 0.1390 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:01:11,091 INFO misc.py line 117 726] Train: [5/20][484/510] Data 1.750 (3.806) Batch 20.951 (28.192) Remain 60:06:38 loss: 0.2975 loss_seg: 0.1932 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:01:46,907 INFO misc.py line 117 726] Train: [5/20][485/510] Data 8.047 (3.814) Batch 35.816 (28.207) Remain 60:08:11 loss: 0.2612 loss_seg: 0.1635 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:02:14,488 INFO misc.py line 117 726] Train: [5/20][486/510] Data 3.119 (3.813) Batch 27.580 (28.206) Remain 60:07:33 loss: 0.2806 loss_seg: 0.1794 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:02:46,530 INFO misc.py line 117 726] Train: [5/20][487/510] Data 5.999 (3.817) Batch 32.043 (28.214) Remain 60:08:05 loss: 0.5090 loss_seg: 0.3928 loss_superpoint_edge: 0.0485 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:03:20,929 INFO misc.py line 117 726] Train: [5/20][488/510] Data 4.144 (3.818) Batch 34.399 (28.227) Remain 60:09:15 loss: 0.2173 loss_seg: 0.1283 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:03:43,097 INFO misc.py line 117 726] Train: [5/20][489/510] Data 2.021 (3.814) Batch 22.167 (28.214) Remain 60:07:11 loss: 0.1935 loss_seg: 0.1063 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:04:15,064 INFO misc.py line 117 726] Train: [5/20][490/510] Data 4.654 (3.816) Batch 31.967 (28.222) Remain 60:07:42 loss: 0.2374 loss_seg: 0.1487 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:04:47,506 INFO misc.py line 117 726] Train: [5/20][491/510] Data 5.116 (3.819) Batch 32.442 (28.231) Remain 60:08:20 loss: 0.2565 loss_seg: 0.1598 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:05:22,657 INFO misc.py line 117 726] Train: [5/20][492/510] Data 6.152 (3.824) Batch 35.151 (28.245) Remain 60:09:40 loss: 0.3309 loss_seg: 0.2158 loss_superpoint_edge: 0.0476 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:05:39,547 INFO misc.py line 117 726] Train: [5/20][493/510] Data 2.225 (3.820) Batch 16.890 (28.222) Remain 60:06:15 loss: 0.2491 loss_seg: 0.1528 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:06:17,709 INFO misc.py line 117 726] Train: [5/20][494/510] Data 9.341 (3.832) Batch 38.162 (28.242) Remain 60:08:22 loss: 0.2102 loss_seg: 0.1213 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:06:37,848 INFO misc.py line 117 726] Train: [5/20][495/510] Data 2.370 (3.829) Batch 20.139 (28.225) Remain 60:05:47 loss: 0.2026 loss_seg: 0.1117 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:07:06,431 INFO misc.py line 117 726] Train: [5/20][496/510] Data 4.767 (3.830) Batch 28.584 (28.226) Remain 60:05:24 loss: 0.3071 loss_seg: 0.2023 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:07:37,693 INFO misc.py line 117 726] Train: [5/20][497/510] Data 3.310 (3.829) Batch 31.261 (28.232) Remain 60:05:43 loss: 0.2382 loss_seg: 0.1438 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:08:04,799 INFO misc.py line 117 726] Train: [5/20][498/510] Data 2.548 (3.827) Batch 27.106 (28.230) Remain 60:04:58 loss: 0.2324 loss_seg: 0.1389 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:08:27,910 INFO misc.py line 117 726] Train: [5/20][499/510] Data 2.732 (3.825) Batch 23.112 (28.220) Remain 60:03:10 loss: 0.2988 loss_seg: 0.1945 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:09:03,769 INFO misc.py line 117 726] Train: [5/20][500/510] Data 5.323 (3.828) Batch 35.859 (28.235) Remain 60:04:40 loss: 0.3381 loss_seg: 0.2255 loss_superpoint_edge: 0.0429 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:09:03,770 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 11:09:29,257 INFO misc.py line 117 726] Train: [5/20][501/510] Data 3.425 (3.827) Batch 25.488 (28.230) Remain 60:03:29 loss: 0.2440 loss_seg: 0.1521 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:09:56,932 INFO misc.py line 117 726] Train: [5/20][502/510] Data 3.429 (3.826) Batch 27.675 (28.228) Remain 60:02:53 loss: 0.2500 loss_seg: 0.1553 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:10:17,727 INFO misc.py line 117 726] Train: [5/20][503/510] Data 2.946 (3.824) Batch 20.795 (28.214) Remain 60:00:31 loss: 0.2643 loss_seg: 0.1712 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:10:42,868 INFO misc.py line 117 726] Train: [5/20][504/510] Data 3.027 (3.823) Batch 25.140 (28.207) Remain 59:59:15 loss: 0.2402 loss_seg: 0.1442 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:11:13,586 INFO misc.py line 117 726] Train: [5/20][505/510] Data 4.318 (3.824) Batch 30.718 (28.212) Remain 59:59:25 loss: 0.2886 loss_seg: 0.1838 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:11:36,580 INFO misc.py line 117 726] Train: [5/20][506/510] Data 2.500 (3.821) Batch 22.994 (28.202) Remain 59:57:38 loss: 0.3112 loss_seg: 0.1992 loss_superpoint_edge: 0.0440 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:12:12,683 INFO misc.py line 117 726] Train: [5/20][507/510] Data 5.166 (3.824) Batch 36.104 (28.218) Remain 59:59:10 loss: 0.2131 loss_seg: 0.1213 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:12:33,539 INFO misc.py line 117 726] Train: [5/20][508/510] Data 2.265 (3.821) Batch 20.855 (28.203) Remain 59:56:50 loss: 0.2087 loss_seg: 0.1158 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:12:52,795 INFO misc.py line 117 726] Train: [5/20][509/510] Data 2.386 (3.818) Batch 19.256 (28.185) Remain 59:54:06 loss: 0.2252 loss_seg: 0.1312 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:13:28,247 INFO misc.py line 117 726] Train: [5/20][510/510] Data 4.730 (3.820) Batch 35.452 (28.200) Remain 59:55:28 loss: 0.3321 loss_seg: 0.2235 loss_superpoint_edge: 0.0421 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:13:28,247 INFO misc.py line 147 726] Train result: loss: 0.2525 loss_seg: 0.1565 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-10 11:13:28,248 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-10 11:13:43,938 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7228 [2026-06-10 11:14:01,427 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6785 [2026-06-10 11:15:16,381 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8978 [2026-06-10 11:15:56,738 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9300 [2026-06-10 11:16:16,064 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0538 [2026-06-10 11:16:52,363 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.1338 [2026-06-10 11:17:39,230 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.0094 [2026-06-10 11:17:54,785 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2273 [2026-06-10 11:18:12,887 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9644 [2026-06-10 11:18:31,755 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.5113 [2026-06-10 11:18:47,666 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4652 [2026-06-10 11:19:09,487 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7546 [2026-06-10 11:19:35,560 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8201 [2026-06-10 11:19:46,826 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7240 [2026-06-10 11:20:18,769 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0009 [2026-06-10 11:20:44,949 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3057 [2026-06-10 11:21:11,899 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.2805 [2026-06-10 11:21:54,772 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 3.9933 [2026-06-10 11:22:15,790 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4071 [2026-06-10 11:22:32,375 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.6546 [2026-06-10 11:23:03,936 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.6822 [2026-06-10 11:23:20,079 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.2781 [2026-06-10 11:23:41,931 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2814 [2026-06-10 11:24:03,248 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7569 [2026-06-10 11:24:16,576 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6300 [2026-06-10 11:24:44,337 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5897 [2026-06-10 11:25:25,987 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0042 [2026-06-10 11:25:43,480 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5533 [2026-06-10 11:26:02,158 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4216 [2026-06-10 11:26:19,232 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3752 [2026-06-10 11:26:44,259 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.0965 [2026-06-10 11:27:02,498 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5371 [2026-06-10 11:27:19,999 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9106 [2026-06-10 11:27:44,653 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.5390 [2026-06-10 11:27:44,665 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6723/0.7476/0.8965. [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9230/0.9576 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9760/0.9880 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8424/0.9671 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0016/0.0136 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3311/0.4082 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6024/0.6334 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6173/0.7166 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7937/0.8922 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9125/0.9471 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6943/0.7670 [2026-06-10 11:27:44,665 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7594/0.8513 [2026-06-10 11:27:44,666 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6893/0.8744 [2026-06-10 11:27:44,666 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5969/0.7021 [2026-06-10 11:27:44,666 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-10 11:27:44,667 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-10 11:27:44,667 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 11:28:08,711 INFO misc.py line 117 726] Train: [6/20][1/510] Data 2.562 (2.562) Batch 22.509 (22.509) Remain 47:49:33 loss: 0.1953 loss_seg: 0.1095 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:28:35,031 INFO misc.py line 117 726] Train: [6/20][2/510] Data 2.968 (2.968) Batch 26.321 (26.321) Remain 55:55:00 loss: 0.2444 loss_seg: 0.1442 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:29:01,921 INFO misc.py line 117 726] Train: [6/20][3/510] Data 2.504 (2.504) Batch 26.889 (26.889) Remain 57:07:03 loss: 0.2942 loss_seg: 0.1891 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:29:28,776 INFO misc.py line 117 726] Train: [6/20][4/510] Data 4.331 (4.331) Batch 26.855 (26.855) Remain 57:02:14 loss: 0.2525 loss_seg: 0.1524 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:29:53,649 INFO misc.py line 117 726] Train: [6/20][5/510] Data 2.791 (3.561) Batch 24.873 (25.864) Remain 54:55:30 loss: 0.1855 loss_seg: 0.0967 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:30:13,531 INFO misc.py line 117 726] Train: [6/20][6/510] Data 2.223 (3.115) Batch 19.882 (23.870) Remain 50:41:02 loss: 0.1642 loss_seg: 0.0829 loss_superpoint_edge: 0.0128 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:30:44,948 INFO misc.py line 117 726] Train: [6/20][7/510] Data 3.791 (3.284) Batch 31.417 (25.757) Remain 54:40:58 loss: 0.2122 loss_seg: 0.1215 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:31:05,843 INFO misc.py line 117 726] Train: [6/20][8/510] Data 2.542 (3.136) Batch 20.896 (24.785) Remain 52:36:43 loss: 0.2313 loss_seg: 0.1330 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:31:45,697 INFO misc.py line 117 726] Train: [6/20][9/510] Data 10.480 (4.360) Batch 39.854 (27.296) Remain 57:56:09 loss: 0.2671 loss_seg: 0.1718 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:32:12,533 INFO misc.py line 117 726] Train: [6/20][10/510] Data 3.129 (4.184) Batch 26.836 (27.230) Remain 57:47:19 loss: 0.2261 loss_seg: 0.1320 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:32:35,064 INFO misc.py line 117 726] Train: [6/20][11/510] Data 3.780 (4.133) Batch 22.530 (26.643) Remain 56:32:04 loss: 0.1872 loss_seg: 0.1027 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:33:12,729 INFO misc.py line 117 726] Train: [6/20][12/510] Data 5.934 (4.334) Batch 37.665 (27.868) Remain 59:07:32 loss: 0.2233 loss_seg: 0.1317 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:33:46,760 INFO misc.py line 117 726] Train: [6/20][13/510] Data 4.001 (4.300) Batch 34.031 (28.484) Remain 60:25:31 loss: 0.2284 loss_seg: 0.1376 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:34:05,989 INFO misc.py line 117 726] Train: [6/20][14/510] Data 2.352 (4.123) Batch 19.229 (27.643) Remain 58:37:58 loss: 0.2102 loss_seg: 0.1220 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:34:35,084 INFO misc.py line 117 726] Train: [6/20][15/510] Data 2.804 (4.013) Batch 29.095 (27.764) Remain 58:52:54 loss: 0.2511 loss_seg: 0.1522 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:35:04,993 INFO misc.py line 117 726] Train: [6/20][16/510] Data 3.193 (3.950) Batch 29.909 (27.929) Remain 59:13:26 loss: 0.2269 loss_seg: 0.1308 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:35:30,893 INFO misc.py line 117 726] Train: [6/20][17/510] Data 2.985 (3.881) Batch 25.900 (27.784) Remain 58:54:33 loss: 0.2040 loss_seg: 0.1149 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:36:05,246 INFO misc.py line 117 726] Train: [6/20][18/510] Data 5.383 (3.981) Batch 34.353 (28.222) Remain 59:49:47 loss: 0.2289 loss_seg: 0.1374 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:36:20,285 INFO misc.py line 117 726] Train: [6/20][19/510] Data 1.722 (3.840) Batch 15.040 (27.398) Remain 58:04:32 loss: 0.2368 loss_seg: 0.1426 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:36:43,378 INFO misc.py line 117 726] Train: [6/20][20/510] Data 2.432 (3.757) Batch 23.092 (27.145) Remain 57:31:52 loss: 0.2358 loss_seg: 0.1433 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:37:16,470 INFO misc.py line 117 726] Train: [6/20][21/510] Data 4.499 (3.798) Batch 33.092 (27.475) Remain 58:13:26 loss: 0.1791 loss_seg: 0.0935 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:37:52,443 INFO misc.py line 117 726] Train: [6/20][22/510] Data 5.480 (3.887) Batch 35.973 (27.922) Remain 59:09:50 loss: 0.2682 loss_seg: 0.1819 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:38:26,540 INFO misc.py line 117 726] Train: [6/20][23/510] Data 3.599 (3.873) Batch 34.097 (28.231) Remain 59:48:37 loss: 0.2187 loss_seg: 0.1288 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:38:47,767 INFO misc.py line 117 726] Train: [6/20][24/510] Data 2.624 (3.813) Batch 21.226 (27.897) Remain 59:05:45 loss: 0.1929 loss_seg: 0.1046 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:39:12,997 INFO misc.py line 117 726] Train: [6/20][25/510] Data 3.321 (3.791) Batch 25.230 (27.776) Remain 58:49:53 loss: 0.2028 loss_seg: 0.1117 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:39:42,547 INFO misc.py line 117 726] Train: [6/20][26/510] Data 4.331 (3.814) Batch 29.551 (27.853) Remain 58:59:13 loss: 0.2568 loss_seg: 0.1594 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:40:11,927 INFO misc.py line 117 726] Train: [6/20][27/510] Data 6.836 (3.940) Batch 29.380 (27.917) Remain 59:06:50 loss: 0.3767 loss_seg: 0.2578 loss_superpoint_edge: 0.0432 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:40:45,190 INFO misc.py line 117 726] Train: [6/20][28/510] Data 7.835 (4.096) Batch 33.263 (28.131) Remain 59:33:32 loss: 0.4575 loss_seg: 0.3206 loss_superpoint_edge: 0.0681 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:41:18,351 INFO misc.py line 117 726] Train: [6/20][29/510] Data 4.055 (4.094) Batch 33.161 (28.324) Remain 59:57:38 loss: 0.2097 loss_seg: 0.1206 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:41:40,864 INFO misc.py line 117 726] Train: [6/20][30/510] Data 1.980 (4.016) Batch 22.513 (28.109) Remain 59:29:50 loss: 0.2313 loss_seg: 0.1396 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:42:10,585 INFO misc.py line 117 726] Train: [6/20][31/510] Data 3.581 (4.000) Batch 29.720 (28.167) Remain 59:36:41 loss: 0.2409 loss_seg: 0.1417 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:42:41,068 INFO misc.py line 117 726] Train: [6/20][32/510] Data 3.407 (3.980) Batch 30.483 (28.246) Remain 59:46:21 loss: 0.2904 loss_seg: 0.1786 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:43:14,139 INFO misc.py line 117 726] Train: [6/20][33/510] Data 4.544 (3.999) Batch 33.071 (28.407) Remain 60:06:18 loss: 0.2574 loss_seg: 0.1623 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:43:34,906 INFO misc.py line 117 726] Train: [6/20][34/510] Data 2.284 (3.943) Batch 20.766 (28.161) Remain 59:34:32 loss: 0.2813 loss_seg: 0.1781 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:44:09,525 INFO misc.py line 117 726] Train: [6/20][35/510] Data 4.135 (3.949) Batch 34.619 (28.363) Remain 59:59:41 loss: 0.2016 loss_seg: 0.1128 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:44:43,767 INFO misc.py line 117 726] Train: [6/20][36/510] Data 3.853 (3.947) Batch 34.242 (28.541) Remain 60:21:49 loss: 0.2304 loss_seg: 0.1360 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:45:11,247 INFO misc.py line 117 726] Train: [6/20][37/510] Data 4.367 (3.959) Batch 27.480 (28.510) Remain 60:17:23 loss: 0.2017 loss_seg: 0.1116 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:45:43,258 INFO misc.py line 117 726] Train: [6/20][38/510] Data 5.417 (4.001) Batch 32.011 (28.610) Remain 60:29:36 loss: 0.4654 loss_seg: 0.3591 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:46:05,647 INFO misc.py line 117 726] Train: [6/20][39/510] Data 3.535 (3.988) Batch 22.389 (28.437) Remain 60:07:12 loss: 0.2224 loss_seg: 0.1335 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:46:27,283 INFO misc.py line 117 726] Train: [6/20][40/510] Data 2.753 (3.954) Batch 21.636 (28.253) Remain 59:43:25 loss: 0.2233 loss_seg: 0.1358 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:46:53,239 INFO misc.py line 117 726] Train: [6/20][41/510] Data 2.930 (3.927) Batch 25.956 (28.193) Remain 59:35:17 loss: 0.2058 loss_seg: 0.1204 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:47:18,184 INFO misc.py line 117 726] Train: [6/20][42/510] Data 3.148 (3.907) Batch 24.945 (28.109) Remain 59:24:15 loss: 0.2060 loss_seg: 0.1179 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:47:40,590 INFO misc.py line 117 726] Train: [6/20][43/510] Data 2.043 (3.861) Batch 22.406 (27.967) Remain 59:05:42 loss: 0.2471 loss_seg: 0.1518 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:48:11,734 INFO misc.py line 117 726] Train: [6/20][44/510] Data 5.138 (3.892) Batch 31.144 (28.044) Remain 59:15:04 loss: 0.2440 loss_seg: 0.1542 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:48:39,805 INFO misc.py line 117 726] Train: [6/20][45/510] Data 3.113 (3.873) Batch 28.071 (28.045) Remain 59:14:41 loss: 0.2096 loss_seg: 0.1215 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:49:14,541 INFO misc.py line 117 726] Train: [6/20][46/510] Data 6.711 (3.939) Batch 34.737 (28.200) Remain 59:33:56 loss: 0.2834 loss_seg: 0.1902 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:49:35,714 INFO misc.py line 117 726] Train: [6/20][47/510] Data 2.389 (3.904) Batch 21.172 (28.041) Remain 59:13:13 loss: 0.2489 loss_seg: 0.1536 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:50:05,608 INFO misc.py line 117 726] Train: [6/20][48/510] Data 3.113 (3.887) Batch 29.894 (28.082) Remain 59:17:58 loss: 0.2797 loss_seg: 0.1912 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:50:36,398 INFO misc.py line 117 726] Train: [6/20][49/510] Data 3.639 (3.881) Batch 30.790 (28.141) Remain 59:24:58 loss: 0.2836 loss_seg: 0.1758 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:51:05,719 INFO misc.py line 117 726] Train: [6/20][50/510] Data 3.163 (3.866) Batch 29.322 (28.166) Remain 59:27:41 loss: 0.1952 loss_seg: 0.1079 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:51:05,720 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 11:51:34,208 INFO misc.py line 117 726] Train: [6/20][51/510] Data 3.827 (3.865) Batch 28.488 (28.173) Remain 59:28:03 loss: 0.2673 loss_seg: 0.1635 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:51:58,279 INFO misc.py line 117 726] Train: [6/20][52/510] Data 3.542 (3.858) Batch 24.071 (28.089) Remain 59:16:59 loss: 0.2186 loss_seg: 0.1265 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:52:22,960 INFO misc.py line 117 726] Train: [6/20][53/510] Data 1.903 (3.819) Batch 24.681 (28.021) Remain 59:07:53 loss: 0.2031 loss_seg: 0.1168 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:52:47,476 INFO misc.py line 117 726] Train: [6/20][54/510] Data 2.816 (3.800) Batch 24.516 (27.952) Remain 58:58:43 loss: 0.2667 loss_seg: 0.1697 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:53:21,541 INFO misc.py line 117 726] Train: [6/20][55/510] Data 4.914 (3.821) Batch 34.065 (28.070) Remain 59:13:08 loss: 0.3215 loss_seg: 0.2164 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:53:58,038 INFO misc.py line 117 726] Train: [6/20][56/510] Data 4.942 (3.842) Batch 36.497 (28.229) Remain 59:32:48 loss: 0.2933 loss_seg: 0.1989 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:54:30,668 INFO misc.py line 117 726] Train: [6/20][57/510] Data 3.975 (3.845) Batch 32.630 (28.310) Remain 59:42:38 loss: 0.2189 loss_seg: 0.1245 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:54:53,513 INFO misc.py line 117 726] Train: [6/20][58/510] Data 3.173 (3.832) Batch 22.845 (28.211) Remain 59:29:36 loss: 0.1931 loss_seg: 0.1019 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:55:18,528 INFO misc.py line 117 726] Train: [6/20][59/510] Data 3.355 (3.824) Batch 25.016 (28.154) Remain 59:21:54 loss: 0.2503 loss_seg: 0.1584 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:55:47,721 INFO misc.py line 117 726] Train: [6/20][60/510] Data 3.958 (3.826) Batch 29.193 (28.172) Remain 59:23:44 loss: 0.2840 loss_seg: 0.1929 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:56:19,953 INFO misc.py line 117 726] Train: [6/20][61/510] Data 4.037 (3.830) Batch 32.232 (28.242) Remain 59:32:08 loss: 0.2516 loss_seg: 0.1560 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:56:53,311 INFO misc.py line 117 726] Train: [6/20][62/510] Data 5.363 (3.856) Batch 33.358 (28.329) Remain 59:42:37 loss: 0.2588 loss_seg: 0.1598 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:57:19,212 INFO misc.py line 117 726] Train: [6/20][63/510] Data 3.422 (3.849) Batch 25.901 (28.288) Remain 59:37:02 loss: 0.2084 loss_seg: 0.1133 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:57:41,455 INFO misc.py line 117 726] Train: [6/20][64/510] Data 2.439 (3.826) Batch 22.243 (28.189) Remain 59:24:02 loss: 0.2211 loss_seg: 0.1299 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:58:10,190 INFO misc.py line 117 726] Train: [6/20][65/510] Data 2.475 (3.804) Batch 28.735 (28.198) Remain 59:24:40 loss: 0.3068 loss_seg: 0.2151 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:58:30,794 INFO misc.py line 117 726] Train: [6/20][66/510] Data 1.750 (3.771) Batch 20.604 (28.077) Remain 59:08:58 loss: 0.2371 loss_seg: 0.1413 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:58:58,312 INFO misc.py line 117 726] Train: [6/20][67/510] Data 2.900 (3.758) Batch 27.519 (28.069) Remain 59:07:24 loss: 0.2297 loss_seg: 0.1344 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:59:25,850 INFO misc.py line 117 726] Train: [6/20][68/510] Data 2.367 (3.736) Batch 27.538 (28.060) Remain 59:05:54 loss: 0.2901 loss_seg: 0.1884 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 11:59:49,984 INFO misc.py line 117 726] Train: [6/20][69/510] Data 2.830 (3.722) Batch 24.133 (28.001) Remain 58:57:55 loss: 0.2356 loss_seg: 0.1415 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:00:08,309 INFO misc.py line 117 726] Train: [6/20][70/510] Data 2.100 (3.698) Batch 18.325 (27.857) Remain 58:39:12 loss: 0.2036 loss_seg: 0.1110 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:00:43,720 INFO misc.py line 117 726] Train: [6/20][71/510] Data 5.754 (3.728) Batch 35.411 (27.968) Remain 58:52:46 loss: 0.2598 loss_seg: 0.1598 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:01:13,522 INFO misc.py line 117 726] Train: [6/20][72/510] Data 3.957 (3.732) Batch 29.802 (27.994) Remain 58:55:40 loss: 0.2481 loss_seg: 0.1506 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:01:42,992 INFO misc.py line 117 726] Train: [6/20][73/510] Data 4.686 (3.745) Batch 29.471 (28.015) Remain 58:57:51 loss: 0.2364 loss_seg: 0.1414 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:02:08,924 INFO misc.py line 117 726] Train: [6/20][74/510] Data 2.882 (3.733) Batch 25.932 (27.986) Remain 58:53:41 loss: 0.3019 loss_seg: 0.2007 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:02:36,718 INFO misc.py line 117 726] Train: [6/20][75/510] Data 4.833 (3.749) Batch 27.793 (27.983) Remain 58:52:53 loss: 0.2061 loss_seg: 0.1174 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:03:11,991 INFO misc.py line 117 726] Train: [6/20][76/510] Data 5.465 (3.772) Batch 35.273 (28.083) Remain 59:05:01 loss: 0.3432 loss_seg: 0.2432 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:03:42,172 INFO misc.py line 117 726] Train: [6/20][77/510] Data 3.532 (3.769) Batch 30.181 (28.111) Remain 59:08:08 loss: 0.2475 loss_seg: 0.1521 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:03:59,167 INFO misc.py line 117 726] Train: [6/20][78/510] Data 2.000 (3.745) Batch 16.995 (27.963) Remain 58:48:57 loss: 0.3089 loss_seg: 0.2034 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:04:25,631 INFO misc.py line 117 726] Train: [6/20][79/510] Data 3.104 (3.737) Batch 26.464 (27.944) Remain 58:46:00 loss: 0.2455 loss_seg: 0.1440 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:04:46,864 INFO misc.py line 117 726] Train: [6/20][80/510] Data 2.458 (3.720) Batch 21.233 (27.856) Remain 58:34:32 loss: 0.2171 loss_seg: 0.1244 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:05:16,104 INFO misc.py line 117 726] Train: [6/20][81/510] Data 3.661 (3.719) Batch 29.239 (27.874) Remain 58:36:19 loss: 0.2462 loss_seg: 0.1483 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:05:44,264 INFO misc.py line 117 726] Train: [6/20][82/510] Data 2.949 (3.710) Batch 28.161 (27.878) Remain 58:36:18 loss: 0.2225 loss_seg: 0.1273 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:06:18,080 INFO misc.py line 117 726] Train: [6/20][83/510] Data 7.743 (3.760) Batch 33.816 (27.952) Remain 58:45:12 loss: 0.2404 loss_seg: 0.1425 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:06:45,061 INFO misc.py line 117 726] Train: [6/20][84/510] Data 3.550 (3.757) Batch 26.981 (27.940) Remain 58:43:13 loss: 0.2546 loss_seg: 0.1550 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:07:19,932 INFO misc.py line 117 726] Train: [6/20][85/510] Data 4.456 (3.766) Batch 34.872 (28.025) Remain 58:53:25 loss: 0.2526 loss_seg: 0.1571 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:07:47,578 INFO misc.py line 117 726] Train: [6/20][86/510] Data 3.231 (3.760) Batch 27.646 (28.020) Remain 58:52:23 loss: 0.2407 loss_seg: 0.1437 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:08:12,864 INFO misc.py line 117 726] Train: [6/20][87/510] Data 3.878 (3.761) Batch 25.285 (27.987) Remain 58:47:48 loss: 0.2941 loss_seg: 0.2031 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:08:47,601 INFO misc.py line 117 726] Train: [6/20][88/510] Data 11.546 (3.853) Batch 34.737 (28.067) Remain 58:57:21 loss: 0.3279 loss_seg: 0.2330 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0459 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:09:12,583 INFO misc.py line 117 726] Train: [6/20][89/510] Data 2.814 (3.840) Batch 24.982 (28.031) Remain 58:52:22 loss: 0.2118 loss_seg: 0.1255 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:09:37,995 INFO misc.py line 117 726] Train: [6/20][90/510] Data 2.618 (3.826) Batch 25.411 (28.001) Remain 58:48:06 loss: 0.3054 loss_seg: 0.1996 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:10:04,012 INFO misc.py line 117 726] Train: [6/20][91/510] Data 2.305 (3.809) Batch 26.018 (27.978) Remain 58:44:48 loss: 0.2897 loss_seg: 0.1796 loss_superpoint_edge: 0.0437 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:10:22,933 INFO misc.py line 117 726] Train: [6/20][92/510] Data 1.903 (3.788) Batch 18.920 (27.877) Remain 58:31:30 loss: 0.4577 loss_seg: 0.3441 loss_superpoint_edge: 0.0421 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:10:53,501 INFO misc.py line 117 726] Train: [6/20][93/510] Data 3.192 (3.781) Batch 30.568 (27.906) Remain 58:34:48 loss: 0.3287 loss_seg: 0.2303 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:11:19,517 INFO misc.py line 117 726] Train: [6/20][94/510] Data 3.471 (3.778) Batch 26.017 (27.886) Remain 58:31:44 loss: 0.2672 loss_seg: 0.1673 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:11:47,345 INFO misc.py line 117 726] Train: [6/20][95/510] Data 2.434 (3.763) Batch 27.828 (27.885) Remain 58:31:11 loss: 0.2878 loss_seg: 0.1892 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:12:10,285 INFO misc.py line 117 726] Train: [6/20][96/510] Data 1.913 (3.743) Batch 22.940 (27.832) Remain 58:24:01 loss: 0.2767 loss_seg: 0.1659 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:12:45,400 INFO misc.py line 117 726] Train: [6/20][97/510] Data 4.596 (3.752) Batch 35.115 (27.909) Remain 58:33:19 loss: 0.2192 loss_seg: 0.1276 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:12:56,809 INFO misc.py line 117 726] Train: [6/20][98/510] Data 1.696 (3.731) Batch 11.409 (27.736) Remain 58:10:59 loss: 0.3567 loss_seg: 0.2563 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:13:21,766 INFO misc.py line 117 726] Train: [6/20][99/510] Data 2.495 (3.718) Batch 24.957 (27.707) Remain 58:06:53 loss: 0.2074 loss_seg: 0.1166 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:13:57,343 INFO misc.py line 117 726] Train: [6/20][100/510] Data 4.913 (3.730) Batch 35.577 (27.788) Remain 58:16:38 loss: 0.2464 loss_seg: 0.1522 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:13:57,344 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 12:14:31,613 INFO misc.py line 117 726] Train: [6/20][101/510] Data 4.390 (3.737) Batch 34.270 (27.854) Remain 58:24:29 loss: 0.2637 loss_seg: 0.1787 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:15:00,149 INFO misc.py line 117 726] Train: [6/20][102/510] Data 2.865 (3.728) Batch 28.536 (27.861) Remain 58:24:53 loss: 0.2078 loss_seg: 0.1192 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:15:27,932 INFO misc.py line 117 726] Train: [6/20][103/510] Data 3.794 (3.729) Batch 27.782 (27.860) Remain 58:24:20 loss: 0.5372 loss_seg: 0.4189 loss_superpoint_edge: 0.0483 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:15:58,216 INFO misc.py line 117 726] Train: [6/20][104/510] Data 3.372 (3.725) Batch 30.284 (27.884) Remain 58:26:53 loss: 0.2922 loss_seg: 0.1867 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:16:30,129 INFO misc.py line 117 726] Train: [6/20][105/510] Data 4.809 (3.736) Batch 31.913 (27.924) Remain 58:31:23 loss: 0.2219 loss_seg: 0.1310 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:16:55,096 INFO misc.py line 117 726] Train: [6/20][106/510] Data 2.624 (3.725) Batch 24.966 (27.895) Remain 58:27:19 loss: 0.1990 loss_seg: 0.1134 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:17:27,822 INFO misc.py line 117 726] Train: [6/20][107/510] Data 4.441 (3.732) Batch 32.727 (27.941) Remain 58:32:41 loss: 0.2559 loss_seg: 0.1561 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:17:59,785 INFO misc.py line 117 726] Train: [6/20][108/510] Data 8.715 (3.779) Batch 31.962 (27.980) Remain 58:37:02 loss: 0.1973 loss_seg: 0.1047 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0449 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:18:23,201 INFO misc.py line 117 726] Train: [6/20][109/510] Data 2.472 (3.767) Batch 23.416 (27.937) Remain 58:31:09 loss: 0.2519 loss_seg: 0.1550 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:18:54,282 INFO misc.py line 117 726] Train: [6/20][110/510] Data 3.908 (3.768) Batch 31.081 (27.966) Remain 58:34:23 loss: 0.2624 loss_seg: 0.1614 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:19:20,576 INFO misc.py line 117 726] Train: [6/20][111/510] Data 3.581 (3.767) Batch 26.294 (27.951) Remain 58:31:58 loss: 0.3069 loss_seg: 0.1912 loss_superpoint_edge: 0.0494 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:19:51,730 INFO misc.py line 117 726] Train: [6/20][112/510] Data 3.039 (3.760) Batch 31.155 (27.980) Remain 58:35:12 loss: 0.2548 loss_seg: 0.1575 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:20:31,262 INFO misc.py line 117 726] Train: [6/20][113/510] Data 6.757 (3.787) Batch 39.531 (28.085) Remain 58:47:55 loss: 0.3166 loss_seg: 0.2126 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:20:46,910 INFO misc.py line 117 726] Train: [6/20][114/510] Data 1.908 (3.770) Batch 15.648 (27.973) Remain 58:33:23 loss: 0.2121 loss_seg: 0.1193 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:21:19,564 INFO misc.py line 117 726] Train: [6/20][115/510] Data 3.153 (3.765) Batch 32.655 (28.015) Remain 58:38:10 loss: 0.2444 loss_seg: 0.1551 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:21:48,393 INFO misc.py line 117 726] Train: [6/20][116/510] Data 3.351 (3.761) Batch 28.828 (28.022) Remain 58:38:36 loss: 0.3260 loss_seg: 0.2232 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:21:59,848 INFO misc.py line 117 726] Train: [6/20][117/510] Data 1.466 (3.741) Batch 11.456 (27.877) Remain 58:19:54 loss: 0.3081 loss_seg: 0.2038 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:22:20,515 INFO misc.py line 117 726] Train: [6/20][118/510] Data 2.269 (3.728) Batch 20.667 (27.814) Remain 58:11:33 loss: 0.2160 loss_seg: 0.1228 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:22:46,132 INFO misc.py line 117 726] Train: [6/20][119/510] Data 2.401 (3.717) Batch 25.617 (27.795) Remain 58:08:43 loss: 0.2648 loss_seg: 0.1688 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:23:12,090 INFO misc.py line 117 726] Train: [6/20][120/510] Data 3.149 (3.712) Batch 25.958 (27.779) Remain 58:06:17 loss: 0.2935 loss_seg: 0.1907 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:23:40,702 INFO misc.py line 117 726] Train: [6/20][121/510] Data 3.420 (3.709) Batch 28.612 (27.786) Remain 58:06:42 loss: 0.2378 loss_seg: 0.1403 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:24:13,428 INFO misc.py line 117 726] Train: [6/20][122/510] Data 3.510 (3.708) Batch 32.726 (27.828) Remain 58:11:27 loss: 0.2749 loss_seg: 0.1736 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:24:48,106 INFO misc.py line 117 726] Train: [6/20][123/510] Data 10.516 (3.764) Batch 34.678 (27.885) Remain 58:18:09 loss: 0.2156 loss_seg: 0.1255 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:25:24,499 INFO misc.py line 117 726] Train: [6/20][124/510] Data 8.726 (3.805) Batch 36.394 (27.955) Remain 58:26:30 loss: 0.1816 loss_seg: 0.0886 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0431 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:25:45,196 INFO misc.py line 117 726] Train: [6/20][125/510] Data 1.997 (3.791) Batch 20.697 (27.896) Remain 58:18:35 loss: 0.2416 loss_seg: 0.1480 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:26:22,885 INFO misc.py line 117 726] Train: [6/20][126/510] Data 5.675 (3.806) Batch 37.689 (27.975) Remain 58:28:06 loss: 0.2574 loss_seg: 0.1656 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:26:47,007 INFO misc.py line 117 726] Train: [6/20][127/510] Data 3.635 (3.805) Batch 24.122 (27.944) Remain 58:23:44 loss: 0.2093 loss_seg: 0.1211 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:27:11,716 INFO misc.py line 117 726] Train: [6/20][128/510] Data 3.873 (3.805) Batch 24.709 (27.918) Remain 58:20:01 loss: 0.2695 loss_seg: 0.1688 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:27:38,472 INFO misc.py line 117 726] Train: [6/20][129/510] Data 3.686 (3.804) Batch 26.756 (27.909) Remain 58:18:24 loss: 0.2853 loss_seg: 0.1881 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:28:04,839 INFO misc.py line 117 726] Train: [6/20][130/510] Data 2.930 (3.797) Batch 26.367 (27.897) Remain 58:16:25 loss: 0.2543 loss_seg: 0.1577 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:28:27,111 INFO misc.py line 117 726] Train: [6/20][131/510] Data 2.239 (3.785) Batch 22.272 (27.853) Remain 58:10:27 loss: 0.2181 loss_seg: 0.1219 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:28:55,923 INFO misc.py line 117 726] Train: [6/20][132/510] Data 4.971 (3.794) Batch 28.812 (27.860) Remain 58:10:55 loss: 0.1716 loss_seg: 0.0868 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:29:25,230 INFO misc.py line 117 726] Train: [6/20][133/510] Data 2.976 (3.788) Batch 29.307 (27.872) Remain 58:11:50 loss: 0.3656 loss_seg: 0.2571 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:29:56,953 INFO misc.py line 117 726] Train: [6/20][134/510] Data 3.326 (3.784) Batch 31.723 (27.901) Remain 58:15:03 loss: 0.2569 loss_seg: 0.1640 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:30:29,712 INFO misc.py line 117 726] Train: [6/20][135/510] Data 3.011 (3.779) Batch 32.760 (27.938) Remain 58:19:12 loss: 0.2631 loss_seg: 0.1623 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:30:53,755 INFO misc.py line 117 726] Train: [6/20][136/510] Data 2.719 (3.771) Batch 24.043 (27.909) Remain 58:15:04 loss: 0.2503 loss_seg: 0.1487 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:31:26,263 INFO misc.py line 117 726] Train: [6/20][137/510] Data 3.379 (3.768) Batch 32.507 (27.943) Remain 58:18:54 loss: 0.2442 loss_seg: 0.1521 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:31:55,487 INFO misc.py line 117 726] Train: [6/20][138/510] Data 4.401 (3.772) Batch 29.224 (27.952) Remain 58:19:37 loss: 0.2146 loss_seg: 0.1261 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:32:29,022 INFO misc.py line 117 726] Train: [6/20][139/510] Data 5.325 (3.784) Batch 33.535 (27.993) Remain 58:24:18 loss: 0.1950 loss_seg: 0.1077 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:32:56,604 INFO misc.py line 117 726] Train: [6/20][140/510] Data 3.166 (3.779) Batch 27.583 (27.990) Remain 58:23:27 loss: 0.1947 loss_seg: 0.1043 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:33:19,268 INFO misc.py line 117 726] Train: [6/20][141/510] Data 2.178 (3.768) Batch 22.663 (27.952) Remain 58:18:09 loss: 0.2036 loss_seg: 0.1167 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:33:42,003 INFO misc.py line 117 726] Train: [6/20][142/510] Data 2.680 (3.760) Batch 22.735 (27.914) Remain 58:13:00 loss: 0.3795 loss_seg: 0.2721 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:34:01,009 INFO misc.py line 117 726] Train: [6/20][143/510] Data 1.827 (3.746) Batch 19.006 (27.851) Remain 58:04:34 loss: 0.2209 loss_seg: 0.1288 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:34:30,085 INFO misc.py line 117 726] Train: [6/20][144/510] Data 3.185 (3.742) Batch 29.076 (27.859) Remain 58:05:12 loss: 0.2018 loss_seg: 0.1118 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:34:54,672 INFO misc.py line 117 726] Train: [6/20][145/510] Data 2.837 (3.736) Batch 24.587 (27.836) Remain 58:01:51 loss: 0.2989 loss_seg: 0.1983 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:35:28,001 INFO misc.py line 117 726] Train: [6/20][146/510] Data 3.858 (3.737) Batch 33.329 (27.875) Remain 58:06:11 loss: 0.2317 loss_seg: 0.1372 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:35:53,702 INFO misc.py line 117 726] Train: [6/20][147/510] Data 3.009 (3.732) Batch 25.701 (27.860) Remain 58:03:50 loss: 0.2561 loss_seg: 0.1595 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:36:09,775 INFO misc.py line 117 726] Train: [6/20][148/510] Data 2.270 (3.721) Batch 16.073 (27.778) Remain 57:53:12 loss: 0.2378 loss_seg: 0.1402 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:36:42,456 INFO misc.py line 117 726] Train: [6/20][149/510] Data 7.054 (3.744) Batch 32.681 (27.812) Remain 57:56:56 loss: 0.2320 loss_seg: 0.1373 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:37:13,037 INFO misc.py line 117 726] Train: [6/20][150/510] Data 3.021 (3.739) Batch 30.581 (27.831) Remain 57:58:50 loss: 0.2271 loss_seg: 0.1354 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:37:13,037 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 12:37:38,847 INFO misc.py line 117 726] Train: [6/20][151/510] Data 3.749 (3.739) Batch 25.811 (27.817) Remain 57:56:40 loss: 0.2307 loss_seg: 0.1354 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:38:04,335 INFO misc.py line 117 726] Train: [6/20][152/510] Data 2.653 (3.732) Batch 25.488 (27.801) Remain 57:54:15 loss: 0.2053 loss_seg: 0.1130 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:38:33,651 INFO misc.py line 117 726] Train: [6/20][153/510] Data 5.491 (3.744) Batch 29.316 (27.812) Remain 57:55:03 loss: 0.2884 loss_seg: 0.1817 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:38:59,784 INFO misc.py line 117 726] Train: [6/20][154/510] Data 2.774 (3.737) Batch 26.133 (27.800) Remain 57:53:11 loss: 0.2163 loss_seg: 0.1219 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:39:37,026 INFO misc.py line 117 726] Train: [6/20][155/510] Data 5.249 (3.747) Batch 37.243 (27.863) Remain 58:00:29 loss: 0.2726 loss_seg: 0.1711 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:39:53,434 INFO misc.py line 117 726] Train: [6/20][156/510] Data 2.103 (3.737) Batch 16.407 (27.788) Remain 57:50:40 loss: 0.2647 loss_seg: 0.1653 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:40:30,414 INFO misc.py line 117 726] Train: [6/20][157/510] Data 5.424 (3.748) Batch 36.981 (27.847) Remain 57:57:40 loss: 0.2553 loss_seg: 0.1572 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:41:00,918 INFO misc.py line 117 726] Train: [6/20][158/510] Data 3.812 (3.748) Batch 30.504 (27.864) Remain 57:59:20 loss: 0.2236 loss_seg: 0.1346 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:41:27,936 INFO misc.py line 117 726] Train: [6/20][159/510] Data 2.367 (3.739) Batch 27.018 (27.859) Remain 57:58:12 loss: 0.2494 loss_seg: 0.1543 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:41:52,536 INFO misc.py line 117 726] Train: [6/20][160/510] Data 2.623 (3.732) Batch 24.600 (27.838) Remain 57:55:08 loss: 0.2639 loss_seg: 0.1613 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:42:20,927 INFO misc.py line 117 726] Train: [6/20][161/510] Data 4.539 (3.737) Batch 28.390 (27.842) Remain 57:55:07 loss: 0.2345 loss_seg: 0.1438 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:42:52,143 INFO misc.py line 117 726] Train: [6/20][162/510] Data 8.073 (3.764) Batch 31.216 (27.863) Remain 57:57:18 loss: 0.5060 loss_seg: 0.3868 loss_superpoint_edge: 0.0473 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:43:15,837 INFO misc.py line 117 726] Train: [6/20][163/510] Data 2.466 (3.756) Batch 23.695 (27.837) Remain 57:53:35 loss: 0.2804 loss_seg: 0.1843 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:43:36,751 INFO misc.py line 117 726] Train: [6/20][164/510] Data 1.898 (3.745) Batch 20.913 (27.794) Remain 57:47:45 loss: 0.2489 loss_seg: 0.1490 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:44:12,208 INFO misc.py line 117 726] Train: [6/20][165/510] Data 4.316 (3.748) Batch 35.457 (27.841) Remain 57:53:11 loss: 0.2453 loss_seg: 0.1459 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:44:35,178 INFO misc.py line 117 726] Train: [6/20][166/510] Data 3.179 (3.745) Batch 22.970 (27.811) Remain 57:49:00 loss: 0.3059 loss_seg: 0.2034 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:45:03,603 INFO misc.py line 117 726] Train: [6/20][167/510] Data 4.640 (3.750) Batch 28.425 (27.815) Remain 57:49:00 loss: 0.1948 loss_seg: 0.1064 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:45:35,108 INFO misc.py line 117 726] Train: [6/20][168/510] Data 3.708 (3.750) Batch 31.505 (27.837) Remain 57:51:20 loss: 0.2484 loss_seg: 0.1544 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:46:04,593 INFO misc.py line 117 726] Train: [6/20][169/510] Data 4.257 (3.753) Batch 29.485 (27.847) Remain 57:52:06 loss: 0.2823 loss_seg: 0.1855 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:46:23,656 INFO misc.py line 117 726] Train: [6/20][170/510] Data 2.262 (3.744) Batch 19.063 (27.795) Remain 57:45:05 loss: 0.2962 loss_seg: 0.1930 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:46:47,793 INFO misc.py line 117 726] Train: [6/20][171/510] Data 2.430 (3.736) Batch 24.137 (27.773) Remain 57:41:54 loss: 0.2283 loss_seg: 0.1364 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:47:20,342 INFO misc.py line 117 726] Train: [6/20][172/510] Data 3.291 (3.734) Batch 32.549 (27.801) Remain 57:44:58 loss: 0.2239 loss_seg: 0.1323 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:47:56,390 INFO misc.py line 117 726] Train: [6/20][173/510] Data 6.385 (3.749) Batch 36.048 (27.850) Remain 57:50:33 loss: 0.1793 loss_seg: 0.0940 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:48:27,270 INFO misc.py line 117 726] Train: [6/20][174/510] Data 3.498 (3.748) Batch 30.880 (27.868) Remain 57:52:17 loss: 0.2725 loss_seg: 0.1760 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:48:56,656 INFO misc.py line 117 726] Train: [6/20][175/510] Data 3.010 (3.743) Batch 29.387 (27.876) Remain 57:52:55 loss: 0.2953 loss_seg: 0.1876 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:49:26,584 INFO misc.py line 117 726] Train: [6/20][176/510] Data 4.141 (3.746) Batch 29.928 (27.888) Remain 57:53:56 loss: 0.2515 loss_seg: 0.1604 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:50:03,430 INFO misc.py line 117 726] Train: [6/20][177/510] Data 5.190 (3.754) Batch 36.845 (27.940) Remain 57:59:53 loss: 0.2317 loss_seg: 0.1376 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:50:23,138 INFO misc.py line 117 726] Train: [6/20][178/510] Data 2.316 (3.746) Batch 19.708 (27.893) Remain 57:53:33 loss: 0.2530 loss_seg: 0.1558 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:50:49,398 INFO misc.py line 117 726] Train: [6/20][179/510] Data 3.036 (3.742) Batch 26.260 (27.883) Remain 57:51:56 loss: 0.3259 loss_seg: 0.2254 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:51:22,477 INFO misc.py line 117 726] Train: [6/20][180/510] Data 3.484 (3.740) Batch 33.079 (27.913) Remain 57:55:08 loss: 0.3616 loss_seg: 0.2508 loss_superpoint_edge: 0.0464 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:51:43,969 INFO misc.py line 117 726] Train: [6/20][181/510] Data 2.910 (3.736) Batch 21.492 (27.877) Remain 57:50:10 loss: 0.4048 loss_seg: 0.2972 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:52:19,437 INFO misc.py line 117 726] Train: [6/20][182/510] Data 6.198 (3.749) Batch 35.468 (27.919) Remain 57:54:59 loss: 0.2240 loss_seg: 0.1316 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:52:42,007 INFO misc.py line 117 726] Train: [6/20][183/510] Data 2.511 (3.743) Batch 22.571 (27.889) Remain 57:50:49 loss: 0.3170 loss_seg: 0.2140 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:53:23,576 INFO misc.py line 117 726] Train: [6/20][184/510] Data 7.751 (3.765) Batch 41.568 (27.965) Remain 57:59:46 loss: 0.2585 loss_seg: 0.1672 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:53:53,716 INFO misc.py line 117 726] Train: [6/20][185/510] Data 4.109 (3.767) Batch 30.141 (27.977) Remain 58:00:47 loss: 0.2015 loss_seg: 0.1110 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:54:31,344 INFO misc.py line 117 726] Train: [6/20][186/510] Data 4.344 (3.770) Batch 37.628 (28.030) Remain 58:06:53 loss: 0.2213 loss_seg: 0.1342 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:54:52,717 INFO misc.py line 117 726] Train: [6/20][187/510] Data 2.602 (3.763) Batch 21.373 (27.993) Remain 58:01:55 loss: 0.2211 loss_seg: 0.1334 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:55:28,914 INFO misc.py line 117 726] Train: [6/20][188/510] Data 8.499 (3.789) Batch 36.197 (28.038) Remain 58:06:58 loss: 0.2559 loss_seg: 0.1566 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:56:03,160 INFO misc.py line 117 726] Train: [6/20][189/510] Data 3.562 (3.788) Batch 34.246 (28.071) Remain 58:10:39 loss: 0.3934 loss_seg: 0.2878 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:56:32,338 INFO misc.py line 117 726] Train: [6/20][190/510] Data 4.803 (3.793) Batch 29.178 (28.077) Remain 58:10:55 loss: 0.2564 loss_seg: 0.1579 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:56:59,630 INFO misc.py line 117 726] Train: [6/20][191/510] Data 3.147 (3.790) Batch 27.292 (28.073) Remain 58:09:55 loss: 0.3547 loss_seg: 0.2485 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:57:26,533 INFO misc.py line 117 726] Train: [6/20][192/510] Data 3.416 (3.788) Batch 26.903 (28.067) Remain 58:08:41 loss: 0.2176 loss_seg: 0.1274 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:57:53,438 INFO misc.py line 117 726] Train: [6/20][193/510] Data 3.052 (3.784) Batch 26.905 (28.061) Remain 58:07:27 loss: 0.2234 loss_seg: 0.1278 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:58:19,462 INFO misc.py line 117 726] Train: [6/20][194/510] Data 2.600 (3.778) Batch 26.024 (28.050) Remain 58:05:40 loss: 0.2164 loss_seg: 0.1271 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:58:48,154 INFO misc.py line 117 726] Train: [6/20][195/510] Data 3.442 (3.776) Batch 28.692 (28.053) Remain 58:05:37 loss: 0.3686 loss_seg: 0.2512 loss_superpoint_edge: 0.0489 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:59:08,681 INFO misc.py line 117 726] Train: [6/20][196/510] Data 2.942 (3.772) Batch 20.527 (28.014) Remain 58:00:18 loss: 0.2481 loss_seg: 0.1488 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 12:59:36,898 INFO misc.py line 117 726] Train: [6/20][197/510] Data 3.003 (3.768) Batch 28.218 (28.015) Remain 57:59:58 loss: 0.2435 loss_seg: 0.1525 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:00:01,518 INFO misc.py line 117 726] Train: [6/20][198/510] Data 2.603 (3.762) Batch 24.619 (27.998) Remain 57:57:20 loss: 0.2374 loss_seg: 0.1489 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:00:24,799 INFO misc.py line 117 726] Train: [6/20][199/510] Data 2.123 (3.753) Batch 23.281 (27.974) Remain 57:53:53 loss: 0.1863 loss_seg: 0.0996 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:01:00,767 INFO misc.py line 117 726] Train: [6/20][200/510] Data 4.975 (3.760) Batch 35.969 (28.014) Remain 57:58:27 loss: 0.2181 loss_seg: 0.1244 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:01:00,768 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 13:01:13,969 INFO misc.py line 117 726] Train: [6/20][201/510] Data 2.479 (3.753) Batch 13.202 (27.940) Remain 57:48:42 loss: 0.2662 loss_seg: 0.1694 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:01:47,094 INFO misc.py line 117 726] Train: [6/20][202/510] Data 2.605 (3.747) Batch 33.124 (27.966) Remain 57:51:28 loss: 0.2488 loss_seg: 0.1552 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:02:17,561 INFO misc.py line 117 726] Train: [6/20][203/510] Data 3.648 (3.747) Batch 30.468 (27.978) Remain 57:52:33 loss: 0.2753 loss_seg: 0.1738 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:02:45,412 INFO misc.py line 117 726] Train: [6/20][204/510] Data 2.388 (3.740) Batch 27.850 (27.978) Remain 57:52:00 loss: 0.2776 loss_seg: 0.1730 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:03:16,354 INFO misc.py line 117 726] Train: [6/20][205/510] Data 5.369 (3.748) Batch 30.943 (27.992) Remain 57:53:22 loss: 0.2277 loss_seg: 0.1347 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:03:52,407 INFO misc.py line 117 726] Train: [6/20][206/510] Data 8.594 (3.772) Batch 36.053 (28.032) Remain 57:57:49 loss: 0.3687 loss_seg: 0.2479 loss_superpoint_edge: 0.0529 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:04:19,494 INFO misc.py line 117 726] Train: [6/20][207/510] Data 2.935 (3.768) Batch 27.087 (28.027) Remain 57:56:47 loss: 0.3192 loss_seg: 0.2240 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:04:44,309 INFO misc.py line 117 726] Train: [6/20][208/510] Data 3.256 (3.765) Batch 24.815 (28.012) Remain 57:54:22 loss: 0.2375 loss_seg: 0.1443 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:05:06,960 INFO misc.py line 117 726] Train: [6/20][209/510] Data 2.446 (3.759) Batch 22.650 (27.986) Remain 57:50:41 loss: 0.2531 loss_seg: 0.1529 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:05:41,093 INFO misc.py line 117 726] Train: [6/20][210/510] Data 7.778 (3.778) Batch 34.134 (28.015) Remain 57:53:53 loss: 0.3475 loss_seg: 0.2379 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:06:05,943 INFO misc.py line 117 726] Train: [6/20][211/510] Data 3.124 (3.775) Batch 24.850 (28.000) Remain 57:51:32 loss: 0.4608 loss_seg: 0.3427 loss_superpoint_edge: 0.0466 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0341 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:06:37,905 INFO misc.py line 117 726] Train: [6/20][212/510] Data 4.543 (3.779) Batch 31.961 (28.019) Remain 57:53:25 loss: 0.2127 loss_seg: 0.1252 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:07:11,490 INFO misc.py line 117 726] Train: [6/20][213/510] Data 4.571 (3.783) Batch 33.585 (28.046) Remain 57:56:14 loss: 0.2845 loss_seg: 0.1855 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:07:42,478 INFO misc.py line 117 726] Train: [6/20][214/510] Data 3.710 (3.782) Batch 30.988 (28.060) Remain 57:57:30 loss: 0.2185 loss_seg: 0.1299 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:08:09,787 INFO misc.py line 117 726] Train: [6/20][215/510] Data 3.454 (3.781) Batch 27.309 (28.056) Remain 57:56:36 loss: 0.2321 loss_seg: 0.1383 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:08:39,989 INFO misc.py line 117 726] Train: [6/20][216/510] Data 5.207 (3.788) Batch 30.202 (28.066) Remain 57:57:22 loss: 0.1635 loss_seg: 0.0777 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:09:00,093 INFO misc.py line 117 726] Train: [6/20][217/510] Data 2.430 (3.781) Batch 20.104 (28.029) Remain 57:52:18 loss: 0.2521 loss_seg: 0.1569 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:09:24,320 INFO misc.py line 117 726] Train: [6/20][218/510] Data 2.763 (3.776) Batch 24.227 (28.011) Remain 57:49:38 loss: 0.2539 loss_seg: 0.1539 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:09:48,090 INFO misc.py line 117 726] Train: [6/20][219/510] Data 2.438 (3.770) Batch 23.770 (27.992) Remain 57:46:44 loss: 0.2821 loss_seg: 0.1922 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:10:21,991 INFO misc.py line 117 726] Train: [6/20][220/510] Data 4.597 (3.774) Batch 33.901 (28.019) Remain 57:49:39 loss: 0.2576 loss_seg: 0.1612 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:10:44,469 INFO misc.py line 117 726] Train: [6/20][221/510] Data 2.237 (3.767) Batch 22.477 (27.993) Remain 57:46:02 loss: 0.2526 loss_seg: 0.1505 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:11:10,838 INFO misc.py line 117 726] Train: [6/20][222/510] Data 2.950 (3.763) Batch 26.369 (27.986) Remain 57:44:39 loss: 0.2413 loss_seg: 0.1432 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:11:39,757 INFO misc.py line 117 726] Train: [6/20][223/510] Data 3.313 (3.761) Batch 28.919 (27.990) Remain 57:44:42 loss: 0.2375 loss_seg: 0.1456 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:11:58,351 INFO misc.py line 117 726] Train: [6/20][224/510] Data 2.524 (3.756) Batch 18.595 (27.948) Remain 57:38:59 loss: 0.2973 loss_seg: 0.1849 loss_superpoint_edge: 0.0433 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:12:26,191 INFO misc.py line 117 726] Train: [6/20][225/510] Data 4.966 (3.761) Batch 27.839 (27.947) Remain 57:38:27 loss: 0.1996 loss_seg: 0.1126 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:12:57,291 INFO misc.py line 117 726] Train: [6/20][226/510] Data 3.140 (3.758) Batch 31.100 (27.961) Remain 57:39:44 loss: 0.2007 loss_seg: 0.1141 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:13:25,495 INFO misc.py line 117 726] Train: [6/20][227/510] Data 2.097 (3.751) Batch 28.204 (27.962) Remain 57:39:24 loss: 0.2556 loss_seg: 0.1571 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:13:43,443 INFO misc.py line 117 726] Train: [6/20][228/510] Data 1.913 (3.743) Batch 17.948 (27.918) Remain 57:33:26 loss: 0.2757 loss_seg: 0.1776 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:14:07,912 INFO misc.py line 117 726] Train: [6/20][229/510] Data 2.574 (3.738) Batch 24.469 (27.903) Remain 57:31:05 loss: 0.2400 loss_seg: 0.1405 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:14:29,903 INFO misc.py line 117 726] Train: [6/20][230/510] Data 3.072 (3.735) Batch 21.990 (27.877) Remain 57:27:24 loss: 0.2480 loss_seg: 0.1479 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:14:52,583 INFO misc.py line 117 726] Train: [6/20][231/510] Data 2.884 (3.731) Batch 22.681 (27.854) Remain 57:24:07 loss: 0.2670 loss_seg: 0.1648 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:15:24,069 INFO misc.py line 117 726] Train: [6/20][232/510] Data 3.105 (3.728) Batch 31.486 (27.870) Remain 57:25:36 loss: 0.2270 loss_seg: 0.1345 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:15:43,716 INFO misc.py line 117 726] Train: [6/20][233/510] Data 2.055 (3.721) Batch 19.647 (27.834) Remain 57:20:43 loss: 0.3267 loss_seg: 0.2094 loss_superpoint_edge: 0.0485 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:16:13,037 INFO misc.py line 117 726] Train: [6/20][234/510] Data 3.432 (3.720) Batch 29.320 (27.840) Remain 57:21:03 loss: 0.2610 loss_seg: 0.1613 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:16:40,278 INFO misc.py line 117 726] Train: [6/20][235/510] Data 4.523 (3.723) Batch 27.242 (27.838) Remain 57:20:16 loss: 0.2984 loss_seg: 0.2043 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:17:15,278 INFO misc.py line 117 726] Train: [6/20][236/510] Data 7.806 (3.741) Batch 34.999 (27.868) Remain 57:23:36 loss: 0.3302 loss_seg: 0.2262 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:17:51,154 INFO misc.py line 117 726] Train: [6/20][237/510] Data 4.019 (3.742) Batch 35.876 (27.903) Remain 57:27:22 loss: 0.2622 loss_seg: 0.1594 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:18:21,599 INFO misc.py line 117 726] Train: [6/20][238/510] Data 3.321 (3.740) Batch 30.445 (27.914) Remain 57:28:15 loss: 0.2472 loss_seg: 0.1479 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:18:47,368 INFO misc.py line 117 726] Train: [6/20][239/510] Data 2.504 (3.735) Batch 25.769 (27.904) Remain 57:26:39 loss: 0.2535 loss_seg: 0.1561 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:19:18,274 INFO misc.py line 117 726] Train: [6/20][240/510] Data 4.769 (3.739) Batch 30.906 (27.917) Remain 57:27:45 loss: 0.3502 loss_seg: 0.2439 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:19:38,882 INFO misc.py line 117 726] Train: [6/20][241/510] Data 2.150 (3.732) Batch 20.608 (27.886) Remain 57:23:30 loss: 0.2333 loss_seg: 0.1350 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:20:17,072 INFO misc.py line 117 726] Train: [6/20][242/510] Data 6.098 (3.742) Batch 38.190 (27.929) Remain 57:28:21 loss: 0.3346 loss_seg: 0.2488 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:20:43,505 INFO misc.py line 117 726] Train: [6/20][243/510] Data 3.915 (3.743) Batch 26.434 (27.923) Remain 57:27:07 loss: 0.2481 loss_seg: 0.1549 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:21:15,118 INFO misc.py line 117 726] Train: [6/20][244/510] Data 3.518 (3.742) Batch 31.613 (27.939) Remain 57:28:33 loss: 0.2194 loss_seg: 0.1319 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:21:41,726 INFO misc.py line 117 726] Train: [6/20][245/510] Data 3.090 (3.739) Batch 26.608 (27.933) Remain 57:27:24 loss: 0.3309 loss_seg: 0.2339 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:22:15,417 INFO misc.py line 117 726] Train: [6/20][246/510] Data 4.200 (3.741) Batch 33.691 (27.957) Remain 57:29:51 loss: 0.2790 loss_seg: 0.1738 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:22:41,328 INFO misc.py line 117 726] Train: [6/20][247/510] Data 2.390 (3.736) Batch 25.911 (27.948) Remain 57:28:21 loss: 0.2696 loss_seg: 0.1674 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:23:15,972 INFO misc.py line 117 726] Train: [6/20][248/510] Data 3.837 (3.736) Batch 34.644 (27.976) Remain 57:31:16 loss: 0.2924 loss_seg: 0.1886 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:23:46,433 INFO misc.py line 117 726] Train: [6/20][249/510] Data 11.310 (3.767) Batch 30.461 (27.986) Remain 57:32:03 loss: 0.1972 loss_seg: 0.1073 loss_superpoint_edge: 0.0147 loss_superpoint_contrast: 0.0452 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:24:20,657 INFO misc.py line 117 726] Train: [6/20][250/510] Data 3.950 (3.768) Batch 34.224 (28.011) Remain 57:34:41 loss: 0.2518 loss_seg: 0.1567 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:24:20,658 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 13:24:36,425 INFO misc.py line 117 726] Train: [6/20][251/510] Data 2.550 (3.763) Batch 15.767 (27.962) Remain 57:28:08 loss: 0.2882 loss_seg: 0.1836 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:24:52,828 INFO misc.py line 117 726] Train: [6/20][252/510] Data 2.203 (3.757) Batch 16.404 (27.915) Remain 57:21:57 loss: 0.2424 loss_seg: 0.1438 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:25:16,134 INFO misc.py line 117 726] Train: [6/20][253/510] Data 2.644 (3.752) Batch 23.306 (27.897) Remain 57:19:12 loss: 0.2971 loss_seg: 0.1931 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:25:41,581 INFO misc.py line 117 726] Train: [6/20][254/510] Data 2.442 (3.747) Batch 25.446 (27.887) Remain 57:17:32 loss: 0.1962 loss_seg: 0.1075 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:26:03,942 INFO misc.py line 117 726] Train: [6/20][255/510] Data 2.045 (3.740) Batch 22.361 (27.865) Remain 57:14:22 loss: 0.3348 loss_seg: 0.2257 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:26:32,769 INFO misc.py line 117 726] Train: [6/20][256/510] Data 4.227 (3.742) Batch 28.827 (27.869) Remain 57:14:23 loss: 0.2553 loss_seg: 0.1545 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:26:58,498 INFO misc.py line 117 726] Train: [6/20][257/510] Data 2.193 (3.736) Batch 25.729 (27.861) Remain 57:12:52 loss: 0.2194 loss_seg: 0.1263 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:27:30,304 INFO misc.py line 117 726] Train: [6/20][258/510] Data 3.345 (3.734) Batch 31.806 (27.876) Remain 57:14:19 loss: 0.2687 loss_seg: 0.1653 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:28:08,801 INFO misc.py line 117 726] Train: [6/20][259/510] Data 6.181 (3.744) Batch 38.497 (27.917) Remain 57:18:58 loss: 0.2190 loss_seg: 0.1296 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:28:46,763 INFO misc.py line 117 726] Train: [6/20][260/510] Data 3.688 (3.744) Batch 37.962 (27.957) Remain 57:23:19 loss: 0.3312 loss_seg: 0.2265 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:29:13,648 INFO misc.py line 117 726] Train: [6/20][261/510] Data 3.494 (3.743) Batch 26.885 (27.952) Remain 57:22:20 loss: 0.2291 loss_seg: 0.1372 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:29:42,441 INFO misc.py line 117 726] Train: [6/20][262/510] Data 2.781 (3.739) Batch 28.793 (27.956) Remain 57:22:16 loss: 0.2544 loss_seg: 0.1667 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:30:04,168 INFO misc.py line 117 726] Train: [6/20][263/510] Data 2.708 (3.735) Batch 21.727 (27.932) Remain 57:18:51 loss: 0.3057 loss_seg: 0.2052 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:30:31,001 INFO misc.py line 117 726] Train: [6/20][264/510] Data 4.485 (3.738) Batch 26.833 (27.928) Remain 57:17:52 loss: 0.1972 loss_seg: 0.1090 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:30:59,038 INFO misc.py line 117 726] Train: [6/20][265/510] Data 4.799 (3.742) Batch 28.037 (27.928) Remain 57:17:27 loss: 0.4427 loss_seg: 0.3373 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:31:22,508 INFO misc.py line 117 726] Train: [6/20][266/510] Data 2.169 (3.736) Batch 23.469 (27.911) Remain 57:14:54 loss: 0.1846 loss_seg: 0.0990 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:31:59,950 INFO misc.py line 117 726] Train: [6/20][267/510] Data 7.588 (3.751) Batch 37.443 (27.947) Remain 57:18:53 loss: 0.3382 loss_seg: 0.2422 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:32:25,800 INFO misc.py line 117 726] Train: [6/20][268/510] Data 2.475 (3.746) Batch 25.849 (27.939) Remain 57:17:26 loss: 0.2204 loss_seg: 0.1276 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:32:56,893 INFO misc.py line 117 726] Train: [6/20][269/510] Data 2.715 (3.742) Batch 31.093 (27.951) Remain 57:18:26 loss: 0.2313 loss_seg: 0.1433 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:33:22,727 INFO misc.py line 117 726] Train: [6/20][270/510] Data 4.386 (3.744) Batch 25.835 (27.943) Remain 57:17:00 loss: 0.2231 loss_seg: 0.1333 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:33:54,331 INFO misc.py line 117 726] Train: [6/20][271/510] Data 5.885 (3.752) Batch 31.603 (27.957) Remain 57:18:12 loss: 0.2464 loss_seg: 0.1571 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:34:21,218 INFO misc.py line 117 726] Train: [6/20][272/510] Data 6.826 (3.764) Batch 26.887 (27.953) Remain 57:17:15 loss: 0.2470 loss_seg: 0.1490 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:34:52,970 INFO misc.py line 117 726] Train: [6/20][273/510] Data 3.813 (3.764) Batch 31.752 (27.967) Remain 57:18:31 loss: 0.2872 loss_seg: 0.1884 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:35:16,426 INFO misc.py line 117 726] Train: [6/20][274/510] Data 2.828 (3.761) Batch 23.456 (27.950) Remain 57:16:00 loss: 0.2276 loss_seg: 0.1369 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:35:43,222 INFO misc.py line 117 726] Train: [6/20][275/510] Data 2.782 (3.757) Batch 26.796 (27.946) Remain 57:15:01 loss: 0.2964 loss_seg: 0.1927 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:36:07,605 INFO misc.py line 117 726] Train: [6/20][276/510] Data 2.862 (3.754) Batch 24.383 (27.933) Remain 57:12:57 loss: 0.1988 loss_seg: 0.1116 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:36:39,457 INFO misc.py line 117 726] Train: [6/20][277/510] Data 3.384 (3.752) Batch 31.852 (27.947) Remain 57:14:14 loss: 0.2820 loss_seg: 0.1821 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:37:16,242 INFO misc.py line 117 726] Train: [6/20][278/510] Data 4.614 (3.755) Batch 36.785 (27.979) Remain 57:17:43 loss: 0.2150 loss_seg: 0.1265 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:37:47,686 INFO misc.py line 117 726] Train: [6/20][279/510] Data 3.247 (3.754) Batch 31.443 (27.992) Remain 57:18:48 loss: 0.2388 loss_seg: 0.1482 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:38:27,088 INFO misc.py line 117 726] Train: [6/20][280/510] Data 8.102 (3.769) Batch 39.403 (28.033) Remain 57:23:23 loss: 0.2336 loss_seg: 0.1403 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:38:59,677 INFO misc.py line 117 726] Train: [6/20][281/510] Data 3.941 (3.770) Batch 32.589 (28.049) Remain 57:24:56 loss: 0.1976 loss_seg: 0.1071 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:39:33,551 INFO misc.py line 117 726] Train: [6/20][282/510] Data 8.063 (3.785) Batch 33.874 (28.070) Remain 57:27:02 loss: 0.2362 loss_seg: 0.1446 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:40:05,430 INFO misc.py line 117 726] Train: [6/20][283/510] Data 5.336 (3.791) Batch 31.879 (28.084) Remain 57:28:14 loss: 0.2805 loss_seg: 0.1795 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:40:33,666 INFO misc.py line 117 726] Train: [6/20][284/510] Data 3.291 (3.789) Batch 28.236 (28.084) Remain 57:27:50 loss: 0.2549 loss_seg: 0.1617 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:41:05,455 INFO misc.py line 117 726] Train: [6/20][285/510] Data 4.743 (3.792) Batch 31.789 (28.098) Remain 57:28:59 loss: 0.2685 loss_seg: 0.1647 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:41:37,443 INFO misc.py line 117 726] Train: [6/20][286/510] Data 5.455 (3.798) Batch 31.988 (28.111) Remain 57:30:12 loss: 0.2852 loss_seg: 0.1788 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:42:05,212 INFO misc.py line 117 726] Train: [6/20][287/510] Data 3.623 (3.798) Batch 27.769 (28.110) Remain 57:29:35 loss: 0.2658 loss_seg: 0.1665 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:42:31,989 INFO misc.py line 117 726] Train: [6/20][288/510] Data 4.273 (3.799) Batch 26.777 (28.105) Remain 57:28:32 loss: 0.2937 loss_seg: 0.1924 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:43:00,825 INFO misc.py line 117 726] Train: [6/20][289/510] Data 3.723 (3.799) Batch 28.836 (28.108) Remain 57:28:23 loss: 0.2362 loss_seg: 0.1457 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:43:24,836 INFO misc.py line 117 726] Train: [6/20][290/510] Data 4.073 (3.800) Batch 24.010 (28.094) Remain 57:26:10 loss: 0.2041 loss_seg: 0.1147 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:43:49,148 INFO misc.py line 117 726] Train: [6/20][291/510] Data 2.143 (3.794) Batch 24.312 (28.081) Remain 57:24:05 loss: 0.1738 loss_seg: 0.0896 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:44:18,842 INFO misc.py line 117 726] Train: [6/20][292/510] Data 2.868 (3.791) Batch 29.695 (28.086) Remain 57:24:18 loss: 0.2354 loss_seg: 0.1406 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:44:44,596 INFO misc.py line 117 726] Train: [6/20][293/510] Data 5.726 (3.798) Batch 25.754 (28.078) Remain 57:22:51 loss: 0.2244 loss_seg: 0.1264 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:45:11,947 INFO misc.py line 117 726] Train: [6/20][294/510] Data 2.136 (3.792) Batch 27.351 (28.076) Remain 57:22:04 loss: 0.2516 loss_seg: 0.1549 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:45:35,963 INFO misc.py line 117 726] Train: [6/20][295/510] Data 2.918 (3.789) Batch 24.016 (28.062) Remain 57:19:54 loss: 0.2858 loss_seg: 0.1952 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:46:03,424 INFO misc.py line 117 726] Train: [6/20][296/510] Data 2.274 (3.784) Batch 27.460 (28.060) Remain 57:19:11 loss: 0.1851 loss_seg: 0.1012 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:46:35,107 INFO misc.py line 117 726] Train: [6/20][297/510] Data 3.588 (3.783) Batch 31.684 (28.072) Remain 57:20:13 loss: 0.2364 loss_seg: 0.1402 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:47:01,346 INFO misc.py line 117 726] Train: [6/20][298/510] Data 2.366 (3.778) Batch 26.239 (28.066) Remain 57:19:00 loss: 0.2928 loss_seg: 0.1905 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:47:26,428 INFO misc.py line 117 726] Train: [6/20][299/510] Data 4.593 (3.781) Batch 25.082 (28.056) Remain 57:17:17 loss: 0.2893 loss_seg: 0.1901 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:48:00,674 INFO misc.py line 117 726] Train: [6/20][300/510] Data 5.082 (3.786) Batch 34.247 (28.077) Remain 57:19:23 loss: 0.2700 loss_seg: 0.1708 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:48:00,675 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 13:48:36,752 INFO misc.py line 117 726] Train: [6/20][301/510] Data 4.315 (3.787) Batch 36.078 (28.103) Remain 57:22:12 loss: 0.2164 loss_seg: 0.1325 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:49:15,700 INFO misc.py line 117 726] Train: [6/20][302/510] Data 10.812 (3.811) Batch 38.948 (28.140) Remain 57:26:10 loss: 0.2390 loss_seg: 0.1432 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:49:45,680 INFO misc.py line 117 726] Train: [6/20][303/510] Data 6.123 (3.819) Batch 29.980 (28.146) Remain 57:26:27 loss: 0.2659 loss_seg: 0.1741 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:50:09,040 INFO misc.py line 117 726] Train: [6/20][304/510] Data 2.887 (3.815) Batch 23.360 (28.130) Remain 57:24:02 loss: 0.2460 loss_seg: 0.1499 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:50:28,344 INFO misc.py line 117 726] Train: [6/20][305/510] Data 2.403 (3.811) Batch 19.304 (28.101) Remain 57:19:59 loss: 0.2245 loss_seg: 0.1262 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:50:53,744 INFO misc.py line 117 726] Train: [6/20][306/510] Data 2.751 (3.807) Batch 25.399 (28.092) Remain 57:18:26 loss: 0.2861 loss_seg: 0.1823 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:51:15,711 INFO misc.py line 117 726] Train: [6/20][307/510] Data 1.981 (3.801) Batch 21.968 (28.072) Remain 57:15:30 loss: 0.2279 loss_seg: 0.1314 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:51:39,682 INFO misc.py line 117 726] Train: [6/20][308/510] Data 2.548 (3.797) Batch 23.971 (28.058) Remain 57:13:23 loss: 0.1668 loss_seg: 0.0839 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:52:06,829 INFO misc.py line 117 726] Train: [6/20][309/510] Data 4.323 (3.799) Batch 27.148 (28.055) Remain 57:12:33 loss: 0.2245 loss_seg: 0.1300 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:52:33,962 INFO misc.py line 117 726] Train: [6/20][310/510] Data 3.715 (3.799) Batch 27.132 (28.052) Remain 57:11:43 loss: 0.2618 loss_seg: 0.1602 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:53:01,629 INFO misc.py line 117 726] Train: [6/20][311/510] Data 3.098 (3.796) Batch 27.667 (28.051) Remain 57:11:06 loss: 0.3367 loss_seg: 0.2344 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:53:31,136 INFO misc.py line 117 726] Train: [6/20][312/510] Data 4.354 (3.798) Batch 29.507 (28.056) Remain 57:11:12 loss: 0.2141 loss_seg: 0.1246 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:53:57,090 INFO misc.py line 117 726] Train: [6/20][313/510] Data 2.852 (3.795) Batch 25.954 (28.049) Remain 57:09:54 loss: 0.1932 loss_seg: 0.1051 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:54:17,924 INFO misc.py line 117 726] Train: [6/20][314/510] Data 2.217 (3.790) Batch 20.834 (28.026) Remain 57:06:36 loss: 0.2624 loss_seg: 0.1636 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:54:44,009 INFO misc.py line 117 726] Train: [6/20][315/510] Data 3.144 (3.788) Batch 26.085 (28.020) Remain 57:05:23 loss: 0.2593 loss_seg: 0.1658 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:55:19,672 INFO misc.py line 117 726] Train: [6/20][316/510] Data 6.041 (3.795) Batch 35.663 (28.044) Remain 57:07:54 loss: 0.2324 loss_seg: 0.1360 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:55:39,448 INFO misc.py line 117 726] Train: [6/20][317/510] Data 2.644 (3.791) Batch 19.776 (28.018) Remain 57:04:13 loss: 0.2763 loss_seg: 0.1772 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:56:06,050 INFO misc.py line 117 726] Train: [6/20][318/510] Data 3.342 (3.790) Batch 26.603 (28.013) Remain 57:03:12 loss: 0.2484 loss_seg: 0.1521 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:56:43,365 INFO misc.py line 117 726] Train: [6/20][319/510] Data 8.738 (3.806) Batch 37.314 (28.043) Remain 57:06:19 loss: 0.3200 loss_seg: 0.2146 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:57:07,566 INFO misc.py line 117 726] Train: [6/20][320/510] Data 2.259 (3.801) Batch 24.201 (28.030) Remain 57:04:22 loss: 0.2463 loss_seg: 0.1501 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:57:35,609 INFO misc.py line 117 726] Train: [6/20][321/510] Data 2.476 (3.797) Batch 28.043 (28.030) Remain 57:03:55 loss: 0.2557 loss_seg: 0.1549 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:58:02,835 INFO misc.py line 117 726] Train: [6/20][322/510] Data 3.352 (3.795) Batch 27.226 (28.028) Remain 57:03:08 loss: 0.2559 loss_seg: 0.1567 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:58:22,325 INFO misc.py line 117 726] Train: [6/20][323/510] Data 2.693 (3.792) Batch 19.491 (28.001) Remain 56:59:25 loss: 0.2163 loss_seg: 0.1296 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:58:55,479 INFO misc.py line 117 726] Train: [6/20][324/510] Data 4.347 (3.794) Batch 33.153 (28.017) Remain 57:00:54 loss: 0.2232 loss_seg: 0.1345 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:59:15,710 INFO misc.py line 117 726] Train: [6/20][325/510] Data 3.003 (3.791) Batch 20.231 (27.993) Remain 56:57:29 loss: 0.2934 loss_seg: 0.1938 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 13:59:51,879 INFO misc.py line 117 726] Train: [6/20][326/510] Data 10.908 (3.813) Batch 36.169 (28.018) Remain 57:00:07 loss: 0.1982 loss_seg: 0.1033 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0452 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:00:17,419 INFO misc.py line 117 726] Train: [6/20][327/510] Data 3.051 (3.811) Batch 25.539 (28.011) Remain 56:58:43 loss: 0.2583 loss_seg: 0.1609 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:00:50,248 INFO misc.py line 117 726] Train: [6/20][328/510] Data 3.759 (3.811) Batch 32.829 (28.026) Remain 57:00:03 loss: 0.3358 loss_seg: 0.2290 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:01:27,164 INFO misc.py line 117 726] Train: [6/20][329/510] Data 6.247 (3.818) Batch 36.916 (28.053) Remain 57:02:55 loss: 0.2512 loss_seg: 0.1584 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:01:57,983 INFO misc.py line 117 726] Train: [6/20][330/510] Data 4.319 (3.820) Batch 30.819 (28.061) Remain 57:03:29 loss: 0.2439 loss_seg: 0.1502 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:02:28,005 INFO misc.py line 117 726] Train: [6/20][331/510] Data 3.748 (3.819) Batch 30.022 (28.067) Remain 57:03:44 loss: 0.2466 loss_seg: 0.1547 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:02:57,682 INFO misc.py line 117 726] Train: [6/20][332/510] Data 3.104 (3.817) Batch 29.676 (28.072) Remain 57:03:52 loss: 0.2581 loss_seg: 0.1564 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:03:34,557 INFO misc.py line 117 726] Train: [6/20][333/510] Data 8.436 (3.831) Batch 36.876 (28.099) Remain 57:06:39 loss: 0.2407 loss_seg: 0.1506 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:04:07,744 INFO misc.py line 117 726] Train: [6/20][334/510] Data 6.454 (3.839) Batch 33.187 (28.114) Remain 57:08:03 loss: 0.3517 loss_seg: 0.2386 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:04:34,194 INFO misc.py line 117 726] Train: [6/20][335/510] Data 3.455 (3.838) Batch 26.450 (28.109) Remain 57:06:59 loss: 0.2609 loss_seg: 0.1639 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:05:07,415 INFO misc.py line 117 726] Train: [6/20][336/510] Data 6.379 (3.846) Batch 33.221 (28.125) Remain 57:08:23 loss: 0.3510 loss_seg: 0.2508 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:05:48,753 INFO misc.py line 117 726] Train: [6/20][337/510] Data 12.441 (3.871) Batch 41.338 (28.164) Remain 57:12:44 loss: 0.4150 loss_seg: 0.2928 loss_superpoint_edge: 0.0500 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:06:29,134 INFO misc.py line 117 726] Train: [6/20][338/510] Data 9.367 (3.888) Batch 40.382 (28.201) Remain 57:16:43 loss: 0.2729 loss_seg: 0.1810 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:06:56,540 INFO misc.py line 117 726] Train: [6/20][339/510] Data 4.034 (3.888) Batch 27.406 (28.198) Remain 57:15:57 loss: 0.2226 loss_seg: 0.1318 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:07:28,784 INFO misc.py line 117 726] Train: [6/20][340/510] Data 3.766 (3.888) Batch 32.244 (28.210) Remain 57:16:57 loss: 0.2620 loss_seg: 0.1632 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:07:55,173 INFO misc.py line 117 726] Train: [6/20][341/510] Data 2.822 (3.885) Batch 26.388 (28.205) Remain 57:15:49 loss: 0.2473 loss_seg: 0.1473 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:08:31,523 INFO misc.py line 117 726] Train: [6/20][342/510] Data 4.983 (3.888) Batch 36.348 (28.229) Remain 57:18:16 loss: 0.2421 loss_seg: 0.1506 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:08:51,179 INFO misc.py line 117 726] Train: [6/20][343/510] Data 2.332 (3.883) Batch 19.659 (28.204) Remain 57:14:44 loss: 0.2325 loss_seg: 0.1420 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:09:19,774 INFO misc.py line 117 726] Train: [6/20][344/510] Data 4.973 (3.887) Batch 28.594 (28.205) Remain 57:14:24 loss: 0.2351 loss_seg: 0.1427 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:09:45,302 INFO misc.py line 117 726] Train: [6/20][345/510] Data 3.380 (3.885) Batch 25.529 (28.197) Remain 57:12:59 loss: 0.2160 loss_seg: 0.1225 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:10:14,003 INFO misc.py line 117 726] Train: [6/20][346/510] Data 4.462 (3.887) Batch 28.701 (28.198) Remain 57:12:41 loss: 0.2498 loss_seg: 0.1574 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:10:39,045 INFO misc.py line 117 726] Train: [6/20][347/510] Data 3.281 (3.885) Batch 25.041 (28.189) Remain 57:11:06 loss: 0.2663 loss_seg: 0.1776 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:11:14,444 INFO misc.py line 117 726] Train: [6/20][348/510] Data 5.016 (3.888) Batch 35.400 (28.210) Remain 57:13:10 loss: 0.2430 loss_seg: 0.1498 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:11:46,455 INFO misc.py line 117 726] Train: [6/20][349/510] Data 4.499 (3.890) Batch 32.011 (28.221) Remain 57:14:02 loss: 0.2520 loss_seg: 0.1515 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:12:15,834 INFO misc.py line 117 726] Train: [6/20][350/510] Data 3.525 (3.889) Batch 29.379 (28.225) Remain 57:13:59 loss: 0.2003 loss_seg: 0.1152 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:12:15,834 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 14:12:53,180 INFO misc.py line 117 726] Train: [6/20][351/510] Data 5.975 (3.895) Batch 37.347 (28.251) Remain 57:16:42 loss: 0.3759 loss_seg: 0.2690 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:13:25,781 INFO misc.py line 117 726] Train: [6/20][352/510] Data 4.341 (3.896) Batch 32.600 (28.263) Remain 57:17:44 loss: 0.3465 loss_seg: 0.2404 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:13:46,474 INFO misc.py line 117 726] Train: [6/20][353/510] Data 3.052 (3.894) Batch 20.694 (28.242) Remain 57:14:38 loss: 0.2441 loss_seg: 0.1519 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:14:15,412 INFO misc.py line 117 726] Train: [6/20][354/510] Data 4.626 (3.896) Batch 28.938 (28.244) Remain 57:14:25 loss: 0.2164 loss_seg: 0.1248 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:14:46,441 INFO misc.py line 117 726] Train: [6/20][355/510] Data 5.419 (3.900) Batch 31.028 (28.251) Remain 57:14:54 loss: 0.2595 loss_seg: 0.1544 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:15:16,424 INFO misc.py line 117 726] Train: [6/20][356/510] Data 4.644 (3.902) Batch 29.983 (28.256) Remain 57:15:02 loss: 0.2517 loss_seg: 0.1569 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:15:43,461 INFO misc.py line 117 726] Train: [6/20][357/510] Data 3.604 (3.902) Batch 27.037 (28.253) Remain 57:14:08 loss: 0.2187 loss_seg: 0.1260 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:16:18,129 INFO misc.py line 117 726] Train: [6/20][358/510] Data 4.215 (3.902) Batch 34.669 (28.271) Remain 57:15:52 loss: 0.3010 loss_seg: 0.1986 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:16:49,592 INFO misc.py line 117 726] Train: [6/20][359/510] Data 4.044 (3.903) Batch 31.463 (28.280) Remain 57:16:29 loss: 0.2216 loss_seg: 0.1351 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:17:25,266 INFO misc.py line 117 726] Train: [6/20][360/510] Data 5.887 (3.908) Batch 35.674 (28.301) Remain 57:18:31 loss: 0.3735 loss_seg: 0.2503 loss_superpoint_edge: 0.0539 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:17:49,335 INFO misc.py line 117 726] Train: [6/20][361/510] Data 3.153 (3.906) Batch 24.069 (28.289) Remain 57:16:37 loss: 0.1890 loss_seg: 0.1032 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:18:14,924 INFO misc.py line 117 726] Train: [6/20][362/510] Data 2.152 (3.901) Batch 25.589 (28.281) Remain 57:15:14 loss: 0.2891 loss_seg: 0.1812 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:18:46,625 INFO misc.py line 117 726] Train: [6/20][363/510] Data 4.174 (3.902) Batch 31.700 (28.291) Remain 57:15:55 loss: 0.2575 loss_seg: 0.1558 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:19:09,397 INFO misc.py line 117 726] Train: [6/20][364/510] Data 2.361 (3.898) Batch 22.773 (28.276) Remain 57:13:35 loss: 0.1883 loss_seg: 0.1015 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:19:34,947 INFO misc.py line 117 726] Train: [6/20][365/510] Data 2.999 (3.895) Batch 25.550 (28.268) Remain 57:12:12 loss: 0.2114 loss_seg: 0.1236 loss_superpoint_edge: 0.0145 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:20:04,480 INFO misc.py line 117 726] Train: [6/20][366/510] Data 5.700 (3.900) Batch 29.533 (28.272) Remain 57:12:09 loss: 0.1985 loss_seg: 0.1058 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:20:35,796 INFO misc.py line 117 726] Train: [6/20][367/510] Data 6.317 (3.907) Batch 31.316 (28.280) Remain 57:12:42 loss: 0.3421 loss_seg: 0.2350 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:21:00,300 INFO misc.py line 117 726] Train: [6/20][368/510] Data 3.000 (3.904) Batch 24.504 (28.270) Remain 57:10:58 loss: 0.3129 loss_seg: 0.2187 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:21:19,393 INFO misc.py line 117 726] Train: [6/20][369/510] Data 2.146 (3.900) Batch 19.093 (28.244) Remain 57:07:27 loss: 0.2260 loss_seg: 0.1321 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:21:42,895 INFO misc.py line 117 726] Train: [6/20][370/510] Data 2.922 (3.897) Batch 23.501 (28.232) Remain 57:05:25 loss: 0.2327 loss_seg: 0.1347 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:22:16,857 INFO misc.py line 117 726] Train: [6/20][371/510] Data 5.930 (3.903) Batch 33.962 (28.247) Remain 57:06:50 loss: 0.2704 loss_seg: 0.1798 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:22:45,661 INFO misc.py line 117 726] Train: [6/20][372/510] Data 3.103 (3.900) Batch 28.804 (28.249) Remain 57:06:33 loss: 0.3204 loss_seg: 0.2186 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:23:16,838 INFO misc.py line 117 726] Train: [6/20][373/510] Data 3.592 (3.900) Batch 31.177 (28.257) Remain 57:07:02 loss: 0.2959 loss_seg: 0.1930 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:23:52,550 INFO misc.py line 117 726] Train: [6/20][374/510] Data 5.997 (3.905) Batch 35.712 (28.277) Remain 57:09:00 loss: 0.3781 loss_seg: 0.2658 loss_superpoint_edge: 0.0443 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:24:15,333 INFO misc.py line 117 726] Train: [6/20][375/510] Data 1.906 (3.900) Batch 22.783 (28.262) Remain 57:06:45 loss: 0.2362 loss_seg: 0.1446 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:24:41,273 INFO misc.py line 117 726] Train: [6/20][376/510] Data 3.638 (3.899) Batch 25.940 (28.256) Remain 57:05:31 loss: 0.3014 loss_seg: 0.2041 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:25:07,562 INFO misc.py line 117 726] Train: [6/20][377/510] Data 2.783 (3.896) Batch 26.289 (28.250) Remain 57:04:24 loss: 0.2112 loss_seg: 0.1231 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:25:28,052 INFO misc.py line 117 726] Train: [6/20][378/510] Data 2.466 (3.892) Batch 20.490 (28.230) Remain 57:01:26 loss: 0.3081 loss_seg: 0.2095 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:25:51,122 INFO misc.py line 117 726] Train: [6/20][379/510] Data 1.955 (3.887) Batch 23.070 (28.216) Remain 56:59:18 loss: 0.2333 loss_seg: 0.1405 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:26:16,606 INFO misc.py line 117 726] Train: [6/20][380/510] Data 3.255 (3.885) Batch 25.484 (28.209) Remain 56:57:57 loss: 0.2270 loss_seg: 0.1361 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:26:53,482 INFO misc.py line 117 726] Train: [6/20][381/510] Data 5.859 (3.891) Batch 36.876 (28.232) Remain 57:00:15 loss: 0.3212 loss_seg: 0.2312 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:27:17,547 INFO misc.py line 117 726] Train: [6/20][382/510] Data 3.082 (3.889) Batch 24.065 (28.221) Remain 56:58:27 loss: 0.2691 loss_seg: 0.1690 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:27:50,109 INFO misc.py line 117 726] Train: [6/20][383/510] Data 3.402 (3.887) Batch 32.562 (28.232) Remain 56:59:22 loss: 0.2514 loss_seg: 0.1548 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:28:23,790 INFO misc.py line 117 726] Train: [6/20][384/510] Data 4.337 (3.888) Batch 33.681 (28.246) Remain 57:00:38 loss: 0.2287 loss_seg: 0.1382 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:29:02,765 INFO misc.py line 117 726] Train: [6/20][385/510] Data 7.059 (3.897) Batch 38.975 (28.274) Remain 57:03:33 loss: 0.4420 loss_seg: 0.3379 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:29:28,800 INFO misc.py line 117 726] Train: [6/20][386/510] Data 2.518 (3.893) Batch 26.036 (28.269) Remain 57:02:23 loss: 0.3396 loss_seg: 0.2396 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:29:54,282 INFO misc.py line 117 726] Train: [6/20][387/510] Data 2.907 (3.891) Batch 25.482 (28.261) Remain 57:01:02 loss: 0.2786 loss_seg: 0.1743 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:30:16,869 INFO misc.py line 117 726] Train: [6/20][388/510] Data 2.847 (3.888) Batch 22.586 (28.247) Remain 56:58:46 loss: 0.2716 loss_seg: 0.1731 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:30:43,812 INFO misc.py line 117 726] Train: [6/20][389/510] Data 4.004 (3.888) Batch 26.943 (28.243) Remain 56:57:54 loss: 0.5747 loss_seg: 0.4696 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:31:10,404 INFO misc.py line 117 726] Train: [6/20][390/510] Data 2.991 (3.886) Batch 26.593 (28.239) Remain 56:56:54 loss: 0.2528 loss_seg: 0.1463 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:31:33,210 INFO misc.py line 117 726] Train: [6/20][391/510] Data 1.813 (3.881) Batch 22.806 (28.225) Remain 56:54:45 loss: 0.1931 loss_seg: 0.1051 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:32:01,612 INFO misc.py line 117 726] Train: [6/20][392/510] Data 5.374 (3.884) Batch 28.402 (28.225) Remain 56:54:20 loss: 0.2012 loss_seg: 0.1101 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:32:21,249 INFO misc.py line 117 726] Train: [6/20][393/510] Data 1.935 (3.879) Batch 19.637 (28.203) Remain 56:51:12 loss: 0.3195 loss_seg: 0.2184 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:32:51,694 INFO misc.py line 117 726] Train: [6/20][394/510] Data 3.451 (3.878) Batch 30.446 (28.209) Remain 56:51:25 loss: 0.2390 loss_seg: 0.1449 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:33:19,791 INFO misc.py line 117 726] Train: [6/20][395/510] Data 3.239 (3.877) Batch 28.097 (28.209) Remain 56:50:55 loss: 0.3698 loss_seg: 0.2658 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:33:47,361 INFO misc.py line 117 726] Train: [6/20][396/510] Data 2.754 (3.874) Batch 27.569 (28.207) Remain 56:50:15 loss: 0.2947 loss_seg: 0.1882 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:34:16,827 INFO misc.py line 117 726] Train: [6/20][397/510] Data 3.925 (3.874) Batch 29.466 (28.210) Remain 56:50:10 loss: 0.2383 loss_seg: 0.1458 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:34:41,398 INFO misc.py line 117 726] Train: [6/20][398/510] Data 2.740 (3.871) Batch 24.572 (28.201) Remain 56:48:35 loss: 0.3025 loss_seg: 0.1987 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:35:00,013 INFO misc.py line 117 726] Train: [6/20][399/510] Data 1.909 (3.866) Batch 18.614 (28.177) Remain 56:45:11 loss: 0.2155 loss_seg: 0.1217 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:35:27,784 INFO misc.py line 117 726] Train: [6/20][400/510] Data 3.136 (3.864) Batch 27.771 (28.176) Remain 56:44:35 loss: 0.2872 loss_seg: 0.1811 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:35:27,784 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 14:35:55,491 INFO misc.py line 117 726] Train: [6/20][401/510] Data 3.204 (3.863) Batch 27.707 (28.175) Remain 56:43:59 loss: 0.2773 loss_seg: 0.1821 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:36:23,621 INFO misc.py line 117 726] Train: [6/20][402/510] Data 2.575 (3.859) Batch 28.131 (28.175) Remain 56:43:30 loss: 0.2513 loss_seg: 0.1524 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:36:51,824 INFO misc.py line 117 726] Train: [6/20][403/510] Data 2.568 (3.856) Batch 28.203 (28.175) Remain 56:43:02 loss: 0.3101 loss_seg: 0.1964 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:37:11,827 INFO misc.py line 117 726] Train: [6/20][404/510] Data 1.933 (3.851) Batch 20.003 (28.154) Remain 56:40:06 loss: 0.3993 loss_seg: 0.2917 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:37:43,089 INFO misc.py line 117 726] Train: [6/20][405/510] Data 3.226 (3.850) Batch 31.262 (28.162) Remain 56:40:34 loss: 0.2330 loss_seg: 0.1390 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:38:03,090 INFO misc.py line 117 726] Train: [6/20][406/510] Data 2.619 (3.847) Batch 20.001 (28.142) Remain 56:37:39 loss: 0.2597 loss_seg: 0.1677 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:38:30,355 INFO misc.py line 117 726] Train: [6/20][407/510] Data 2.895 (3.844) Batch 27.265 (28.140) Remain 56:36:55 loss: 0.2721 loss_seg: 0.1688 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:38:59,494 INFO misc.py line 117 726] Train: [6/20][408/510] Data 2.949 (3.842) Batch 29.140 (28.142) Remain 56:36:45 loss: 0.1913 loss_seg: 0.1052 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:39:40,445 INFO misc.py line 117 726] Train: [6/20][409/510] Data 8.555 (3.854) Batch 40.950 (28.174) Remain 56:40:05 loss: 0.2297 loss_seg: 0.1369 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:40:11,498 INFO misc.py line 117 726] Train: [6/20][410/510] Data 3.796 (3.854) Batch 31.053 (28.181) Remain 56:40:28 loss: 0.3656 loss_seg: 0.2586 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:40:33,899 INFO misc.py line 117 726] Train: [6/20][411/510] Data 2.651 (3.851) Batch 22.401 (28.167) Remain 56:38:18 loss: 0.2009 loss_seg: 0.1129 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:40:59,612 INFO misc.py line 117 726] Train: [6/20][412/510] Data 6.539 (3.857) Batch 25.713 (28.161) Remain 56:37:06 loss: 0.2165 loss_seg: 0.1268 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0432 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:41:38,742 INFO misc.py line 117 726] Train: [6/20][413/510] Data 6.251 (3.863) Batch 39.130 (28.187) Remain 56:39:51 loss: 0.3105 loss_seg: 0.2116 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:42:08,896 INFO misc.py line 117 726] Train: [6/20][414/510] Data 3.406 (3.862) Batch 30.154 (28.192) Remain 56:39:58 loss: 0.2153 loss_seg: 0.1257 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:42:33,638 INFO misc.py line 117 726] Train: [6/20][415/510] Data 3.369 (3.861) Batch 24.742 (28.184) Remain 56:38:29 loss: 0.3404 loss_seg: 0.2338 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:43:08,482 INFO misc.py line 117 726] Train: [6/20][416/510] Data 4.920 (3.863) Batch 34.844 (28.200) Remain 56:39:58 loss: 0.2729 loss_seg: 0.1852 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:43:28,153 INFO misc.py line 117 726] Train: [6/20][417/510] Data 2.061 (3.859) Batch 19.672 (28.179) Remain 56:37:00 loss: 0.3097 loss_seg: 0.2130 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:43:54,914 INFO misc.py line 117 726] Train: [6/20][418/510] Data 3.389 (3.858) Batch 26.761 (28.176) Remain 56:36:07 loss: 0.2126 loss_seg: 0.1224 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:44:28,238 INFO misc.py line 117 726] Train: [6/20][419/510] Data 3.607 (3.857) Batch 33.324 (28.188) Remain 56:37:09 loss: 0.2291 loss_seg: 0.1361 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:44:56,381 INFO misc.py line 117 726] Train: [6/20][420/510] Data 3.377 (3.856) Batch 28.144 (28.188) Remain 56:36:40 loss: 0.2538 loss_seg: 0.1560 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:45:20,612 INFO misc.py line 117 726] Train: [6/20][421/510] Data 2.885 (3.854) Batch 24.231 (28.179) Remain 56:35:03 loss: 0.2297 loss_seg: 0.1336 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:45:46,552 INFO misc.py line 117 726] Train: [6/20][422/510] Data 2.475 (3.851) Batch 25.940 (28.173) Remain 56:33:56 loss: 0.2109 loss_seg: 0.1214 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:46:25,236 INFO misc.py line 117 726] Train: [6/20][423/510] Data 5.488 (3.854) Batch 38.684 (28.198) Remain 56:36:29 loss: 0.2728 loss_seg: 0.1808 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:46:58,038 INFO misc.py line 117 726] Train: [6/20][424/510] Data 4.014 (3.855) Batch 32.801 (28.209) Remain 56:37:20 loss: 0.2585 loss_seg: 0.1588 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:47:34,222 INFO misc.py line 117 726] Train: [6/20][425/510] Data 4.854 (3.857) Batch 36.184 (28.228) Remain 56:39:08 loss: 0.2353 loss_seg: 0.1383 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:48:11,914 INFO misc.py line 117 726] Train: [6/20][426/510] Data 7.457 (3.866) Batch 37.692 (28.251) Remain 56:41:22 loss: 0.2690 loss_seg: 0.1732 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:48:38,864 INFO misc.py line 117 726] Train: [6/20][427/510] Data 2.188 (3.862) Batch 26.950 (28.248) Remain 56:40:31 loss: 0.2046 loss_seg: 0.1184 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:49:07,418 INFO misc.py line 117 726] Train: [6/20][428/510] Data 3.013 (3.860) Batch 28.554 (28.248) Remain 56:40:08 loss: 0.2253 loss_seg: 0.1368 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0320 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:49:39,061 INFO misc.py line 117 726] Train: [6/20][429/510] Data 3.214 (3.858) Batch 31.643 (28.256) Remain 56:40:37 loss: 0.2475 loss_seg: 0.1496 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:50:09,783 INFO misc.py line 117 726] Train: [6/20][430/510] Data 3.128 (3.856) Batch 30.722 (28.262) Remain 56:40:51 loss: 0.1674 loss_seg: 0.0893 loss_superpoint_edge: 0.0140 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:50:39,889 INFO misc.py line 117 726] Train: [6/20][431/510] Data 4.042 (3.857) Batch 30.107 (28.266) Remain 56:40:54 loss: 0.2701 loss_seg: 0.1681 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:51:16,829 INFO misc.py line 117 726] Train: [6/20][432/510] Data 5.708 (3.861) Batch 36.939 (28.286) Remain 56:42:51 loss: 0.1996 loss_seg: 0.1126 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:51:43,324 INFO misc.py line 117 726] Train: [6/20][433/510] Data 4.985 (3.864) Batch 26.495 (28.282) Remain 56:41:53 loss: 0.2177 loss_seg: 0.1240 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:52:08,401 INFO misc.py line 117 726] Train: [6/20][434/510] Data 2.585 (3.861) Batch 25.077 (28.275) Remain 56:40:31 loss: 0.3210 loss_seg: 0.2249 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:52:41,119 INFO misc.py line 117 726] Train: [6/20][435/510] Data 3.640 (3.860) Batch 32.718 (28.285) Remain 56:41:17 loss: 0.2608 loss_seg: 0.1648 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:53:03,755 INFO misc.py line 117 726] Train: [6/20][436/510] Data 2.349 (3.857) Batch 22.636 (28.272) Remain 56:39:15 loss: 0.1882 loss_seg: 0.1027 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:53:29,430 INFO misc.py line 117 726] Train: [6/20][437/510] Data 3.324 (3.856) Batch 25.675 (28.266) Remain 56:38:03 loss: 0.2373 loss_seg: 0.1419 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:54:02,258 INFO misc.py line 117 726] Train: [6/20][438/510] Data 6.445 (3.862) Batch 32.828 (28.277) Remain 56:38:51 loss: 0.2258 loss_seg: 0.1330 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:54:25,058 INFO misc.py line 117 726] Train: [6/20][439/510] Data 2.209 (3.858) Batch 22.800 (28.264) Remain 56:36:52 loss: 0.2650 loss_seg: 0.1641 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:54:54,028 INFO misc.py line 117 726] Train: [6/20][440/510] Data 3.381 (3.857) Batch 28.969 (28.266) Remain 56:36:35 loss: 0.2459 loss_seg: 0.1492 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:55:21,965 INFO misc.py line 117 726] Train: [6/20][441/510] Data 3.838 (3.857) Batch 27.937 (28.265) Remain 56:36:01 loss: 0.2952 loss_seg: 0.1951 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:55:49,275 INFO misc.py line 117 726] Train: [6/20][442/510] Data 4.074 (3.857) Batch 27.309 (28.263) Remain 56:35:17 loss: 0.1987 loss_seg: 0.1069 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:56:17,233 INFO misc.py line 117 726] Train: [6/20][443/510] Data 4.030 (3.858) Batch 27.959 (28.262) Remain 56:34:44 loss: 0.3433 loss_seg: 0.2285 loss_superpoint_edge: 0.0449 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:56:47,371 INFO misc.py line 117 726] Train: [6/20][444/510] Data 3.643 (3.857) Batch 30.138 (28.266) Remain 56:34:47 loss: 0.2183 loss_seg: 0.1276 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:57:05,495 INFO misc.py line 117 726] Train: [6/20][445/510] Data 2.090 (3.853) Batch 18.124 (28.243) Remain 56:31:33 loss: 0.2475 loss_seg: 0.1468 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:57:20,255 INFO misc.py line 117 726] Train: [6/20][446/510] Data 1.443 (3.848) Batch 14.761 (28.213) Remain 56:27:26 loss: 0.2165 loss_seg: 0.1184 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:57:38,640 INFO misc.py line 117 726] Train: [6/20][447/510] Data 1.638 (3.843) Batch 18.385 (28.191) Remain 56:24:18 loss: 0.2179 loss_seg: 0.1258 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:58:08,157 INFO misc.py line 117 726] Train: [6/20][448/510] Data 2.831 (3.840) Batch 29.516 (28.194) Remain 56:24:11 loss: 0.2155 loss_seg: 0.1201 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:58:31,917 INFO misc.py line 117 726] Train: [6/20][449/510] Data 2.361 (3.837) Batch 23.760 (28.184) Remain 56:22:31 loss: 0.2084 loss_seg: 0.1197 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:59:08,058 INFO misc.py line 117 726] Train: [6/20][450/510] Data 6.059 (3.842) Batch 36.141 (28.202) Remain 56:24:11 loss: 0.3988 loss_seg: 0.3036 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 14:59:08,059 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 14:59:35,802 INFO misc.py line 117 726] Train: [6/20][451/510] Data 3.573 (3.841) Batch 27.744 (28.201) Remain 56:23:36 loss: 0.1854 loss_seg: 0.1001 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:00:01,619 INFO misc.py line 117 726] Train: [6/20][452/510] Data 3.338 (3.840) Batch 25.817 (28.195) Remain 56:22:29 loss: 0.4662 loss_seg: 0.3420 loss_superpoint_edge: 0.0537 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:00:35,691 INFO misc.py line 117 726] Train: [6/20][453/510] Data 4.955 (3.843) Batch 34.072 (28.208) Remain 56:23:35 loss: 0.2290 loss_seg: 0.1367 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:01:03,987 INFO misc.py line 117 726] Train: [6/20][454/510] Data 4.092 (3.843) Batch 28.296 (28.209) Remain 56:23:08 loss: 0.2898 loss_seg: 0.1894 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:01:44,166 INFO misc.py line 117 726] Train: [6/20][455/510] Data 7.357 (3.851) Batch 40.179 (28.235) Remain 56:25:51 loss: 0.2541 loss_seg: 0.1558 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:02:13,055 INFO misc.py line 117 726] Train: [6/20][456/510] Data 3.169 (3.850) Batch 28.889 (28.236) Remain 56:25:33 loss: 0.2216 loss_seg: 0.1305 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:02:46,258 INFO misc.py line 117 726] Train: [6/20][457/510] Data 2.626 (3.847) Batch 33.203 (28.247) Remain 56:26:23 loss: 0.2652 loss_seg: 0.1651 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:03:03,957 INFO misc.py line 117 726] Train: [6/20][458/510] Data 2.518 (3.844) Batch 17.699 (28.224) Remain 56:23:08 loss: 0.2486 loss_seg: 0.1497 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:03:31,436 INFO misc.py line 117 726] Train: [6/20][459/510] Data 2.820 (3.842) Batch 27.479 (28.223) Remain 56:22:28 loss: 0.2003 loss_seg: 0.1120 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:03:49,633 INFO misc.py line 117 726] Train: [6/20][460/510] Data 2.049 (3.838) Batch 18.197 (28.201) Remain 56:19:22 loss: 0.2294 loss_seg: 0.1349 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:04:12,857 INFO misc.py line 117 726] Train: [6/20][461/510] Data 2.209 (3.834) Batch 23.224 (28.190) Remain 56:17:36 loss: 0.2123 loss_seg: 0.1191 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:04:44,696 INFO misc.py line 117 726] Train: [6/20][462/510] Data 3.527 (3.834) Batch 31.839 (28.198) Remain 56:18:05 loss: 0.2186 loss_seg: 0.1301 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:05:10,429 INFO misc.py line 117 726] Train: [6/20][463/510] Data 2.089 (3.830) Batch 25.733 (28.192) Remain 56:16:58 loss: 0.2325 loss_seg: 0.1381 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:05:33,053 INFO misc.py line 117 726] Train: [6/20][464/510] Data 3.205 (3.828) Batch 22.623 (28.180) Remain 56:15:03 loss: 0.2692 loss_seg: 0.1733 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:06:03,117 INFO misc.py line 117 726] Train: [6/20][465/510] Data 4.143 (3.829) Batch 30.064 (28.184) Remain 56:15:04 loss: 0.2076 loss_seg: 0.1168 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:06:30,876 INFO misc.py line 117 726] Train: [6/20][466/510] Data 3.781 (3.829) Batch 27.758 (28.183) Remain 56:14:30 loss: 0.2530 loss_seg: 0.1572 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:06:57,233 INFO misc.py line 117 726] Train: [6/20][467/510] Data 3.567 (3.828) Batch 26.358 (28.180) Remain 56:13:33 loss: 0.2993 loss_seg: 0.1903 loss_superpoint_edge: 0.0425 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:07:24,717 INFO misc.py line 117 726] Train: [6/20][468/510] Data 3.726 (3.828) Batch 27.484 (28.178) Remain 56:12:54 loss: 0.2704 loss_seg: 0.1729 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:07:54,830 INFO misc.py line 117 726] Train: [6/20][469/510] Data 3.138 (3.827) Batch 30.113 (28.182) Remain 56:12:56 loss: 0.2053 loss_seg: 0.1157 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:08:20,434 INFO misc.py line 117 726] Train: [6/20][470/510] Data 2.610 (3.824) Batch 25.604 (28.177) Remain 56:11:48 loss: 0.2403 loss_seg: 0.1493 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:08:37,007 INFO misc.py line 117 726] Train: [6/20][471/510] Data 2.223 (3.821) Batch 16.573 (28.152) Remain 56:08:22 loss: 0.2125 loss_seg: 0.1201 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:08:59,813 INFO misc.py line 117 726] Train: [6/20][472/510] Data 2.298 (3.817) Batch 22.806 (28.140) Remain 56:06:32 loss: 0.2683 loss_seg: 0.1680 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:09:23,683 INFO misc.py line 117 726] Train: [6/20][473/510] Data 2.310 (3.814) Batch 23.870 (28.131) Remain 56:04:59 loss: 0.2533 loss_seg: 0.1524 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:09:47,414 INFO misc.py line 117 726] Train: [6/20][474/510] Data 3.083 (3.813) Batch 23.731 (28.122) Remain 56:03:23 loss: 0.2718 loss_seg: 0.1724 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:10:11,356 INFO misc.py line 117 726] Train: [6/20][475/510] Data 2.390 (3.810) Batch 23.942 (28.113) Remain 56:01:52 loss: 0.2297 loss_seg: 0.1343 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:10:35,007 INFO misc.py line 117 726] Train: [6/20][476/510] Data 3.127 (3.808) Batch 23.652 (28.104) Remain 56:00:16 loss: 0.2387 loss_seg: 0.1401 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:10:57,174 INFO misc.py line 117 726] Train: [6/20][477/510] Data 2.667 (3.806) Batch 22.167 (28.091) Remain 55:58:18 loss: 0.2149 loss_seg: 0.1213 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:11:27,846 INFO misc.py line 117 726] Train: [6/20][478/510] Data 3.413 (3.805) Batch 30.671 (28.097) Remain 55:58:29 loss: 0.2562 loss_seg: 0.1601 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:11:55,623 INFO misc.py line 117 726] Train: [6/20][479/510] Data 4.161 (3.806) Batch 27.777 (28.096) Remain 55:57:56 loss: 0.2663 loss_seg: 0.1591 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:12:28,956 INFO misc.py line 117 726] Train: [6/20][480/510] Data 5.343 (3.809) Batch 33.334 (28.107) Remain 55:58:47 loss: 0.2502 loss_seg: 0.1603 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:12:50,397 INFO misc.py line 117 726] Train: [6/20][481/510] Data 2.373 (3.806) Batch 21.441 (28.093) Remain 55:56:39 loss: 0.3382 loss_seg: 0.2358 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:13:25,679 INFO misc.py line 117 726] Train: [6/20][482/510] Data 4.621 (3.808) Batch 35.282 (28.108) Remain 55:57:58 loss: 0.2725 loss_seg: 0.1711 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:13:43,295 INFO misc.py line 117 726] Train: [6/20][483/510] Data 2.192 (3.804) Batch 17.616 (28.086) Remain 55:54:53 loss: 0.2171 loss_seg: 0.1273 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:14:02,382 INFO misc.py line 117 726] Train: [6/20][484/510] Data 2.035 (3.801) Batch 19.086 (28.067) Remain 55:52:11 loss: 0.2669 loss_seg: 0.1726 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:14:26,059 INFO misc.py line 117 726] Train: [6/20][485/510] Data 2.551 (3.798) Batch 23.677 (28.058) Remain 55:50:38 loss: 0.2089 loss_seg: 0.1209 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:14:47,976 INFO misc.py line 117 726] Train: [6/20][486/510] Data 2.147 (3.795) Batch 21.917 (28.046) Remain 55:48:39 loss: 0.2724 loss_seg: 0.1840 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:15:07,757 INFO misc.py line 117 726] Train: [6/20][487/510] Data 2.671 (3.792) Batch 19.782 (28.029) Remain 55:46:08 loss: 0.2019 loss_seg: 0.1150 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:15:41,580 INFO misc.py line 117 726] Train: [6/20][488/510] Data 5.766 (3.796) Batch 33.823 (28.041) Remain 55:47:06 loss: 0.3134 loss_seg: 0.2063 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:16:09,529 INFO misc.py line 117 726] Train: [6/20][489/510] Data 2.915 (3.795) Batch 27.949 (28.040) Remain 55:46:36 loss: 0.1908 loss_seg: 0.1005 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:16:44,234 INFO misc.py line 117 726] Train: [6/20][490/510] Data 5.177 (3.797) Batch 34.705 (28.054) Remain 55:47:46 loss: 0.2296 loss_seg: 0.1374 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:17:08,435 INFO misc.py line 117 726] Train: [6/20][491/510] Data 2.857 (3.796) Batch 24.200 (28.046) Remain 55:46:22 loss: 0.2541 loss_seg: 0.1579 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:17:36,142 INFO misc.py line 117 726] Train: [6/20][492/510] Data 2.419 (3.793) Batch 27.708 (28.045) Remain 55:45:49 loss: 0.2851 loss_seg: 0.1773 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:18:06,123 INFO misc.py line 117 726] Train: [6/20][493/510] Data 7.195 (3.800) Batch 29.980 (28.049) Remain 55:45:49 loss: 0.2889 loss_seg: 0.1959 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:18:43,718 INFO misc.py line 117 726] Train: [6/20][494/510] Data 6.501 (3.805) Batch 37.595 (28.069) Remain 55:47:40 loss: 0.2621 loss_seg: 0.1654 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:19:14,424 INFO misc.py line 117 726] Train: [6/20][495/510] Data 4.068 (3.806) Batch 30.706 (28.074) Remain 55:47:50 loss: 0.2230 loss_seg: 0.1324 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:19:46,245 INFO misc.py line 117 726] Train: [6/20][496/510] Data 6.094 (3.810) Batch 31.822 (28.082) Remain 55:48:17 loss: 0.2038 loss_seg: 0.1114 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:20:19,225 INFO misc.py line 117 726] Train: [6/20][497/510] Data 3.031 (3.809) Batch 32.980 (28.092) Remain 55:48:59 loss: 0.2231 loss_seg: 0.1285 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:20:59,035 INFO misc.py line 117 726] Train: [6/20][498/510] Data 9.557 (3.820) Batch 39.809 (28.115) Remain 55:51:21 loss: 0.2151 loss_seg: 0.1253 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:21:29,475 INFO misc.py line 117 726] Train: [6/20][499/510] Data 2.698 (3.818) Batch 30.441 (28.120) Remain 55:51:26 loss: 0.2200 loss_seg: 0.1292 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:21:49,644 INFO misc.py line 117 726] Train: [6/20][500/510] Data 2.217 (3.815) Batch 20.169 (28.104) Remain 55:49:04 loss: 0.2363 loss_seg: 0.1379 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:21:49,644 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 15:22:26,327 INFO misc.py line 117 726] Train: [6/20][501/510] Data 4.251 (3.816) Batch 36.683 (28.121) Remain 55:50:39 loss: 0.2023 loss_seg: 0.1126 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:22:50,838 INFO misc.py line 117 726] Train: [6/20][502/510] Data 2.794 (3.814) Batch 24.511 (28.114) Remain 55:49:19 loss: 0.2191 loss_seg: 0.1242 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:23:15,147 INFO misc.py line 117 726] Train: [6/20][503/510] Data 2.453 (3.811) Batch 24.309 (28.106) Remain 55:47:56 loss: 0.2937 loss_seg: 0.1887 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:23:37,078 INFO misc.py line 117 726] Train: [6/20][504/510] Data 2.988 (3.809) Batch 21.930 (28.094) Remain 55:46:00 loss: 0.2553 loss_seg: 0.1568 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:24:08,394 INFO misc.py line 117 726] Train: [6/20][505/510] Data 3.863 (3.809) Batch 31.316 (28.101) Remain 55:46:18 loss: 0.2650 loss_seg: 0.1694 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:24:29,726 INFO misc.py line 117 726] Train: [6/20][506/510] Data 2.582 (3.807) Batch 21.332 (28.087) Remain 55:44:14 loss: 0.2396 loss_seg: 0.1431 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:25:05,258 INFO misc.py line 117 726] Train: [6/20][507/510] Data 7.323 (3.814) Batch 35.532 (28.102) Remain 55:45:31 loss: 0.2869 loss_seg: 0.1930 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:25:27,212 INFO misc.py line 117 726] Train: [6/20][508/510] Data 2.346 (3.811) Batch 21.954 (28.090) Remain 55:43:36 loss: 0.1857 loss_seg: 0.0999 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:25:54,972 INFO misc.py line 117 726] Train: [6/20][509/510] Data 2.849 (3.809) Batch 27.760 (28.089) Remain 55:43:03 loss: 0.2521 loss_seg: 0.1547 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:26:25,553 INFO misc.py line 117 726] Train: [6/20][510/510] Data 3.442 (3.808) Batch 30.581 (28.094) Remain 55:43:10 loss: 0.2429 loss_seg: 0.1498 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:26:25,554 INFO misc.py line 147 726] Train result: loss: 0.2577 loss_seg: 0.1614 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-10 15:26:25,554 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-10 15:26:41,485 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6642 [2026-06-10 15:26:59,217 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6593 [2026-06-10 15:28:14,321 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9873 [2026-06-10 15:28:54,871 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0265 [2026-06-10 15:29:14,365 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9807 [2026-06-10 15:29:50,732 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.0206 [2026-06-10 15:30:37,552 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1619 [2026-06-10 15:30:53,262 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.4004 [2026-06-10 15:31:11,394 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9992 [2026-06-10 15:31:30,308 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4740 [2026-06-10 15:31:46,288 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5103 [2026-06-10 15:32:08,182 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.8440 [2026-06-10 15:32:34,129 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8557 [2026-06-10 15:32:45,549 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7568 [2026-06-10 15:33:17,231 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0826 [2026-06-10 15:33:43,539 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3649 [2026-06-10 15:34:10,466 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3720 [2026-06-10 15:34:53,633 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1138 [2026-06-10 15:35:15,205 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4160 [2026-06-10 15:35:31,810 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.6497 [2026-06-10 15:36:03,053 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.8881 [2026-06-10 15:36:19,429 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.3651 [2026-06-10 15:36:41,575 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2528 [2026-06-10 15:37:03,289 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7906 [2026-06-10 15:37:16,918 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6938 [2026-06-10 15:37:44,711 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5384 [2026-06-10 15:38:26,217 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.3403 [2026-06-10 15:38:43,445 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5659 [2026-06-10 15:39:01,960 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.5545 [2026-06-10 15:39:18,824 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4016 [2026-06-10 15:39:43,950 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1010 [2026-06-10 15:40:02,165 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5933 [2026-06-10 15:40:19,609 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1525 [2026-06-10 15:40:43,981 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6177 [2026-06-10 15:40:43,997 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6690/0.7371/0.8960. [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9257/0.9637 [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9753/0.9876 [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8385/0.9710 [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0012/0.0099 [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3353/0.3984 [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.5986/0.6282 [2026-06-10 15:40:43,997 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5760/0.6682 [2026-06-10 15:40:43,998 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7955/0.8976 [2026-06-10 15:40:43,998 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9138/0.9534 [2026-06-10 15:40:43,998 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6479/0.7053 [2026-06-10 15:40:43,998 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7623/0.8487 [2026-06-10 15:40:43,998 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7332/0.8527 [2026-06-10 15:40:43,998 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5941/0.6971 [2026-06-10 15:40:43,998 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-10 15:40:43,999 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-10 15:40:43,999 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 15:41:02,069 INFO misc.py line 117 726] Train: [7/20][1/510] Data 2.133 (2.133) Batch 16.531 (16.531) Remain 32:46:52 loss: 0.2229 loss_seg: 0.1289 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:41:31,709 INFO misc.py line 117 726] Train: [7/20][2/510] Data 4.792 (4.792) Batch 29.640 (29.640) Remain 58:46:08 loss: 0.2738 loss_seg: 0.1779 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:41:52,383 INFO misc.py line 117 726] Train: [7/20][3/510] Data 2.375 (2.375) Batch 20.674 (20.674) Remain 40:59:09 loss: 0.2541 loss_seg: 0.1528 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:42:28,254 INFO misc.py line 117 726] Train: [7/20][4/510] Data 4.666 (4.666) Batch 35.871 (35.871) Remain 71:06:17 loss: 0.2697 loss_seg: 0.1744 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:43:01,702 INFO misc.py line 117 726] Train: [7/20][5/510] Data 6.151 (5.409) Batch 33.448 (34.660) Remain 68:41:35 loss: 0.2272 loss_seg: 0.1366 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:43:25,794 INFO misc.py line 117 726] Train: [7/20][6/510] Data 2.887 (4.568) Batch 24.092 (31.137) Remain 61:42:12 loss: 0.2578 loss_seg: 0.1555 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:43:56,277 INFO misc.py line 117 726] Train: [7/20][7/510] Data 3.541 (4.311) Batch 30.483 (30.974) Remain 61:22:14 loss: 0.2736 loss_seg: 0.1767 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:44:25,808 INFO misc.py line 117 726] Train: [7/20][8/510] Data 3.108 (4.071) Batch 29.531 (30.685) Remain 60:47:25 loss: 0.2137 loss_seg: 0.1231 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:44:54,261 INFO misc.py line 117 726] Train: [7/20][9/510] Data 3.635 (3.998) Batch 28.453 (30.313) Remain 60:02:41 loss: 0.3442 loss_seg: 0.2447 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:45:27,247 INFO misc.py line 117 726] Train: [7/20][10/510] Data 4.405 (4.056) Batch 32.986 (30.695) Remain 60:47:34 loss: 0.2678 loss_seg: 0.1738 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:45:57,787 INFO misc.py line 117 726] Train: [7/20][11/510] Data 2.878 (3.909) Batch 30.540 (30.676) Remain 60:44:45 loss: 0.2288 loss_seg: 0.1328 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:46:37,298 INFO misc.py line 117 726] Train: [7/20][12/510] Data 7.923 (4.355) Batch 39.510 (31.657) Remain 62:40:52 loss: 0.3176 loss_seg: 0.2252 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:47:04,615 INFO misc.py line 117 726] Train: [7/20][13/510] Data 2.503 (4.170) Batch 27.318 (31.223) Remain 61:48:48 loss: 0.1803 loss_seg: 0.0978 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:47:26,622 INFO misc.py line 117 726] Train: [7/20][14/510] Data 3.118 (4.074) Batch 22.006 (30.385) Remain 60:08:45 loss: 0.2153 loss_seg: 0.1263 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:47:55,003 INFO misc.py line 117 726] Train: [7/20][15/510] Data 3.867 (4.057) Batch 28.382 (30.218) Remain 59:48:25 loss: 0.2189 loss_seg: 0.1332 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:48:28,322 INFO misc.py line 117 726] Train: [7/20][16/510] Data 4.694 (4.106) Batch 33.319 (30.457) Remain 60:16:14 loss: 0.2666 loss_seg: 0.1744 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:48:58,743 INFO misc.py line 117 726] Train: [7/20][17/510] Data 3.306 (4.049) Batch 30.420 (30.454) Remain 60:15:25 loss: 0.2824 loss_seg: 0.1797 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:49:28,090 INFO misc.py line 117 726] Train: [7/20][18/510] Data 5.439 (4.141) Batch 29.347 (30.380) Remain 60:06:09 loss: 0.1851 loss_seg: 0.1010 loss_superpoint_edge: 0.0128 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:49:58,495 INFO misc.py line 117 726] Train: [7/20][19/510] Data 3.065 (4.074) Batch 30.406 (30.382) Remain 60:05:50 loss: 0.2563 loss_seg: 0.1590 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:50:29,764 INFO misc.py line 117 726] Train: [7/20][20/510] Data 3.178 (4.021) Batch 31.268 (30.434) Remain 60:11:31 loss: 0.1734 loss_seg: 0.0892 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:50:58,752 INFO misc.py line 117 726] Train: [7/20][21/510] Data 2.683 (3.947) Batch 28.988 (30.354) Remain 60:01:29 loss: 0.2397 loss_seg: 0.1463 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:51:29,917 INFO misc.py line 117 726] Train: [7/20][22/510] Data 5.585 (4.033) Batch 31.165 (30.397) Remain 60:06:02 loss: 0.2180 loss_seg: 0.1305 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:51:57,425 INFO misc.py line 117 726] Train: [7/20][23/510] Data 3.355 (3.999) Batch 27.508 (30.252) Remain 59:48:24 loss: 0.2562 loss_seg: 0.1565 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:52:29,219 INFO misc.py line 117 726] Train: [7/20][24/510] Data 3.048 (3.954) Batch 31.794 (30.326) Remain 59:56:36 loss: 0.2720 loss_seg: 0.1667 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:53:02,702 INFO misc.py line 117 726] Train: [7/20][25/510] Data 3.598 (3.938) Batch 33.483 (30.469) Remain 60:13:07 loss: 0.2628 loss_seg: 0.1616 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:53:31,521 INFO misc.py line 117 726] Train: [7/20][26/510] Data 3.605 (3.923) Batch 28.819 (30.397) Remain 60:04:06 loss: 0.2319 loss_seg: 0.1394 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:53:56,176 INFO misc.py line 117 726] Train: [7/20][27/510] Data 2.537 (3.866) Batch 24.654 (30.158) Remain 59:35:14 loss: 0.2638 loss_seg: 0.1643 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:54:23,386 INFO misc.py line 117 726] Train: [7/20][28/510] Data 2.872 (3.826) Batch 27.210 (30.040) Remain 59:20:45 loss: 0.2796 loss_seg: 0.1782 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:54:55,002 INFO misc.py line 117 726] Train: [7/20][29/510] Data 4.238 (3.842) Batch 31.616 (30.101) Remain 59:27:26 loss: 0.2126 loss_seg: 0.1244 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:55:17,547 INFO misc.py line 117 726] Train: [7/20][30/510] Data 2.031 (3.775) Batch 22.545 (29.821) Remain 58:53:46 loss: 0.2197 loss_seg: 0.1255 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:55:57,273 INFO misc.py line 117 726] Train: [7/20][31/510] Data 7.329 (3.902) Batch 39.726 (30.175) Remain 59:35:11 loss: 0.3464 loss_seg: 0.2509 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:56:32,482 INFO misc.py line 117 726] Train: [7/20][32/510] Data 4.363 (3.918) Batch 35.209 (30.348) Remain 59:55:15 loss: 0.2985 loss_seg: 0.1935 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:57:01,607 INFO misc.py line 117 726] Train: [7/20][33/510] Data 4.073 (3.923) Batch 29.125 (30.307) Remain 59:49:55 loss: 0.2412 loss_seg: 0.1454 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:57:20,829 INFO misc.py line 117 726] Train: [7/20][34/510] Data 2.013 (3.861) Batch 19.223 (29.950) Remain 59:07:03 loss: 0.2264 loss_seg: 0.1362 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:57:49,506 INFO misc.py line 117 726] Train: [7/20][35/510] Data 3.429 (3.848) Batch 28.677 (29.910) Remain 59:01:51 loss: 0.2814 loss_seg: 0.1733 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:58:23,909 INFO misc.py line 117 726] Train: [7/20][36/510] Data 4.405 (3.864) Batch 34.403 (30.046) Remain 59:17:28 loss: 0.2507 loss_seg: 0.1584 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:59:03,368 INFO misc.py line 117 726] Train: [7/20][37/510] Data 11.162 (4.079) Batch 39.459 (30.323) Remain 59:49:44 loss: 0.2271 loss_seg: 0.1341 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 15:59:36,973 INFO misc.py line 117 726] Train: [7/20][38/510] Data 5.154 (4.110) Batch 33.605 (30.417) Remain 60:00:20 loss: 0.3418 loss_seg: 0.2450 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:00:08,393 INFO misc.py line 117 726] Train: [7/20][39/510] Data 3.103 (4.082) Batch 31.420 (30.445) Remain 60:03:07 loss: 0.2503 loss_seg: 0.1597 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:00:31,893 INFO misc.py line 117 726] Train: [7/20][40/510] Data 3.403 (4.064) Batch 23.501 (30.257) Remain 59:40:24 loss: 0.3193 loss_seg: 0.2159 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:00:50,250 INFO misc.py line 117 726] Train: [7/20][41/510] Data 1.883 (4.006) Batch 18.357 (29.944) Remain 59:02:51 loss: 0.2117 loss_seg: 0.1179 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:01:18,612 INFO misc.py line 117 726] Train: [7/20][42/510] Data 3.085 (3.983) Batch 28.361 (29.903) Remain 58:57:33 loss: 0.2506 loss_seg: 0.1550 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:01:38,403 INFO misc.py line 117 726] Train: [7/20][43/510] Data 2.531 (3.946) Batch 19.792 (29.651) Remain 58:27:09 loss: 0.2757 loss_seg: 0.1753 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:02:10,882 INFO misc.py line 117 726] Train: [7/20][44/510] Data 3.451 (3.934) Batch 32.479 (29.719) Remain 58:34:49 loss: 0.2483 loss_seg: 0.1501 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:02:46,917 INFO misc.py line 117 726] Train: [7/20][45/510] Data 4.979 (3.959) Batch 36.035 (29.870) Remain 58:52:06 loss: 0.3465 loss_seg: 0.2431 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:03:19,186 INFO misc.py line 117 726] Train: [7/20][46/510] Data 2.843 (3.933) Batch 32.269 (29.926) Remain 58:58:12 loss: 0.1791 loss_seg: 0.0926 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:03:47,236 INFO misc.py line 117 726] Train: [7/20][47/510] Data 5.714 (3.974) Batch 28.050 (29.883) Remain 58:52:40 loss: 0.2393 loss_seg: 0.1482 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:04:22,425 INFO misc.py line 117 726] Train: [7/20][48/510] Data 4.502 (3.985) Batch 35.189 (30.001) Remain 59:06:06 loss: 0.2628 loss_seg: 0.1620 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:04:50,050 INFO misc.py line 117 726] Train: [7/20][49/510] Data 3.201 (3.968) Batch 27.626 (29.949) Remain 58:59:30 loss: 0.2581 loss_seg: 0.1659 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:05:08,959 INFO misc.py line 117 726] Train: [7/20][50/510] Data 2.397 (3.935) Batch 18.908 (29.714) Remain 58:31:14 loss: 0.3182 loss_seg: 0.2242 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:05:08,959 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 16:05:39,008 INFO misc.py line 117 726] Train: [7/20][51/510] Data 3.810 (3.932) Batch 30.049 (29.721) Remain 58:31:34 loss: 0.2442 loss_seg: 0.1516 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:06:12,300 INFO misc.py line 117 726] Train: [7/20][52/510] Data 3.491 (3.923) Batch 33.292 (29.794) Remain 58:39:41 loss: 0.2696 loss_seg: 0.1743 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:06:35,391 INFO misc.py line 117 726] Train: [7/20][53/510] Data 3.306 (3.911) Batch 23.091 (29.660) Remain 58:23:21 loss: 0.2432 loss_seg: 0.1455 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:07:04,416 INFO misc.py line 117 726] Train: [7/20][54/510] Data 3.359 (3.900) Batch 29.025 (29.648) Remain 58:21:23 loss: 0.3190 loss_seg: 0.2155 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:07:26,760 INFO misc.py line 117 726] Train: [7/20][55/510] Data 2.672 (3.876) Batch 22.344 (29.507) Remain 58:04:18 loss: 0.2491 loss_seg: 0.1538 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:08:03,312 INFO misc.py line 117 726] Train: [7/20][56/510] Data 5.127 (3.900) Batch 36.552 (29.640) Remain 58:19:30 loss: 0.1971 loss_seg: 0.1130 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:08:41,796 INFO misc.py line 117 726] Train: [7/20][57/510] Data 12.968 (4.068) Batch 38.484 (29.804) Remain 58:38:21 loss: 0.3209 loss_seg: 0.2202 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:09:19,860 INFO misc.py line 117 726] Train: [7/20][58/510] Data 5.334 (4.091) Batch 38.064 (29.954) Remain 58:55:35 loss: 0.2637 loss_seg: 0.1624 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:09:50,990 INFO misc.py line 117 726] Train: [7/20][59/510] Data 3.786 (4.086) Batch 31.130 (29.975) Remain 58:57:33 loss: 0.3292 loss_seg: 0.2205 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:10:22,814 INFO misc.py line 117 726] Train: [7/20][60/510] Data 3.112 (4.068) Batch 31.824 (30.008) Remain 59:00:53 loss: 0.2229 loss_seg: 0.1306 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:10:59,200 INFO misc.py line 117 726] Train: [7/20][61/510] Data 3.769 (4.063) Batch 36.387 (30.118) Remain 59:13:22 loss: 0.3041 loss_seg: 0.1880 loss_superpoint_edge: 0.0466 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:11:37,901 INFO misc.py line 117 726] Train: [7/20][62/510] Data 6.759 (4.109) Batch 38.701 (30.263) Remain 59:30:01 loss: 0.2244 loss_seg: 0.1331 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:12:08,460 INFO misc.py line 117 726] Train: [7/20][63/510] Data 2.994 (4.090) Batch 30.559 (30.268) Remain 59:30:06 loss: 0.2437 loss_seg: 0.1483 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:12:36,818 INFO misc.py line 117 726] Train: [7/20][64/510] Data 3.288 (4.077) Batch 28.358 (30.237) Remain 59:25:54 loss: 0.2759 loss_seg: 0.1704 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:13:01,814 INFO misc.py line 117 726] Train: [7/20][65/510] Data 2.329 (4.049) Batch 24.996 (30.152) Remain 59:15:26 loss: 0.3061 loss_seg: 0.2076 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:13:30,121 INFO misc.py line 117 726] Train: [7/20][66/510] Data 4.996 (4.064) Batch 28.307 (30.123) Remain 59:11:28 loss: 0.4381 loss_seg: 0.3325 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:13:58,676 INFO misc.py line 117 726] Train: [7/20][67/510] Data 4.522 (4.071) Batch 28.554 (30.098) Remain 59:08:05 loss: 0.2712 loss_seg: 0.1710 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:14:29,699 INFO misc.py line 117 726] Train: [7/20][68/510] Data 3.241 (4.058) Batch 31.023 (30.113) Remain 59:09:15 loss: 0.2593 loss_seg: 0.1748 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:14:47,821 INFO misc.py line 117 726] Train: [7/20][69/510] Data 2.393 (4.033) Batch 18.122 (29.931) Remain 58:47:21 loss: 0.3772 loss_seg: 0.2787 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:15:11,002 INFO misc.py line 117 726] Train: [7/20][70/510] Data 2.674 (4.013) Batch 23.181 (29.830) Remain 58:34:59 loss: 0.2662 loss_seg: 0.1701 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:15:40,232 INFO misc.py line 117 726] Train: [7/20][71/510] Data 2.808 (3.995) Batch 29.230 (29.821) Remain 58:33:26 loss: 0.2537 loss_seg: 0.1528 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:16:20,312 INFO misc.py line 117 726] Train: [7/20][72/510] Data 9.373 (4.073) Batch 40.080 (29.970) Remain 58:50:27 loss: 0.2587 loss_seg: 0.1620 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:16:42,229 INFO misc.py line 117 726] Train: [7/20][73/510] Data 3.429 (4.064) Batch 21.917 (29.855) Remain 58:36:24 loss: 0.2814 loss_seg: 0.1788 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:16:55,312 INFO misc.py line 117 726] Train: [7/20][74/510] Data 1.423 (4.027) Batch 13.083 (29.619) Remain 58:08:05 loss: 0.2020 loss_seg: 0.1082 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:17:21,209 INFO misc.py line 117 726] Train: [7/20][75/510] Data 2.635 (4.007) Batch 25.898 (29.567) Remain 58:01:31 loss: 0.3169 loss_seg: 0.2107 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:17:57,473 INFO misc.py line 117 726] Train: [7/20][76/510] Data 6.463 (4.041) Batch 36.263 (29.659) Remain 58:11:49 loss: 0.3261 loss_seg: 0.2235 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:18:21,849 INFO misc.py line 117 726] Train: [7/20][77/510] Data 2.384 (4.019) Batch 24.376 (29.587) Remain 58:02:55 loss: 0.2311 loss_seg: 0.1373 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:18:49,817 INFO misc.py line 117 726] Train: [7/20][78/510] Data 3.521 (4.012) Batch 27.968 (29.566) Remain 57:59:53 loss: 0.2555 loss_seg: 0.1567 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:19:18,624 INFO misc.py line 117 726] Train: [7/20][79/510] Data 4.891 (4.024) Batch 28.807 (29.556) Remain 57:58:13 loss: 0.3097 loss_seg: 0.2014 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:19:51,624 INFO misc.py line 117 726] Train: [7/20][80/510] Data 4.601 (4.031) Batch 33.000 (29.601) Remain 58:02:59 loss: 0.2414 loss_seg: 0.1473 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:20:26,082 INFO misc.py line 117 726] Train: [7/20][81/510] Data 9.861 (4.106) Batch 34.459 (29.663) Remain 58:09:49 loss: 0.2295 loss_seg: 0.1346 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:21:02,736 INFO misc.py line 117 726] Train: [7/20][82/510] Data 6.652 (4.138) Batch 36.654 (29.751) Remain 58:19:44 loss: 0.2323 loss_seg: 0.1354 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:21:36,823 INFO misc.py line 117 726] Train: [7/20][83/510] Data 6.410 (4.166) Batch 34.087 (29.806) Remain 58:25:37 loss: 0.2583 loss_seg: 0.1592 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:21:58,609 INFO misc.py line 117 726] Train: [7/20][84/510] Data 2.559 (4.147) Batch 21.786 (29.706) Remain 58:13:29 loss: 0.1596 loss_seg: 0.0782 loss_superpoint_edge: 0.0132 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:22:30,855 INFO misc.py line 117 726] Train: [7/20][85/510] Data 4.281 (4.148) Batch 32.246 (29.737) Remain 58:16:37 loss: 0.2473 loss_seg: 0.1516 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:23:02,940 INFO misc.py line 117 726] Train: [7/20][86/510] Data 2.999 (4.134) Batch 32.085 (29.766) Remain 58:19:27 loss: 0.2394 loss_seg: 0.1449 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:23:29,593 INFO misc.py line 117 726] Train: [7/20][87/510] Data 3.092 (4.122) Batch 26.653 (29.729) Remain 58:14:36 loss: 0.2953 loss_seg: 0.1896 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:23:44,429 INFO misc.py line 117 726] Train: [7/20][88/510] Data 1.651 (4.093) Batch 14.836 (29.553) Remain 57:53:31 loss: 0.5028 loss_seg: 0.3933 loss_superpoint_edge: 0.0404 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0343 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:24:11,384 INFO misc.py line 117 726] Train: [7/20][89/510] Data 4.030 (4.092) Batch 26.955 (29.523) Remain 57:49:28 loss: 0.2532 loss_seg: 0.1545 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:24:46,471 INFO misc.py line 117 726] Train: [7/20][90/510] Data 4.206 (4.093) Batch 35.087 (29.587) Remain 57:56:29 loss: 0.3606 loss_seg: 0.2526 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:25:16,261 INFO misc.py line 117 726] Train: [7/20][91/510] Data 2.638 (4.077) Batch 29.790 (29.590) Remain 57:56:16 loss: 0.2338 loss_seg: 0.1369 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:25:45,254 INFO misc.py line 117 726] Train: [7/20][92/510] Data 3.188 (4.067) Batch 28.993 (29.583) Remain 57:54:59 loss: 0.2602 loss_seg: 0.1653 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:26:06,861 INFO misc.py line 117 726] Train: [7/20][93/510] Data 2.328 (4.048) Batch 21.607 (29.494) Remain 57:44:05 loss: 0.2034 loss_seg: 0.1140 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:26:35,475 INFO misc.py line 117 726] Train: [7/20][94/510] Data 5.467 (4.063) Batch 28.614 (29.485) Remain 57:42:27 loss: 0.5620 loss_seg: 0.4606 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:26:58,300 INFO misc.py line 117 726] Train: [7/20][95/510] Data 2.418 (4.045) Batch 22.826 (29.412) Remain 57:33:28 loss: 0.2352 loss_seg: 0.1370 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:27:22,370 INFO misc.py line 117 726] Train: [7/20][96/510] Data 2.734 (4.031) Batch 24.069 (29.355) Remain 57:26:14 loss: 0.2724 loss_seg: 0.1732 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:27:50,609 INFO misc.py line 117 726] Train: [7/20][97/510] Data 2.902 (4.019) Batch 28.239 (29.343) Remain 57:24:21 loss: 0.2292 loss_seg: 0.1373 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:28:07,730 INFO misc.py line 117 726] Train: [7/20][98/510] Data 2.295 (4.001) Batch 17.121 (29.214) Remain 57:08:46 loss: 0.2449 loss_seg: 0.1457 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:28:29,750 INFO misc.py line 117 726] Train: [7/20][99/510] Data 3.043 (3.991) Batch 22.020 (29.139) Remain 56:59:29 loss: 0.2637 loss_seg: 0.1645 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:29:04,274 INFO misc.py line 117 726] Train: [7/20][100/510] Data 3.472 (3.986) Batch 34.523 (29.195) Remain 57:05:31 loss: 0.2224 loss_seg: 0.1286 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:29:04,275 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 16:29:30,913 INFO misc.py line 117 726] Train: [7/20][101/510] Data 3.647 (3.982) Batch 26.639 (29.169) Remain 57:01:58 loss: 0.3151 loss_seg: 0.2131 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:29:54,014 INFO misc.py line 117 726] Train: [7/20][102/510] Data 2.550 (3.968) Batch 23.101 (29.107) Remain 56:54:17 loss: 0.2296 loss_seg: 0.1346 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:30:20,525 INFO misc.py line 117 726] Train: [7/20][103/510] Data 2.623 (3.954) Batch 26.511 (29.081) Remain 56:50:45 loss: 0.2252 loss_seg: 0.1308 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:30:50,041 INFO misc.py line 117 726] Train: [7/20][104/510] Data 3.559 (3.950) Batch 29.516 (29.086) Remain 56:50:47 loss: 0.2875 loss_seg: 0.1846 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:31:20,800 INFO misc.py line 117 726] Train: [7/20][105/510] Data 8.770 (3.998) Batch 30.758 (29.102) Remain 56:52:13 loss: 0.3452 loss_seg: 0.2344 loss_superpoint_edge: 0.0430 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:31:59,188 INFO misc.py line 117 726] Train: [7/20][106/510] Data 6.999 (4.027) Batch 38.389 (29.192) Remain 57:02:18 loss: 0.2326 loss_seg: 0.1396 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:32:28,742 INFO misc.py line 117 726] Train: [7/20][107/510] Data 4.599 (4.032) Batch 29.553 (29.196) Remain 57:02:13 loss: 0.1926 loss_seg: 0.1033 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:33:01,422 INFO misc.py line 117 726] Train: [7/20][108/510] Data 3.650 (4.029) Batch 32.681 (29.229) Remain 57:05:37 loss: 0.2378 loss_seg: 0.1447 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:33:40,051 INFO misc.py line 117 726] Train: [7/20][109/510] Data 4.635 (4.034) Batch 38.629 (29.318) Remain 57:15:32 loss: 0.3240 loss_seg: 0.2221 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:34:09,117 INFO misc.py line 117 726] Train: [7/20][110/510] Data 2.948 (4.024) Batch 29.066 (29.315) Remain 57:14:46 loss: 0.2919 loss_seg: 0.1900 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:34:34,153 INFO misc.py line 117 726] Train: [7/20][111/510] Data 2.574 (4.011) Batch 25.036 (29.276) Remain 57:09:38 loss: 0.2731 loss_seg: 0.1689 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:34:53,913 INFO misc.py line 117 726] Train: [7/20][112/510] Data 2.208 (3.994) Batch 19.760 (29.188) Remain 56:58:55 loss: 0.2116 loss_seg: 0.1205 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:35:31,687 INFO misc.py line 117 726] Train: [7/20][113/510] Data 6.515 (4.017) Batch 37.775 (29.266) Remain 57:07:35 loss: 0.2067 loss_seg: 0.1183 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:35:55,990 INFO misc.py line 117 726] Train: [7/20][114/510] Data 2.678 (4.005) Batch 24.303 (29.222) Remain 57:01:51 loss: 0.2767 loss_seg: 0.1720 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:36:20,244 INFO misc.py line 117 726] Train: [7/20][115/510] Data 3.263 (3.999) Batch 24.254 (29.177) Remain 56:56:10 loss: 0.2684 loss_seg: 0.1631 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:36:56,239 INFO misc.py line 117 726] Train: [7/20][116/510] Data 5.544 (4.012) Batch 35.995 (29.238) Remain 57:02:45 loss: 0.2823 loss_seg: 0.1775 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:37:21,476 INFO misc.py line 117 726] Train: [7/20][117/510] Data 2.660 (4.000) Batch 25.237 (29.203) Remain 56:58:09 loss: 0.2957 loss_seg: 0.1893 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:37:36,816 INFO misc.py line 117 726] Train: [7/20][118/510] Data 1.775 (3.981) Batch 15.340 (29.082) Remain 56:43:33 loss: 0.3828 loss_seg: 0.2640 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:38:04,683 INFO misc.py line 117 726] Train: [7/20][119/510] Data 3.460 (3.977) Batch 27.868 (29.072) Remain 56:41:51 loss: 0.2298 loss_seg: 0.1391 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:38:29,132 INFO misc.py line 117 726] Train: [7/20][120/510] Data 2.547 (3.964) Batch 24.449 (29.032) Remain 56:36:44 loss: 0.2399 loss_seg: 0.1491 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:38:44,138 INFO misc.py line 117 726] Train: [7/20][121/510] Data 1.142 (3.940) Batch 15.006 (28.913) Remain 56:22:21 loss: 0.2604 loss_seg: 0.1558 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:39:13,819 INFO misc.py line 117 726] Train: [7/20][122/510] Data 4.698 (3.947) Batch 29.681 (28.920) Remain 56:22:37 loss: 0.2753 loss_seg: 0.1825 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:39:46,213 INFO misc.py line 117 726] Train: [7/20][123/510] Data 4.036 (3.947) Batch 32.394 (28.949) Remain 56:25:32 loss: 0.2704 loss_seg: 0.1737 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:40:10,665 INFO misc.py line 117 726] Train: [7/20][124/510] Data 2.584 (3.936) Batch 24.452 (28.911) Remain 56:20:42 loss: 0.2170 loss_seg: 0.1241 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:40:42,842 INFO misc.py line 117 726] Train: [7/20][125/510] Data 5.141 (3.946) Batch 32.177 (28.938) Remain 56:23:21 loss: 0.2594 loss_seg: 0.1615 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:41:05,283 INFO misc.py line 117 726] Train: [7/20][126/510] Data 3.176 (3.940) Batch 22.441 (28.885) Remain 56:16:41 loss: 0.2971 loss_seg: 0.1982 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:41:37,470 INFO misc.py line 117 726] Train: [7/20][127/510] Data 3.204 (3.934) Batch 32.187 (28.912) Remain 56:19:19 loss: 0.1902 loss_seg: 0.1055 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:41:57,752 INFO misc.py line 117 726] Train: [7/20][128/510] Data 2.072 (3.919) Batch 20.282 (28.843) Remain 56:10:46 loss: 0.2192 loss_seg: 0.1283 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:42:27,920 INFO misc.py line 117 726] Train: [7/20][129/510] Data 3.677 (3.917) Batch 30.168 (28.853) Remain 56:11:31 loss: 0.2183 loss_seg: 0.1238 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:43:05,778 INFO misc.py line 117 726] Train: [7/20][130/510] Data 7.992 (3.949) Batch 37.858 (28.924) Remain 56:19:19 loss: 0.1908 loss_seg: 0.1067 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:43:37,043 INFO misc.py line 117 726] Train: [7/20][131/510] Data 4.737 (3.955) Batch 31.265 (28.943) Remain 56:20:59 loss: 0.2307 loss_seg: 0.1363 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:44:04,396 INFO misc.py line 117 726] Train: [7/20][132/510] Data 3.718 (3.953) Batch 27.353 (28.930) Remain 56:19:03 loss: 0.2619 loss_seg: 0.1610 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:44:28,533 INFO misc.py line 117 726] Train: [7/20][133/510] Data 3.080 (3.947) Batch 24.137 (28.893) Remain 56:14:16 loss: 0.1777 loss_seg: 0.0926 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:44:54,562 INFO misc.py line 117 726] Train: [7/20][134/510] Data 3.277 (3.942) Batch 26.029 (28.872) Remain 56:11:14 loss: 0.2292 loss_seg: 0.1356 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:45:30,160 INFO misc.py line 117 726] Train: [7/20][135/510] Data 3.598 (3.939) Batch 35.598 (28.923) Remain 56:16:42 loss: 0.2640 loss_seg: 0.1750 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:45:56,493 INFO misc.py line 117 726] Train: [7/20][136/510] Data 2.044 (3.925) Batch 26.332 (28.903) Remain 56:13:57 loss: 0.2689 loss_seg: 0.1727 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:46:15,676 INFO misc.py line 117 726] Train: [7/20][137/510] Data 2.416 (3.914) Batch 19.184 (28.831) Remain 56:05:00 loss: 0.2699 loss_seg: 0.1704 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:46:50,117 INFO misc.py line 117 726] Train: [7/20][138/510] Data 6.115 (3.930) Batch 34.440 (28.872) Remain 56:09:22 loss: 0.2094 loss_seg: 0.1205 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:47:20,953 INFO misc.py line 117 726] Train: [7/20][139/510] Data 2.870 (3.922) Batch 30.837 (28.887) Remain 56:10:34 loss: 0.4076 loss_seg: 0.3002 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:47:49,988 INFO misc.py line 117 726] Train: [7/20][140/510] Data 7.819 (3.951) Batch 29.034 (28.888) Remain 56:10:13 loss: 0.2057 loss_seg: 0.1142 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:48:19,353 INFO misc.py line 117 726] Train: [7/20][141/510] Data 6.504 (3.969) Batch 29.365 (28.891) Remain 56:10:08 loss: 0.2893 loss_seg: 0.1858 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:48:42,793 INFO misc.py line 117 726] Train: [7/20][142/510] Data 2.798 (3.961) Batch 23.439 (28.852) Remain 56:05:05 loss: 0.2389 loss_seg: 0.1465 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:49:17,541 INFO misc.py line 117 726] Train: [7/20][143/510] Data 5.590 (3.972) Batch 34.748 (28.894) Remain 56:09:31 loss: 0.3958 loss_seg: 0.2892 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:49:48,185 INFO misc.py line 117 726] Train: [7/20][144/510] Data 3.487 (3.969) Batch 30.644 (28.906) Remain 56:10:29 loss: 0.1887 loss_seg: 0.1021 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:50:06,011 INFO misc.py line 117 726] Train: [7/20][145/510] Data 1.778 (3.953) Batch 17.826 (28.828) Remain 56:00:54 loss: 0.1797 loss_seg: 0.0923 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:50:35,350 INFO misc.py line 117 726] Train: [7/20][146/510] Data 3.151 (3.948) Batch 29.338 (28.832) Remain 56:00:50 loss: 0.1958 loss_seg: 0.1126 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:50:55,712 INFO misc.py line 117 726] Train: [7/20][147/510] Data 2.275 (3.936) Batch 20.363 (28.773) Remain 55:53:30 loss: 0.2448 loss_seg: 0.1480 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:51:17,832 INFO misc.py line 117 726] Train: [7/20][148/510] Data 2.895 (3.929) Batch 22.120 (28.727) Remain 55:47:40 loss: 0.2050 loss_seg: 0.1143 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:51:46,674 INFO misc.py line 117 726] Train: [7/20][149/510] Data 3.024 (3.923) Batch 28.841 (28.728) Remain 55:47:17 loss: 0.2311 loss_seg: 0.1307 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:52:02,042 INFO misc.py line 117 726] Train: [7/20][150/510] Data 1.514 (3.906) Batch 15.368 (28.637) Remain 55:36:13 loss: 0.2553 loss_seg: 0.1588 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:52:02,043 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 16:52:38,344 INFO misc.py line 117 726] Train: [7/20][151/510] Data 7.912 (3.933) Batch 36.302 (28.689) Remain 55:41:46 loss: 0.2500 loss_seg: 0.1533 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:53:09,061 INFO misc.py line 117 726] Train: [7/20][152/510] Data 4.353 (3.936) Batch 30.718 (28.703) Remain 55:42:53 loss: 0.2941 loss_seg: 0.1925 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:53:32,488 INFO misc.py line 117 726] Train: [7/20][153/510] Data 2.797 (3.929) Batch 23.426 (28.667) Remain 55:38:18 loss: 0.2357 loss_seg: 0.1397 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:53:49,947 INFO misc.py line 117 726] Train: [7/20][154/510] Data 1.793 (3.915) Batch 17.460 (28.593) Remain 55:29:11 loss: 0.2610 loss_seg: 0.1712 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:54:12,849 INFO misc.py line 117 726] Train: [7/20][155/510] Data 2.682 (3.906) Batch 22.902 (28.556) Remain 55:24:21 loss: 0.2152 loss_seg: 0.1197 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:54:39,196 INFO misc.py line 117 726] Train: [7/20][156/510] Data 3.197 (3.902) Batch 26.347 (28.541) Remain 55:22:12 loss: 0.2065 loss_seg: 0.1184 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:55:06,927 INFO misc.py line 117 726] Train: [7/20][157/510] Data 5.007 (3.909) Batch 27.731 (28.536) Remain 55:21:06 loss: 0.2251 loss_seg: 0.1349 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:55:28,011 INFO misc.py line 117 726] Train: [7/20][158/510] Data 2.461 (3.900) Batch 21.084 (28.488) Remain 55:15:02 loss: 0.2260 loss_seg: 0.1302 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:56:02,222 INFO misc.py line 117 726] Train: [7/20][159/510] Data 5.225 (3.908) Batch 34.211 (28.525) Remain 55:18:50 loss: 0.2300 loss_seg: 0.1393 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:56:35,063 INFO misc.py line 117 726] Train: [7/20][160/510] Data 5.535 (3.918) Batch 32.841 (28.552) Remain 55:21:33 loss: 0.2236 loss_seg: 0.1296 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:57:01,506 INFO misc.py line 117 726] Train: [7/20][161/510] Data 3.202 (3.914) Batch 26.442 (28.539) Remain 55:19:31 loss: 0.2423 loss_seg: 0.1425 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:57:33,516 INFO misc.py line 117 726] Train: [7/20][162/510] Data 3.693 (3.913) Batch 32.010 (28.561) Remain 55:21:35 loss: 0.3193 loss_seg: 0.2116 loss_superpoint_edge: 0.0429 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:58:05,219 INFO misc.py line 117 726] Train: [7/20][163/510] Data 3.637 (3.911) Batch 31.704 (28.580) Remain 55:23:24 loss: 0.2276 loss_seg: 0.1321 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:58:26,566 INFO misc.py line 117 726] Train: [7/20][164/510] Data 3.036 (3.905) Batch 21.346 (28.535) Remain 55:17:42 loss: 0.2579 loss_seg: 0.1648 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:58:53,722 INFO misc.py line 117 726] Train: [7/20][165/510] Data 4.038 (3.906) Batch 27.157 (28.527) Remain 55:16:14 loss: 0.2491 loss_seg: 0.1529 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:59:27,694 INFO misc.py line 117 726] Train: [7/20][166/510] Data 4.606 (3.910) Batch 33.971 (28.560) Remain 55:19:38 loss: 0.2112 loss_seg: 0.1215 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 16:59:47,697 INFO misc.py line 117 726] Train: [7/20][167/510] Data 2.613 (3.903) Batch 20.003 (28.508) Remain 55:13:06 loss: 0.2424 loss_seg: 0.1426 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:00:18,955 INFO misc.py line 117 726] Train: [7/20][168/510] Data 4.444 (3.906) Batch 31.258 (28.525) Remain 55:14:34 loss: 0.2593 loss_seg: 0.1592 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:00:52,945 INFO misc.py line 117 726] Train: [7/20][169/510] Data 5.409 (3.915) Batch 33.990 (28.558) Remain 55:17:55 loss: 0.2380 loss_seg: 0.1438 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:01:21,931 INFO misc.py line 117 726] Train: [7/20][170/510] Data 3.396 (3.912) Batch 28.986 (28.560) Remain 55:17:44 loss: 0.3296 loss_seg: 0.2340 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:01:41,543 INFO misc.py line 117 726] Train: [7/20][171/510] Data 2.391 (3.903) Batch 19.611 (28.507) Remain 55:11:04 loss: 0.1890 loss_seg: 0.0982 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:02:12,666 INFO misc.py line 117 726] Train: [7/20][172/510] Data 3.220 (3.899) Batch 31.123 (28.522) Remain 55:12:23 loss: 0.2145 loss_seg: 0.1246 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:02:34,530 INFO misc.py line 117 726] Train: [7/20][173/510] Data 2.720 (3.892) Batch 21.865 (28.483) Remain 55:07:22 loss: 0.1902 loss_seg: 0.1031 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:02:59,604 INFO misc.py line 117 726] Train: [7/20][174/510] Data 3.487 (3.889) Batch 25.074 (28.463) Remain 55:04:35 loss: 0.3440 loss_seg: 0.2301 loss_superpoint_edge: 0.0455 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:03:30,354 INFO misc.py line 117 726] Train: [7/20][175/510] Data 7.148 (3.908) Batch 30.750 (28.477) Remain 55:05:39 loss: 0.3475 loss_seg: 0.2394 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:03:46,625 INFO misc.py line 117 726] Train: [7/20][176/510] Data 1.745 (3.896) Batch 16.270 (28.406) Remain 54:56:59 loss: 0.2330 loss_seg: 0.1424 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:04:25,878 INFO misc.py line 117 726] Train: [7/20][177/510] Data 10.758 (3.935) Batch 39.254 (28.468) Remain 55:03:45 loss: 0.3225 loss_seg: 0.2173 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0437 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:05:00,970 INFO misc.py line 117 726] Train: [7/20][178/510] Data 4.282 (3.937) Batch 35.091 (28.506) Remain 55:07:40 loss: 0.1800 loss_seg: 0.0947 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:05:30,054 INFO misc.py line 117 726] Train: [7/20][179/510] Data 3.413 (3.934) Batch 29.084 (28.509) Remain 55:07:34 loss: 0.2261 loss_seg: 0.1305 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:06:05,409 INFO misc.py line 117 726] Train: [7/20][180/510] Data 5.184 (3.941) Batch 35.355 (28.548) Remain 55:11:35 loss: 0.2144 loss_seg: 0.1252 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:06:34,642 INFO misc.py line 117 726] Train: [7/20][181/510] Data 4.581 (3.945) Batch 29.233 (28.552) Remain 55:11:33 loss: 0.2548 loss_seg: 0.1532 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:06:56,808 INFO misc.py line 117 726] Train: [7/20][182/510] Data 2.313 (3.936) Batch 22.167 (28.516) Remain 55:06:56 loss: 0.2291 loss_seg: 0.1306 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:07:34,965 INFO misc.py line 117 726] Train: [7/20][183/510] Data 5.664 (3.945) Batch 38.157 (28.570) Remain 55:12:40 loss: 0.2710 loss_seg: 0.1689 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:07:57,888 INFO misc.py line 117 726] Train: [7/20][184/510] Data 3.491 (3.943) Batch 22.923 (28.539) Remain 55:08:35 loss: 0.2534 loss_seg: 0.1604 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:08:28,573 INFO misc.py line 117 726] Train: [7/20][185/510] Data 3.581 (3.941) Batch 30.686 (28.550) Remain 55:09:28 loss: 0.2106 loss_seg: 0.1203 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:08:48,482 INFO misc.py line 117 726] Train: [7/20][186/510] Data 1.910 (3.930) Batch 19.909 (28.503) Remain 55:03:31 loss: 0.2696 loss_seg: 0.1748 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:09:24,018 INFO misc.py line 117 726] Train: [7/20][187/510] Data 4.708 (3.934) Batch 35.535 (28.541) Remain 55:07:28 loss: 0.2453 loss_seg: 0.1524 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:09:52,050 INFO misc.py line 117 726] Train: [7/20][188/510] Data 2.574 (3.927) Batch 28.032 (28.539) Remain 55:06:41 loss: 0.1951 loss_seg: 0.1051 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:10:21,144 INFO misc.py line 117 726] Train: [7/20][189/510] Data 5.148 (3.933) Batch 29.094 (28.542) Remain 55:06:33 loss: 0.2854 loss_seg: 0.1817 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:10:49,552 INFO misc.py line 117 726] Train: [7/20][190/510] Data 3.432 (3.931) Batch 28.407 (28.541) Remain 55:06:00 loss: 0.2288 loss_seg: 0.1342 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:11:06,964 INFO misc.py line 117 726] Train: [7/20][191/510] Data 2.002 (3.920) Batch 17.413 (28.482) Remain 54:58:40 loss: 0.3287 loss_seg: 0.2154 loss_superpoint_edge: 0.0433 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:11:37,441 INFO misc.py line 117 726] Train: [7/20][192/510] Data 3.249 (3.917) Batch 30.477 (28.492) Remain 54:59:24 loss: 0.3349 loss_seg: 0.2242 loss_superpoint_edge: 0.0431 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:12:05,653 INFO misc.py line 117 726] Train: [7/20][193/510] Data 3.434 (3.914) Batch 28.212 (28.491) Remain 54:58:46 loss: 0.2605 loss_seg: 0.1612 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:12:32,093 INFO misc.py line 117 726] Train: [7/20][194/510] Data 2.668 (3.908) Batch 26.440 (28.480) Remain 54:57:03 loss: 0.2791 loss_seg: 0.1832 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:13:04,745 INFO misc.py line 117 726] Train: [7/20][195/510] Data 3.280 (3.904) Batch 32.652 (28.502) Remain 54:59:05 loss: 0.2505 loss_seg: 0.1515 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:13:43,660 INFO misc.py line 117 726] Train: [7/20][196/510] Data 5.915 (3.915) Batch 38.915 (28.556) Remain 55:04:51 loss: 0.3125 loss_seg: 0.2144 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:14:06,967 INFO misc.py line 117 726] Train: [7/20][197/510] Data 2.640 (3.908) Batch 23.306 (28.529) Remain 55:01:15 loss: 0.2115 loss_seg: 0.1182 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:14:33,314 INFO misc.py line 117 726] Train: [7/20][198/510] Data 2.558 (3.901) Batch 26.347 (28.518) Remain 54:59:29 loss: 0.3432 loss_seg: 0.2432 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:15:10,396 INFO misc.py line 117 726] Train: [7/20][199/510] Data 8.159 (3.923) Batch 37.082 (28.561) Remain 55:04:03 loss: 0.5110 loss_seg: 0.4041 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:15:35,920 INFO misc.py line 117 726] Train: [7/20][200/510] Data 2.824 (3.918) Batch 25.524 (28.546) Remain 55:01:48 loss: 0.1979 loss_seg: 0.1068 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:15:35,920 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 17:16:05,564 INFO misc.py line 117 726] Train: [7/20][201/510] Data 4.691 (3.921) Batch 29.645 (28.551) Remain 55:01:58 loss: 0.3099 loss_seg: 0.2042 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:16:39,875 INFO misc.py line 117 726] Train: [7/20][202/510] Data 4.217 (3.923) Batch 34.310 (28.580) Remain 55:04:50 loss: 0.1969 loss_seg: 0.1060 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:17:10,718 INFO misc.py line 117 726] Train: [7/20][203/510] Data 3.807 (3.922) Batch 30.843 (28.592) Remain 55:05:40 loss: 0.2203 loss_seg: 0.1285 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:17:39,204 INFO misc.py line 117 726] Train: [7/20][204/510] Data 4.352 (3.924) Batch 28.486 (28.591) Remain 55:05:08 loss: 0.2092 loss_seg: 0.1192 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:18:00,973 INFO misc.py line 117 726] Train: [7/20][205/510] Data 2.160 (3.916) Batch 21.770 (28.557) Remain 55:00:45 loss: 0.2695 loss_seg: 0.1775 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:18:28,094 INFO misc.py line 117 726] Train: [7/20][206/510] Data 3.027 (3.911) Batch 27.121 (28.550) Remain 54:59:27 loss: 0.1928 loss_seg: 0.1043 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:18:54,192 INFO misc.py line 117 726] Train: [7/20][207/510] Data 2.584 (3.905) Batch 26.098 (28.538) Remain 54:57:35 loss: 0.2373 loss_seg: 0.1466 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:19:16,740 INFO misc.py line 117 726] Train: [7/20][208/510] Data 3.222 (3.902) Batch 22.547 (28.509) Remain 54:53:44 loss: 0.2731 loss_seg: 0.1734 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:19:40,069 INFO misc.py line 117 726] Train: [7/20][209/510] Data 2.329 (3.894) Batch 23.329 (28.484) Remain 54:50:21 loss: 0.2491 loss_seg: 0.1555 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:20:00,277 INFO misc.py line 117 726] Train: [7/20][210/510] Data 2.499 (3.887) Batch 20.209 (28.444) Remain 54:45:16 loss: 0.2974 loss_seg: 0.1968 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:20:29,596 INFO misc.py line 117 726] Train: [7/20][211/510] Data 3.110 (3.883) Batch 29.318 (28.448) Remain 54:45:17 loss: 0.2377 loss_seg: 0.1467 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:20:58,031 INFO misc.py line 117 726] Train: [7/20][212/510] Data 2.776 (3.878) Batch 28.436 (28.448) Remain 54:44:48 loss: 0.3006 loss_seg: 0.1885 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:21:21,584 INFO misc.py line 117 726] Train: [7/20][213/510] Data 2.974 (3.874) Batch 23.552 (28.425) Remain 54:41:38 loss: 0.2187 loss_seg: 0.1288 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:22:01,493 INFO misc.py line 117 726] Train: [7/20][214/510] Data 5.320 (3.881) Batch 39.909 (28.479) Remain 54:47:26 loss: 0.2399 loss_seg: 0.1444 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:22:17,932 INFO misc.py line 117 726] Train: [7/20][215/510] Data 2.205 (3.873) Batch 16.439 (28.422) Remain 54:40:25 loss: 0.2199 loss_seg: 0.1236 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:22:40,188 INFO misc.py line 117 726] Train: [7/20][216/510] Data 2.917 (3.868) Batch 22.255 (28.393) Remain 54:36:36 loss: 0.2999 loss_seg: 0.2061 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:23:02,821 INFO misc.py line 117 726] Train: [7/20][217/510] Data 3.197 (3.865) Batch 22.634 (28.367) Remain 54:33:01 loss: 0.2572 loss_seg: 0.1608 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:23:35,352 INFO misc.py line 117 726] Train: [7/20][218/510] Data 8.055 (3.885) Batch 32.531 (28.386) Remain 54:34:47 loss: 0.2324 loss_seg: 0.1392 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:23:55,284 INFO misc.py line 117 726] Train: [7/20][219/510] Data 2.431 (3.878) Batch 19.932 (28.347) Remain 54:29:47 loss: 0.1940 loss_seg: 0.1068 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:24:17,811 INFO misc.py line 117 726] Train: [7/20][220/510] Data 2.739 (3.873) Batch 22.527 (28.320) Remain 54:26:14 loss: 0.3014 loss_seg: 0.2065 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:24:43,013 INFO misc.py line 117 726] Train: [7/20][221/510] Data 1.918 (3.864) Batch 25.203 (28.306) Remain 54:24:06 loss: 0.2170 loss_seg: 0.1272 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:25:05,632 INFO misc.py line 117 726] Train: [7/20][222/510] Data 2.081 (3.856) Batch 22.619 (28.280) Remain 54:20:38 loss: 0.1845 loss_seg: 0.0957 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:25:36,673 INFO misc.py line 117 726] Train: [7/20][223/510] Data 4.171 (3.857) Batch 31.040 (28.292) Remain 54:21:37 loss: 0.1994 loss_seg: 0.1114 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:26:08,775 INFO misc.py line 117 726] Train: [7/20][224/510] Data 4.103 (3.858) Batch 32.102 (28.309) Remain 54:23:08 loss: 0.3079 loss_seg: 0.2008 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:26:38,249 INFO misc.py line 117 726] Train: [7/20][225/510] Data 6.036 (3.868) Batch 29.474 (28.315) Remain 54:23:16 loss: 0.2021 loss_seg: 0.1147 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:27:11,168 INFO misc.py line 117 726] Train: [7/20][226/510] Data 4.732 (3.872) Batch 32.919 (28.335) Remain 54:25:10 loss: 0.2574 loss_seg: 0.1571 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:27:29,812 INFO misc.py line 117 726] Train: [7/20][227/510] Data 1.917 (3.863) Batch 18.644 (28.292) Remain 54:19:43 loss: 0.2393 loss_seg: 0.1492 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:28:05,390 INFO misc.py line 117 726] Train: [7/20][228/510] Data 5.113 (3.869) Batch 35.578 (28.324) Remain 54:22:58 loss: 0.3221 loss_seg: 0.2211 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:28:38,644 INFO misc.py line 117 726] Train: [7/20][229/510] Data 3.416 (3.867) Batch 33.254 (28.346) Remain 54:25:01 loss: 0.1878 loss_seg: 0.0998 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:29:09,325 INFO misc.py line 117 726] Train: [7/20][230/510] Data 3.929 (3.867) Batch 30.681 (28.357) Remain 54:25:43 loss: 0.2315 loss_seg: 0.1395 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:29:39,114 INFO misc.py line 117 726] Train: [7/20][231/510] Data 3.353 (3.865) Batch 29.789 (28.363) Remain 54:25:58 loss: 0.2435 loss_seg: 0.1462 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:30:05,525 INFO misc.py line 117 726] Train: [7/20][232/510] Data 2.841 (3.860) Batch 26.411 (28.354) Remain 54:24:31 loss: 0.1828 loss_seg: 0.0987 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:30:38,363 INFO misc.py line 117 726] Train: [7/20][233/510] Data 3.328 (3.858) Batch 32.838 (28.374) Remain 54:26:17 loss: 0.1957 loss_seg: 0.1093 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:30:55,922 INFO misc.py line 117 726] Train: [7/20][234/510] Data 2.406 (3.852) Batch 17.559 (28.327) Remain 54:20:26 loss: 0.3846 loss_seg: 0.2852 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:31:23,627 INFO misc.py line 117 726] Train: [7/20][235/510] Data 4.060 (3.852) Batch 27.705 (28.324) Remain 54:19:39 loss: 0.2996 loss_seg: 0.1923 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:31:54,638 INFO misc.py line 117 726] Train: [7/20][236/510] Data 6.319 (3.863) Batch 31.011 (28.336) Remain 54:20:30 loss: 0.3703 loss_seg: 0.2709 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:32:25,661 INFO misc.py line 117 726] Train: [7/20][237/510] Data 3.847 (3.863) Batch 31.023 (28.347) Remain 54:21:21 loss: 0.1926 loss_seg: 0.1062 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:32:47,054 INFO misc.py line 117 726] Train: [7/20][238/510] Data 2.581 (3.857) Batch 21.393 (28.318) Remain 54:17:29 loss: 0.2987 loss_seg: 0.1969 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:33:16,715 INFO misc.py line 117 726] Train: [7/20][239/510] Data 4.743 (3.861) Batch 29.662 (28.323) Remain 54:17:40 loss: 0.2510 loss_seg: 0.1528 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:33:48,216 INFO misc.py line 117 726] Train: [7/20][240/510] Data 3.672 (3.860) Batch 31.500 (28.337) Remain 54:18:44 loss: 0.2282 loss_seg: 0.1343 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:34:17,954 INFO misc.py line 117 726] Train: [7/20][241/510] Data 3.851 (3.860) Batch 29.739 (28.343) Remain 54:18:56 loss: 0.2838 loss_seg: 0.1756 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:34:48,634 INFO misc.py line 117 726] Train: [7/20][242/510] Data 3.686 (3.860) Batch 30.679 (28.353) Remain 54:19:35 loss: 0.2028 loss_seg: 0.1126 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:35:22,645 INFO misc.py line 117 726] Train: [7/20][243/510] Data 4.998 (3.864) Batch 34.011 (28.376) Remain 54:21:49 loss: 0.3118 loss_seg: 0.1980 loss_superpoint_edge: 0.0456 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:35:45,415 INFO misc.py line 117 726] Train: [7/20][244/510] Data 2.853 (3.860) Batch 22.770 (28.353) Remain 54:18:41 loss: 0.3197 loss_seg: 0.2171 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:36:10,224 INFO misc.py line 117 726] Train: [7/20][245/510] Data 2.999 (3.857) Batch 24.809 (28.338) Remain 54:16:31 loss: 0.2305 loss_seg: 0.1352 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:36:37,866 INFO misc.py line 117 726] Train: [7/20][246/510] Data 3.449 (3.855) Batch 27.642 (28.335) Remain 54:15:43 loss: 0.2535 loss_seg: 0.1561 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:37:11,915 INFO misc.py line 117 726] Train: [7/20][247/510] Data 4.332 (3.857) Batch 34.049 (28.359) Remain 54:17:56 loss: 0.2064 loss_seg: 0.1163 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:37:38,753 INFO misc.py line 117 726] Train: [7/20][248/510] Data 5.852 (3.865) Batch 26.838 (28.353) Remain 54:16:45 loss: 0.3374 loss_seg: 0.2332 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:38:03,333 INFO misc.py line 117 726] Train: [7/20][249/510] Data 5.018 (3.870) Batch 24.580 (28.337) Remain 54:14:31 loss: 0.2060 loss_seg: 0.1143 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:38:30,319 INFO misc.py line 117 726] Train: [7/20][250/510] Data 3.118 (3.867) Batch 26.986 (28.332) Remain 54:13:25 loss: 0.2488 loss_seg: 0.1510 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:38:30,319 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 17:39:05,835 INFO misc.py line 117 726] Train: [7/20][251/510] Data 6.144 (3.876) Batch 35.516 (28.361) Remain 54:16:16 loss: 0.2157 loss_seg: 0.1257 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:39:30,994 INFO misc.py line 117 726] Train: [7/20][252/510] Data 2.921 (3.872) Batch 25.159 (28.348) Remain 54:14:19 loss: 0.2183 loss_seg: 0.1258 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:40:08,003 INFO misc.py line 117 726] Train: [7/20][253/510] Data 5.781 (3.880) Batch 37.009 (28.382) Remain 54:17:50 loss: 0.2544 loss_seg: 0.1601 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:40:37,629 INFO misc.py line 117 726] Train: [7/20][254/510] Data 3.380 (3.878) Batch 29.626 (28.387) Remain 54:17:55 loss: 0.2196 loss_seg: 0.1257 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:41:09,482 INFO misc.py line 117 726] Train: [7/20][255/510] Data 5.959 (3.886) Batch 31.853 (28.401) Remain 54:19:02 loss: 0.2880 loss_seg: 0.1866 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:41:32,913 INFO misc.py line 117 726] Train: [7/20][256/510] Data 2.749 (3.881) Batch 23.431 (28.382) Remain 54:16:18 loss: 0.2186 loss_seg: 0.1255 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:41:54,099 INFO misc.py line 117 726] Train: [7/20][257/510] Data 2.754 (3.877) Batch 21.186 (28.353) Remain 54:12:35 loss: 0.2321 loss_seg: 0.1384 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:42:16,672 INFO misc.py line 117 726] Train: [7/20][258/510] Data 2.505 (3.872) Batch 22.573 (28.331) Remain 54:09:30 loss: 0.2770 loss_seg: 0.1729 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:42:42,160 INFO misc.py line 117 726] Train: [7/20][259/510] Data 2.995 (3.868) Batch 25.488 (28.319) Remain 54:07:46 loss: 0.4085 loss_seg: 0.2939 loss_superpoint_edge: 0.0479 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:43:05,082 INFO misc.py line 117 726] Train: [7/20][260/510] Data 3.713 (3.868) Batch 22.922 (28.298) Remain 54:04:53 loss: 0.2648 loss_seg: 0.1663 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:43:20,686 INFO misc.py line 117 726] Train: [7/20][261/510] Data 2.362 (3.862) Batch 15.604 (28.249) Remain 53:58:46 loss: 0.3415 loss_seg: 0.2316 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:43:51,946 INFO misc.py line 117 726] Train: [7/20][262/510] Data 4.077 (3.863) Batch 31.260 (28.261) Remain 53:59:38 loss: 0.3197 loss_seg: 0.2262 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:44:23,169 INFO misc.py line 117 726] Train: [7/20][263/510] Data 4.544 (3.865) Batch 31.223 (28.272) Remain 54:00:28 loss: 0.2736 loss_seg: 0.1725 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:44:54,516 INFO misc.py line 117 726] Train: [7/20][264/510] Data 5.427 (3.871) Batch 31.347 (28.284) Remain 54:01:20 loss: 0.3511 loss_seg: 0.2520 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:45:22,664 INFO misc.py line 117 726] Train: [7/20][265/510] Data 4.271 (3.873) Batch 28.149 (28.284) Remain 54:00:49 loss: 0.2881 loss_seg: 0.1852 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:45:48,452 INFO misc.py line 117 726] Train: [7/20][266/510] Data 3.117 (3.870) Batch 25.787 (28.274) Remain 53:59:15 loss: 0.2291 loss_seg: 0.1337 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:46:16,752 INFO misc.py line 117 726] Train: [7/20][267/510] Data 4.816 (3.873) Batch 28.300 (28.274) Remain 53:58:48 loss: 0.2699 loss_seg: 0.1716 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:46:52,647 INFO misc.py line 117 726] Train: [7/20][268/510] Data 5.308 (3.879) Batch 35.895 (28.303) Remain 54:01:37 loss: 0.2379 loss_seg: 0.1429 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:47:27,915 INFO misc.py line 117 726] Train: [7/20][269/510] Data 4.022 (3.879) Batch 35.268 (28.329) Remain 54:04:09 loss: 0.2619 loss_seg: 0.1619 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:48:02,225 INFO misc.py line 117 726] Train: [7/20][270/510] Data 4.099 (3.880) Batch 34.310 (28.351) Remain 54:06:14 loss: 0.2921 loss_seg: 0.2004 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:48:20,238 INFO misc.py line 117 726] Train: [7/20][271/510] Data 1.865 (3.873) Batch 18.014 (28.313) Remain 54:01:21 loss: 0.2448 loss_seg: 0.1487 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:48:49,501 INFO misc.py line 117 726] Train: [7/20][272/510] Data 3.014 (3.870) Batch 29.263 (28.316) Remain 54:01:17 loss: 0.2412 loss_seg: 0.1481 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:49:18,122 INFO misc.py line 117 726] Train: [7/20][273/510] Data 5.209 (3.874) Batch 28.621 (28.318) Remain 54:00:56 loss: 0.2290 loss_seg: 0.1274 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0445 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:49:47,139 INFO misc.py line 117 726] Train: [7/20][274/510] Data 2.838 (3.871) Batch 29.017 (28.320) Remain 54:00:46 loss: 0.2543 loss_seg: 0.1585 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:50:10,175 INFO misc.py line 117 726] Train: [7/20][275/510] Data 4.538 (3.873) Batch 23.036 (28.301) Remain 53:58:04 loss: 0.2119 loss_seg: 0.1218 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:50:46,007 INFO misc.py line 117 726] Train: [7/20][276/510] Data 10.296 (3.897) Batch 35.832 (28.328) Remain 54:00:45 loss: 0.2564 loss_seg: 0.1615 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:51:11,353 INFO misc.py line 117 726] Train: [7/20][277/510] Data 2.815 (3.893) Batch 25.346 (28.317) Remain 53:59:02 loss: 0.2356 loss_seg: 0.1429 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:51:34,335 INFO misc.py line 117 726] Train: [7/20][278/510] Data 3.232 (3.890) Batch 22.982 (28.298) Remain 53:56:20 loss: 0.3060 loss_seg: 0.2040 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:51:51,579 INFO misc.py line 117 726] Train: [7/20][279/510] Data 1.984 (3.883) Batch 17.244 (28.258) Remain 53:51:17 loss: 0.1966 loss_seg: 0.1053 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:52:25,788 INFO misc.py line 117 726] Train: [7/20][280/510] Data 3.853 (3.883) Batch 34.209 (28.279) Remain 53:53:16 loss: 0.1976 loss_seg: 0.1104 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:52:52,777 INFO misc.py line 117 726] Train: [7/20][281/510] Data 4.559 (3.886) Batch 26.989 (28.275) Remain 53:52:16 loss: 0.2464 loss_seg: 0.1459 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:53:21,780 INFO misc.py line 117 726] Train: [7/20][282/510] Data 4.597 (3.888) Batch 29.003 (28.277) Remain 53:52:06 loss: 0.2569 loss_seg: 0.1609 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:53:54,470 INFO misc.py line 117 726] Train: [7/20][283/510] Data 5.107 (3.893) Batch 32.690 (28.293) Remain 53:53:26 loss: 0.2238 loss_seg: 0.1317 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:54:29,014 INFO misc.py line 117 726] Train: [7/20][284/510] Data 4.581 (3.895) Batch 34.544 (28.315) Remain 53:55:30 loss: 0.2270 loss_seg: 0.1370 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:54:59,164 INFO misc.py line 117 726] Train: [7/20][285/510] Data 3.768 (3.895) Batch 30.150 (28.322) Remain 53:55:46 loss: 0.2321 loss_seg: 0.1432 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:55:28,210 INFO misc.py line 117 726] Train: [7/20][286/510] Data 4.627 (3.897) Batch 29.046 (28.324) Remain 53:55:35 loss: 0.2458 loss_seg: 0.1479 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:56:03,602 INFO misc.py line 117 726] Train: [7/20][287/510] Data 6.085 (3.905) Batch 35.391 (28.349) Remain 53:57:58 loss: 0.2785 loss_seg: 0.1855 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:56:29,497 INFO misc.py line 117 726] Train: [7/20][288/510] Data 3.428 (3.903) Batch 25.895 (28.341) Remain 53:56:30 loss: 0.2385 loss_seg: 0.1453 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:57:02,383 INFO misc.py line 117 726] Train: [7/20][289/510] Data 4.637 (3.906) Batch 32.887 (28.357) Remain 53:57:51 loss: 0.3546 loss_seg: 0.2333 loss_superpoint_edge: 0.0555 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:57:31,569 INFO misc.py line 117 726] Train: [7/20][290/510] Data 3.476 (3.904) Batch 29.185 (28.360) Remain 53:57:42 loss: 0.2834 loss_seg: 0.1781 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:58:01,554 INFO misc.py line 117 726] Train: [7/20][291/510] Data 3.357 (3.902) Batch 29.985 (28.365) Remain 53:57:53 loss: 0.1710 loss_seg: 0.0854 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:58:20,513 INFO misc.py line 117 726] Train: [7/20][292/510] Data 2.145 (3.896) Batch 18.958 (28.333) Remain 53:53:41 loss: 0.2412 loss_seg: 0.1461 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:58:53,074 INFO misc.py line 117 726] Train: [7/20][293/510] Data 4.681 (3.899) Batch 32.561 (28.347) Remain 53:54:53 loss: 0.2911 loss_seg: 0.1961 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:59:15,406 INFO misc.py line 117 726] Train: [7/20][294/510] Data 2.737 (3.895) Batch 22.333 (28.327) Remain 53:52:03 loss: 0.2201 loss_seg: 0.1326 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 17:59:41,117 INFO misc.py line 117 726] Train: [7/20][295/510] Data 2.849 (3.891) Batch 25.710 (28.318) Remain 53:50:33 loss: 0.3753 loss_seg: 0.2611 loss_superpoint_edge: 0.0442 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:00:06,167 INFO misc.py line 117 726] Train: [7/20][296/510] Data 2.187 (3.886) Batch 25.051 (28.306) Remain 53:48:49 loss: 0.3482 loss_seg: 0.2307 loss_superpoint_edge: 0.0500 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:00:42,016 INFO misc.py line 117 726] Train: [7/20][297/510] Data 8.923 (3.903) Batch 35.849 (28.332) Remain 53:51:16 loss: 0.2055 loss_seg: 0.1159 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:00:56,945 INFO misc.py line 117 726] Train: [7/20][298/510] Data 1.624 (3.895) Batch 14.929 (28.287) Remain 53:45:37 loss: 0.2698 loss_seg: 0.1694 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:01:28,702 INFO misc.py line 117 726] Train: [7/20][299/510] Data 3.256 (3.893) Batch 31.757 (28.298) Remain 53:46:29 loss: 0.2255 loss_seg: 0.1327 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:01:50,183 INFO misc.py line 117 726] Train: [7/20][300/510] Data 2.287 (3.887) Batch 21.481 (28.275) Remain 53:43:23 loss: 0.2841 loss_seg: 0.1760 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:01:50,183 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 18:02:10,598 INFO misc.py line 117 726] Train: [7/20][301/510] Data 4.013 (3.888) Batch 20.415 (28.249) Remain 53:39:55 loss: 0.1663 loss_seg: 0.0809 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:02:46,966 INFO misc.py line 117 726] Train: [7/20][302/510] Data 4.525 (3.890) Batch 36.367 (28.276) Remain 53:42:32 loss: 0.3060 loss_seg: 0.2131 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:03:09,295 INFO misc.py line 117 726] Train: [7/20][303/510] Data 2.445 (3.885) Batch 22.330 (28.256) Remain 53:39:48 loss: 0.2117 loss_seg: 0.1193 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:03:35,474 INFO misc.py line 117 726] Train: [7/20][304/510] Data 9.069 (3.902) Batch 26.179 (28.249) Remain 53:38:33 loss: 0.2742 loss_seg: 0.1751 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:04:07,532 INFO misc.py line 117 726] Train: [7/20][305/510] Data 6.150 (3.910) Batch 32.058 (28.262) Remain 53:39:31 loss: 0.2640 loss_seg: 0.1649 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:04:33,873 INFO misc.py line 117 726] Train: [7/20][306/510] Data 4.290 (3.911) Batch 26.341 (28.256) Remain 53:38:19 loss: 0.2768 loss_seg: 0.1789 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:04:52,295 INFO misc.py line 117 726] Train: [7/20][307/510] Data 2.295 (3.906) Batch 18.421 (28.223) Remain 53:34:10 loss: 0.3601 loss_seg: 0.2387 loss_superpoint_edge: 0.0533 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:05:28,486 INFO misc.py line 117 726] Train: [7/20][308/510] Data 4.313 (3.907) Batch 36.191 (28.250) Remain 53:36:40 loss: 0.3235 loss_seg: 0.2285 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:06:01,766 INFO misc.py line 117 726] Train: [7/20][309/510] Data 5.172 (3.911) Batch 33.281 (28.266) Remain 53:38:04 loss: 0.2476 loss_seg: 0.1471 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:06:35,041 INFO misc.py line 117 726] Train: [7/20][310/510] Data 3.668 (3.910) Batch 33.275 (28.282) Remain 53:39:27 loss: 0.2294 loss_seg: 0.1391 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:06:59,966 INFO misc.py line 117 726] Train: [7/20][311/510] Data 3.509 (3.909) Batch 24.925 (28.271) Remain 53:37:45 loss: 0.2164 loss_seg: 0.1303 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:07:20,803 INFO misc.py line 117 726] Train: [7/20][312/510] Data 2.590 (3.905) Batch 20.836 (28.247) Remain 53:34:32 loss: 0.2093 loss_seg: 0.1201 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:07:47,653 INFO misc.py line 117 726] Train: [7/20][313/510] Data 3.138 (3.902) Batch 26.850 (28.243) Remain 53:33:33 loss: 0.2699 loss_seg: 0.1694 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:08:08,021 INFO misc.py line 117 726] Train: [7/20][314/510] Data 2.238 (3.897) Batch 20.368 (28.217) Remain 53:30:12 loss: 0.2302 loss_seg: 0.1367 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:08:46,643 INFO misc.py line 117 726] Train: [7/20][315/510] Data 7.043 (3.907) Batch 38.623 (28.251) Remain 53:33:31 loss: 0.2929 loss_seg: 0.1971 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:09:23,900 INFO misc.py line 117 726] Train: [7/20][316/510] Data 8.369 (3.921) Batch 37.257 (28.280) Remain 53:36:20 loss: 0.4429 loss_seg: 0.3283 loss_superpoint_edge: 0.0454 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:09:44,993 INFO misc.py line 117 726] Train: [7/20][317/510] Data 3.124 (3.919) Batch 21.094 (28.257) Remain 53:33:15 loss: 0.3167 loss_seg: 0.2202 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:10:21,795 INFO misc.py line 117 726] Train: [7/20][318/510] Data 5.233 (3.923) Batch 36.802 (28.284) Remain 53:35:52 loss: 0.2373 loss_seg: 0.1472 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:10:56,580 INFO misc.py line 117 726] Train: [7/20][319/510] Data 5.746 (3.929) Batch 34.784 (28.304) Remain 53:37:44 loss: 0.2288 loss_seg: 0.1378 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:11:19,956 INFO misc.py line 117 726] Train: [7/20][320/510] Data 2.530 (3.924) Batch 23.376 (28.289) Remain 53:35:30 loss: 0.1821 loss_seg: 0.0976 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:11:46,587 INFO misc.py line 117 726] Train: [7/20][321/510] Data 4.831 (3.927) Batch 26.631 (28.284) Remain 53:34:26 loss: 0.3763 loss_seg: 0.2698 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0340 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:12:05,361 INFO misc.py line 117 726] Train: [7/20][322/510] Data 1.643 (3.920) Batch 18.774 (28.254) Remain 53:30:34 loss: 0.1852 loss_seg: 0.1036 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:12:28,321 INFO misc.py line 117 726] Train: [7/20][323/510] Data 3.305 (3.918) Batch 22.960 (28.237) Remain 53:28:13 loss: 0.2278 loss_seg: 0.1401 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:13:00,390 INFO misc.py line 117 726] Train: [7/20][324/510] Data 3.901 (3.918) Batch 32.069 (28.249) Remain 53:29:06 loss: 0.1592 loss_seg: 0.0744 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:13:19,398 INFO misc.py line 117 726] Train: [7/20][325/510] Data 2.811 (3.915) Batch 19.008 (28.221) Remain 53:25:22 loss: 0.2654 loss_seg: 0.1666 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:13:32,305 INFO misc.py line 117 726] Train: [7/20][326/510] Data 2.075 (3.909) Batch 12.907 (28.173) Remain 53:19:31 loss: 0.3092 loss_seg: 0.1972 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:13:55,188 INFO misc.py line 117 726] Train: [7/20][327/510] Data 2.673 (3.905) Batch 22.883 (28.157) Remain 53:17:12 loss: 0.2685 loss_seg: 0.1698 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:14:27,416 INFO misc.py line 117 726] Train: [7/20][328/510] Data 3.294 (3.903) Batch 32.228 (28.169) Remain 53:18:09 loss: 0.2711 loss_seg: 0.1768 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:14:52,439 INFO misc.py line 117 726] Train: [7/20][329/510] Data 2.064 (3.898) Batch 25.023 (28.160) Remain 53:16:35 loss: 0.2658 loss_seg: 0.1681 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:15:17,350 INFO misc.py line 117 726] Train: [7/20][330/510] Data 3.322 (3.896) Batch 24.911 (28.150) Remain 53:14:59 loss: 0.2825 loss_seg: 0.1765 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:15:51,060 INFO misc.py line 117 726] Train: [7/20][331/510] Data 3.609 (3.895) Batch 33.710 (28.167) Remain 53:16:27 loss: 0.2874 loss_seg: 0.1849 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:16:17,839 INFO misc.py line 117 726] Train: [7/20][332/510] Data 4.588 (3.897) Batch 26.779 (28.162) Remain 53:15:30 loss: 0.2183 loss_seg: 0.1272 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:16:46,448 INFO misc.py line 117 726] Train: [7/20][333/510] Data 2.789 (3.894) Batch 28.609 (28.164) Remain 53:15:11 loss: 0.2443 loss_seg: 0.1471 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:17:17,627 INFO misc.py line 117 726] Train: [7/20][334/510] Data 3.645 (3.893) Batch 31.178 (28.173) Remain 53:15:45 loss: 0.2274 loss_seg: 0.1366 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:17:38,811 INFO misc.py line 117 726] Train: [7/20][335/510] Data 2.859 (3.890) Batch 21.185 (28.152) Remain 53:12:53 loss: 0.2516 loss_seg: 0.1524 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:18:05,511 INFO misc.py line 117 726] Train: [7/20][336/510] Data 6.226 (3.897) Batch 26.699 (28.148) Remain 53:11:55 loss: 0.2453 loss_seg: 0.1543 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:18:39,538 INFO misc.py line 117 726] Train: [7/20][337/510] Data 5.211 (3.901) Batch 34.028 (28.165) Remain 53:13:27 loss: 0.2843 loss_seg: 0.1887 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:18:55,763 INFO misc.py line 117 726] Train: [7/20][338/510] Data 1.779 (3.895) Batch 16.225 (28.129) Remain 53:08:56 loss: 0.1837 loss_seg: 0.0976 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:19:27,708 INFO misc.py line 117 726] Train: [7/20][339/510] Data 5.057 (3.898) Batch 31.945 (28.141) Remain 53:09:45 loss: 0.2326 loss_seg: 0.1395 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:19:49,887 INFO misc.py line 117 726] Train: [7/20][340/510] Data 4.310 (3.899) Batch 22.179 (28.123) Remain 53:07:17 loss: 0.2332 loss_seg: 0.1391 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0445 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:20:21,705 INFO misc.py line 117 726] Train: [7/20][341/510] Data 3.935 (3.899) Batch 31.818 (28.134) Remain 53:08:03 loss: 0.2119 loss_seg: 0.1220 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:20:59,916 INFO misc.py line 117 726] Train: [7/20][342/510] Data 4.848 (3.902) Batch 38.210 (28.164) Remain 53:10:57 loss: 0.2557 loss_seg: 0.1566 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:21:26,491 INFO misc.py line 117 726] Train: [7/20][343/510] Data 3.610 (3.901) Batch 26.575 (28.159) Remain 53:09:57 loss: 0.2135 loss_seg: 0.1235 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:21:49,089 INFO misc.py line 117 726] Train: [7/20][344/510] Data 2.476 (3.897) Batch 22.599 (28.143) Remain 53:07:38 loss: 0.2277 loss_seg: 0.1337 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:22:21,293 INFO misc.py line 117 726] Train: [7/20][345/510] Data 5.695 (3.902) Batch 32.204 (28.155) Remain 53:08:31 loss: 0.2514 loss_seg: 0.1562 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:22:50,510 INFO misc.py line 117 726] Train: [7/20][346/510] Data 3.426 (3.901) Batch 29.217 (28.158) Remain 53:08:24 loss: 0.2459 loss_seg: 0.1480 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:23:14,545 INFO misc.py line 117 726] Train: [7/20][347/510] Data 2.502 (3.897) Batch 24.036 (28.146) Remain 53:06:34 loss: 0.2607 loss_seg: 0.1590 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:23:43,112 INFO misc.py line 117 726] Train: [7/20][348/510] Data 3.565 (3.896) Batch 28.566 (28.147) Remain 53:06:14 loss: 0.2666 loss_seg: 0.1648 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:24:12,398 INFO misc.py line 117 726] Train: [7/20][349/510] Data 3.758 (3.896) Batch 29.286 (28.150) Remain 53:06:08 loss: 0.2642 loss_seg: 0.1679 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:24:40,531 INFO misc.py line 117 726] Train: [7/20][350/510] Data 3.659 (3.895) Batch 28.133 (28.150) Remain 53:05:40 loss: 0.2161 loss_seg: 0.1257 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:24:40,532 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 18:25:20,405 INFO misc.py line 117 726] Train: [7/20][351/510] Data 10.855 (3.915) Batch 39.873 (28.184) Remain 53:09:00 loss: 0.3063 loss_seg: 0.2030 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:25:44,355 INFO misc.py line 117 726] Train: [7/20][352/510] Data 2.222 (3.910) Batch 23.950 (28.172) Remain 53:07:10 loss: 0.2618 loss_seg: 0.1550 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:26:15,562 INFO misc.py line 117 726] Train: [7/20][353/510] Data 3.878 (3.910) Batch 31.207 (28.181) Remain 53:07:41 loss: 0.2793 loss_seg: 0.1830 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:26:41,861 INFO misc.py line 117 726] Train: [7/20][354/510] Data 2.927 (3.907) Batch 26.299 (28.175) Remain 53:06:36 loss: 0.1947 loss_seg: 0.1072 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:27:10,497 INFO misc.py line 117 726] Train: [7/20][355/510] Data 3.421 (3.906) Batch 28.636 (28.176) Remain 53:06:17 loss: 0.2585 loss_seg: 0.1592 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:27:41,278 INFO misc.py line 117 726] Train: [7/20][356/510] Data 4.432 (3.907) Batch 30.781 (28.184) Remain 53:06:39 loss: 0.2204 loss_seg: 0.1279 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:28:10,301 INFO misc.py line 117 726] Train: [7/20][357/510] Data 3.584 (3.906) Batch 29.023 (28.186) Remain 53:06:27 loss: 0.3279 loss_seg: 0.2369 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:28:34,241 INFO misc.py line 117 726] Train: [7/20][358/510] Data 3.153 (3.904) Batch 23.940 (28.174) Remain 53:04:37 loss: 0.2598 loss_seg: 0.1596 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:29:04,959 INFO misc.py line 117 726] Train: [7/20][359/510] Data 4.745 (3.907) Batch 30.718 (28.181) Remain 53:04:58 loss: 0.2394 loss_seg: 0.1457 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:29:34,410 INFO misc.py line 117 726] Train: [7/20][360/510] Data 3.764 (3.906) Batch 29.451 (28.185) Remain 53:04:53 loss: 0.3052 loss_seg: 0.2215 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:30:11,002 INFO misc.py line 117 726] Train: [7/20][361/510] Data 4.535 (3.908) Batch 36.593 (28.208) Remain 53:07:04 loss: 0.2447 loss_seg: 0.1545 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:30:45,294 INFO misc.py line 117 726] Train: [7/20][362/510] Data 6.187 (3.914) Batch 34.292 (28.225) Remain 53:08:31 loss: 0.2183 loss_seg: 0.1244 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:31:11,921 INFO misc.py line 117 726] Train: [7/20][363/510] Data 4.592 (3.916) Batch 26.627 (28.221) Remain 53:07:33 loss: 0.2434 loss_seg: 0.1459 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:31:31,865 INFO misc.py line 117 726] Train: [7/20][364/510] Data 2.262 (3.912) Batch 19.944 (28.198) Remain 53:04:29 loss: 0.3751 loss_seg: 0.2741 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:32:01,703 INFO misc.py line 117 726] Train: [7/20][365/510] Data 3.792 (3.911) Batch 29.838 (28.203) Remain 53:04:32 loss: 0.2467 loss_seg: 0.1506 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:32:18,776 INFO misc.py line 117 726] Train: [7/20][366/510] Data 2.582 (3.908) Batch 17.073 (28.172) Remain 53:00:36 loss: 0.2871 loss_seg: 0.1950 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:32:45,404 INFO misc.py line 117 726] Train: [7/20][367/510] Data 2.947 (3.905) Batch 26.628 (28.168) Remain 52:59:39 loss: 0.2556 loss_seg: 0.1595 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:33:20,224 INFO misc.py line 117 726] Train: [7/20][368/510] Data 4.586 (3.907) Batch 34.820 (28.186) Remain 53:01:14 loss: 0.3226 loss_seg: 0.2271 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:33:48,364 INFO misc.py line 117 726] Train: [7/20][369/510] Data 4.015 (3.907) Batch 28.141 (28.186) Remain 53:00:45 loss: 0.2270 loss_seg: 0.1339 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:34:10,421 INFO misc.py line 117 726] Train: [7/20][370/510] Data 2.726 (3.904) Batch 22.056 (28.169) Remain 52:58:24 loss: 0.2849 loss_seg: 0.1835 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:34:37,991 INFO misc.py line 117 726] Train: [7/20][371/510] Data 2.843 (3.901) Batch 27.570 (28.167) Remain 52:57:45 loss: 0.2117 loss_seg: 0.1205 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:35:10,616 INFO misc.py line 117 726] Train: [7/20][372/510] Data 5.948 (3.907) Batch 32.625 (28.179) Remain 52:58:38 loss: 0.3671 loss_seg: 0.2697 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:35:36,356 INFO misc.py line 117 726] Train: [7/20][373/510] Data 3.150 (3.904) Batch 25.741 (28.173) Remain 52:57:25 loss: 0.2761 loss_seg: 0.1736 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:36:04,944 INFO misc.py line 117 726] Train: [7/20][374/510] Data 3.199 (3.903) Batch 28.588 (28.174) Remain 52:57:05 loss: 0.2435 loss_seg: 0.1412 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:36:28,666 INFO misc.py line 117 726] Train: [7/20][375/510] Data 2.237 (3.898) Batch 23.723 (28.162) Remain 52:55:16 loss: 0.2663 loss_seg: 0.1671 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:36:55,390 INFO misc.py line 117 726] Train: [7/20][376/510] Data 2.688 (3.895) Batch 26.724 (28.158) Remain 52:54:22 loss: 0.2519 loss_seg: 0.1557 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:37:24,261 INFO misc.py line 117 726] Train: [7/20][377/510] Data 2.752 (3.892) Batch 28.871 (28.160) Remain 52:54:06 loss: 0.2483 loss_seg: 0.1476 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:37:44,252 INFO misc.py line 117 726] Train: [7/20][378/510] Data 2.746 (3.889) Batch 19.991 (28.138) Remain 52:51:11 loss: 0.3391 loss_seg: 0.2280 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:38:16,017 INFO misc.py line 117 726] Train: [7/20][379/510] Data 4.474 (3.890) Batch 31.766 (28.148) Remain 52:51:48 loss: 0.1904 loss_seg: 0.1023 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:38:38,335 INFO misc.py line 117 726] Train: [7/20][380/510] Data 3.344 (3.889) Batch 22.318 (28.132) Remain 52:49:35 loss: 0.2738 loss_seg: 0.1765 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:39:10,076 INFO misc.py line 117 726] Train: [7/20][381/510] Data 6.030 (3.895) Batch 31.740 (28.142) Remain 52:50:12 loss: 0.2591 loss_seg: 0.1609 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:39:39,720 INFO misc.py line 117 726] Train: [7/20][382/510] Data 3.296 (3.893) Batch 29.644 (28.146) Remain 52:50:10 loss: 0.2189 loss_seg: 0.1283 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:40:06,208 INFO misc.py line 117 726] Train: [7/20][383/510] Data 2.017 (3.888) Batch 26.489 (28.142) Remain 52:49:13 loss: 0.2727 loss_seg: 0.1751 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:40:21,857 INFO misc.py line 117 726] Train: [7/20][384/510] Data 2.622 (3.885) Batch 15.649 (28.109) Remain 52:45:03 loss: 0.2119 loss_seg: 0.1209 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:40:40,023 INFO misc.py line 117 726] Train: [7/20][385/510] Data 2.065 (3.880) Batch 18.166 (28.083) Remain 52:41:39 loss: 0.2332 loss_seg: 0.1382 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:41:02,548 INFO misc.py line 117 726] Train: [7/20][386/510] Data 2.586 (3.877) Batch 22.525 (28.068) Remain 52:39:33 loss: 0.2051 loss_seg: 0.1149 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:41:37,743 INFO misc.py line 117 726] Train: [7/20][387/510] Data 5.778 (3.881) Batch 35.195 (28.087) Remain 52:41:10 loss: 0.2225 loss_seg: 0.1329 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:42:10,763 INFO misc.py line 117 726] Train: [7/20][388/510] Data 5.049 (3.885) Batch 33.020 (28.100) Remain 52:42:09 loss: 0.2869 loss_seg: 0.1913 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:42:43,396 INFO misc.py line 117 726] Train: [7/20][389/510] Data 5.564 (3.889) Batch 32.633 (28.111) Remain 52:43:00 loss: 0.1908 loss_seg: 0.1041 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:43:10,184 INFO misc.py line 117 726] Train: [7/20][390/510] Data 5.327 (3.893) Batch 26.788 (28.108) Remain 52:42:09 loss: 0.2585 loss_seg: 0.1625 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:43:23,008 INFO misc.py line 117 726] Train: [7/20][391/510] Data 1.553 (3.887) Batch 12.824 (28.069) Remain 52:37:15 loss: 0.1947 loss_seg: 0.1126 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:43:44,352 INFO misc.py line 117 726] Train: [7/20][392/510] Data 2.428 (3.883) Batch 21.344 (28.051) Remain 52:34:50 loss: 0.2166 loss_seg: 0.1227 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:44:18,165 INFO misc.py line 117 726] Train: [7/20][393/510] Data 4.630 (3.885) Batch 33.813 (28.066) Remain 52:36:02 loss: 0.2439 loss_seg: 0.1411 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:44:45,385 INFO misc.py line 117 726] Train: [7/20][394/510] Data 3.051 (3.883) Batch 27.219 (28.064) Remain 52:35:19 loss: 0.2478 loss_seg: 0.1507 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:45:11,024 INFO misc.py line 117 726] Train: [7/20][395/510] Data 2.410 (3.879) Batch 25.639 (28.058) Remain 52:34:09 loss: 0.2518 loss_seg: 0.1575 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:45:35,964 INFO misc.py line 117 726] Train: [7/20][396/510] Data 2.415 (3.875) Batch 24.940 (28.050) Remain 52:32:47 loss: 0.2614 loss_seg: 0.1611 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:46:07,663 INFO misc.py line 117 726] Train: [7/20][397/510] Data 4.445 (3.877) Batch 31.699 (28.059) Remain 52:33:22 loss: 0.2849 loss_seg: 0.1884 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:46:31,504 INFO misc.py line 117 726] Train: [7/20][398/510] Data 2.659 (3.873) Batch 23.842 (28.048) Remain 52:31:42 loss: 0.2071 loss_seg: 0.1148 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:46:57,071 INFO misc.py line 117 726] Train: [7/20][399/510] Data 2.367 (3.870) Batch 25.566 (28.042) Remain 52:30:32 loss: 0.2072 loss_seg: 0.1200 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:47:31,761 INFO misc.py line 117 726] Train: [7/20][400/510] Data 4.111 (3.870) Batch 34.691 (28.059) Remain 52:31:56 loss: 0.3183 loss_seg: 0.2070 loss_superpoint_edge: 0.0423 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:47:31,762 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 18:48:02,226 INFO misc.py line 117 726] Train: [7/20][401/510] Data 3.840 (3.870) Batch 30.465 (28.065) Remain 52:32:09 loss: 0.2556 loss_seg: 0.1662 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:48:21,901 INFO misc.py line 117 726] Train: [7/20][402/510] Data 2.670 (3.867) Batch 19.675 (28.044) Remain 52:29:19 loss: 0.2486 loss_seg: 0.1497 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:48:45,211 INFO misc.py line 117 726] Train: [7/20][403/510] Data 3.244 (3.866) Batch 23.310 (28.032) Remain 52:27:32 loss: 0.2207 loss_seg: 0.1305 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:49:16,484 INFO misc.py line 117 726] Train: [7/20][404/510] Data 3.362 (3.864) Batch 31.273 (28.040) Remain 52:27:58 loss: 0.2412 loss_seg: 0.1423 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:49:43,074 INFO misc.py line 117 726] Train: [7/20][405/510] Data 4.004 (3.865) Batch 26.591 (28.037) Remain 52:27:06 loss: 0.1808 loss_seg: 0.0985 loss_superpoint_edge: 0.0125 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:50:04,122 INFO misc.py line 117 726] Train: [7/20][406/510] Data 2.408 (3.861) Batch 21.048 (28.019) Remain 52:24:41 loss: 0.2814 loss_seg: 0.1831 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:50:30,372 INFO misc.py line 117 726] Train: [7/20][407/510] Data 3.451 (3.860) Batch 26.250 (28.015) Remain 52:23:43 loss: 0.2193 loss_seg: 0.1300 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:50:58,856 INFO misc.py line 117 726] Train: [7/20][408/510] Data 3.185 (3.858) Batch 28.484 (28.016) Remain 52:23:23 loss: 0.2106 loss_seg: 0.1201 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:51:20,342 INFO misc.py line 117 726] Train: [7/20][409/510] Data 2.849 (3.856) Batch 21.486 (28.000) Remain 52:21:07 loss: 0.3466 loss_seg: 0.2259 loss_superpoint_edge: 0.0516 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:51:53,456 INFO misc.py line 117 726] Train: [7/20][410/510] Data 4.055 (3.856) Batch 33.114 (28.012) Remain 52:22:03 loss: 0.3122 loss_seg: 0.2103 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:52:19,847 INFO misc.py line 117 726] Train: [7/20][411/510] Data 3.070 (3.854) Batch 26.391 (28.008) Remain 52:21:09 loss: 0.3015 loss_seg: 0.2106 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:52:50,025 INFO misc.py line 117 726] Train: [7/20][412/510] Data 3.371 (3.853) Batch 30.178 (28.014) Remain 52:21:16 loss: 0.2996 loss_seg: 0.1960 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:53:18,469 INFO misc.py line 117 726] Train: [7/20][413/510] Data 2.976 (3.851) Batch 28.445 (28.015) Remain 52:20:55 loss: 0.2139 loss_seg: 0.1245 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:53:45,506 INFO misc.py line 117 726] Train: [7/20][414/510] Data 3.221 (3.850) Batch 27.036 (28.012) Remain 52:20:11 loss: 0.3021 loss_seg: 0.2146 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:54:18,876 INFO misc.py line 117 726] Train: [7/20][415/510] Data 4.079 (3.850) Batch 33.371 (28.025) Remain 52:21:11 loss: 0.2940 loss_seg: 0.1851 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:54:42,724 INFO misc.py line 117 726] Train: [7/20][416/510] Data 3.164 (3.849) Batch 23.848 (28.015) Remain 52:19:35 loss: 0.3038 loss_seg: 0.1996 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:55:06,963 INFO misc.py line 117 726] Train: [7/20][417/510] Data 3.127 (3.847) Batch 24.239 (28.006) Remain 52:18:05 loss: 0.2782 loss_seg: 0.1814 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:55:32,103 INFO misc.py line 117 726] Train: [7/20][418/510] Data 3.519 (3.846) Batch 25.141 (27.999) Remain 52:16:51 loss: 0.2421 loss_seg: 0.1478 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:55:52,497 INFO misc.py line 117 726] Train: [7/20][419/510] Data 2.194 (3.842) Batch 20.394 (27.981) Remain 52:14:20 loss: 0.2168 loss_seg: 0.1262 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:56:31,702 INFO misc.py line 117 726] Train: [7/20][420/510] Data 10.898 (3.859) Batch 39.205 (28.008) Remain 52:16:53 loss: 0.2645 loss_seg: 0.1695 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:57:03,076 INFO misc.py line 117 726] Train: [7/20][421/510] Data 3.457 (3.858) Batch 31.374 (28.016) Remain 52:17:19 loss: 0.2419 loss_seg: 0.1457 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:57:46,220 INFO misc.py line 117 726] Train: [7/20][422/510] Data 11.803 (3.877) Batch 43.144 (28.052) Remain 52:20:54 loss: 0.2394 loss_seg: 0.1416 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:58:15,088 INFO misc.py line 117 726] Train: [7/20][423/510] Data 3.023 (3.875) Batch 28.868 (28.054) Remain 52:20:39 loss: 0.2182 loss_seg: 0.1266 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:58:43,875 INFO misc.py line 117 726] Train: [7/20][424/510] Data 2.933 (3.873) Batch 28.787 (28.056) Remain 52:20:22 loss: 0.2348 loss_seg: 0.1441 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:59:25,532 INFO misc.py line 117 726] Train: [7/20][425/510] Data 9.664 (3.886) Batch 41.658 (28.088) Remain 52:23:31 loss: 0.2337 loss_seg: 0.1420 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 18:59:56,382 INFO misc.py line 117 726] Train: [7/20][426/510] Data 3.443 (3.885) Batch 30.849 (28.095) Remain 52:23:46 loss: 0.2255 loss_seg: 0.1305 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:00:22,270 INFO misc.py line 117 726] Train: [7/20][427/510] Data 2.671 (3.882) Batch 25.889 (28.089) Remain 52:22:43 loss: 0.2662 loss_seg: 0.1652 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:01:02,142 INFO misc.py line 117 726] Train: [7/20][428/510] Data 5.817 (3.887) Batch 39.871 (28.117) Remain 52:25:21 loss: 0.2038 loss_seg: 0.1137 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:01:36,416 INFO misc.py line 117 726] Train: [7/20][429/510] Data 4.294 (3.888) Batch 34.275 (28.132) Remain 52:26:30 loss: 0.2830 loss_seg: 0.1804 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:02:11,136 INFO misc.py line 117 726] Train: [7/20][430/510] Data 6.250 (3.894) Batch 34.719 (28.147) Remain 52:27:46 loss: 0.2586 loss_seg: 0.1614 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:02:31,018 INFO misc.py line 117 726] Train: [7/20][431/510] Data 2.548 (3.890) Batch 19.883 (28.128) Remain 52:25:08 loss: 0.1870 loss_seg: 0.1013 loss_superpoint_edge: 0.0140 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:02:58,374 INFO misc.py line 117 726] Train: [7/20][432/510] Data 3.064 (3.888) Batch 27.356 (28.126) Remain 52:24:28 loss: 0.2778 loss_seg: 0.1742 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:03:23,803 INFO misc.py line 117 726] Train: [7/20][433/510] Data 4.529 (3.890) Batch 25.429 (28.120) Remain 52:23:18 loss: 0.2172 loss_seg: 0.1266 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:04:01,860 INFO misc.py line 117 726] Train: [7/20][434/510] Data 7.019 (3.897) Batch 38.056 (28.143) Remain 52:25:24 loss: 0.3304 loss_seg: 0.2258 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:04:21,974 INFO misc.py line 117 726] Train: [7/20][435/510] Data 2.747 (3.895) Batch 20.115 (28.124) Remain 52:22:51 loss: 0.2329 loss_seg: 0.1443 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:04:52,615 INFO misc.py line 117 726] Train: [7/20][436/510] Data 2.880 (3.892) Batch 30.640 (28.130) Remain 52:23:02 loss: 0.3290 loss_seg: 0.2324 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:05:24,488 INFO misc.py line 117 726] Train: [7/20][437/510] Data 3.006 (3.890) Batch 31.874 (28.138) Remain 52:23:32 loss: 0.2402 loss_seg: 0.1441 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:05:50,103 INFO misc.py line 117 726] Train: [7/20][438/510] Data 3.016 (3.888) Batch 25.614 (28.133) Remain 52:22:25 loss: 0.3260 loss_seg: 0.2219 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:06:22,132 INFO misc.py line 117 726] Train: [7/20][439/510] Data 3.976 (3.888) Batch 32.030 (28.142) Remain 52:22:57 loss: 0.2782 loss_seg: 0.1784 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:06:53,964 INFO misc.py line 117 726] Train: [7/20][440/510] Data 5.861 (3.893) Batch 31.831 (28.150) Remain 52:23:25 loss: 0.3493 loss_seg: 0.2480 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:07:24,606 INFO misc.py line 117 726] Train: [7/20][441/510] Data 3.946 (3.893) Batch 30.642 (28.156) Remain 52:23:35 loss: 0.2171 loss_seg: 0.1265 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:07:54,247 INFO misc.py line 117 726] Train: [7/20][442/510] Data 3.645 (3.892) Batch 29.642 (28.159) Remain 52:23:29 loss: 0.2453 loss_seg: 0.1519 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:08:25,295 INFO misc.py line 117 726] Train: [7/20][443/510] Data 3.719 (3.892) Batch 31.047 (28.166) Remain 52:23:45 loss: 0.2433 loss_seg: 0.1467 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:08:54,824 INFO misc.py line 117 726] Train: [7/20][444/510] Data 5.477 (3.896) Batch 29.529 (28.169) Remain 52:23:38 loss: 0.2618 loss_seg: 0.1705 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:09:23,148 INFO misc.py line 117 726] Train: [7/20][445/510] Data 2.945 (3.893) Batch 28.324 (28.169) Remain 52:23:12 loss: 0.3545 loss_seg: 0.2558 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:09:47,687 INFO misc.py line 117 726] Train: [7/20][446/510] Data 2.714 (3.891) Batch 24.539 (28.161) Remain 52:21:49 loss: 0.2504 loss_seg: 0.1593 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:10:19,723 INFO misc.py line 117 726] Train: [7/20][447/510] Data 5.216 (3.894) Batch 32.036 (28.170) Remain 52:22:19 loss: 0.2496 loss_seg: 0.1594 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:10:39,109 INFO misc.py line 117 726] Train: [7/20][448/510] Data 1.922 (3.889) Batch 19.386 (28.150) Remain 52:19:39 loss: 0.2115 loss_seg: 0.1218 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:11:02,615 INFO misc.py line 117 726] Train: [7/20][449/510] Data 2.733 (3.887) Batch 23.506 (28.140) Remain 52:18:01 loss: 0.3705 loss_seg: 0.2633 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:11:38,846 INFO misc.py line 117 726] Train: [7/20][450/510] Data 6.217 (3.892) Batch 36.231 (28.158) Remain 52:19:34 loss: 0.2582 loss_seg: 0.1645 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:11:38,847 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 19:12:08,763 INFO misc.py line 117 726] Train: [7/20][451/510] Data 3.939 (3.892) Batch 29.917 (28.162) Remain 52:19:32 loss: 0.2282 loss_seg: 0.1341 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:12:44,039 INFO misc.py line 117 726] Train: [7/20][452/510] Data 4.033 (3.892) Batch 35.276 (28.177) Remain 52:20:50 loss: 0.1920 loss_seg: 0.1048 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:13:12,422 INFO misc.py line 117 726] Train: [7/20][453/510] Data 3.565 (3.892) Batch 28.383 (28.178) Remain 52:20:25 loss: 0.2664 loss_seg: 0.1632 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:13:54,189 INFO misc.py line 117 726] Train: [7/20][454/510] Data 8.437 (3.902) Batch 41.767 (28.208) Remain 52:23:18 loss: 0.2732 loss_seg: 0.1808 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:14:13,647 INFO misc.py line 117 726] Train: [7/20][455/510] Data 2.717 (3.899) Batch 19.458 (28.189) Remain 52:20:41 loss: 0.2320 loss_seg: 0.1339 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:14:39,561 INFO misc.py line 117 726] Train: [7/20][456/510] Data 3.476 (3.898) Batch 25.914 (28.184) Remain 52:19:39 loss: 0.2719 loss_seg: 0.1711 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:15:15,925 INFO misc.py line 117 726] Train: [7/20][457/510] Data 5.139 (3.901) Batch 36.364 (28.202) Remain 52:21:11 loss: 0.2805 loss_seg: 0.1844 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:15:39,018 INFO misc.py line 117 726] Train: [7/20][458/510] Data 3.402 (3.900) Batch 23.093 (28.190) Remain 52:19:28 loss: 0.1795 loss_seg: 0.0928 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:16:07,890 INFO misc.py line 117 726] Train: [7/20][459/510] Data 3.036 (3.898) Batch 28.872 (28.192) Remain 52:19:10 loss: 0.3444 loss_seg: 0.2416 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:16:46,446 INFO misc.py line 117 726] Train: [7/20][460/510] Data 10.904 (3.913) Batch 38.556 (28.215) Remain 52:21:13 loss: 0.3787 loss_seg: 0.2639 loss_superpoint_edge: 0.0434 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:17:14,427 INFO misc.py line 117 726] Train: [7/20][461/510] Data 4.945 (3.916) Batch 27.981 (28.214) Remain 52:20:41 loss: 0.2159 loss_seg: 0.1232 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:17:44,495 INFO misc.py line 117 726] Train: [7/20][462/510] Data 3.609 (3.915) Batch 30.069 (28.218) Remain 52:20:40 loss: 0.3381 loss_seg: 0.2407 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:18:16,623 INFO misc.py line 117 726] Train: [7/20][463/510] Data 6.062 (3.920) Batch 32.127 (28.227) Remain 52:21:09 loss: 0.4927 loss_seg: 0.3740 loss_superpoint_edge: 0.0488 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:18:49,351 INFO misc.py line 117 726] Train: [7/20][464/510] Data 4.998 (3.922) Batch 32.728 (28.236) Remain 52:21:46 loss: 0.2526 loss_seg: 0.1576 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:19:15,407 INFO misc.py line 117 726] Train: [7/20][465/510] Data 3.084 (3.920) Batch 26.056 (28.232) Remain 52:20:46 loss: 0.3154 loss_seg: 0.2094 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:19:39,934 INFO misc.py line 117 726] Train: [7/20][466/510] Data 3.687 (3.920) Batch 24.527 (28.224) Remain 52:19:24 loss: 0.2983 loss_seg: 0.1952 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:20:18,093 INFO misc.py line 117 726] Train: [7/20][467/510] Data 9.383 (3.931) Batch 38.159 (28.245) Remain 52:21:19 loss: 0.2204 loss_seg: 0.1288 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:20:46,526 INFO misc.py line 117 726] Train: [7/20][468/510] Data 3.258 (3.930) Batch 28.433 (28.245) Remain 52:20:53 loss: 0.3453 loss_seg: 0.2447 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:21:13,819 INFO misc.py line 117 726] Train: [7/20][469/510] Data 3.342 (3.929) Batch 27.292 (28.243) Remain 52:20:11 loss: 0.2136 loss_seg: 0.1208 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:21:37,469 INFO misc.py line 117 726] Train: [7/20][470/510] Data 2.312 (3.925) Batch 23.650 (28.234) Remain 52:18:38 loss: 0.2099 loss_seg: 0.1185 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:22:10,839 INFO misc.py line 117 726] Train: [7/20][471/510] Data 3.723 (3.925) Batch 33.370 (28.245) Remain 52:19:22 loss: 0.2279 loss_seg: 0.1326 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:22:41,614 INFO misc.py line 117 726] Train: [7/20][472/510] Data 3.282 (3.923) Batch 30.775 (28.250) Remain 52:19:30 loss: 0.1988 loss_seg: 0.1167 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:23:11,122 INFO misc.py line 117 726] Train: [7/20][473/510] Data 3.007 (3.921) Batch 29.508 (28.253) Remain 52:19:20 loss: 0.2252 loss_seg: 0.1299 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:23:36,365 INFO misc.py line 117 726] Train: [7/20][474/510] Data 2.351 (3.918) Batch 25.243 (28.246) Remain 52:18:09 loss: 0.2353 loss_seg: 0.1397 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:24:00,385 INFO misc.py line 117 726] Train: [7/20][475/510] Data 3.529 (3.917) Batch 24.020 (28.237) Remain 52:16:41 loss: 0.2230 loss_seg: 0.1336 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:24:32,736 INFO misc.py line 117 726] Train: [7/20][476/510] Data 3.485 (3.916) Batch 32.351 (28.246) Remain 52:17:11 loss: 0.2094 loss_seg: 0.1243 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:24:57,449 INFO misc.py line 117 726] Train: [7/20][477/510] Data 3.257 (3.915) Batch 24.714 (28.239) Remain 52:15:53 loss: 0.2639 loss_seg: 0.1645 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:25:26,234 INFO misc.py line 117 726] Train: [7/20][478/510] Data 3.201 (3.913) Batch 28.785 (28.240) Remain 52:15:32 loss: 0.3438 loss_seg: 0.2484 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:25:54,281 INFO misc.py line 117 726] Train: [7/20][479/510] Data 2.789 (3.911) Batch 28.047 (28.239) Remain 52:15:01 loss: 0.2752 loss_seg: 0.1734 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:26:15,432 INFO misc.py line 117 726] Train: [7/20][480/510] Data 2.725 (3.909) Batch 21.151 (28.224) Remain 52:12:54 loss: 0.2622 loss_seg: 0.1691 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:26:33,896 INFO misc.py line 117 726] Train: [7/20][481/510] Data 2.028 (3.905) Batch 18.464 (28.204) Remain 52:10:10 loss: 0.2420 loss_seg: 0.1478 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:27:04,849 INFO misc.py line 117 726] Train: [7/20][482/510] Data 3.683 (3.904) Batch 30.953 (28.210) Remain 52:10:20 loss: 0.2693 loss_seg: 0.1686 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:27:27,545 INFO misc.py line 117 726] Train: [7/20][483/510] Data 2.884 (3.902) Batch 22.696 (28.198) Remain 52:08:35 loss: 0.2628 loss_seg: 0.1619 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:28:08,844 INFO misc.py line 117 726] Train: [7/20][484/510] Data 7.520 (3.910) Batch 41.299 (28.225) Remain 52:11:08 loss: 0.3081 loss_seg: 0.2123 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:28:35,363 INFO misc.py line 117 726] Train: [7/20][485/510] Data 3.381 (3.908) Batch 26.519 (28.222) Remain 52:10:17 loss: 0.2267 loss_seg: 0.1360 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:29:16,364 INFO misc.py line 117 726] Train: [7/20][486/510] Data 6.225 (3.913) Batch 41.001 (28.248) Remain 52:12:44 loss: 0.2003 loss_seg: 0.1125 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:29:49,108 INFO misc.py line 117 726] Train: [7/20][487/510] Data 10.691 (3.927) Batch 32.744 (28.258) Remain 52:13:18 loss: 0.2595 loss_seg: 0.1539 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:30:29,007 INFO misc.py line 117 726] Train: [7/20][488/510] Data 6.274 (3.932) Batch 39.900 (28.282) Remain 52:15:29 loss: 0.1869 loss_seg: 0.1026 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:31:01,318 INFO misc.py line 117 726] Train: [7/20][489/510] Data 4.680 (3.934) Batch 32.311 (28.290) Remain 52:15:56 loss: 0.2495 loss_seg: 0.1586 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:31:28,666 INFO misc.py line 117 726] Train: [7/20][490/510] Data 5.348 (3.937) Batch 27.348 (28.288) Remain 52:15:15 loss: 0.2827 loss_seg: 0.1842 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:32:07,023 INFO misc.py line 117 726] Train: [7/20][491/510] Data 5.926 (3.941) Batch 38.357 (28.309) Remain 52:17:04 loss: 0.2035 loss_seg: 0.1157 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:32:32,473 INFO misc.py line 117 726] Train: [7/20][492/510] Data 2.578 (3.938) Batch 25.450 (28.303) Remain 52:15:57 loss: 0.2437 loss_seg: 0.1494 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:33:03,472 INFO misc.py line 117 726] Train: [7/20][493/510] Data 3.865 (3.938) Batch 30.999 (28.308) Remain 52:16:05 loss: 0.2361 loss_seg: 0.1414 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:33:36,066 INFO misc.py line 117 726] Train: [7/20][494/510] Data 2.943 (3.936) Batch 32.594 (28.317) Remain 52:16:35 loss: 0.2012 loss_seg: 0.1107 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:34:08,897 INFO misc.py line 117 726] Train: [7/20][495/510] Data 10.470 (3.949) Batch 32.832 (28.326) Remain 52:17:07 loss: 0.2315 loss_seg: 0.1364 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:34:24,524 INFO misc.py line 117 726] Train: [7/20][496/510] Data 1.856 (3.945) Batch 15.627 (28.300) Remain 52:13:48 loss: 0.1971 loss_seg: 0.1103 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:34:53,741 INFO misc.py line 117 726] Train: [7/20][497/510] Data 5.767 (3.948) Batch 29.218 (28.302) Remain 52:13:32 loss: 0.2300 loss_seg: 0.1398 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:35:25,543 INFO misc.py line 117 726] Train: [7/20][498/510] Data 3.801 (3.948) Batch 31.801 (28.309) Remain 52:13:51 loss: 0.1960 loss_seg: 0.1103 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:35:39,421 INFO misc.py line 117 726] Train: [7/20][499/510] Data 1.567 (3.943) Batch 13.878 (28.280) Remain 52:10:09 loss: 0.2266 loss_seg: 0.1352 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:36:14,662 INFO misc.py line 117 726] Train: [7/20][500/510] Data 4.032 (3.943) Batch 35.241 (28.294) Remain 52:11:14 loss: 0.3256 loss_seg: 0.2306 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:36:14,663 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 19:36:49,492 INFO misc.py line 117 726] Train: [7/20][501/510] Data 3.371 (3.942) Batch 34.830 (28.307) Remain 52:12:13 loss: 0.2308 loss_seg: 0.1367 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:37:11,387 INFO misc.py line 117 726] Train: [7/20][502/510] Data 2.284 (3.939) Batch 21.895 (28.295) Remain 52:10:19 loss: 0.2560 loss_seg: 0.1533 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:37:37,493 INFO misc.py line 117 726] Train: [7/20][503/510] Data 3.087 (3.937) Batch 26.105 (28.290) Remain 52:09:22 loss: 0.2317 loss_seg: 0.1343 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:37:59,035 INFO misc.py line 117 726] Train: [7/20][504/510] Data 2.841 (3.935) Batch 21.542 (28.277) Remain 52:07:24 loss: 0.2825 loss_seg: 0.1926 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:38:35,783 INFO misc.py line 117 726] Train: [7/20][505/510] Data 7.288 (3.942) Batch 36.748 (28.294) Remain 52:08:48 loss: 0.2705 loss_seg: 0.1664 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:39:08,531 INFO misc.py line 117 726] Train: [7/20][506/510] Data 5.279 (3.944) Batch 32.748 (28.302) Remain 52:09:18 loss: 0.3345 loss_seg: 0.2410 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:39:38,144 INFO misc.py line 117 726] Train: [7/20][507/510] Data 3.055 (3.943) Batch 29.612 (28.305) Remain 52:09:07 loss: 0.2524 loss_seg: 0.1563 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:40:09,445 INFO misc.py line 117 726] Train: [7/20][508/510] Data 6.031 (3.947) Batch 31.302 (28.311) Remain 52:09:18 loss: 0.1738 loss_seg: 0.0910 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:40:41,735 INFO misc.py line 117 726] Train: [7/20][509/510] Data 3.848 (3.947) Batch 32.290 (28.319) Remain 52:09:42 loss: 0.3006 loss_seg: 0.2068 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:41:15,444 INFO misc.py line 117 726] Train: [7/20][510/510] Data 4.205 (3.947) Batch 33.709 (28.330) Remain 52:10:24 loss: 0.2704 loss_seg: 0.1703 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:41:15,444 INFO misc.py line 147 726] Train result: loss: 0.2583 loss_seg: 0.1622 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-10 19:41:15,445 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-10 19:41:31,350 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6684 [2026-06-10 19:41:47,263 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6248 [2026-06-10 19:43:01,672 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8876 [2026-06-10 19:43:41,992 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9827 [2026-06-10 19:44:01,416 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0764 [2026-06-10 19:44:37,909 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.0913 [2026-06-10 19:45:25,114 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1574 [2026-06-10 19:45:40,662 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2719 [2026-06-10 19:45:58,522 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.0248 [2026-06-10 19:46:17,408 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4244 [2026-06-10 19:46:33,204 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4341 [2026-06-10 19:46:54,955 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.6338 [2026-06-10 19:47:21,121 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9666 [2026-06-10 19:47:32,437 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7003 [2026-06-10 19:48:03,998 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0010 [2026-06-10 19:48:30,010 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3675 [2026-06-10 19:48:56,783 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.4001 [2026-06-10 19:49:40,767 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.2736 [2026-06-10 19:50:02,402 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.5116 [2026-06-10 19:50:19,132 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.9064 [2026-06-10 19:50:50,535 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 2.0116 [2026-06-10 19:51:06,957 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.5463 [2026-06-10 19:51:29,033 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2989 [2026-06-10 19:51:51,042 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7832 [2026-06-10 19:52:04,725 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6650 [2026-06-10 19:52:32,965 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5689 [2026-06-10 19:53:14,755 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0876 [2026-06-10 19:53:32,131 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5196 [2026-06-10 19:53:50,933 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4626 [2026-06-10 19:54:08,094 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3497 [2026-06-10 19:54:33,325 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1861 [2026-06-10 19:54:51,493 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.7237 [2026-06-10 19:55:08,997 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9581 [2026-06-10 19:55:33,216 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.8175 [2026-06-10 19:55:33,230 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6724/0.7427/0.8969. [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9248/0.9607 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9760/0.9880 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8400/0.9713 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0027/0.0162 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3129/0.3693 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6133/0.6409 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6069/0.6909 [2026-06-10 19:55:33,231 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7921/0.8962 [2026-06-10 19:55:33,232 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9133/0.9503 [2026-06-10 19:55:33,232 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.7019/0.7696 [2026-06-10 19:55:33,232 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7625/0.8541 [2026-06-10 19:55:33,232 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7020/0.8498 [2026-06-10 19:55:33,232 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5933/0.6982 [2026-06-10 19:55:33,233 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-10 19:55:33,233 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-10 19:55:33,233 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 19:55:59,957 INFO misc.py line 117 726] Train: [8/20][1/510] Data 3.902 (3.902) Batch 25.205 (25.205) Remain 46:24:42 loss: 0.3524 loss_seg: 0.2529 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:56:23,885 INFO misc.py line 117 726] Train: [8/20][2/510] Data 2.932 (2.932) Batch 23.928 (23.928) Remain 44:03:16 loss: 0.2559 loss_seg: 0.1608 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:56:46,550 INFO misc.py line 117 726] Train: [8/20][3/510] Data 2.976 (2.976) Batch 22.664 (22.664) Remain 41:43:16 loss: 0.2222 loss_seg: 0.1298 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:57:18,582 INFO misc.py line 117 726] Train: [8/20][4/510] Data 4.365 (4.365) Batch 32.033 (32.033) Remain 58:57:29 loss: 0.3160 loss_seg: 0.2139 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:57:53,633 INFO misc.py line 117 726] Train: [8/20][5/510] Data 4.889 (4.627) Batch 35.050 (33.542) Remain 61:43:33 loss: 0.2103 loss_seg: 0.1179 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:58:21,179 INFO misc.py line 117 726] Train: [8/20][6/510] Data 3.062 (4.105) Batch 27.546 (31.543) Remain 58:02:22 loss: 0.2588 loss_seg: 0.1565 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:58:40,015 INFO misc.py line 117 726] Train: [8/20][7/510] Data 2.303 (3.655) Batch 18.835 (28.366) Remain 52:11:09 loss: 0.3077 loss_seg: 0.2007 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:58:58,775 INFO misc.py line 117 726] Train: [8/20][8/510] Data 2.167 (3.357) Batch 18.760 (26.445) Remain 48:38:39 loss: 0.2629 loss_seg: 0.1680 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:59:21,962 INFO misc.py line 117 726] Train: [8/20][9/510] Data 2.610 (3.233) Batch 23.187 (25.902) Remain 47:38:17 loss: 0.2662 loss_seg: 0.1658 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 19:59:46,675 INFO misc.py line 117 726] Train: [8/20][10/510] Data 2.993 (3.198) Batch 24.713 (25.732) Remain 47:19:07 loss: 0.2090 loss_seg: 0.1163 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:00:23,953 INFO misc.py line 117 726] Train: [8/20][11/510] Data 6.874 (3.658) Batch 37.278 (27.175) Remain 49:57:54 loss: 0.5535 loss_seg: 0.4297 loss_superpoint_edge: 0.0532 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:00:46,808 INFO misc.py line 117 726] Train: [8/20][12/510] Data 2.951 (3.579) Batch 22.856 (26.695) Remain 49:04:30 loss: 0.3093 loss_seg: 0.2024 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:01:05,907 INFO misc.py line 117 726] Train: [8/20][13/510] Data 2.957 (3.517) Batch 19.099 (25.936) Remain 47:40:16 loss: 0.2371 loss_seg: 0.1417 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:01:35,402 INFO misc.py line 117 726] Train: [8/20][14/510] Data 5.504 (3.698) Batch 29.495 (26.259) Remain 48:15:31 loss: 0.2303 loss_seg: 0.1317 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:02:07,894 INFO misc.py line 117 726] Train: [8/20][15/510] Data 3.678 (3.696) Batch 32.491 (26.779) Remain 49:12:20 loss: 0.2377 loss_seg: 0.1456 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:02:37,018 INFO misc.py line 117 726] Train: [8/20][16/510] Data 2.882 (3.633) Batch 29.125 (26.959) Remain 49:31:47 loss: 0.2372 loss_seg: 0.1436 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:02:58,453 INFO misc.py line 117 726] Train: [8/20][17/510] Data 2.505 (3.553) Batch 21.434 (26.565) Remain 48:47:51 loss: 0.2484 loss_seg: 0.1557 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:03:22,799 INFO misc.py line 117 726] Train: [8/20][18/510] Data 3.115 (3.524) Batch 24.346 (26.417) Remain 48:31:06 loss: 0.2104 loss_seg: 0.1174 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:03:45,722 INFO misc.py line 117 726] Train: [8/20][19/510] Data 2.240 (3.443) Batch 22.923 (26.198) Remain 48:06:36 loss: 0.1999 loss_seg: 0.1120 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:04:23,916 INFO misc.py line 117 726] Train: [8/20][20/510] Data 11.136 (3.896) Batch 38.195 (26.904) Remain 49:23:54 loss: 0.2201 loss_seg: 0.1294 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:04:48,616 INFO misc.py line 117 726] Train: [8/20][21/510] Data 3.966 (3.900) Batch 24.700 (26.781) Remain 49:09:58 loss: 0.2394 loss_seg: 0.1459 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:05:16,274 INFO misc.py line 117 726] Train: [8/20][22/510] Data 2.031 (3.801) Batch 27.657 (26.828) Remain 49:14:36 loss: 0.2225 loss_seg: 0.1307 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:05:53,464 INFO misc.py line 117 726] Train: [8/20][23/510] Data 5.244 (3.873) Batch 37.191 (27.346) Remain 50:11:13 loss: 0.2297 loss_seg: 0.1398 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:06:24,191 INFO misc.py line 117 726] Train: [8/20][24/510] Data 3.034 (3.833) Batch 30.727 (27.507) Remain 50:28:29 loss: 0.2570 loss_seg: 0.1589 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:06:44,253 INFO misc.py line 117 726] Train: [8/20][25/510] Data 2.568 (3.776) Batch 20.062 (27.168) Remain 49:50:46 loss: 0.2293 loss_seg: 0.1340 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:07:17,830 INFO misc.py line 117 726] Train: [8/20][26/510] Data 4.054 (3.788) Batch 33.577 (27.447) Remain 50:20:59 loss: 0.2726 loss_seg: 0.1714 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:07:47,039 INFO misc.py line 117 726] Train: [8/20][27/510] Data 3.151 (3.761) Batch 29.210 (27.520) Remain 50:28:37 loss: 0.2957 loss_seg: 0.2018 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:08:13,288 INFO misc.py line 117 726] Train: [8/20][28/510] Data 3.944 (3.769) Batch 26.248 (27.470) Remain 50:22:33 loss: 0.4186 loss_seg: 0.3008 loss_superpoint_edge: 0.0487 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:08:44,705 INFO misc.py line 117 726] Train: [8/20][29/510] Data 3.348 (3.753) Batch 31.418 (27.621) Remain 50:38:48 loss: 0.2455 loss_seg: 0.1589 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:09:06,416 INFO misc.py line 117 726] Train: [8/20][30/510] Data 2.594 (3.710) Batch 21.711 (27.402) Remain 50:14:16 loss: 0.2946 loss_seg: 0.1900 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0455 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:09:27,101 INFO misc.py line 117 726] Train: [8/20][31/510] Data 3.379 (3.698) Batch 20.685 (27.163) Remain 49:47:25 loss: 0.3157 loss_seg: 0.2269 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:09:52,977 INFO misc.py line 117 726] Train: [8/20][32/510] Data 2.767 (3.666) Batch 25.876 (27.118) Remain 49:42:05 loss: 0.2272 loss_seg: 0.1332 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:10:12,186 INFO misc.py line 117 726] Train: [8/20][33/510] Data 2.038 (3.612) Batch 19.209 (26.855) Remain 49:12:39 loss: 0.1788 loss_seg: 0.0930 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:10:41,266 INFO misc.py line 117 726] Train: [8/20][34/510] Data 3.165 (3.597) Batch 29.080 (26.926) Remain 49:20:06 loss: 0.3013 loss_seg: 0.2021 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:11:06,228 INFO misc.py line 117 726] Train: [8/20][35/510] Data 2.760 (3.571) Batch 24.962 (26.865) Remain 49:12:54 loss: 0.2889 loss_seg: 0.1843 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:11:33,690 INFO misc.py line 117 726] Train: [8/20][36/510] Data 2.863 (3.550) Batch 27.462 (26.883) Remain 49:14:26 loss: 0.2321 loss_seg: 0.1369 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:12:00,375 INFO misc.py line 117 726] Train: [8/20][37/510] Data 2.805 (3.528) Batch 26.684 (26.877) Remain 49:13:21 loss: 0.2140 loss_seg: 0.1221 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:12:27,353 INFO misc.py line 117 726] Train: [8/20][38/510] Data 3.427 (3.525) Batch 26.978 (26.880) Remain 49:13:13 loss: 0.2503 loss_seg: 0.1564 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:12:58,284 INFO misc.py line 117 726] Train: [8/20][39/510] Data 3.937 (3.536) Batch 30.931 (26.993) Remain 49:25:08 loss: 0.2773 loss_seg: 0.1727 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:13:18,078 INFO misc.py line 117 726] Train: [8/20][40/510] Data 1.908 (3.492) Batch 19.794 (26.798) Remain 49:03:19 loss: 0.2051 loss_seg: 0.1158 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:13:49,073 INFO misc.py line 117 726] Train: [8/20][41/510] Data 3.997 (3.505) Batch 30.994 (26.908) Remain 49:15:00 loss: 0.2308 loss_seg: 0.1366 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:14:20,157 INFO misc.py line 117 726] Train: [8/20][42/510] Data 3.614 (3.508) Batch 31.084 (27.016) Remain 49:26:18 loss: 0.2614 loss_seg: 0.1618 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:14:48,403 INFO misc.py line 117 726] Train: [8/20][43/510] Data 3.158 (3.499) Batch 28.246 (27.046) Remain 49:29:14 loss: 0.2666 loss_seg: 0.1683 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:15:23,736 INFO misc.py line 117 726] Train: [8/20][44/510] Data 3.995 (3.512) Batch 35.333 (27.248) Remain 49:50:58 loss: 0.2503 loss_seg: 0.1538 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:15:55,128 INFO misc.py line 117 726] Train: [8/20][45/510] Data 2.813 (3.495) Batch 31.392 (27.347) Remain 50:01:20 loss: 0.2398 loss_seg: 0.1475 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:16:18,472 INFO misc.py line 117 726] Train: [8/20][46/510] Data 2.456 (3.471) Batch 23.344 (27.254) Remain 49:50:40 loss: 0.2843 loss_seg: 0.1891 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:16:59,554 INFO misc.py line 117 726] Train: [8/20][47/510] Data 8.965 (3.596) Batch 41.082 (27.568) Remain 50:24:42 loss: 0.2715 loss_seg: 0.1670 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:17:26,149 INFO misc.py line 117 726] Train: [8/20][48/510] Data 5.218 (3.632) Batch 26.594 (27.547) Remain 50:21:52 loss: 0.1770 loss_seg: 0.0916 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:17:50,548 INFO misc.py line 117 726] Train: [8/20][49/510] Data 2.210 (3.601) Batch 24.400 (27.478) Remain 50:13:54 loss: 0.2886 loss_seg: 0.1787 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:18:21,091 INFO misc.py line 117 726] Train: [8/20][50/510] Data 4.502 (3.620) Batch 30.543 (27.543) Remain 50:20:35 loss: 0.2347 loss_seg: 0.1409 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:18:21,092 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 20:18:54,961 INFO misc.py line 117 726] Train: [8/20][51/510] Data 6.403 (3.678) Batch 33.870 (27.675) Remain 50:34:35 loss: 0.2515 loss_seg: 0.1557 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0441 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:19:21,478 INFO misc.py line 117 726] Train: [8/20][52/510] Data 3.054 (3.665) Batch 26.517 (27.652) Remain 50:31:32 loss: 0.3513 loss_seg: 0.2301 loss_superpoint_edge: 0.0550 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:19:46,820 INFO misc.py line 117 726] Train: [8/20][53/510] Data 4.702 (3.686) Batch 25.342 (27.605) Remain 50:26:00 loss: 0.2661 loss_seg: 0.1684 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:20:12,189 INFO misc.py line 117 726] Train: [8/20][54/510] Data 2.986 (3.672) Batch 25.369 (27.562) Remain 50:20:44 loss: 0.2336 loss_seg: 0.1352 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:20:41,016 INFO misc.py line 117 726] Train: [8/20][55/510] Data 2.940 (3.658) Batch 28.828 (27.586) Remain 50:22:57 loss: 0.2367 loss_seg: 0.1450 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:21:10,892 INFO misc.py line 117 726] Train: [8/20][56/510] Data 3.376 (3.653) Batch 29.876 (27.629) Remain 50:27:13 loss: 0.2582 loss_seg: 0.1618 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:21:36,854 INFO misc.py line 117 726] Train: [8/20][57/510] Data 2.495 (3.631) Batch 25.962 (27.598) Remain 50:23:23 loss: 0.2290 loss_seg: 0.1360 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:22:01,800 INFO misc.py line 117 726] Train: [8/20][58/510] Data 2.582 (3.612) Batch 24.946 (27.550) Remain 50:17:38 loss: 0.2671 loss_seg: 0.1728 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:22:17,720 INFO misc.py line 117 726] Train: [8/20][59/510] Data 2.040 (3.584) Batch 15.920 (27.342) Remain 49:54:26 loss: 0.2091 loss_seg: 0.1134 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:22:50,511 INFO misc.py line 117 726] Train: [8/20][60/510] Data 5.549 (3.619) Batch 32.791 (27.438) Remain 50:04:27 loss: 0.2523 loss_seg: 0.1571 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:23:23,674 INFO misc.py line 117 726] Train: [8/20][61/510] Data 3.414 (3.615) Batch 33.164 (27.537) Remain 50:14:48 loss: 0.3227 loss_seg: 0.2271 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:23:57,882 INFO misc.py line 117 726] Train: [8/20][62/510] Data 4.113 (3.624) Batch 34.207 (27.650) Remain 50:26:43 loss: 0.1587 loss_seg: 0.0791 loss_superpoint_edge: 0.0135 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:24:17,463 INFO misc.py line 117 726] Train: [8/20][63/510] Data 2.323 (3.602) Batch 19.581 (27.515) Remain 50:11:32 loss: 0.2153 loss_seg: 0.1246 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:24:50,726 INFO misc.py line 117 726] Train: [8/20][64/510] Data 3.792 (3.605) Batch 33.263 (27.609) Remain 50:21:23 loss: 0.2234 loss_seg: 0.1313 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:25:20,211 INFO misc.py line 117 726] Train: [8/20][65/510] Data 2.986 (3.595) Batch 29.485 (27.640) Remain 50:24:14 loss: 0.1894 loss_seg: 0.1028 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:25:52,364 INFO misc.py line 117 726] Train: [8/20][66/510] Data 3.718 (3.597) Batch 32.154 (27.711) Remain 50:31:37 loss: 0.2556 loss_seg: 0.1576 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:26:17,692 INFO misc.py line 117 726] Train: [8/20][67/510] Data 2.776 (3.584) Batch 25.328 (27.674) Remain 50:27:05 loss: 0.2433 loss_seg: 0.1500 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:26:39,026 INFO misc.py line 117 726] Train: [8/20][68/510] Data 2.083 (3.561) Batch 21.333 (27.577) Remain 50:15:57 loss: 0.2255 loss_seg: 0.1320 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:27:05,700 INFO misc.py line 117 726] Train: [8/20][69/510] Data 3.177 (3.555) Batch 26.675 (27.563) Remain 50:14:00 loss: 0.2559 loss_seg: 0.1645 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:27:35,349 INFO misc.py line 117 726] Train: [8/20][70/510] Data 5.809 (3.589) Batch 29.649 (27.594) Remain 50:16:56 loss: 0.2383 loss_seg: 0.1435 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:28:03,198 INFO misc.py line 117 726] Train: [8/20][71/510] Data 3.061 (3.581) Batch 27.849 (27.598) Remain 50:16:53 loss: 0.2414 loss_seg: 0.1461 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:28:28,454 INFO misc.py line 117 726] Train: [8/20][72/510] Data 3.513 (3.580) Batch 25.256 (27.564) Remain 50:12:43 loss: 0.2482 loss_seg: 0.1554 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:29:00,097 INFO misc.py line 117 726] Train: [8/20][73/510] Data 3.651 (3.581) Batch 31.643 (27.622) Remain 50:18:38 loss: 0.2222 loss_seg: 0.1293 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:29:16,802 INFO misc.py line 117 726] Train: [8/20][74/510] Data 1.734 (3.555) Batch 16.705 (27.468) Remain 50:01:22 loss: 0.1946 loss_seg: 0.1081 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:29:44,111 INFO misc.py line 117 726] Train: [8/20][75/510] Data 2.611 (3.542) Batch 27.309 (27.466) Remain 50:00:40 loss: 0.2162 loss_seg: 0.1238 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:30:16,154 INFO misc.py line 117 726] Train: [8/20][76/510] Data 5.404 (3.568) Batch 32.043 (27.529) Remain 50:07:03 loss: 0.1947 loss_seg: 0.1041 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:30:37,984 INFO misc.py line 117 726] Train: [8/20][77/510] Data 2.641 (3.555) Batch 21.830 (27.452) Remain 49:58:11 loss: 0.2072 loss_seg: 0.1150 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:31:16,816 INFO misc.py line 117 726] Train: [8/20][78/510] Data 7.304 (3.605) Batch 38.833 (27.604) Remain 50:14:18 loss: 0.2698 loss_seg: 0.1758 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:31:42,087 INFO misc.py line 117 726] Train: [8/20][79/510] Data 3.250 (3.600) Batch 25.270 (27.573) Remain 50:10:29 loss: 0.2087 loss_seg: 0.1192 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:32:12,487 INFO misc.py line 117 726] Train: [8/20][80/510] Data 2.792 (3.590) Batch 30.400 (27.610) Remain 50:14:02 loss: 0.2521 loss_seg: 0.1517 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:32:38,452 INFO misc.py line 117 726] Train: [8/20][81/510] Data 4.363 (3.600) Batch 25.965 (27.588) Remain 50:11:17 loss: 0.2353 loss_seg: 0.1388 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:33:01,371 INFO misc.py line 117 726] Train: [8/20][82/510] Data 2.786 (3.589) Batch 22.919 (27.529) Remain 50:04:22 loss: 0.2340 loss_seg: 0.1375 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:33:30,386 INFO misc.py line 117 726] Train: [8/20][83/510] Data 5.204 (3.610) Batch 29.016 (27.548) Remain 50:05:56 loss: 0.2297 loss_seg: 0.1348 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:34:06,384 INFO misc.py line 117 726] Train: [8/20][84/510] Data 5.226 (3.630) Batch 35.998 (27.652) Remain 50:16:51 loss: 0.2238 loss_seg: 0.1281 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:34:36,405 INFO misc.py line 117 726] Train: [8/20][85/510] Data 3.427 (3.627) Batch 30.021 (27.681) Remain 50:19:33 loss: 0.2532 loss_seg: 0.1600 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:34:56,568 INFO misc.py line 117 726] Train: [8/20][86/510] Data 2.177 (3.610) Batch 20.163 (27.591) Remain 50:09:12 loss: 0.1988 loss_seg: 0.1087 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:35:13,317 INFO misc.py line 117 726] Train: [8/20][87/510] Data 1.842 (3.589) Batch 16.749 (27.462) Remain 49:54:40 loss: 0.3370 loss_seg: 0.2333 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:35:47,590 INFO misc.py line 117 726] Train: [8/20][88/510] Data 3.441 (3.587) Batch 34.273 (27.542) Remain 50:02:57 loss: 0.3065 loss_seg: 0.2010 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:36:13,574 INFO misc.py line 117 726] Train: [8/20][89/510] Data 4.674 (3.600) Batch 25.984 (27.524) Remain 50:00:31 loss: 0.2591 loss_seg: 0.1603 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:36:51,514 INFO misc.py line 117 726] Train: [8/20][90/510] Data 13.146 (3.709) Batch 37.940 (27.643) Remain 50:13:06 loss: 0.5604 loss_seg: 0.4457 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0441 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:37:27,977 INFO misc.py line 117 726] Train: [8/20][91/510] Data 4.719 (3.721) Batch 36.463 (27.743) Remain 50:23:34 loss: 0.2031 loss_seg: 0.1122 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:38:00,060 INFO misc.py line 117 726] Train: [8/20][92/510] Data 5.242 (3.738) Batch 32.083 (27.792) Remain 50:28:25 loss: 0.3790 loss_seg: 0.2791 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:38:36,360 INFO misc.py line 117 726] Train: [8/20][93/510] Data 4.455 (3.746) Batch 36.300 (27.887) Remain 50:38:15 loss: 0.2693 loss_seg: 0.1681 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:39:07,151 INFO misc.py line 117 726] Train: [8/20][94/510] Data 3.729 (3.746) Batch 30.791 (27.919) Remain 50:41:16 loss: 0.2518 loss_seg: 0.1570 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:39:36,847 INFO misc.py line 117 726] Train: [8/20][95/510] Data 3.679 (3.745) Batch 29.695 (27.938) Remain 50:42:54 loss: 0.2558 loss_seg: 0.1562 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:40:07,863 INFO misc.py line 117 726] Train: [8/20][96/510] Data 3.756 (3.745) Batch 31.016 (27.971) Remain 50:46:03 loss: 0.3066 loss_seg: 0.2035 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0311 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:40:44,840 INFO misc.py line 117 726] Train: [8/20][97/510] Data 4.758 (3.756) Batch 36.977 (28.067) Remain 50:56:01 loss: 0.2987 loss_seg: 0.2026 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:41:12,821 INFO misc.py line 117 726] Train: [8/20][98/510] Data 3.087 (3.749) Batch 27.981 (28.066) Remain 50:55:27 loss: 0.2234 loss_seg: 0.1301 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:41:37,442 INFO misc.py line 117 726] Train: [8/20][99/510] Data 4.563 (3.757) Batch 24.622 (28.030) Remain 50:51:04 loss: 0.2300 loss_seg: 0.1332 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:42:07,687 INFO misc.py line 117 726] Train: [8/20][100/510] Data 3.550 (3.755) Batch 30.245 (28.053) Remain 50:53:05 loss: 0.2259 loss_seg: 0.1404 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:42:07,687 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 20:42:33,877 INFO misc.py line 117 726] Train: [8/20][101/510] Data 3.633 (3.754) Batch 26.191 (28.034) Remain 50:50:33 loss: 0.2205 loss_seg: 0.1276 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:43:00,721 INFO misc.py line 117 726] Train: [8/20][102/510] Data 3.150 (3.748) Batch 26.843 (28.022) Remain 50:48:47 loss: 0.2320 loss_seg: 0.1391 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:43:38,071 INFO misc.py line 117 726] Train: [8/20][103/510] Data 6.301 (3.773) Batch 37.350 (28.115) Remain 50:58:27 loss: 0.2460 loss_seg: 0.1544 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:44:11,763 INFO misc.py line 117 726] Train: [8/20][104/510] Data 5.689 (3.792) Batch 33.692 (28.170) Remain 51:04:00 loss: 0.2245 loss_seg: 0.1298 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:44:28,792 INFO misc.py line 117 726] Train: [8/20][105/510] Data 1.802 (3.773) Batch 17.029 (28.061) Remain 50:51:39 loss: 0.2425 loss_seg: 0.1451 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:45:03,591 INFO misc.py line 117 726] Train: [8/20][106/510] Data 3.822 (3.773) Batch 34.799 (28.127) Remain 50:58:17 loss: 0.2603 loss_seg: 0.1630 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:45:29,914 INFO misc.py line 117 726] Train: [8/20][107/510] Data 2.692 (3.763) Batch 26.323 (28.109) Remain 50:55:56 loss: 0.2216 loss_seg: 0.1285 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:46:05,802 INFO misc.py line 117 726] Train: [8/20][108/510] Data 6.104 (3.785) Batch 35.888 (28.183) Remain 51:03:31 loss: 0.2298 loss_seg: 0.1355 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:46:39,542 INFO misc.py line 117 726] Train: [8/20][109/510] Data 6.053 (3.806) Batch 33.741 (28.236) Remain 51:08:45 loss: 0.2967 loss_seg: 0.1888 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:47:13,777 INFO misc.py line 117 726] Train: [8/20][110/510] Data 3.738 (3.806) Batch 34.235 (28.292) Remain 51:14:22 loss: 0.2060 loss_seg: 0.1165 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:47:42,512 INFO misc.py line 117 726] Train: [8/20][111/510] Data 3.044 (3.799) Batch 28.736 (28.296) Remain 51:14:21 loss: 0.2524 loss_seg: 0.1528 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:47:59,907 INFO misc.py line 117 726] Train: [8/20][112/510] Data 1.792 (3.780) Batch 17.394 (28.196) Remain 51:03:01 loss: 0.2448 loss_seg: 0.1454 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:48:34,001 INFO misc.py line 117 726] Train: [8/20][113/510] Data 3.757 (3.780) Batch 34.094 (28.250) Remain 51:08:22 loss: 0.2667 loss_seg: 0.1740 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:49:01,991 INFO misc.py line 117 726] Train: [8/20][114/510] Data 3.558 (3.778) Batch 27.989 (28.247) Remain 51:07:38 loss: 0.2457 loss_seg: 0.1507 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:49:32,609 INFO misc.py line 117 726] Train: [8/20][115/510] Data 2.795 (3.769) Batch 30.619 (28.268) Remain 51:09:28 loss: 0.2355 loss_seg: 0.1426 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:49:58,155 INFO misc.py line 117 726] Train: [8/20][116/510] Data 3.363 (3.766) Batch 25.546 (28.244) Remain 51:06:23 loss: 0.2309 loss_seg: 0.1386 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:50:27,867 INFO misc.py line 117 726] Train: [8/20][117/510] Data 3.808 (3.766) Batch 29.712 (28.257) Remain 51:07:18 loss: 0.1939 loss_seg: 0.1072 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:50:53,536 INFO misc.py line 117 726] Train: [8/20][118/510] Data 3.357 (3.763) Batch 25.669 (28.235) Remain 51:04:24 loss: 0.2515 loss_seg: 0.1534 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:51:26,569 INFO misc.py line 117 726] Train: [8/20][119/510] Data 6.220 (3.784) Batch 33.033 (28.276) Remain 51:08:25 loss: 0.1917 loss_seg: 0.0929 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0457 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:52:00,712 INFO misc.py line 117 726] Train: [8/20][120/510] Data 3.853 (3.784) Batch 34.143 (28.326) Remain 51:13:23 loss: 0.3527 loss_seg: 0.2509 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:52:21,300 INFO misc.py line 117 726] Train: [8/20][121/510] Data 2.432 (3.773) Batch 20.588 (28.261) Remain 51:05:48 loss: 0.3211 loss_seg: 0.2253 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:52:47,029 INFO misc.py line 117 726] Train: [8/20][122/510] Data 2.411 (3.761) Batch 25.729 (28.239) Remain 51:03:01 loss: 0.2237 loss_seg: 0.1297 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:53:18,515 INFO misc.py line 117 726] Train: [8/20][123/510] Data 3.551 (3.760) Batch 31.486 (28.266) Remain 51:05:29 loss: 0.2539 loss_seg: 0.1594 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:53:51,083 INFO misc.py line 117 726] Train: [8/20][124/510] Data 4.020 (3.762) Batch 32.567 (28.302) Remain 51:08:52 loss: 0.2527 loss_seg: 0.1641 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:54:14,716 INFO misc.py line 117 726] Train: [8/20][125/510] Data 2.916 (3.755) Batch 23.633 (28.264) Remain 51:04:15 loss: 0.2231 loss_seg: 0.1308 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:54:41,922 INFO misc.py line 117 726] Train: [8/20][126/510] Data 3.065 (3.749) Batch 27.206 (28.255) Remain 51:02:50 loss: 0.2999 loss_seg: 0.2098 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:55:02,728 INFO misc.py line 117 726] Train: [8/20][127/510] Data 2.460 (3.739) Batch 20.806 (28.195) Remain 50:55:51 loss: 0.2157 loss_seg: 0.1275 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:55:32,426 INFO misc.py line 117 726] Train: [8/20][128/510] Data 2.705 (3.731) Batch 29.698 (28.207) Remain 50:56:41 loss: 0.2315 loss_seg: 0.1353 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:56:03,540 INFO misc.py line 117 726] Train: [8/20][129/510] Data 2.694 (3.722) Batch 31.113 (28.230) Remain 50:58:43 loss: 0.2061 loss_seg: 0.1137 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:56:34,925 INFO misc.py line 117 726] Train: [8/20][130/510] Data 4.900 (3.732) Batch 31.386 (28.255) Remain 51:00:56 loss: 0.2347 loss_seg: 0.1386 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:57:02,850 INFO misc.py line 117 726] Train: [8/20][131/510] Data 5.440 (3.745) Batch 27.926 (28.252) Remain 51:00:11 loss: 0.2195 loss_seg: 0.1271 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:57:31,226 INFO misc.py line 117 726] Train: [8/20][132/510] Data 4.794 (3.753) Batch 28.375 (28.253) Remain 50:59:49 loss: 0.2673 loss_seg: 0.1714 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:57:56,441 INFO misc.py line 117 726] Train: [8/20][133/510] Data 2.716 (3.745) Batch 25.216 (28.230) Remain 50:56:49 loss: 0.2704 loss_seg: 0.1725 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:58:21,064 INFO misc.py line 117 726] Train: [8/20][134/510] Data 2.708 (3.737) Batch 24.623 (28.202) Remain 50:53:22 loss: 0.2654 loss_seg: 0.1615 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:58:45,649 INFO misc.py line 117 726] Train: [8/20][135/510] Data 2.891 (3.731) Batch 24.585 (28.175) Remain 50:49:56 loss: 0.2510 loss_seg: 0.1533 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:59:14,692 INFO misc.py line 117 726] Train: [8/20][136/510] Data 3.006 (3.725) Batch 29.042 (28.182) Remain 50:50:10 loss: 0.3126 loss_seg: 0.2189 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 20:59:47,637 INFO misc.py line 117 726] Train: [8/20][137/510] Data 3.398 (3.723) Batch 32.945 (28.217) Remain 50:53:33 loss: 0.2167 loss_seg: 0.1245 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:00:26,957 INFO misc.py line 117 726] Train: [8/20][138/510] Data 8.655 (3.759) Batch 39.320 (28.299) Remain 51:01:59 loss: 0.2756 loss_seg: 0.1849 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:00:56,715 INFO misc.py line 117 726] Train: [8/20][139/510] Data 3.727 (3.759) Batch 29.759 (28.310) Remain 51:02:40 loss: 0.2615 loss_seg: 0.1692 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:01:19,053 INFO misc.py line 117 726] Train: [8/20][140/510] Data 2.518 (3.750) Batch 22.338 (28.266) Remain 50:57:29 loss: 0.2713 loss_seg: 0.1805 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:01:41,880 INFO misc.py line 117 726] Train: [8/20][141/510] Data 2.016 (3.738) Batch 22.827 (28.227) Remain 50:52:45 loss: 0.2830 loss_seg: 0.1825 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:02:13,515 INFO misc.py line 117 726] Train: [8/20][142/510] Data 3.874 (3.739) Batch 31.634 (28.252) Remain 50:54:56 loss: 0.2479 loss_seg: 0.1472 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:02:36,996 INFO misc.py line 117 726] Train: [8/20][143/510] Data 2.270 (3.728) Batch 23.481 (28.217) Remain 50:50:46 loss: 0.2027 loss_seg: 0.1139 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:03:12,171 INFO misc.py line 117 726] Train: [8/20][144/510] Data 4.492 (3.734) Batch 35.175 (28.267) Remain 50:55:38 loss: 0.3372 loss_seg: 0.2296 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:03:34,606 INFO misc.py line 117 726] Train: [8/20][145/510] Data 2.312 (3.724) Batch 22.435 (28.226) Remain 50:50:43 loss: 0.1870 loss_seg: 0.1010 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:04:02,745 INFO misc.py line 117 726] Train: [8/20][146/510] Data 3.330 (3.721) Batch 28.139 (28.225) Remain 50:50:11 loss: 0.3393 loss_seg: 0.2267 loss_superpoint_edge: 0.0446 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:04:37,939 INFO misc.py line 117 726] Train: [8/20][147/510] Data 4.435 (3.726) Batch 35.194 (28.274) Remain 50:54:57 loss: 0.2526 loss_seg: 0.1570 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:04:59,037 INFO misc.py line 117 726] Train: [8/20][148/510] Data 3.086 (3.721) Batch 21.098 (28.224) Remain 50:49:08 loss: 0.2641 loss_seg: 0.1777 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:05:34,054 INFO misc.py line 117 726] Train: [8/20][149/510] Data 4.195 (3.725) Batch 35.017 (28.271) Remain 50:53:41 loss: 0.2600 loss_seg: 0.1665 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:06:05,583 INFO misc.py line 117 726] Train: [8/20][150/510] Data 5.101 (3.734) Batch 31.529 (28.293) Remain 50:55:36 loss: 0.2743 loss_seg: 0.1726 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:06:05,584 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 21:06:25,940 INFO misc.py line 117 726] Train: [8/20][151/510] Data 3.831 (3.735) Batch 20.357 (28.239) Remain 50:49:21 loss: 0.3767 loss_seg: 0.2734 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:06:44,908 INFO misc.py line 117 726] Train: [8/20][152/510] Data 2.762 (3.728) Batch 18.967 (28.177) Remain 50:42:09 loss: 0.1917 loss_seg: 0.1023 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:07:11,190 INFO misc.py line 117 726] Train: [8/20][153/510] Data 2.787 (3.722) Batch 26.283 (28.164) Remain 50:40:19 loss: 0.2553 loss_seg: 0.1582 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:07:36,518 INFO misc.py line 117 726] Train: [8/20][154/510] Data 2.518 (3.714) Batch 25.328 (28.145) Remain 50:37:50 loss: 0.2053 loss_seg: 0.1126 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:08:03,964 INFO misc.py line 117 726] Train: [8/20][155/510] Data 5.237 (3.724) Batch 27.446 (28.141) Remain 50:36:52 loss: 0.3200 loss_seg: 0.2192 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:08:25,119 INFO misc.py line 117 726] Train: [8/20][156/510] Data 3.016 (3.719) Batch 21.155 (28.095) Remain 50:31:28 loss: 0.2819 loss_seg: 0.1784 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:08:52,869 INFO misc.py line 117 726] Train: [8/20][157/510] Data 2.866 (3.714) Batch 27.749 (28.093) Remain 50:30:45 loss: 0.2119 loss_seg: 0.1235 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:09:24,556 INFO misc.py line 117 726] Train: [8/20][158/510] Data 6.566 (3.732) Batch 31.688 (28.116) Remain 50:32:47 loss: 0.2061 loss_seg: 0.1158 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:09:58,236 INFO misc.py line 117 726] Train: [8/20][159/510] Data 3.935 (3.733) Batch 33.680 (28.152) Remain 50:36:10 loss: 0.2171 loss_seg: 0.1283 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:10:30,908 INFO misc.py line 117 726] Train: [8/20][160/510] Data 4.856 (3.741) Batch 32.672 (28.181) Remain 50:38:48 loss: 0.3577 loss_seg: 0.2534 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:10:53,413 INFO misc.py line 117 726] Train: [8/20][161/510] Data 2.752 (3.734) Batch 22.505 (28.145) Remain 50:34:28 loss: 0.3114 loss_seg: 0.2150 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:11:28,250 INFO misc.py line 117 726] Train: [8/20][162/510] Data 3.429 (3.732) Batch 34.836 (28.187) Remain 50:38:32 loss: 0.2230 loss_seg: 0.1279 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:12:03,113 INFO misc.py line 117 726] Train: [8/20][163/510] Data 5.144 (3.741) Batch 34.863 (28.229) Remain 50:42:33 loss: 0.2472 loss_seg: 0.1563 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:12:36,585 INFO misc.py line 117 726] Train: [8/20][164/510] Data 5.659 (3.753) Batch 33.473 (28.261) Remain 50:45:36 loss: 0.2567 loss_seg: 0.1556 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:12:57,867 INFO misc.py line 117 726] Train: [8/20][165/510] Data 2.470 (3.745) Batch 21.282 (28.218) Remain 50:40:29 loss: 0.4481 loss_seg: 0.3428 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:13:21,443 INFO misc.py line 117 726] Train: [8/20][166/510] Data 2.767 (3.739) Batch 23.576 (28.190) Remain 50:36:57 loss: 0.3041 loss_seg: 0.2031 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:13:58,022 INFO misc.py line 117 726] Train: [8/20][167/510] Data 6.298 (3.755) Batch 36.579 (28.241) Remain 50:41:59 loss: 0.1822 loss_seg: 0.0955 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:14:36,662 INFO misc.py line 117 726] Train: [8/20][168/510] Data 8.678 (3.785) Batch 38.640 (28.304) Remain 50:48:18 loss: 0.2086 loss_seg: 0.1237 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:15:14,418 INFO misc.py line 117 726] Train: [8/20][169/510] Data 6.131 (3.799) Batch 37.756 (28.361) Remain 50:53:58 loss: 0.2401 loss_seg: 0.1444 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:15:47,225 INFO misc.py line 117 726] Train: [8/20][170/510] Data 3.738 (3.798) Batch 32.808 (28.387) Remain 50:56:21 loss: 0.2327 loss_seg: 0.1327 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00002 [2026-06-10 21:16:11,515 INFO misc.py line 117 726] Train: [8/20][171/510] Data 2.817 (3.793) Batch 24.290 (28.363) Remain 50:53:15 loss: 0.2526 loss_seg: 0.1605 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:16:30,240 INFO misc.py line 117 726] Train: [8/20][172/510] Data 2.105 (3.783) Batch 18.724 (28.306) Remain 50:46:39 loss: 0.2018 loss_seg: 0.1132 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:17:04,025 INFO misc.py line 117 726] Train: [8/20][173/510] Data 5.496 (3.793) Batch 33.785 (28.338) Remain 50:49:39 loss: 0.3258 loss_seg: 0.2283 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:17:21,786 INFO misc.py line 117 726] Train: [8/20][174/510] Data 2.074 (3.783) Batch 17.761 (28.276) Remain 50:42:31 loss: 0.1943 loss_seg: 0.1093 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:17:45,473 INFO misc.py line 117 726] Train: [8/20][175/510] Data 2.546 (3.775) Batch 23.688 (28.250) Remain 50:39:10 loss: 0.2300 loss_seg: 0.1377 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:18:17,842 INFO misc.py line 117 726] Train: [8/20][176/510] Data 5.140 (3.783) Batch 32.368 (28.273) Remain 50:41:16 loss: 0.2118 loss_seg: 0.1229 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:18:44,557 INFO misc.py line 117 726] Train: [8/20][177/510] Data 3.461 (3.781) Batch 26.715 (28.264) Remain 50:39:50 loss: 0.2309 loss_seg: 0.1364 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:19:16,677 INFO misc.py line 117 726] Train: [8/20][178/510] Data 3.884 (3.782) Batch 32.120 (28.286) Remain 50:41:44 loss: 0.1970 loss_seg: 0.1093 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:19:46,325 INFO misc.py line 117 726] Train: [8/20][179/510] Data 5.690 (3.793) Batch 29.648 (28.294) Remain 50:42:05 loss: 0.2340 loss_seg: 0.1388 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:20:10,135 INFO misc.py line 117 726] Train: [8/20][180/510] Data 2.695 (3.787) Batch 23.810 (28.269) Remain 50:38:54 loss: 0.2719 loss_seg: 0.1719 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:20:38,828 INFO misc.py line 117 726] Train: [8/20][181/510] Data 3.653 (3.786) Batch 28.693 (28.271) Remain 50:38:41 loss: 0.2554 loss_seg: 0.1584 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:21:00,955 INFO misc.py line 117 726] Train: [8/20][182/510] Data 2.695 (3.780) Batch 22.128 (28.237) Remain 50:34:31 loss: 0.2082 loss_seg: 0.1172 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:21:31,729 INFO misc.py line 117 726] Train: [8/20][183/510] Data 3.933 (3.781) Batch 30.773 (28.251) Remain 50:35:34 loss: 0.2307 loss_seg: 0.1371 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:22:03,517 INFO misc.py line 117 726] Train: [8/20][184/510] Data 4.257 (3.783) Batch 31.788 (28.271) Remain 50:37:11 loss: 0.2820 loss_seg: 0.1819 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:22:23,641 INFO misc.py line 117 726] Train: [8/20][185/510] Data 2.254 (3.775) Batch 20.124 (28.226) Remain 50:31:55 loss: 0.2283 loss_seg: 0.1372 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:22:50,360 INFO misc.py line 117 726] Train: [8/20][186/510] Data 3.520 (3.773) Batch 26.719 (28.218) Remain 50:30:33 loss: 0.2588 loss_seg: 0.1633 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:23:27,455 INFO misc.py line 117 726] Train: [8/20][187/510] Data 6.197 (3.787) Batch 37.095 (28.266) Remain 50:35:16 loss: 0.2774 loss_seg: 0.1740 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:23:48,377 INFO misc.py line 117 726] Train: [8/20][188/510] Data 2.109 (3.778) Batch 20.922 (28.226) Remain 50:30:32 loss: 0.1851 loss_seg: 0.0992 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:24:14,527 INFO misc.py line 117 726] Train: [8/20][189/510] Data 2.673 (3.772) Batch 26.150 (28.215) Remain 50:28:52 loss: 0.2422 loss_seg: 0.1456 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:24:43,997 INFO misc.py line 117 726] Train: [8/20][190/510] Data 5.466 (3.781) Batch 29.469 (28.222) Remain 50:29:07 loss: 0.3553 loss_seg: 0.2537 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:25:10,665 INFO misc.py line 117 726] Train: [8/20][191/510] Data 3.347 (3.778) Batch 26.668 (28.213) Remain 50:27:45 loss: 0.2173 loss_seg: 0.1260 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:25:29,765 INFO misc.py line 117 726] Train: [8/20][192/510] Data 2.699 (3.773) Batch 19.100 (28.165) Remain 50:22:07 loss: 0.2313 loss_seg: 0.1385 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:26:02,792 INFO misc.py line 117 726] Train: [8/20][193/510] Data 4.132 (3.775) Batch 33.027 (28.191) Remain 50:24:23 loss: 0.2632 loss_seg: 0.1701 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:26:31,786 INFO misc.py line 117 726] Train: [8/20][194/510] Data 3.436 (3.773) Batch 28.994 (28.195) Remain 50:24:22 loss: 0.2341 loss_seg: 0.1402 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:27:01,371 INFO misc.py line 117 726] Train: [8/20][195/510] Data 4.221 (3.775) Batch 29.585 (28.202) Remain 50:24:41 loss: 0.1704 loss_seg: 0.0885 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:27:28,372 INFO misc.py line 117 726] Train: [8/20][196/510] Data 2.105 (3.766) Batch 27.000 (28.196) Remain 50:23:32 loss: 0.2677 loss_seg: 0.1695 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:27:57,609 INFO misc.py line 117 726] Train: [8/20][197/510] Data 3.468 (3.765) Batch 29.238 (28.201) Remain 50:23:39 loss: 0.1832 loss_seg: 0.0979 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:28:32,888 INFO misc.py line 117 726] Train: [8/20][198/510] Data 3.411 (3.763) Batch 35.278 (28.238) Remain 50:27:04 loss: 0.2389 loss_seg: 0.1433 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:29:01,813 INFO misc.py line 117 726] Train: [8/20][199/510] Data 5.869 (3.774) Batch 28.926 (28.241) Remain 50:26:58 loss: 0.3104 loss_seg: 0.2149 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:29:33,573 INFO misc.py line 117 726] Train: [8/20][200/510] Data 2.933 (3.770) Batch 31.760 (28.259) Remain 50:28:25 loss: 0.2242 loss_seg: 0.1344 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:29:33,574 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 21:29:56,695 INFO misc.py line 117 726] Train: [8/20][201/510] Data 2.415 (3.763) Batch 23.122 (28.233) Remain 50:25:10 loss: 0.2511 loss_seg: 0.1554 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:30:14,279 INFO misc.py line 117 726] Train: [8/20][202/510] Data 1.461 (3.751) Batch 17.584 (28.180) Remain 50:18:58 loss: 0.2258 loss_seg: 0.1307 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:30:45,065 INFO misc.py line 117 726] Train: [8/20][203/510] Data 2.742 (3.746) Batch 30.786 (28.193) Remain 50:19:53 loss: 0.2363 loss_seg: 0.1423 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:31:12,077 INFO misc.py line 117 726] Train: [8/20][204/510] Data 4.288 (3.749) Batch 27.012 (28.187) Remain 50:18:47 loss: 0.2459 loss_seg: 0.1547 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:31:39,661 INFO misc.py line 117 726] Train: [8/20][205/510] Data 3.009 (3.745) Batch 27.584 (28.184) Remain 50:18:00 loss: 0.2865 loss_seg: 0.1879 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:32:05,192 INFO misc.py line 117 726] Train: [8/20][206/510] Data 5.155 (3.752) Batch 25.531 (28.171) Remain 50:16:08 loss: 0.2540 loss_seg: 0.1605 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:32:31,784 INFO misc.py line 117 726] Train: [8/20][207/510] Data 4.694 (3.757) Batch 26.592 (28.163) Remain 50:14:50 loss: 0.1930 loss_seg: 0.1047 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:33:07,023 INFO misc.py line 117 726] Train: [8/20][208/510] Data 4.624 (3.761) Batch 35.239 (28.197) Remain 50:18:03 loss: 0.2279 loss_seg: 0.1350 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:33:41,486 INFO misc.py line 117 726] Train: [8/20][209/510] Data 3.597 (3.760) Batch 34.463 (28.228) Remain 50:20:50 loss: 0.2603 loss_seg: 0.1610 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:34:06,888 INFO misc.py line 117 726] Train: [8/20][210/510] Data 4.853 (3.765) Batch 25.402 (28.214) Remain 50:18:55 loss: 0.2142 loss_seg: 0.1270 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:34:43,298 INFO misc.py line 117 726] Train: [8/20][211/510] Data 6.997 (3.781) Batch 36.410 (28.254) Remain 50:22:39 loss: 0.2077 loss_seg: 0.1197 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:35:07,670 INFO misc.py line 117 726] Train: [8/20][212/510] Data 3.011 (3.777) Batch 24.372 (28.235) Remain 50:20:12 loss: 0.3106 loss_seg: 0.2185 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:35:37,668 INFO misc.py line 117 726] Train: [8/20][213/510] Data 3.622 (3.777) Batch 29.997 (28.243) Remain 50:20:37 loss: 0.2004 loss_seg: 0.1128 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:36:05,142 INFO misc.py line 117 726] Train: [8/20][214/510] Data 2.916 (3.772) Batch 27.475 (28.240) Remain 50:19:46 loss: 0.2187 loss_seg: 0.1273 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:36:36,483 INFO misc.py line 117 726] Train: [8/20][215/510] Data 2.911 (3.768) Batch 31.341 (28.254) Remain 50:20:51 loss: 0.2754 loss_seg: 0.1683 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:37:01,582 INFO misc.py line 117 726] Train: [8/20][216/510] Data 2.774 (3.764) Batch 25.099 (28.240) Remain 50:18:48 loss: 0.2470 loss_seg: 0.1522 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:37:23,051 INFO misc.py line 117 726] Train: [8/20][217/510] Data 2.627 (3.758) Batch 21.469 (28.208) Remain 50:14:57 loss: 0.2093 loss_seg: 0.1174 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:37:57,485 INFO misc.py line 117 726] Train: [8/20][218/510] Data 5.027 (3.764) Batch 34.434 (28.237) Remain 50:17:35 loss: 0.3181 loss_seg: 0.2027 loss_superpoint_edge: 0.0454 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:38:37,423 INFO misc.py line 117 726] Train: [8/20][219/510] Data 8.187 (3.785) Batch 39.938 (28.291) Remain 50:22:54 loss: 0.1909 loss_seg: 0.1077 loss_superpoint_edge: 0.0148 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:39:07,144 INFO misc.py line 117 726] Train: [8/20][220/510] Data 2.961 (3.781) Batch 29.722 (28.298) Remain 50:23:08 loss: 0.2376 loss_seg: 0.1434 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:39:34,679 INFO misc.py line 117 726] Train: [8/20][221/510] Data 3.630 (3.780) Batch 27.534 (28.294) Remain 50:22:17 loss: 0.2288 loss_seg: 0.1337 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:40:02,428 INFO misc.py line 117 726] Train: [8/20][222/510] Data 5.250 (3.787) Batch 27.749 (28.292) Remain 50:21:33 loss: 0.3032 loss_seg: 0.2031 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:40:32,561 INFO misc.py line 117 726] Train: [8/20][223/510] Data 2.923 (3.783) Batch 30.133 (28.300) Remain 50:21:58 loss: 0.2183 loss_seg: 0.1281 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:40:57,675 INFO misc.py line 117 726] Train: [8/20][224/510] Data 3.066 (3.780) Batch 25.114 (28.286) Remain 50:19:57 loss: 0.2363 loss_seg: 0.1455 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:41:30,034 INFO misc.py line 117 726] Train: [8/20][225/510] Data 3.972 (3.781) Batch 32.359 (28.304) Remain 50:21:27 loss: 0.2632 loss_seg: 0.1633 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:42:01,557 INFO misc.py line 117 726] Train: [8/20][226/510] Data 5.340 (3.788) Batch 31.522 (28.318) Remain 50:22:31 loss: 0.3710 loss_seg: 0.2699 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:42:26,317 INFO misc.py line 117 726] Train: [8/20][227/510] Data 3.038 (3.784) Batch 24.760 (28.303) Remain 50:20:21 loss: 0.2614 loss_seg: 0.1616 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:42:54,185 INFO misc.py line 117 726] Train: [8/20][228/510] Data 3.286 (3.782) Batch 27.868 (28.301) Remain 50:19:40 loss: 0.3135 loss_seg: 0.2068 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:43:24,106 INFO misc.py line 117 726] Train: [8/20][229/510] Data 4.797 (3.787) Batch 29.921 (28.308) Remain 50:19:58 loss: 0.1816 loss_seg: 0.0958 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:43:54,239 INFO misc.py line 117 726] Train: [8/20][230/510] Data 3.436 (3.785) Batch 30.133 (28.316) Remain 50:20:21 loss: 0.2485 loss_seg: 0.1524 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:44:19,101 INFO misc.py line 117 726] Train: [8/20][231/510] Data 4.063 (3.786) Batch 24.862 (28.301) Remain 50:18:15 loss: 0.2987 loss_seg: 0.2004 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:44:41,214 INFO misc.py line 117 726] Train: [8/20][232/510] Data 2.942 (3.783) Batch 22.113 (28.274) Remain 50:14:54 loss: 0.2077 loss_seg: 0.1191 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:45:06,278 INFO misc.py line 117 726] Train: [8/20][233/510] Data 2.660 (3.778) Batch 25.064 (28.260) Remain 50:12:57 loss: 0.2267 loss_seg: 0.1337 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:45:45,793 INFO misc.py line 117 726] Train: [8/20][234/510] Data 7.448 (3.794) Batch 39.515 (28.308) Remain 50:17:40 loss: 0.2640 loss_seg: 0.1705 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:46:10,496 INFO misc.py line 117 726] Train: [8/20][235/510] Data 2.707 (3.789) Batch 24.703 (28.293) Remain 50:15:32 loss: 0.2411 loss_seg: 0.1455 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:46:35,439 INFO misc.py line 117 726] Train: [8/20][236/510] Data 2.710 (3.784) Batch 24.943 (28.278) Remain 50:13:32 loss: 0.2185 loss_seg: 0.1266 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:47:00,169 INFO misc.py line 117 726] Train: [8/20][237/510] Data 2.449 (3.779) Batch 24.730 (28.263) Remain 50:11:27 loss: 0.2411 loss_seg: 0.1474 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:47:16,359 INFO misc.py line 117 726] Train: [8/20][238/510] Data 1.630 (3.769) Batch 16.190 (28.212) Remain 50:05:30 loss: 0.2382 loss_seg: 0.1427 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:47:37,545 INFO misc.py line 117 726] Train: [8/20][239/510] Data 1.947 (3.762) Batch 21.186 (28.182) Remain 50:01:52 loss: 0.2191 loss_seg: 0.1257 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:48:04,706 INFO misc.py line 117 726] Train: [8/20][240/510] Data 4.164 (3.763) Batch 27.161 (28.178) Remain 50:00:56 loss: 0.2620 loss_seg: 0.1689 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:48:26,301 INFO misc.py line 117 726] Train: [8/20][241/510] Data 2.261 (3.757) Batch 21.595 (28.150) Remain 49:57:31 loss: 0.2992 loss_seg: 0.1917 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:48:52,229 INFO misc.py line 117 726] Train: [8/20][242/510] Data 2.776 (3.753) Batch 25.928 (28.141) Remain 49:56:04 loss: 0.2299 loss_seg: 0.1323 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:49:23,414 INFO misc.py line 117 726] Train: [8/20][243/510] Data 4.248 (3.755) Batch 31.185 (28.154) Remain 49:56:57 loss: 0.1799 loss_seg: 0.0942 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:49:44,982 INFO misc.py line 117 726] Train: [8/20][244/510] Data 3.041 (3.752) Batch 21.568 (28.126) Remain 49:53:34 loss: 0.3621 loss_seg: 0.2578 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:50:09,260 INFO misc.py line 117 726] Train: [8/20][245/510] Data 4.802 (3.756) Batch 24.277 (28.110) Remain 49:51:24 loss: 0.2322 loss_seg: 0.1416 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:50:52,443 INFO misc.py line 117 726] Train: [8/20][246/510] Data 12.749 (3.793) Batch 43.184 (28.172) Remain 49:57:32 loss: 0.2264 loss_seg: 0.1316 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:51:22,006 INFO misc.py line 117 726] Train: [8/20][247/510] Data 5.053 (3.799) Batch 29.563 (28.178) Remain 49:57:40 loss: 0.2871 loss_seg: 0.1819 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:52:01,165 INFO misc.py line 117 726] Train: [8/20][248/510] Data 6.634 (3.810) Batch 39.159 (28.223) Remain 50:01:58 loss: 0.2260 loss_seg: 0.1339 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:52:28,857 INFO misc.py line 117 726] Train: [8/20][249/510] Data 3.766 (3.810) Batch 27.692 (28.221) Remain 50:01:16 loss: 0.2273 loss_seg: 0.1313 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:53:00,570 INFO misc.py line 117 726] Train: [8/20][250/510] Data 6.071 (3.819) Batch 31.712 (28.235) Remain 50:02:18 loss: 0.3218 loss_seg: 0.2140 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:53:00,570 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 21:53:34,037 INFO misc.py line 117 726] Train: [8/20][251/510] Data 6.111 (3.828) Batch 33.467 (28.256) Remain 50:04:04 loss: 0.2212 loss_seg: 0.1247 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:54:12,823 INFO misc.py line 117 726] Train: [8/20][252/510] Data 4.356 (3.831) Batch 38.786 (28.298) Remain 50:08:06 loss: 0.2529 loss_seg: 0.1597 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:54:44,380 INFO misc.py line 117 726] Train: [8/20][253/510] Data 3.920 (3.831) Batch 31.557 (28.311) Remain 50:09:01 loss: 0.2522 loss_seg: 0.1553 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:55:18,790 INFO misc.py line 117 726] Train: [8/20][254/510] Data 4.826 (3.835) Batch 34.410 (28.336) Remain 50:11:07 loss: 0.2510 loss_seg: 0.1554 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:55:46,633 INFO misc.py line 117 726] Train: [8/20][255/510] Data 3.692 (3.834) Batch 27.843 (28.334) Remain 50:10:27 loss: 0.2646 loss_seg: 0.1707 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:56:15,686 INFO misc.py line 117 726] Train: [8/20][256/510] Data 3.185 (3.832) Batch 29.053 (28.337) Remain 50:10:16 loss: 0.1974 loss_seg: 0.1089 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:56:40,451 INFO misc.py line 117 726] Train: [8/20][257/510] Data 2.387 (3.826) Batch 24.765 (28.322) Remain 50:08:18 loss: 0.2634 loss_seg: 0.1618 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:57:03,195 INFO misc.py line 117 726] Train: [8/20][258/510] Data 2.747 (3.822) Batch 22.744 (28.301) Remain 50:05:31 loss: 0.2369 loss_seg: 0.1408 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:57:28,268 INFO misc.py line 117 726] Train: [8/20][259/510] Data 2.513 (3.817) Batch 25.073 (28.288) Remain 50:03:42 loss: 0.2360 loss_seg: 0.1342 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:57:53,860 INFO misc.py line 117 726] Train: [8/20][260/510] Data 3.381 (3.815) Batch 25.592 (28.277) Remain 50:02:07 loss: 0.2540 loss_seg: 0.1616 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:58:18,628 INFO misc.py line 117 726] Train: [8/20][261/510] Data 2.470 (3.810) Batch 24.768 (28.264) Remain 50:00:12 loss: 0.3018 loss_seg: 0.2101 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:58:42,248 INFO misc.py line 117 726] Train: [8/20][262/510] Data 2.570 (3.805) Batch 23.620 (28.246) Remain 49:57:50 loss: 0.2364 loss_seg: 0.1378 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:59:21,100 INFO misc.py line 117 726] Train: [8/20][263/510] Data 6.922 (3.817) Batch 38.853 (28.287) Remain 50:01:41 loss: 0.2269 loss_seg: 0.1378 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 21:59:49,742 INFO misc.py line 117 726] Train: [8/20][264/510] Data 3.271 (3.815) Batch 28.641 (28.288) Remain 50:01:21 loss: 0.2340 loss_seg: 0.1376 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:00:29,409 INFO misc.py line 117 726] Train: [8/20][265/510] Data 4.770 (3.819) Batch 39.667 (28.332) Remain 50:05:30 loss: 0.2862 loss_seg: 0.1876 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:01:06,160 INFO misc.py line 117 726] Train: [8/20][266/510] Data 7.301 (3.832) Batch 36.751 (28.364) Remain 50:08:25 loss: 0.2590 loss_seg: 0.1663 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:01:35,360 INFO misc.py line 117 726] Train: [8/20][267/510] Data 3.170 (3.829) Batch 29.200 (28.367) Remain 50:08:17 loss: 0.2768 loss_seg: 0.1753 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:02:01,198 INFO misc.py line 117 726] Train: [8/20][268/510] Data 3.128 (3.827) Batch 25.838 (28.357) Remain 50:06:48 loss: 0.3959 loss_seg: 0.2728 loss_superpoint_edge: 0.0562 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:02:21,447 INFO misc.py line 117 726] Train: [8/20][269/510] Data 2.198 (3.821) Batch 20.250 (28.327) Remain 50:03:06 loss: 0.2608 loss_seg: 0.1653 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:02:47,065 INFO misc.py line 117 726] Train: [8/20][270/510] Data 3.331 (3.819) Batch 25.618 (28.317) Remain 50:01:33 loss: 0.2056 loss_seg: 0.1126 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:03:15,721 INFO misc.py line 117 726] Train: [8/20][271/510] Data 3.551 (3.818) Batch 28.656 (28.318) Remain 50:01:12 loss: 0.2981 loss_seg: 0.1932 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:03:51,869 INFO misc.py line 117 726] Train: [8/20][272/510] Data 5.291 (3.823) Batch 36.147 (28.347) Remain 50:03:49 loss: 0.2336 loss_seg: 0.1363 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:04:11,514 INFO misc.py line 117 726] Train: [8/20][273/510] Data 2.183 (3.817) Batch 19.645 (28.315) Remain 49:59:56 loss: 0.2825 loss_seg: 0.1782 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:04:32,769 INFO misc.py line 117 726] Train: [8/20][274/510] Data 2.651 (3.813) Batch 21.255 (28.289) Remain 49:56:42 loss: 0.2749 loss_seg: 0.1700 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:04:53,338 INFO misc.py line 117 726] Train: [8/20][275/510] Data 1.992 (3.806) Batch 20.569 (28.260) Remain 49:53:13 loss: 0.2974 loss_seg: 0.1956 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:05:16,173 INFO misc.py line 117 726] Train: [8/20][276/510] Data 2.651 (3.802) Batch 22.835 (28.240) Remain 49:50:39 loss: 0.2642 loss_seg: 0.1750 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:05:40,984 INFO misc.py line 117 726] Train: [8/20][277/510] Data 2.819 (3.798) Batch 24.811 (28.228) Remain 49:48:51 loss: 0.2729 loss_seg: 0.1681 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:06:08,106 INFO misc.py line 117 726] Train: [8/20][278/510] Data 3.366 (3.797) Batch 27.123 (28.224) Remain 49:47:57 loss: 0.3108 loss_seg: 0.2090 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:06:40,771 INFO misc.py line 117 726] Train: [8/20][279/510] Data 4.808 (3.800) Batch 32.664 (28.240) Remain 49:49:11 loss: 0.1874 loss_seg: 0.1041 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:07:10,732 INFO misc.py line 117 726] Train: [8/20][280/510] Data 3.480 (3.799) Batch 29.961 (28.246) Remain 49:49:23 loss: 0.2183 loss_seg: 0.1256 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:07:35,186 INFO misc.py line 117 726] Train: [8/20][281/510] Data 2.823 (3.796) Batch 24.454 (28.233) Remain 49:47:28 loss: 0.3095 loss_seg: 0.2178 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:07:51,511 INFO misc.py line 117 726] Train: [8/20][282/510] Data 1.644 (3.788) Batch 16.325 (28.190) Remain 49:42:28 loss: 0.3318 loss_seg: 0.2190 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:08:22,565 INFO misc.py line 117 726] Train: [8/20][283/510] Data 6.212 (3.797) Batch 31.054 (28.200) Remain 49:43:05 loss: 0.2413 loss_seg: 0.1463 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:08:53,605 INFO misc.py line 117 726] Train: [8/20][284/510] Data 3.088 (3.794) Batch 31.040 (28.210) Remain 49:43:41 loss: 0.2628 loss_seg: 0.1575 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:09:22,239 INFO misc.py line 117 726] Train: [8/20][285/510] Data 3.486 (3.793) Batch 28.633 (28.212) Remain 49:43:22 loss: 0.2845 loss_seg: 0.1938 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:09:55,283 INFO misc.py line 117 726] Train: [8/20][286/510] Data 4.284 (3.795) Batch 33.044 (28.229) Remain 49:44:43 loss: 0.1866 loss_seg: 0.1023 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:10:29,107 INFO misc.py line 117 726] Train: [8/20][287/510] Data 3.269 (3.793) Batch 33.825 (28.248) Remain 49:46:19 loss: 0.2395 loss_seg: 0.1565 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:10:55,577 INFO misc.py line 117 726] Train: [8/20][288/510] Data 5.193 (3.798) Batch 26.469 (28.242) Remain 49:45:12 loss: 0.1844 loss_seg: 0.0960 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:11:22,072 INFO misc.py line 117 726] Train: [8/20][289/510] Data 2.382 (3.793) Batch 26.495 (28.236) Remain 49:44:05 loss: 0.2607 loss_seg: 0.1569 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:11:50,965 INFO misc.py line 117 726] Train: [8/20][290/510] Data 3.601 (3.792) Batch 28.893 (28.238) Remain 49:43:51 loss: 0.2440 loss_seg: 0.1447 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:12:16,636 INFO misc.py line 117 726] Train: [8/20][291/510] Data 2.854 (3.789) Batch 25.672 (28.229) Remain 49:42:26 loss: 0.2483 loss_seg: 0.1492 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:12:47,523 INFO misc.py line 117 726] Train: [8/20][292/510] Data 4.688 (3.792) Batch 30.886 (28.239) Remain 49:42:56 loss: 0.2003 loss_seg: 0.1116 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:13:16,419 INFO misc.py line 117 726] Train: [8/20][293/510] Data 4.392 (3.794) Batch 28.896 (28.241) Remain 49:42:42 loss: 0.2226 loss_seg: 0.1274 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:13:44,850 INFO misc.py line 117 726] Train: [8/20][294/510] Data 2.963 (3.791) Batch 28.431 (28.242) Remain 49:42:18 loss: 0.3506 loss_seg: 0.2385 loss_superpoint_edge: 0.0446 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:14:08,681 INFO misc.py line 117 726] Train: [8/20][295/510] Data 2.739 (3.788) Batch 23.831 (28.226) Remain 49:40:14 loss: 0.2535 loss_seg: 0.1559 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:14:38,108 INFO misc.py line 117 726] Train: [8/20][296/510] Data 4.441 (3.790) Batch 29.428 (28.231) Remain 49:40:12 loss: 0.2340 loss_seg: 0.1443 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:15:03,877 INFO misc.py line 117 726] Train: [8/20][297/510] Data 3.070 (3.787) Batch 25.769 (28.222) Remain 49:38:51 loss: 0.2308 loss_seg: 0.1398 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:15:23,357 INFO misc.py line 117 726] Train: [8/20][298/510] Data 1.888 (3.781) Batch 19.480 (28.193) Remain 49:35:15 loss: 0.2508 loss_seg: 0.1508 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:15:42,199 INFO misc.py line 117 726] Train: [8/20][299/510] Data 2.827 (3.778) Batch 18.842 (28.161) Remain 49:31:27 loss: 0.1832 loss_seg: 0.0964 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:16:03,638 INFO misc.py line 117 726] Train: [8/20][300/510] Data 2.384 (3.773) Batch 21.439 (28.138) Remain 49:28:35 loss: 0.2921 loss_seg: 0.1819 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:16:03,639 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 22:16:38,656 INFO misc.py line 117 726] Train: [8/20][301/510] Data 6.358 (3.782) Batch 35.018 (28.161) Remain 49:30:33 loss: 0.1920 loss_seg: 0.1066 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:17:12,169 INFO misc.py line 117 726] Train: [8/20][302/510] Data 7.115 (3.793) Batch 33.513 (28.179) Remain 49:31:58 loss: 0.2036 loss_seg: 0.1129 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:17:44,137 INFO misc.py line 117 726] Train: [8/20][303/510] Data 5.619 (3.799) Batch 31.967 (28.192) Remain 49:32:50 loss: 0.2484 loss_seg: 0.1467 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:18:02,560 INFO misc.py line 117 726] Train: [8/20][304/510] Data 2.612 (3.795) Batch 18.424 (28.160) Remain 49:28:56 loss: 0.2570 loss_seg: 0.1580 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:18:30,774 INFO misc.py line 117 726] Train: [8/20][305/510] Data 3.619 (3.794) Batch 28.214 (28.160) Remain 49:28:29 loss: 0.1950 loss_seg: 0.1047 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:18:50,193 INFO misc.py line 117 726] Train: [8/20][306/510] Data 2.755 (3.791) Batch 19.419 (28.131) Remain 49:24:59 loss: 0.3313 loss_seg: 0.2366 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:19:15,305 INFO misc.py line 117 726] Train: [8/20][307/510] Data 3.013 (3.788) Batch 25.112 (28.121) Remain 49:23:28 loss: 0.2472 loss_seg: 0.1491 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:19:45,219 INFO misc.py line 117 726] Train: [8/20][308/510] Data 5.943 (3.796) Batch 29.914 (28.127) Remain 49:23:37 loss: 0.2890 loss_seg: 0.1988 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:20:23,205 INFO misc.py line 117 726] Train: [8/20][309/510] Data 6.555 (3.805) Batch 37.986 (28.159) Remain 49:26:33 loss: 0.2522 loss_seg: 0.1547 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:20:53,878 INFO misc.py line 117 726] Train: [8/20][310/510] Data 6.680 (3.814) Batch 30.673 (28.167) Remain 49:26:56 loss: 0.2506 loss_seg: 0.1585 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:21:08,050 INFO misc.py line 117 726] Train: [8/20][311/510] Data 1.735 (3.807) Batch 14.172 (28.122) Remain 49:21:41 loss: 0.2192 loss_seg: 0.1259 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:21:35,648 INFO misc.py line 117 726] Train: [8/20][312/510] Data 2.862 (3.804) Batch 27.598 (28.120) Remain 49:21:02 loss: 0.2156 loss_seg: 0.1210 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:21:55,958 INFO misc.py line 117 726] Train: [8/20][313/510] Data 2.942 (3.801) Batch 20.309 (28.095) Remain 49:17:55 loss: 0.3487 loss_seg: 0.2489 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:22:18,888 INFO misc.py line 117 726] Train: [8/20][314/510] Data 2.819 (3.798) Batch 22.930 (28.078) Remain 49:15:42 loss: 0.2465 loss_seg: 0.1483 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:22:42,415 INFO misc.py line 117 726] Train: [8/20][315/510] Data 3.050 (3.796) Batch 23.527 (28.064) Remain 49:13:42 loss: 0.2159 loss_seg: 0.1280 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:23:17,620 INFO misc.py line 117 726] Train: [8/20][316/510] Data 5.446 (3.801) Batch 35.205 (28.086) Remain 49:15:38 loss: 0.2666 loss_seg: 0.1715 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:23:45,726 INFO misc.py line 117 726] Train: [8/20][317/510] Data 2.783 (3.798) Batch 28.106 (28.087) Remain 49:15:10 loss: 0.2241 loss_seg: 0.1273 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:24:18,678 INFO misc.py line 117 726] Train: [8/20][318/510] Data 4.613 (3.800) Batch 32.952 (28.102) Remain 49:16:19 loss: 0.2163 loss_seg: 0.1281 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:24:37,000 INFO misc.py line 117 726] Train: [8/20][319/510] Data 2.406 (3.796) Batch 18.323 (28.071) Remain 49:12:36 loss: 0.3080 loss_seg: 0.2015 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:25:06,752 INFO misc.py line 117 726] Train: [8/20][320/510] Data 2.909 (3.793) Batch 29.752 (28.076) Remain 49:12:41 loss: 0.2337 loss_seg: 0.1417 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:25:32,727 INFO misc.py line 117 726] Train: [8/20][321/510] Data 2.895 (3.790) Batch 25.976 (28.070) Remain 49:11:31 loss: 0.2352 loss_seg: 0.1422 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:26:08,243 INFO misc.py line 117 726] Train: [8/20][322/510] Data 4.042 (3.791) Batch 35.515 (28.093) Remain 49:13:31 loss: 0.1916 loss_seg: 0.1086 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:26:35,948 INFO misc.py line 117 726] Train: [8/20][323/510] Data 3.249 (3.789) Batch 27.705 (28.092) Remain 49:12:55 loss: 0.1838 loss_seg: 0.1006 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:27:01,588 INFO misc.py line 117 726] Train: [8/20][324/510] Data 2.981 (3.787) Batch 25.641 (28.084) Remain 49:11:39 loss: 0.2440 loss_seg: 0.1425 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:27:26,602 INFO misc.py line 117 726] Train: [8/20][325/510] Data 3.061 (3.785) Batch 25.014 (28.075) Remain 49:10:10 loss: 0.2069 loss_seg: 0.1180 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:27:47,199 INFO misc.py line 117 726] Train: [8/20][326/510] Data 3.856 (3.785) Batch 20.597 (28.052) Remain 49:07:16 loss: 0.3273 loss_seg: 0.2302 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:28:18,705 INFO misc.py line 117 726] Train: [8/20][327/510] Data 4.359 (3.787) Batch 31.507 (28.062) Remain 49:07:56 loss: 0.2129 loss_seg: 0.1258 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:28:42,825 INFO misc.py line 117 726] Train: [8/20][328/510] Data 2.780 (3.784) Batch 24.120 (28.050) Remain 49:06:11 loss: 0.2254 loss_seg: 0.1269 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:29:16,641 INFO misc.py line 117 726] Train: [8/20][329/510] Data 5.410 (3.789) Batch 33.816 (28.068) Remain 49:07:34 loss: 0.2398 loss_seg: 0.1429 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:29:49,230 INFO misc.py line 117 726] Train: [8/20][330/510] Data 4.612 (3.791) Batch 32.589 (28.082) Remain 49:08:34 loss: 0.2210 loss_seg: 0.1291 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:30:06,645 INFO misc.py line 117 726] Train: [8/20][331/510] Data 2.704 (3.788) Batch 17.415 (28.049) Remain 49:04:41 loss: 0.2751 loss_seg: 0.1751 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:30:31,074 INFO misc.py line 117 726] Train: [8/20][332/510] Data 2.457 (3.784) Batch 24.429 (28.038) Remain 49:03:03 loss: 0.2791 loss_seg: 0.1835 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:30:58,447 INFO misc.py line 117 726] Train: [8/20][333/510] Data 3.911 (3.784) Batch 27.373 (28.036) Remain 49:02:23 loss: 0.2624 loss_seg: 0.1650 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:31:35,404 INFO misc.py line 117 726] Train: [8/20][334/510] Data 10.685 (3.805) Batch 36.957 (28.063) Remain 49:04:44 loss: 0.2481 loss_seg: 0.1490 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:32:09,012 INFO misc.py line 117 726] Train: [8/20][335/510] Data 3.500 (3.804) Batch 33.608 (28.080) Remain 49:06:01 loss: 0.2315 loss_seg: 0.1372 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:32:28,838 INFO misc.py line 117 726] Train: [8/20][336/510] Data 2.441 (3.800) Batch 19.826 (28.055) Remain 49:02:57 loss: 0.2232 loss_seg: 0.1271 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:32:51,834 INFO misc.py line 117 726] Train: [8/20][337/510] Data 3.493 (3.799) Batch 22.996 (28.040) Remain 49:00:54 loss: 0.2906 loss_seg: 0.1927 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:33:31,134 INFO misc.py line 117 726] Train: [8/20][338/510] Data 9.283 (3.815) Batch 39.300 (28.073) Remain 49:03:57 loss: 0.2324 loss_seg: 0.1365 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:33:56,927 INFO misc.py line 117 726] Train: [8/20][339/510] Data 2.749 (3.812) Batch 25.793 (28.067) Remain 49:02:46 loss: 0.2208 loss_seg: 0.1298 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:34:31,754 INFO misc.py line 117 726] Train: [8/20][340/510] Data 4.596 (3.815) Batch 34.827 (28.087) Remain 49:04:25 loss: 0.2370 loss_seg: 0.1434 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:35:04,951 INFO misc.py line 117 726] Train: [8/20][341/510] Data 6.203 (3.822) Batch 33.196 (28.102) Remain 49:05:32 loss: 0.2637 loss_seg: 0.1645 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:35:30,163 INFO misc.py line 117 726] Train: [8/20][342/510] Data 2.432 (3.818) Batch 25.213 (28.093) Remain 49:04:10 loss: 0.2409 loss_seg: 0.1479 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:36:05,460 INFO misc.py line 117 726] Train: [8/20][343/510] Data 4.483 (3.819) Batch 35.297 (28.114) Remain 49:05:55 loss: 0.2484 loss_seg: 0.1555 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:36:42,107 INFO misc.py line 117 726] Train: [8/20][344/510] Data 4.122 (3.820) Batch 36.647 (28.139) Remain 49:08:04 loss: 0.2510 loss_seg: 0.1560 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:37:07,576 INFO misc.py line 117 726] Train: [8/20][345/510] Data 3.753 (3.820) Batch 25.469 (28.132) Remain 49:06:47 loss: 0.2679 loss_seg: 0.1669 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:37:43,427 INFO misc.py line 117 726] Train: [8/20][346/510] Data 8.283 (3.833) Batch 35.851 (28.154) Remain 49:08:40 loss: 0.1939 loss_seg: 0.1054 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:38:07,752 INFO misc.py line 117 726] Train: [8/20][347/510] Data 3.475 (3.832) Batch 24.325 (28.143) Remain 49:07:02 loss: 0.2331 loss_seg: 0.1400 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:38:32,805 INFO misc.py line 117 726] Train: [8/20][348/510] Data 3.171 (3.830) Batch 25.053 (28.134) Remain 49:05:38 loss: 0.2030 loss_seg: 0.1169 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:38:54,065 INFO misc.py line 117 726] Train: [8/20][349/510] Data 2.235 (3.826) Batch 21.260 (28.114) Remain 49:03:05 loss: 0.2740 loss_seg: 0.1737 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:39:20,450 INFO misc.py line 117 726] Train: [8/20][350/510] Data 3.475 (3.825) Batch 26.385 (28.109) Remain 49:02:05 loss: 0.3595 loss_seg: 0.2618 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:39:20,451 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 22:39:50,336 INFO misc.py line 117 726] Train: [8/20][351/510] Data 2.662 (3.821) Batch 29.885 (28.114) Remain 49:02:09 loss: 0.2550 loss_seg: 0.1568 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:40:09,734 INFO misc.py line 117 726] Train: [8/20][352/510] Data 2.496 (3.817) Batch 19.398 (28.089) Remain 48:59:04 loss: 0.2624 loss_seg: 0.1635 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:40:48,641 INFO misc.py line 117 726] Train: [8/20][353/510] Data 5.990 (3.824) Batch 38.906 (28.120) Remain 49:01:50 loss: 0.2091 loss_seg: 0.1166 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:41:21,825 INFO misc.py line 117 726] Train: [8/20][354/510] Data 3.371 (3.822) Batch 33.184 (28.135) Remain 49:02:53 loss: 0.1891 loss_seg: 0.1040 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:41:54,393 INFO misc.py line 117 726] Train: [8/20][355/510] Data 2.949 (3.820) Batch 32.568 (28.147) Remain 49:03:44 loss: 0.2109 loss_seg: 0.1220 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:42:19,124 INFO misc.py line 117 726] Train: [8/20][356/510] Data 3.603 (3.819) Batch 24.731 (28.138) Remain 49:02:15 loss: 0.3222 loss_seg: 0.2246 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:43:00,644 INFO misc.py line 117 726] Train: [8/20][357/510] Data 8.379 (3.832) Batch 41.520 (28.175) Remain 49:05:44 loss: 0.2583 loss_seg: 0.1601 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:43:23,015 INFO misc.py line 117 726] Train: [8/20][358/510] Data 2.540 (3.829) Batch 22.371 (28.159) Remain 49:03:33 loss: 0.3184 loss_seg: 0.2038 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:43:40,057 INFO misc.py line 117 726] Train: [8/20][359/510] Data 1.812 (3.823) Batch 17.042 (28.128) Remain 48:59:49 loss: 0.3073 loss_seg: 0.2059 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:44:02,613 INFO misc.py line 117 726] Train: [8/20][360/510] Data 3.898 (3.823) Batch 22.556 (28.112) Remain 48:57:43 loss: 0.2890 loss_seg: 0.1945 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:44:32,709 INFO misc.py line 117 726] Train: [8/20][361/510] Data 5.259 (3.827) Batch 30.096 (28.118) Remain 48:57:50 loss: 0.3255 loss_seg: 0.2050 loss_superpoint_edge: 0.0539 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:45:05,662 INFO misc.py line 117 726] Train: [8/20][362/510] Data 13.002 (3.853) Batch 32.953 (28.131) Remain 48:58:46 loss: 0.2994 loss_seg: 0.2061 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:45:32,267 INFO misc.py line 117 726] Train: [8/20][363/510] Data 3.452 (3.852) Batch 26.605 (28.127) Remain 48:57:51 loss: 0.3125 loss_seg: 0.2143 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:46:02,180 INFO misc.py line 117 726] Train: [8/20][364/510] Data 4.612 (3.854) Batch 29.913 (28.132) Remain 48:57:54 loss: 0.2180 loss_seg: 0.1230 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:46:40,235 INFO misc.py line 117 726] Train: [8/20][365/510] Data 6.405 (3.861) Batch 38.055 (28.159) Remain 49:00:18 loss: 0.3892 loss_seg: 0.2862 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:47:16,027 INFO misc.py line 117 726] Train: [8/20][366/510] Data 9.864 (3.877) Batch 35.792 (28.180) Remain 49:02:01 loss: 0.5322 loss_seg: 0.3704 loss_superpoint_edge: 0.0961 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:47:41,561 INFO misc.py line 117 726] Train: [8/20][367/510] Data 2.630 (3.874) Batch 25.535 (28.173) Remain 49:00:48 loss: 0.2317 loss_seg: 0.1423 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:48:15,553 INFO misc.py line 117 726] Train: [8/20][368/510] Data 7.227 (3.883) Batch 33.992 (28.189) Remain 49:01:59 loss: 0.2504 loss_seg: 0.1583 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:48:44,167 INFO misc.py line 117 726] Train: [8/20][369/510] Data 2.315 (3.879) Batch 28.614 (28.190) Remain 49:01:38 loss: 0.2182 loss_seg: 0.1247 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:49:07,334 INFO misc.py line 117 726] Train: [8/20][370/510] Data 3.257 (3.877) Batch 23.167 (28.177) Remain 48:59:45 loss: 0.4832 loss_seg: 0.3803 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:49:34,871 INFO misc.py line 117 726] Train: [8/20][371/510] Data 3.325 (3.876) Batch 27.537 (28.175) Remain 48:59:05 loss: 0.2112 loss_seg: 0.1194 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:50:03,887 INFO misc.py line 117 726] Train: [8/20][372/510] Data 4.097 (3.876) Batch 29.016 (28.177) Remain 48:58:52 loss: 0.2923 loss_seg: 0.1963 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:50:28,051 INFO misc.py line 117 726] Train: [8/20][373/510] Data 2.623 (3.873) Batch 24.164 (28.166) Remain 48:57:16 loss: 0.1806 loss_seg: 0.0952 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:50:51,701 INFO misc.py line 117 726] Train: [8/20][374/510] Data 3.634 (3.872) Batch 23.649 (28.154) Remain 48:55:31 loss: 0.2805 loss_seg: 0.1841 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:51:17,359 INFO misc.py line 117 726] Train: [8/20][375/510] Data 3.483 (3.871) Batch 25.657 (28.147) Remain 48:54:21 loss: 0.2461 loss_seg: 0.1528 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:51:41,684 INFO misc.py line 117 726] Train: [8/20][376/510] Data 2.224 (3.867) Batch 24.325 (28.137) Remain 48:52:49 loss: 0.2046 loss_seg: 0.1170 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:52:00,845 INFO misc.py line 117 726] Train: [8/20][377/510] Data 2.750 (3.864) Batch 19.162 (28.113) Remain 48:49:51 loss: 0.2177 loss_seg: 0.1239 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:52:34,411 INFO misc.py line 117 726] Train: [8/20][378/510] Data 5.393 (3.868) Batch 33.566 (28.128) Remain 48:50:53 loss: 0.2503 loss_seg: 0.1552 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:53:07,606 INFO misc.py line 117 726] Train: [8/20][379/510] Data 3.061 (3.866) Batch 33.195 (28.141) Remain 48:51:50 loss: 0.3255 loss_seg: 0.2203 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:53:29,100 INFO misc.py line 117 726] Train: [8/20][380/510] Data 3.176 (3.864) Batch 21.494 (28.123) Remain 48:49:31 loss: 0.2373 loss_seg: 0.1344 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:53:56,118 INFO misc.py line 117 726] Train: [8/20][381/510] Data 3.380 (3.862) Batch 27.018 (28.121) Remain 48:48:45 loss: 0.2877 loss_seg: 0.1826 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:54:24,587 INFO misc.py line 117 726] Train: [8/20][382/510] Data 3.225 (3.861) Batch 28.469 (28.121) Remain 48:48:22 loss: 0.1965 loss_seg: 0.1104 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:54:51,314 INFO misc.py line 117 726] Train: [8/20][383/510] Data 4.494 (3.862) Batch 26.727 (28.118) Remain 48:47:31 loss: 0.2448 loss_seg: 0.1532 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:55:16,696 INFO misc.py line 117 726] Train: [8/20][384/510] Data 2.824 (3.860) Batch 25.382 (28.111) Remain 48:46:18 loss: 0.3229 loss_seg: 0.2200 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:55:45,675 INFO misc.py line 117 726] Train: [8/20][385/510] Data 5.197 (3.863) Batch 28.979 (28.113) Remain 48:46:04 loss: 0.2491 loss_seg: 0.1601 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:55:57,738 INFO misc.py line 117 726] Train: [8/20][386/510] Data 2.012 (3.858) Batch 12.063 (28.071) Remain 48:41:15 loss: 0.2661 loss_seg: 0.1623 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:56:24,247 INFO misc.py line 117 726] Train: [8/20][387/510] Data 3.715 (3.858) Batch 26.508 (28.067) Remain 48:40:21 loss: 0.3160 loss_seg: 0.2227 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:56:54,083 INFO misc.py line 117 726] Train: [8/20][388/510] Data 5.107 (3.861) Batch 29.836 (28.072) Remain 48:40:22 loss: 0.2617 loss_seg: 0.1609 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:57:17,118 INFO misc.py line 117 726] Train: [8/20][389/510] Data 3.423 (3.860) Batch 23.035 (28.058) Remain 48:38:32 loss: 0.1701 loss_seg: 0.0874 loss_superpoint_edge: 0.0138 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:57:48,438 INFO misc.py line 117 726] Train: [8/20][390/510] Data 3.445 (3.859) Batch 31.320 (28.067) Remain 48:38:57 loss: 0.2026 loss_seg: 0.1102 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:58:23,838 INFO misc.py line 117 726] Train: [8/20][391/510] Data 4.222 (3.860) Batch 35.399 (28.086) Remain 48:40:27 loss: 0.2239 loss_seg: 0.1287 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:58:43,821 INFO misc.py line 117 726] Train: [8/20][392/510] Data 1.903 (3.855) Batch 19.983 (28.065) Remain 48:37:49 loss: 0.2457 loss_seg: 0.1527 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:59:06,679 INFO misc.py line 117 726] Train: [8/20][393/510] Data 3.058 (3.853) Batch 22.858 (28.052) Remain 48:35:57 loss: 0.3715 loss_seg: 0.2624 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:59:35,596 INFO misc.py line 117 726] Train: [8/20][394/510] Data 3.606 (3.852) Batch 28.917 (28.054) Remain 48:35:43 loss: 0.3856 loss_seg: 0.2723 loss_superpoint_edge: 0.0443 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 22:59:57,010 INFO misc.py line 117 726] Train: [8/20][395/510] Data 2.555 (3.849) Batch 21.414 (28.037) Remain 48:33:29 loss: 0.2359 loss_seg: 0.1422 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:00:27,377 INFO misc.py line 117 726] Train: [8/20][396/510] Data 4.695 (3.851) Batch 30.367 (28.043) Remain 48:33:38 loss: 0.2326 loss_seg: 0.1396 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:00:58,142 INFO misc.py line 117 726] Train: [8/20][397/510] Data 3.528 (3.850) Batch 30.765 (28.050) Remain 48:33:53 loss: 0.2632 loss_seg: 0.1654 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:01:36,263 INFO misc.py line 117 726] Train: [8/20][398/510] Data 5.806 (3.855) Batch 38.121 (28.075) Remain 48:36:04 loss: 0.2007 loss_seg: 0.1072 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:02:08,118 INFO misc.py line 117 726] Train: [8/20][399/510] Data 4.399 (3.857) Batch 31.855 (28.085) Remain 48:36:36 loss: 0.2659 loss_seg: 0.1641 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:02:36,398 INFO misc.py line 117 726] Train: [8/20][400/510] Data 3.016 (3.854) Batch 28.280 (28.085) Remain 48:36:11 loss: 0.3052 loss_seg: 0.1993 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:02:36,399 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 23:02:57,897 INFO misc.py line 117 726] Train: [8/20][401/510] Data 2.474 (3.851) Batch 21.499 (28.069) Remain 48:33:59 loss: 0.3191 loss_seg: 0.2050 loss_superpoint_edge: 0.0462 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:03:25,456 INFO misc.py line 117 726] Train: [8/20][402/510] Data 3.498 (3.850) Batch 27.560 (28.067) Remain 48:33:23 loss: 0.3083 loss_seg: 0.1975 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:03:50,896 INFO misc.py line 117 726] Train: [8/20][403/510] Data 3.671 (3.850) Batch 25.439 (28.061) Remain 48:32:14 loss: 0.1997 loss_seg: 0.1128 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:04:23,379 INFO misc.py line 117 726] Train: [8/20][404/510] Data 4.316 (3.851) Batch 32.483 (28.072) Remain 48:32:55 loss: 0.2131 loss_seg: 0.1192 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:04:49,446 INFO misc.py line 117 726] Train: [8/20][405/510] Data 5.145 (3.854) Batch 26.067 (28.067) Remain 48:31:56 loss: 0.3241 loss_seg: 0.2099 loss_superpoint_edge: 0.0436 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:05:25,624 INFO misc.py line 117 726] Train: [8/20][406/510] Data 4.237 (3.855) Batch 36.178 (28.087) Remain 48:33:33 loss: 0.2534 loss_seg: 0.1590 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:05:55,084 INFO misc.py line 117 726] Train: [8/20][407/510] Data 2.985 (3.853) Batch 29.460 (28.090) Remain 48:33:26 loss: 0.2421 loss_seg: 0.1479 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:06:23,279 INFO misc.py line 117 726] Train: [8/20][408/510] Data 3.504 (3.852) Batch 28.196 (28.091) Remain 48:33:00 loss: 0.2540 loss_seg: 0.1589 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:06:56,256 INFO misc.py line 117 726] Train: [8/20][409/510] Data 3.264 (3.851) Batch 32.977 (28.103) Remain 48:33:47 loss: 0.2598 loss_seg: 0.1615 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:07:22,697 INFO misc.py line 117 726] Train: [8/20][410/510] Data 3.526 (3.850) Batch 26.441 (28.099) Remain 48:32:53 loss: 0.2184 loss_seg: 0.1313 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:07:41,236 INFO misc.py line 117 726] Train: [8/20][411/510] Data 2.624 (3.847) Batch 18.539 (28.075) Remain 48:29:59 loss: 0.2762 loss_seg: 0.1788 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:08:05,731 INFO misc.py line 117 726] Train: [8/20][412/510] Data 3.615 (3.846) Batch 24.495 (28.066) Remain 48:28:37 loss: 0.2568 loss_seg: 0.1619 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:08:37,386 INFO misc.py line 117 726] Train: [8/20][413/510] Data 3.752 (3.846) Batch 31.654 (28.075) Remain 48:29:03 loss: 0.1938 loss_seg: 0.1060 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:09:08,810 INFO misc.py line 117 726] Train: [8/20][414/510] Data 5.954 (3.851) Batch 31.424 (28.083) Remain 48:29:26 loss: 0.2562 loss_seg: 0.1591 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:09:44,536 INFO misc.py line 117 726] Train: [8/20][415/510] Data 4.821 (3.853) Batch 35.727 (28.102) Remain 48:30:53 loss: 0.3285 loss_seg: 0.2213 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:10:11,031 INFO misc.py line 117 726] Train: [8/20][416/510] Data 2.509 (3.850) Batch 26.495 (28.098) Remain 48:30:01 loss: 0.2787 loss_seg: 0.1779 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:10:43,414 INFO misc.py line 117 726] Train: [8/20][417/510] Data 3.641 (3.850) Batch 32.383 (28.108) Remain 48:30:37 loss: 0.2399 loss_seg: 0.1484 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:11:07,763 INFO misc.py line 117 726] Train: [8/20][418/510] Data 2.732 (3.847) Batch 24.349 (28.099) Remain 48:29:12 loss: 0.2636 loss_seg: 0.1608 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:11:34,276 INFO misc.py line 117 726] Train: [8/20][419/510] Data 2.722 (3.844) Batch 26.513 (28.095) Remain 48:28:21 loss: 0.2160 loss_seg: 0.1221 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:11:58,377 INFO misc.py line 117 726] Train: [8/20][420/510] Data 2.562 (3.841) Batch 24.101 (28.086) Remain 48:26:53 loss: 0.2027 loss_seg: 0.1152 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:12:18,393 INFO misc.py line 117 726] Train: [8/20][421/510] Data 2.869 (3.839) Batch 20.015 (28.067) Remain 48:24:25 loss: 0.2606 loss_seg: 0.1603 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:12:48,308 INFO misc.py line 117 726] Train: [8/20][422/510] Data 3.349 (3.838) Batch 29.915 (28.071) Remain 48:24:24 loss: 0.3114 loss_seg: 0.2027 loss_superpoint_edge: 0.0419 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:13:00,965 INFO misc.py line 117 726] Train: [8/20][423/510] Data 1.453 (3.832) Batch 12.657 (28.034) Remain 48:20:09 loss: 0.2145 loss_seg: 0.1215 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:13:31,920 INFO misc.py line 117 726] Train: [8/20][424/510] Data 9.929 (3.847) Batch 30.955 (28.041) Remain 48:20:24 loss: 0.1741 loss_seg: 0.0911 loss_superpoint_edge: 0.0115 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:14:00,448 INFO misc.py line 117 726] Train: [8/20][425/510] Data 2.576 (3.844) Batch 28.528 (28.042) Remain 48:20:03 loss: 0.2010 loss_seg: 0.1129 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:14:23,139 INFO misc.py line 117 726] Train: [8/20][426/510] Data 2.285 (3.840) Batch 22.691 (28.030) Remain 48:18:16 loss: 0.2552 loss_seg: 0.1565 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:15:02,756 INFO misc.py line 117 726] Train: [8/20][427/510] Data 9.871 (3.854) Batch 39.618 (28.057) Remain 48:20:38 loss: 0.2920 loss_seg: 0.1931 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:15:38,057 INFO misc.py line 117 726] Train: [8/20][428/510] Data 4.821 (3.856) Batch 35.301 (28.074) Remain 48:21:55 loss: 0.2033 loss_seg: 0.1190 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:16:05,654 INFO misc.py line 117 726] Train: [8/20][429/510] Data 3.770 (3.856) Batch 27.597 (28.073) Remain 48:21:20 loss: 0.2742 loss_seg: 0.1887 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:16:40,675 INFO misc.py line 117 726] Train: [8/20][430/510] Data 6.028 (3.861) Batch 35.021 (28.089) Remain 48:22:33 loss: 0.2652 loss_seg: 0.1710 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:17:09,017 INFO misc.py line 117 726] Train: [8/20][431/510] Data 4.089 (3.862) Batch 28.342 (28.090) Remain 48:22:09 loss: 0.2405 loss_seg: 0.1442 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:17:46,017 INFO misc.py line 117 726] Train: [8/20][432/510] Data 5.974 (3.867) Batch 37.000 (28.111) Remain 48:23:49 loss: 0.2448 loss_seg: 0.1510 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:18:10,970 INFO misc.py line 117 726] Train: [8/20][433/510] Data 2.779 (3.864) Batch 24.953 (28.103) Remain 48:22:36 loss: 0.2454 loss_seg: 0.1529 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:18:33,850 INFO misc.py line 117 726] Train: [8/20][434/510] Data 3.034 (3.862) Batch 22.880 (28.091) Remain 48:20:52 loss: 0.2156 loss_seg: 0.1229 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:18:58,318 INFO misc.py line 117 726] Train: [8/20][435/510] Data 3.524 (3.861) Batch 24.468 (28.083) Remain 48:19:32 loss: 0.2985 loss_seg: 0.2068 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:19:28,654 INFO misc.py line 117 726] Train: [8/20][436/510] Data 3.723 (3.861) Batch 30.336 (28.088) Remain 48:19:37 loss: 0.3426 loss_seg: 0.2338 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:19:56,030 INFO misc.py line 117 726] Train: [8/20][437/510] Data 2.363 (3.858) Batch 27.376 (28.086) Remain 48:18:58 loss: 0.2244 loss_seg: 0.1338 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:20:25,280 INFO misc.py line 117 726] Train: [8/20][438/510] Data 2.897 (3.855) Batch 29.251 (28.089) Remain 48:18:47 loss: 0.2595 loss_seg: 0.1679 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:20:54,940 INFO misc.py line 117 726] Train: [8/20][439/510] Data 3.833 (3.855) Batch 29.660 (28.093) Remain 48:18:41 loss: 0.2058 loss_seg: 0.1161 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:21:28,566 INFO misc.py line 117 726] Train: [8/20][440/510] Data 5.259 (3.859) Batch 33.626 (28.105) Remain 48:19:31 loss: 0.1899 loss_seg: 0.1025 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:21:57,230 INFO misc.py line 117 726] Train: [8/20][441/510] Data 2.936 (3.857) Batch 28.664 (28.107) Remain 48:19:11 loss: 0.2177 loss_seg: 0.1291 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:22:23,928 INFO misc.py line 117 726] Train: [8/20][442/510] Data 3.428 (3.856) Batch 26.698 (28.103) Remain 48:18:23 loss: 0.3078 loss_seg: 0.1960 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:22:53,110 INFO misc.py line 117 726] Train: [8/20][443/510] Data 4.043 (3.856) Batch 29.182 (28.106) Remain 48:18:10 loss: 0.2380 loss_seg: 0.1436 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:23:15,520 INFO misc.py line 117 726] Train: [8/20][444/510] Data 2.230 (3.852) Batch 22.409 (28.093) Remain 48:16:22 loss: 0.3341 loss_seg: 0.2233 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:23:43,639 INFO misc.py line 117 726] Train: [8/20][445/510] Data 2.199 (3.849) Batch 28.120 (28.093) Remain 48:15:54 loss: 0.3263 loss_seg: 0.2283 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:24:13,307 INFO misc.py line 117 726] Train: [8/20][446/510] Data 4.951 (3.851) Batch 29.667 (28.097) Remain 48:15:48 loss: 0.1951 loss_seg: 0.1104 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:24:29,871 INFO misc.py line 117 726] Train: [8/20][447/510] Data 2.200 (3.847) Batch 16.565 (28.071) Remain 48:12:40 loss: 0.2621 loss_seg: 0.1737 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:24:59,945 INFO misc.py line 117 726] Train: [8/20][448/510] Data 3.299 (3.846) Batch 30.073 (28.075) Remain 48:12:39 loss: 0.2067 loss_seg: 0.1192 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:25:35,503 INFO misc.py line 117 726] Train: [8/20][449/510] Data 6.547 (3.852) Batch 35.558 (28.092) Remain 48:13:55 loss: 0.2086 loss_seg: 0.1269 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:26:09,046 INFO misc.py line 117 726] Train: [8/20][450/510] Data 4.144 (3.853) Batch 33.542 (28.104) Remain 48:14:42 loss: 0.2461 loss_seg: 0.1528 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:26:09,046 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 23:26:39,797 INFO misc.py line 117 726] Train: [8/20][451/510] Data 4.429 (3.854) Batch 30.751 (28.110) Remain 48:14:51 loss: 0.2838 loss_seg: 0.1886 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:27:12,646 INFO misc.py line 117 726] Train: [8/20][452/510] Data 7.089 (3.861) Batch 32.849 (28.120) Remain 48:15:28 loss: 0.2863 loss_seg: 0.1900 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:27:41,350 INFO misc.py line 117 726] Train: [8/20][453/510] Data 3.347 (3.860) Batch 28.704 (28.122) Remain 48:15:08 loss: 0.2243 loss_seg: 0.1309 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:28:15,721 INFO misc.py line 117 726] Train: [8/20][454/510] Data 5.398 (3.864) Batch 34.371 (28.136) Remain 48:16:05 loss: 0.2646 loss_seg: 0.1669 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:28:49,290 INFO misc.py line 117 726] Train: [8/20][455/510] Data 4.365 (3.865) Batch 33.569 (28.148) Remain 48:16:51 loss: 0.2728 loss_seg: 0.1757 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:29:15,559 INFO misc.py line 117 726] Train: [8/20][456/510] Data 3.539 (3.864) Batch 26.270 (28.144) Remain 48:15:58 loss: 0.2371 loss_seg: 0.1454 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:30:00,916 INFO misc.py line 117 726] Train: [8/20][457/510] Data 12.417 (3.883) Batch 45.357 (28.181) Remain 48:19:23 loss: 0.3587 loss_seg: 0.2653 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:30:36,907 INFO misc.py line 117 726] Train: [8/20][458/510] Data 5.774 (3.887) Batch 35.990 (28.199) Remain 48:20:41 loss: 0.2739 loss_seg: 0.1717 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:31:07,576 INFO misc.py line 117 726] Train: [8/20][459/510] Data 4.179 (3.888) Batch 30.669 (28.204) Remain 48:20:46 loss: 0.2330 loss_seg: 0.1424 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:31:47,131 INFO misc.py line 117 726] Train: [8/20][460/510] Data 7.110 (3.895) Batch 39.555 (28.229) Remain 48:22:51 loss: 0.2634 loss_seg: 0.1598 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:32:15,662 INFO misc.py line 117 726] Train: [8/20][461/510] Data 2.876 (3.892) Batch 28.531 (28.229) Remain 48:22:27 loss: 0.2355 loss_seg: 0.1402 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:32:42,522 INFO misc.py line 117 726] Train: [8/20][462/510] Data 2.496 (3.889) Batch 26.860 (28.227) Remain 48:21:41 loss: 0.2661 loss_seg: 0.1627 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:33:13,714 INFO misc.py line 117 726] Train: [8/20][463/510] Data 3.399 (3.888) Batch 31.192 (28.233) Remain 48:21:52 loss: 0.2236 loss_seg: 0.1322 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:33:37,628 INFO misc.py line 117 726] Train: [8/20][464/510] Data 2.250 (3.885) Batch 23.914 (28.224) Remain 48:20:26 loss: 0.2469 loss_seg: 0.1494 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:34:09,366 INFO misc.py line 117 726] Train: [8/20][465/510] Data 5.116 (3.887) Batch 31.738 (28.231) Remain 48:20:45 loss: 0.3376 loss_seg: 0.2267 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:34:41,732 INFO misc.py line 117 726] Train: [8/20][466/510] Data 4.219 (3.888) Batch 32.366 (28.240) Remain 48:21:12 loss: 0.2825 loss_seg: 0.1814 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:35:06,322 INFO misc.py line 117 726] Train: [8/20][467/510] Data 3.249 (3.887) Batch 24.591 (28.232) Remain 48:19:55 loss: 0.2876 loss_seg: 0.1810 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:35:30,097 INFO misc.py line 117 726] Train: [8/20][468/510] Data 2.558 (3.884) Batch 23.775 (28.223) Remain 48:18:28 loss: 0.2618 loss_seg: 0.1612 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:36:03,712 INFO misc.py line 117 726] Train: [8/20][469/510] Data 5.386 (3.887) Batch 33.614 (28.234) Remain 48:19:11 loss: 0.2114 loss_seg: 0.1221 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:36:31,590 INFO misc.py line 117 726] Train: [8/20][470/510] Data 2.875 (3.885) Batch 27.878 (28.233) Remain 48:18:38 loss: 0.3333 loss_seg: 0.2365 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:36:53,418 INFO misc.py line 117 726] Train: [8/20][471/510] Data 2.504 (3.882) Batch 21.828 (28.220) Remain 48:16:45 loss: 0.2427 loss_seg: 0.1492 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:37:34,968 INFO misc.py line 117 726] Train: [8/20][472/510] Data 8.592 (3.892) Batch 41.550 (28.248) Remain 48:19:12 loss: 0.2174 loss_seg: 0.1245 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:38:04,049 INFO misc.py line 117 726] Train: [8/20][473/510] Data 2.981 (3.890) Batch 29.081 (28.250) Remain 48:18:55 loss: 0.2730 loss_seg: 0.1721 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:38:32,523 INFO misc.py line 117 726] Train: [8/20][474/510] Data 3.467 (3.889) Batch 28.473 (28.250) Remain 48:18:29 loss: 0.2546 loss_seg: 0.1619 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:38:52,961 INFO misc.py line 117 726] Train: [8/20][475/510] Data 2.013 (3.885) Batch 20.438 (28.234) Remain 48:16:19 loss: 0.2706 loss_seg: 0.1763 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:39:29,486 INFO misc.py line 117 726] Train: [8/20][476/510] Data 5.578 (3.889) Batch 36.525 (28.251) Remain 48:17:39 loss: 0.2729 loss_seg: 0.1696 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:40:01,069 INFO misc.py line 117 726] Train: [8/20][477/510] Data 3.931 (3.889) Batch 31.583 (28.258) Remain 48:17:54 loss: 0.2199 loss_seg: 0.1296 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:40:25,239 INFO misc.py line 117 726] Train: [8/20][478/510] Data 2.582 (3.886) Batch 24.170 (28.250) Remain 48:16:33 loss: 0.2362 loss_seg: 0.1419 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:40:54,247 INFO misc.py line 117 726] Train: [8/20][479/510] Data 3.083 (3.884) Batch 29.008 (28.251) Remain 48:16:14 loss: 0.2925 loss_seg: 0.1869 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:41:26,006 INFO misc.py line 117 726] Train: [8/20][480/510] Data 5.167 (3.887) Batch 31.758 (28.259) Remain 48:16:31 loss: 0.2966 loss_seg: 0.1938 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:41:54,045 INFO misc.py line 117 726] Train: [8/20][481/510] Data 7.022 (3.894) Batch 28.039 (28.258) Remain 48:16:00 loss: 0.3991 loss_seg: 0.2955 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:42:19,611 INFO misc.py line 117 726] Train: [8/20][482/510] Data 2.639 (3.891) Batch 25.566 (28.253) Remain 48:14:57 loss: 0.2795 loss_seg: 0.1821 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:42:39,488 INFO misc.py line 117 726] Train: [8/20][483/510] Data 2.406 (3.888) Batch 19.876 (28.235) Remain 48:12:42 loss: 0.2313 loss_seg: 0.1351 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:43:07,421 INFO misc.py line 117 726] Train: [8/20][484/510] Data 3.989 (3.888) Batch 27.933 (28.235) Remain 48:12:10 loss: 0.2195 loss_seg: 0.1269 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:43:39,673 INFO misc.py line 117 726] Train: [8/20][485/510] Data 3.525 (3.887) Batch 32.252 (28.243) Remain 48:12:33 loss: 0.3289 loss_seg: 0.2239 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:44:01,690 INFO misc.py line 117 726] Train: [8/20][486/510] Data 2.587 (3.885) Batch 22.017 (28.230) Remain 48:10:45 loss: 0.2167 loss_seg: 0.1214 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:44:22,266 INFO misc.py line 117 726] Train: [8/20][487/510] Data 2.178 (3.881) Batch 20.576 (28.214) Remain 48:08:40 loss: 0.2858 loss_seg: 0.1829 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:44:44,694 INFO misc.py line 117 726] Train: [8/20][488/510] Data 2.186 (3.878) Batch 22.429 (28.202) Remain 48:06:58 loss: 0.2131 loss_seg: 0.1248 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:45:10,010 INFO misc.py line 117 726] Train: [8/20][489/510] Data 2.799 (3.875) Batch 25.316 (28.196) Remain 48:05:54 loss: 0.2594 loss_seg: 0.1618 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:45:38,335 INFO misc.py line 117 726] Train: [8/20][490/510] Data 3.255 (3.874) Batch 28.325 (28.197) Remain 48:05:27 loss: 0.2155 loss_seg: 0.1255 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:46:09,476 INFO misc.py line 117 726] Train: [8/20][491/510] Data 3.477 (3.873) Batch 31.141 (28.203) Remain 48:05:36 loss: 0.2897 loss_seg: 0.1826 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:46:39,575 INFO misc.py line 117 726] Train: [8/20][492/510] Data 3.398 (3.872) Batch 30.099 (28.207) Remain 48:05:32 loss: 0.2808 loss_seg: 0.1781 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:47:15,729 INFO misc.py line 117 726] Train: [8/20][493/510] Data 3.615 (3.872) Batch 36.154 (28.223) Remain 48:06:43 loss: 0.2525 loss_seg: 0.1556 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:47:44,855 INFO misc.py line 117 726] Train: [8/20][494/510] Data 3.113 (3.870) Batch 29.126 (28.225) Remain 48:06:26 loss: 0.2087 loss_seg: 0.1175 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:48:10,942 INFO misc.py line 117 726] Train: [8/20][495/510] Data 2.951 (3.868) Batch 26.087 (28.220) Remain 48:05:31 loss: 0.3727 loss_seg: 0.2787 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:48:47,507 INFO misc.py line 117 726] Train: [8/20][496/510] Data 5.798 (3.872) Batch 36.565 (28.237) Remain 48:06:47 loss: 0.1925 loss_seg: 0.1104 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:49:18,263 INFO misc.py line 117 726] Train: [8/20][497/510] Data 4.068 (3.873) Batch 30.756 (28.242) Remain 48:06:50 loss: 0.2650 loss_seg: 0.1656 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:49:48,861 INFO misc.py line 117 726] Train: [8/20][498/510] Data 4.584 (3.874) Batch 30.598 (28.247) Remain 48:06:51 loss: 0.2405 loss_seg: 0.1506 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:50:20,692 INFO misc.py line 117 726] Train: [8/20][499/510] Data 3.743 (3.874) Batch 31.831 (28.254) Remain 48:07:07 loss: 0.2089 loss_seg: 0.1252 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:50:51,527 INFO misc.py line 117 726] Train: [8/20][500/510] Data 3.083 (3.872) Batch 30.835 (28.260) Remain 48:07:10 loss: 0.1966 loss_seg: 0.1108 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:50:51,527 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-10 23:51:25,020 INFO misc.py line 117 726] Train: [8/20][501/510] Data 6.979 (3.879) Batch 33.493 (28.270) Remain 48:07:46 loss: 0.2575 loss_seg: 0.1604 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:51:55,340 INFO misc.py line 117 726] Train: [8/20][502/510] Data 4.033 (3.879) Batch 30.320 (28.274) Remain 48:07:43 loss: 0.3510 loss_seg: 0.2513 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:52:26,218 INFO misc.py line 117 726] Train: [8/20][503/510] Data 3.067 (3.877) Batch 30.879 (28.279) Remain 48:07:47 loss: 0.2184 loss_seg: 0.1262 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:52:49,410 INFO misc.py line 117 726] Train: [8/20][504/510] Data 2.627 (3.875) Batch 23.192 (28.269) Remain 48:06:16 loss: 0.2016 loss_seg: 0.1098 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:53:29,744 INFO misc.py line 117 726] Train: [8/20][505/510] Data 10.581 (3.888) Batch 40.334 (28.293) Remain 48:08:15 loss: 0.1946 loss_seg: 0.1043 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:54:06,492 INFO misc.py line 117 726] Train: [8/20][506/510] Data 6.292 (3.893) Batch 36.748 (28.310) Remain 48:09:30 loss: 0.4220 loss_seg: 0.3159 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:54:26,188 INFO misc.py line 117 726] Train: [8/20][507/510] Data 2.369 (3.890) Batch 19.696 (28.293) Remain 48:07:17 loss: 0.3629 loss_seg: 0.2561 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:55:03,162 INFO misc.py line 117 726] Train: [8/20][508/510] Data 5.299 (3.893) Batch 36.974 (28.310) Remain 48:08:34 loss: 0.2562 loss_seg: 0.1556 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:55:31,219 INFO misc.py line 117 726] Train: [8/20][509/510] Data 4.131 (3.893) Batch 28.057 (28.310) Remain 48:08:03 loss: 0.2099 loss_seg: 0.1178 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:56:05,733 INFO misc.py line 117 726] Train: [8/20][510/510] Data 9.238 (3.904) Batch 34.513 (28.322) Remain 48:08:49 loss: 0.2584 loss_seg: 0.1616 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-10 23:56:05,734 INFO misc.py line 147 726] Train result: loss: 0.2553 loss_seg: 0.1595 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-10 23:56:05,734 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-10 23:56:21,340 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7226 [2026-06-10 23:56:37,294 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6463 [2026-06-10 23:57:52,606 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9487 [2026-06-10 23:58:33,519 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9757 [2026-06-10 23:58:52,961 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.1747 [2026-06-10 23:59:29,432 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.0104 [2026-06-11 00:00:16,425 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.0188 [2026-06-11 00:00:32,249 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.1894 [2026-06-11 00:00:50,113 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.8247 [2026-06-11 00:01:08,853 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4805 [2026-06-11 00:01:24,738 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5930 [2026-06-11 00:01:46,535 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.8037 [2026-06-11 00:02:12,668 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8466 [2026-06-11 00:02:24,036 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6518 [2026-06-11 00:02:55,804 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0399 [2026-06-11 00:03:22,103 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3047 [2026-06-11 00:03:49,057 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.1171 [2026-06-11 00:04:32,255 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.0951 [2026-06-11 00:04:53,563 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4614 [2026-06-11 00:05:10,231 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8838 [2026-06-11 00:05:41,682 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.8508 [2026-06-11 00:05:58,196 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.2236 [2026-06-11 00:06:20,299 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2840 [2026-06-11 00:06:42,249 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8113 [2026-06-11 00:06:55,941 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6263 [2026-06-11 00:07:23,946 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5422 [2026-06-11 00:08:05,798 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0285 [2026-06-11 00:08:23,338 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5349 [2026-06-11 00:08:42,190 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.5236 [2026-06-11 00:08:59,285 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4835 [2026-06-11 00:09:24,553 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1100 [2026-06-11 00:09:42,912 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6303 [2026-06-11 00:10:00,610 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.0596 [2026-06-11 00:10:25,278 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6682 [2026-06-11 00:10:25,291 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6691/0.7432/0.8958. [2026-06-11 00:10:25,291 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9246/0.9552 [2026-06-11 00:10:25,291 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9764/0.9883 [2026-06-11 00:10:25,291 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8393/0.9694 [2026-06-11 00:10:25,291 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0016/0.0139 [2026-06-11 00:10:25,291 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3464/0.4355 [2026-06-11 00:10:25,291 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6082/0.6355 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5831/0.6749 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7893/0.8952 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9151/0.9561 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6374/0.7045 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7603/0.8526 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7203/0.8845 [2026-06-11 00:10:25,292 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5959/0.6966 [2026-06-11 00:10:25,292 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-11 00:10:25,293 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-11 00:10:25,293 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 00:10:52,082 INFO misc.py line 117 726] Train: [9/20][1/510] Data 2.845 (2.845) Batch 25.245 (25.245) Remain 42:54:35 loss: 0.2558 loss_seg: 0.1581 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:11:21,041 INFO misc.py line 117 726] Train: [9/20][2/510] Data 3.984 (3.984) Batch 28.959 (28.959) Remain 49:12:49 loss: 0.2610 loss_seg: 0.1667 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:11:49,048 INFO misc.py line 117 726] Train: [9/20][3/510] Data 4.802 (4.802) Batch 28.007 (28.007) Remain 47:35:18 loss: 0.4561 loss_seg: 0.3518 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:12:18,693 INFO misc.py line 117 726] Train: [9/20][4/510] Data 3.787 (3.787) Batch 29.645 (29.645) Remain 50:21:51 loss: 0.2168 loss_seg: 0.1294 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:12:39,461 INFO misc.py line 117 726] Train: [9/20][5/510] Data 2.516 (3.152) Batch 20.768 (25.207) Remain 42:48:59 loss: 0.2655 loss_seg: 0.1671 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:13:10,612 INFO misc.py line 117 726] Train: [9/20][6/510] Data 2.612 (2.972) Batch 31.151 (27.188) Remain 46:10:28 loss: 0.2908 loss_seg: 0.2034 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:13:43,438 INFO misc.py line 117 726] Train: [9/20][7/510] Data 5.036 (3.488) Batch 32.826 (28.598) Remain 48:33:37 loss: 0.2233 loss_seg: 0.1299 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:14:08,588 INFO misc.py line 117 726] Train: [9/20][8/510] Data 2.465 (3.283) Batch 25.150 (27.908) Remain 47:22:54 loss: 0.2859 loss_seg: 0.1822 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:14:36,624 INFO misc.py line 117 726] Train: [9/20][9/510] Data 5.961 (3.730) Batch 28.036 (27.929) Remain 47:24:36 loss: 0.3362 loss_seg: 0.2214 loss_superpoint_edge: 0.0445 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:15:09,081 INFO misc.py line 117 726] Train: [9/20][10/510] Data 3.540 (3.702) Batch 32.457 (28.576) Remain 48:30:00 loss: 0.2715 loss_seg: 0.1705 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:15:38,478 INFO misc.py line 117 726] Train: [9/20][11/510] Data 3.047 (3.620) Batch 29.396 (28.679) Remain 48:39:58 loss: 0.2393 loss_seg: 0.1413 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:16:01,609 INFO misc.py line 117 726] Train: [9/20][12/510] Data 2.468 (3.492) Batch 23.131 (28.062) Remain 47:36:45 loss: 0.1992 loss_seg: 0.1091 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:16:22,225 INFO misc.py line 117 726] Train: [9/20][13/510] Data 2.589 (3.402) Batch 20.616 (27.318) Remain 46:20:29 loss: 0.2699 loss_seg: 0.1711 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:16:54,736 INFO misc.py line 117 726] Train: [9/20][14/510] Data 3.817 (3.440) Batch 32.511 (27.790) Remain 47:08:04 loss: 0.2306 loss_seg: 0.1371 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:17:21,967 INFO misc.py line 117 726] Train: [9/20][15/510] Data 4.129 (3.497) Batch 27.231 (27.743) Remain 47:02:52 loss: 0.3101 loss_seg: 0.2192 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:17:47,831 INFO misc.py line 117 726] Train: [9/20][16/510] Data 2.319 (3.407) Batch 25.864 (27.599) Remain 46:47:42 loss: 0.2496 loss_seg: 0.1543 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:18:15,477 INFO misc.py line 117 726] Train: [9/20][17/510] Data 3.256 (3.396) Batch 27.646 (27.602) Remain 46:47:35 loss: 0.2446 loss_seg: 0.1490 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:18:41,902 INFO misc.py line 117 726] Train: [9/20][18/510] Data 3.347 (3.393) Batch 26.425 (27.524) Remain 46:39:09 loss: 0.2153 loss_seg: 0.1223 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:19:09,977 INFO misc.py line 117 726] Train: [9/20][19/510] Data 3.992 (3.430) Batch 28.075 (27.558) Remain 46:42:11 loss: 0.2147 loss_seg: 0.1284 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:19:37,135 INFO misc.py line 117 726] Train: [9/20][20/510] Data 3.049 (3.408) Batch 27.158 (27.535) Remain 46:39:20 loss: 0.2095 loss_seg: 0.1179 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:20:04,050 INFO misc.py line 117 726] Train: [9/20][21/510] Data 5.791 (3.540) Batch 26.914 (27.500) Remain 46:35:23 loss: 0.2620 loss_seg: 0.1677 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:20:24,388 INFO misc.py line 117 726] Train: [9/20][22/510] Data 2.032 (3.461) Batch 20.338 (27.123) Remain 45:56:37 loss: 0.2248 loss_seg: 0.1296 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:20:56,889 INFO misc.py line 117 726] Train: [9/20][23/510] Data 4.825 (3.529) Batch 32.501 (27.392) Remain 46:23:29 loss: 0.2482 loss_seg: 0.1444 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:21:18,651 INFO misc.py line 117 726] Train: [9/20][24/510] Data 2.838 (3.496) Batch 21.762 (27.124) Remain 45:55:47 loss: 0.2486 loss_seg: 0.1475 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:21:50,129 INFO misc.py line 117 726] Train: [9/20][25/510] Data 4.851 (3.558) Batch 31.478 (27.322) Remain 46:15:26 loss: 0.1975 loss_seg: 0.1096 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:22:14,609 INFO misc.py line 117 726] Train: [9/20][26/510] Data 3.786 (3.568) Batch 24.479 (27.198) Remain 46:02:26 loss: 0.3569 loss_seg: 0.2565 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:22:44,327 INFO misc.py line 117 726] Train: [9/20][27/510] Data 4.418 (3.603) Batch 29.718 (27.303) Remain 46:12:38 loss: 0.2083 loss_seg: 0.1168 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:23:23,903 INFO misc.py line 117 726] Train: [9/20][28/510] Data 5.231 (3.668) Batch 39.576 (27.794) Remain 47:02:02 loss: 0.1881 loss_seg: 0.1030 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:23:49,516 INFO misc.py line 117 726] Train: [9/20][29/510] Data 2.808 (3.635) Batch 25.613 (27.710) Remain 46:53:03 loss: 0.2576 loss_seg: 0.1560 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:24:14,267 INFO misc.py line 117 726] Train: [9/20][30/510] Data 3.168 (3.618) Batch 24.751 (27.601) Remain 46:41:28 loss: 0.1755 loss_seg: 0.0899 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:24:39,463 INFO misc.py line 117 726] Train: [9/20][31/510] Data 3.415 (3.610) Batch 25.195 (27.515) Remain 46:32:17 loss: 0.3056 loss_seg: 0.2046 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:25:08,884 INFO misc.py line 117 726] Train: [9/20][32/510] Data 4.113 (3.628) Batch 29.422 (27.581) Remain 46:38:30 loss: 0.3232 loss_seg: 0.2161 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:25:37,816 INFO misc.py line 117 726] Train: [9/20][33/510] Data 3.828 (3.634) Batch 28.932 (27.626) Remain 46:42:37 loss: 0.2263 loss_seg: 0.1319 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:26:17,873 INFO misc.py line 117 726] Train: [9/20][34/510] Data 9.363 (3.819) Batch 40.057 (28.027) Remain 47:22:50 loss: 0.2378 loss_seg: 0.1461 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:26:45,611 INFO misc.py line 117 726] Train: [9/20][35/510] Data 2.962 (3.793) Batch 27.738 (28.018) Remain 47:21:27 loss: 0.2562 loss_seg: 0.1565 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:27:20,180 INFO misc.py line 117 726] Train: [9/20][36/510] Data 4.874 (3.825) Batch 34.569 (28.216) Remain 47:41:06 loss: 0.1784 loss_seg: 0.0914 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:27:44,051 INFO misc.py line 117 726] Train: [9/20][37/510] Data 3.386 (3.812) Batch 23.871 (28.088) Remain 47:27:41 loss: 0.2599 loss_seg: 0.1620 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:28:01,574 INFO misc.py line 117 726] Train: [9/20][38/510] Data 2.155 (3.765) Batch 17.523 (27.786) Remain 46:56:37 loss: 0.1765 loss_seg: 0.0936 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:28:26,972 INFO misc.py line 117 726] Train: [9/20][39/510] Data 2.911 (3.741) Batch 25.398 (27.720) Remain 46:49:26 loss: 0.2382 loss_seg: 0.1470 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:28:57,796 INFO misc.py line 117 726] Train: [9/20][40/510] Data 4.010 (3.749) Batch 30.823 (27.804) Remain 46:57:28 loss: 0.1868 loss_seg: 0.1020 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:29:25,985 INFO misc.py line 117 726] Train: [9/20][41/510] Data 2.916 (3.727) Batch 28.189 (27.814) Remain 46:58:02 loss: 0.2107 loss_seg: 0.1222 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:29:51,224 INFO misc.py line 117 726] Train: [9/20][42/510] Data 2.909 (3.706) Batch 25.239 (27.748) Remain 46:50:53 loss: 0.3689 loss_seg: 0.2636 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:30:14,106 INFO misc.py line 117 726] Train: [9/20][43/510] Data 2.201 (3.668) Batch 22.882 (27.626) Remain 46:38:05 loss: 0.2388 loss_seg: 0.1432 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:30:44,399 INFO misc.py line 117 726] Train: [9/20][44/510] Data 4.087 (3.678) Batch 30.293 (27.691) Remain 46:44:13 loss: 0.2353 loss_seg: 0.1372 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:31:15,245 INFO misc.py line 117 726] Train: [9/20][45/510] Data 4.968 (3.709) Batch 30.846 (27.767) Remain 46:51:22 loss: 0.3012 loss_seg: 0.1984 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:31:51,214 INFO misc.py line 117 726] Train: [9/20][46/510] Data 11.144 (3.882) Batch 35.969 (27.957) Remain 47:10:13 loss: 0.2125 loss_seg: 0.1208 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:32:17,444 INFO misc.py line 117 726] Train: [9/20][47/510] Data 2.809 (3.858) Batch 26.230 (27.918) Remain 47:05:46 loss: 0.2268 loss_seg: 0.1351 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:32:41,258 INFO misc.py line 117 726] Train: [9/20][48/510] Data 3.235 (3.844) Batch 23.814 (27.827) Remain 46:56:04 loss: 0.2536 loss_seg: 0.1550 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:33:17,956 INFO misc.py line 117 726] Train: [9/20][49/510] Data 5.649 (3.883) Batch 36.698 (28.020) Remain 47:15:07 loss: 0.2184 loss_seg: 0.1238 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:33:45,672 INFO misc.py line 117 726] Train: [9/20][50/510] Data 3.120 (3.867) Batch 27.716 (28.013) Remain 47:14:00 loss: 0.2331 loss_seg: 0.1392 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:33:45,672 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 00:34:12,231 INFO misc.py line 117 726] Train: [9/20][51/510] Data 2.929 (3.847) Batch 26.560 (27.983) Remain 47:10:28 loss: 0.2135 loss_seg: 0.1264 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:34:39,516 INFO misc.py line 117 726] Train: [9/20][52/510] Data 2.556 (3.821) Batch 27.285 (27.969) Remain 47:08:34 loss: 0.2319 loss_seg: 0.1369 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:35:14,343 INFO misc.py line 117 726] Train: [9/20][53/510] Data 5.914 (3.863) Batch 34.827 (28.106) Remain 47:21:58 loss: 0.2597 loss_seg: 0.1617 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:35:45,080 INFO misc.py line 117 726] Train: [9/20][54/510] Data 5.529 (3.895) Batch 30.737 (28.158) Remain 47:26:43 loss: 0.2638 loss_seg: 0.1621 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:36:17,622 INFO misc.py line 117 726] Train: [9/20][55/510] Data 4.087 (3.899) Batch 32.542 (28.242) Remain 47:34:46 loss: 0.3697 loss_seg: 0.2676 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:36:57,384 INFO misc.py line 117 726] Train: [9/20][56/510] Data 6.661 (3.951) Batch 39.762 (28.459) Remain 47:56:16 loss: 0.3017 loss_seg: 0.2000 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:37:22,971 INFO misc.py line 117 726] Train: [9/20][57/510] Data 3.834 (3.949) Batch 25.587 (28.406) Remain 47:50:25 loss: 0.2853 loss_seg: 0.1851 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:37:50,322 INFO misc.py line 117 726] Train: [9/20][58/510] Data 2.867 (3.929) Batch 27.350 (28.387) Remain 47:48:00 loss: 0.2207 loss_seg: 0.1298 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:38:10,321 INFO misc.py line 117 726] Train: [9/20][59/510] Data 2.283 (3.900) Batch 20.000 (28.237) Remain 47:32:24 loss: 0.2021 loss_seg: 0.1127 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:38:41,839 INFO misc.py line 117 726] Train: [9/20][60/510] Data 4.200 (3.905) Batch 31.518 (28.295) Remain 47:37:45 loss: 0.2940 loss_seg: 0.1889 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:39:13,882 INFO misc.py line 117 726] Train: [9/20][61/510] Data 7.429 (3.966) Batch 32.043 (28.359) Remain 47:43:48 loss: 0.1887 loss_seg: 0.0991 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:39:41,420 INFO misc.py line 117 726] Train: [9/20][62/510] Data 3.101 (3.951) Batch 27.537 (28.345) Remain 47:41:55 loss: 0.2690 loss_seg: 0.1770 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:40:08,754 INFO misc.py line 117 726] Train: [9/20][63/510] Data 2.718 (3.931) Batch 27.335 (28.328) Remain 47:39:45 loss: 0.2081 loss_seg: 0.1188 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:40:39,363 INFO misc.py line 117 726] Train: [9/20][64/510] Data 4.303 (3.937) Batch 30.608 (28.366) Remain 47:43:03 loss: 0.3928 loss_seg: 0.2830 loss_superpoint_edge: 0.0421 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:41:00,426 INFO misc.py line 117 726] Train: [9/20][65/510] Data 2.487 (3.913) Batch 21.063 (28.248) Remain 47:30:41 loss: 0.2262 loss_seg: 0.1370 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:41:30,159 INFO misc.py line 117 726] Train: [9/20][66/510] Data 3.058 (3.900) Batch 29.733 (28.272) Remain 47:32:36 loss: 0.3053 loss_seg: 0.2045 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:41:55,049 INFO misc.py line 117 726] Train: [9/20][67/510] Data 2.403 (3.876) Batch 24.890 (28.219) Remain 47:26:48 loss: 0.2194 loss_seg: 0.1241 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:42:11,399 INFO misc.py line 117 726] Train: [9/20][68/510] Data 1.806 (3.845) Batch 16.350 (28.036) Remain 47:07:54 loss: 0.2317 loss_seg: 0.1362 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:42:38,023 INFO misc.py line 117 726] Train: [9/20][69/510] Data 3.621 (3.841) Batch 26.624 (28.015) Remain 47:05:17 loss: 0.2970 loss_seg: 0.1941 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:43:15,831 INFO misc.py line 117 726] Train: [9/20][70/510] Data 4.431 (3.850) Batch 37.808 (28.161) Remain 47:19:33 loss: 0.2155 loss_seg: 0.1236 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:43:42,396 INFO misc.py line 117 726] Train: [9/20][71/510] Data 4.094 (3.854) Batch 26.566 (28.137) Remain 47:16:43 loss: 0.2789 loss_seg: 0.1819 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:44:13,957 INFO misc.py line 117 726] Train: [9/20][72/510] Data 3.306 (3.846) Batch 31.561 (28.187) Remain 47:21:15 loss: 0.2035 loss_seg: 0.1146 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:44:52,050 INFO misc.py line 117 726] Train: [9/20][73/510] Data 7.663 (3.900) Batch 38.093 (28.329) Remain 47:35:03 loss: 0.2016 loss_seg: 0.1148 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:45:25,164 INFO misc.py line 117 726] Train: [9/20][74/510] Data 4.187 (3.904) Batch 33.113 (28.396) Remain 47:41:22 loss: 0.2156 loss_seg: 0.1296 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:45:51,734 INFO misc.py line 117 726] Train: [9/20][75/510] Data 4.502 (3.913) Batch 26.572 (28.371) Remain 47:38:20 loss: 0.2716 loss_seg: 0.1719 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:46:12,171 INFO misc.py line 117 726] Train: [9/20][76/510] Data 2.375 (3.892) Batch 20.437 (28.262) Remain 47:26:55 loss: 0.3039 loss_seg: 0.2066 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:46:32,324 INFO misc.py line 117 726] Train: [9/20][77/510] Data 1.846 (3.864) Batch 20.153 (28.152) Remain 47:15:24 loss: 0.2796 loss_seg: 0.1765 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:47:00,310 INFO misc.py line 117 726] Train: [9/20][78/510] Data 2.765 (3.849) Batch 27.986 (28.150) Remain 47:14:43 loss: 0.1840 loss_seg: 0.0995 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:47:28,630 INFO misc.py line 117 726] Train: [9/20][79/510] Data 2.380 (3.830) Batch 28.320 (28.152) Remain 47:14:28 loss: 0.2796 loss_seg: 0.1709 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:47:57,914 INFO misc.py line 117 726] Train: [9/20][80/510] Data 2.488 (3.812) Batch 29.284 (28.167) Remain 47:15:29 loss: 0.2159 loss_seg: 0.1251 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:48:31,053 INFO misc.py line 117 726] Train: [9/20][81/510] Data 3.290 (3.806) Batch 33.139 (28.231) Remain 47:21:25 loss: 0.4046 loss_seg: 0.2874 loss_superpoint_edge: 0.0469 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:49:02,023 INFO misc.py line 117 726] Train: [9/20][82/510] Data 5.265 (3.824) Batch 30.971 (28.266) Remain 47:24:27 loss: 0.2939 loss_seg: 0.1889 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:49:32,853 INFO misc.py line 117 726] Train: [9/20][83/510] Data 3.462 (3.820) Batch 30.829 (28.298) Remain 47:27:12 loss: 0.2518 loss_seg: 0.1565 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:50:01,477 INFO misc.py line 117 726] Train: [9/20][84/510] Data 4.274 (3.825) Batch 28.625 (28.302) Remain 47:27:08 loss: 0.2231 loss_seg: 0.1321 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:50:37,581 INFO misc.py line 117 726] Train: [9/20][85/510] Data 4.906 (3.839) Batch 36.103 (28.397) Remain 47:36:14 loss: 0.2118 loss_seg: 0.1236 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:51:02,785 INFO misc.py line 117 726] Train: [9/20][86/510] Data 2.643 (3.824) Batch 25.204 (28.358) Remain 47:31:53 loss: 0.2458 loss_seg: 0.1514 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:51:29,416 INFO misc.py line 117 726] Train: [9/20][87/510] Data 2.424 (3.807) Batch 26.631 (28.338) Remain 47:29:21 loss: 0.1988 loss_seg: 0.1146 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:51:58,250 INFO misc.py line 117 726] Train: [9/20][88/510] Data 3.063 (3.799) Batch 28.834 (28.344) Remain 47:29:28 loss: 0.3231 loss_seg: 0.2200 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:52:16,385 INFO misc.py line 117 726] Train: [9/20][89/510] Data 1.822 (3.776) Batch 18.135 (28.225) Remain 47:17:04 loss: 0.2630 loss_seg: 0.1652 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:52:45,287 INFO misc.py line 117 726] Train: [9/20][90/510] Data 3.274 (3.770) Batch 28.902 (28.233) Remain 47:17:22 loss: 0.1884 loss_seg: 0.1019 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:53:16,973 INFO misc.py line 117 726] Train: [9/20][91/510] Data 3.303 (3.765) Batch 31.686 (28.272) Remain 47:20:51 loss: 0.2494 loss_seg: 0.1564 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:53:46,456 INFO misc.py line 117 726] Train: [9/20][92/510] Data 4.335 (3.771) Batch 29.482 (28.285) Remain 47:21:44 loss: 0.2899 loss_seg: 0.1956 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:54:04,899 INFO misc.py line 117 726] Train: [9/20][93/510] Data 2.054 (3.752) Batch 18.443 (28.176) Remain 47:10:17 loss: 0.2735 loss_seg: 0.1679 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:54:24,655 INFO misc.py line 117 726] Train: [9/20][94/510] Data 2.392 (3.737) Batch 19.756 (28.084) Remain 47:00:31 loss: 0.2904 loss_seg: 0.1898 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:54:58,868 INFO misc.py line 117 726] Train: [9/20][95/510] Data 4.968 (3.750) Batch 34.213 (28.150) Remain 47:06:45 loss: 0.1947 loss_seg: 0.1075 loss_superpoint_edge: 0.0136 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:55:27,808 INFO misc.py line 117 726] Train: [9/20][96/510] Data 4.777 (3.761) Batch 28.939 (28.159) Remain 47:07:08 loss: 0.2155 loss_seg: 0.1265 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:55:47,448 INFO misc.py line 117 726] Train: [9/20][97/510] Data 2.348 (3.746) Batch 19.640 (28.068) Remain 46:57:34 loss: 0.3707 loss_seg: 0.2707 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:56:15,710 INFO misc.py line 117 726] Train: [9/20][98/510] Data 2.914 (3.738) Batch 28.262 (28.070) Remain 46:57:18 loss: 0.1958 loss_seg: 0.1119 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:56:44,327 INFO misc.py line 117 726] Train: [9/20][99/510] Data 3.020 (3.730) Batch 28.618 (28.076) Remain 46:57:24 loss: 0.2028 loss_seg: 0.1122 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:57:15,408 INFO misc.py line 117 726] Train: [9/20][100/510] Data 3.158 (3.724) Batch 31.080 (28.107) Remain 47:00:02 loss: 0.2350 loss_seg: 0.1388 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:57:15,409 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 00:57:48,393 INFO misc.py line 117 726] Train: [9/20][101/510] Data 4.523 (3.732) Batch 32.986 (28.157) Remain 47:04:34 loss: 0.2659 loss_seg: 0.1644 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:58:23,082 INFO misc.py line 117 726] Train: [9/20][102/510] Data 5.437 (3.750) Batch 34.689 (28.223) Remain 47:10:43 loss: 0.2375 loss_seg: 0.1398 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:58:55,088 INFO misc.py line 117 726] Train: [9/20][103/510] Data 5.889 (3.771) Batch 32.006 (28.260) Remain 47:14:02 loss: 0.2109 loss_seg: 0.1249 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:59:20,938 INFO misc.py line 117 726] Train: [9/20][104/510] Data 2.242 (3.756) Batch 25.850 (28.237) Remain 47:11:11 loss: 0.2607 loss_seg: 0.1722 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 00:59:43,209 INFO misc.py line 117 726] Train: [9/20][105/510] Data 2.934 (3.748) Batch 22.271 (28.178) Remain 47:04:50 loss: 0.2465 loss_seg: 0.1472 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:00:20,827 INFO misc.py line 117 726] Train: [9/20][106/510] Data 12.235 (3.830) Batch 37.618 (28.270) Remain 47:13:33 loss: 0.2557 loss_seg: 0.1492 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:00:40,966 INFO misc.py line 117 726] Train: [9/20][107/510] Data 2.456 (3.817) Batch 20.139 (28.192) Remain 47:05:15 loss: 0.2457 loss_seg: 0.1512 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:01:08,460 INFO misc.py line 117 726] Train: [9/20][108/510] Data 3.156 (3.811) Batch 27.494 (28.185) Remain 47:04:07 loss: 0.2046 loss_seg: 0.1143 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:01:31,775 INFO misc.py line 117 726] Train: [9/20][109/510] Data 2.393 (3.797) Batch 23.315 (28.139) Remain 46:59:03 loss: 0.2451 loss_seg: 0.1468 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:02:00,140 INFO misc.py line 117 726] Train: [9/20][110/510] Data 7.402 (3.831) Batch 28.365 (28.141) Remain 46:58:47 loss: 0.2326 loss_seg: 0.1390 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:02:34,203 INFO misc.py line 117 726] Train: [9/20][111/510] Data 5.088 (3.843) Batch 34.064 (28.196) Remain 47:03:49 loss: 0.2989 loss_seg: 0.2079 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:03:00,019 INFO misc.py line 117 726] Train: [9/20][112/510] Data 3.096 (3.836) Batch 25.816 (28.174) Remain 47:01:09 loss: 0.2069 loss_seg: 0.1156 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:03:29,523 INFO misc.py line 117 726] Train: [9/20][113/510] Data 5.923 (3.855) Batch 29.504 (28.186) Remain 47:01:54 loss: 0.2670 loss_seg: 0.1668 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:04:01,991 INFO misc.py line 117 726] Train: [9/20][114/510] Data 4.570 (3.861) Batch 32.468 (28.225) Remain 47:05:17 loss: 0.2433 loss_seg: 0.1460 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:04:38,191 INFO misc.py line 117 726] Train: [9/20][115/510] Data 9.644 (3.913) Batch 36.200 (28.296) Remain 47:11:56 loss: 0.2146 loss_seg: 0.1194 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0458 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:05:19,730 INFO misc.py line 117 726] Train: [9/20][116/510] Data 9.066 (3.958) Batch 41.539 (28.413) Remain 47:23:12 loss: 0.2263 loss_seg: 0.1347 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:05:43,689 INFO misc.py line 117 726] Train: [9/20][117/510] Data 2.803 (3.948) Batch 23.959 (28.374) Remain 47:18:49 loss: 0.2621 loss_seg: 0.1651 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:06:14,059 INFO misc.py line 117 726] Train: [9/20][118/510] Data 3.375 (3.943) Batch 30.371 (28.391) Remain 47:20:05 loss: 0.2608 loss_seg: 0.1555 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:06:51,146 INFO misc.py line 117 726] Train: [9/20][119/510] Data 8.981 (3.987) Batch 37.086 (28.466) Remain 47:27:06 loss: 0.2209 loss_seg: 0.1312 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:07:25,809 INFO misc.py line 117 726] Train: [9/20][120/510] Data 3.417 (3.982) Batch 34.664 (28.519) Remain 47:31:55 loss: 0.2459 loss_seg: 0.1487 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:08:04,250 INFO misc.py line 117 726] Train: [9/20][121/510] Data 6.094 (4.000) Batch 38.441 (28.603) Remain 47:39:51 loss: 0.2424 loss_seg: 0.1502 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:08:34,153 INFO misc.py line 117 726] Train: [9/20][122/510] Data 3.296 (3.994) Batch 29.903 (28.614) Remain 47:40:28 loss: 0.2035 loss_seg: 0.1147 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:08:59,191 INFO misc.py line 117 726] Train: [9/20][123/510] Data 2.972 (3.985) Batch 25.038 (28.585) Remain 47:37:01 loss: 0.2225 loss_seg: 0.1281 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:09:26,251 INFO misc.py line 117 726] Train: [9/20][124/510] Data 2.550 (3.974) Batch 27.060 (28.572) Remain 47:35:17 loss: 0.2264 loss_seg: 0.1333 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:09:52,032 INFO misc.py line 117 726] Train: [9/20][125/510] Data 3.076 (3.966) Batch 25.780 (28.549) Remain 47:32:31 loss: 0.2077 loss_seg: 0.1167 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:10:12,263 INFO misc.py line 117 726] Train: [9/20][126/510] Data 2.380 (3.953) Batch 20.231 (28.481) Remain 47:25:17 loss: 0.2394 loss_seg: 0.1440 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:10:39,156 INFO misc.py line 117 726] Train: [9/20][127/510] Data 3.090 (3.946) Batch 26.893 (28.469) Remain 47:23:32 loss: 0.2656 loss_seg: 0.1627 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:11:07,189 INFO misc.py line 117 726] Train: [9/20][128/510] Data 3.546 (3.943) Batch 28.034 (28.465) Remain 47:22:43 loss: 0.3394 loss_seg: 0.2349 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:11:37,279 INFO misc.py line 117 726] Train: [9/20][129/510] Data 3.872 (3.943) Batch 30.090 (28.478) Remain 47:23:31 loss: 0.2652 loss_seg: 0.1629 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:12:05,559 INFO misc.py line 117 726] Train: [9/20][130/510] Data 3.037 (3.935) Batch 28.280 (28.476) Remain 47:22:54 loss: 0.3603 loss_seg: 0.2495 loss_superpoint_edge: 0.0444 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:12:46,319 INFO misc.py line 117 726] Train: [9/20][131/510] Data 6.587 (3.956) Batch 40.760 (28.572) Remain 47:32:00 loss: 0.2989 loss_seg: 0.1975 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0346 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:13:09,163 INFO misc.py line 117 726] Train: [9/20][132/510] Data 4.565 (3.961) Batch 22.844 (28.528) Remain 47:27:05 loss: 0.2350 loss_seg: 0.1421 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:13:32,791 INFO misc.py line 117 726] Train: [9/20][133/510] Data 2.763 (3.952) Batch 23.628 (28.490) Remain 47:22:51 loss: 0.2030 loss_seg: 0.1100 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:13:57,208 INFO misc.py line 117 726] Train: [9/20][134/510] Data 3.150 (3.946) Batch 24.417 (28.459) Remain 47:19:16 loss: 0.3230 loss_seg: 0.2170 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:14:30,786 INFO misc.py line 117 726] Train: [9/20][135/510] Data 8.247 (3.978) Batch 33.578 (28.498) Remain 47:22:40 loss: 0.2713 loss_seg: 0.1761 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:15:00,672 INFO misc.py line 117 726] Train: [9/20][136/510] Data 4.488 (3.982) Batch 29.887 (28.508) Remain 47:23:14 loss: 0.2330 loss_seg: 0.1454 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:15:20,471 INFO misc.py line 117 726] Train: [9/20][137/510] Data 3.088 (3.975) Batch 19.799 (28.443) Remain 47:16:17 loss: 0.3352 loss_seg: 0.2248 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:15:50,187 INFO misc.py line 117 726] Train: [9/20][138/510] Data 3.128 (3.969) Batch 29.716 (28.453) Remain 47:16:45 loss: 0.2185 loss_seg: 0.1235 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:16:19,125 INFO misc.py line 117 726] Train: [9/20][139/510] Data 4.631 (3.974) Batch 28.938 (28.456) Remain 47:16:37 loss: 0.2231 loss_seg: 0.1308 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:16:59,564 INFO misc.py line 117 726] Train: [9/20][140/510] Data 6.440 (3.992) Batch 40.439 (28.544) Remain 47:24:52 loss: 0.3362 loss_seg: 0.2397 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:17:35,700 INFO misc.py line 117 726] Train: [9/20][141/510] Data 5.959 (4.006) Batch 36.136 (28.599) Remain 47:29:52 loss: 0.2661 loss_seg: 0.1749 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:17:57,368 INFO misc.py line 117 726] Train: [9/20][142/510] Data 2.510 (3.995) Batch 21.668 (28.549) Remain 47:24:26 loss: 0.2755 loss_seg: 0.1773 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:18:28,260 INFO misc.py line 117 726] Train: [9/20][143/510] Data 3.379 (3.991) Batch 30.892 (28.566) Remain 47:25:37 loss: 0.2482 loss_seg: 0.1546 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:18:50,827 INFO misc.py line 117 726] Train: [9/20][144/510] Data 3.426 (3.987) Batch 22.567 (28.523) Remain 47:20:54 loss: 0.3307 loss_seg: 0.2236 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:19:09,046 INFO misc.py line 117 726] Train: [9/20][145/510] Data 1.595 (3.970) Batch 18.219 (28.451) Remain 47:13:12 loss: 0.2046 loss_seg: 0.1106 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:19:35,585 INFO misc.py line 117 726] Train: [9/20][146/510] Data 2.964 (3.963) Batch 26.538 (28.437) Remain 47:11:24 loss: 0.2488 loss_seg: 0.1548 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:20:00,579 INFO misc.py line 117 726] Train: [9/20][147/510] Data 2.696 (3.954) Batch 24.994 (28.413) Remain 47:08:33 loss: 0.2544 loss_seg: 0.1550 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:20:21,910 INFO misc.py line 117 726] Train: [9/20][148/510] Data 2.805 (3.946) Batch 21.331 (28.365) Remain 47:03:13 loss: 0.2936 loss_seg: 0.1884 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:20:56,414 INFO misc.py line 117 726] Train: [9/20][149/510] Data 5.166 (3.955) Batch 34.504 (28.407) Remain 47:06:55 loss: 0.4876 loss_seg: 0.3847 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:21:25,231 INFO misc.py line 117 726] Train: [9/20][150/510] Data 3.149 (3.949) Batch 28.818 (28.409) Remain 47:06:44 loss: 0.2519 loss_seg: 0.1503 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:21:25,232 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 01:21:43,872 INFO misc.py line 117 726] Train: [9/20][151/510] Data 3.048 (3.943) Batch 18.641 (28.343) Remain 46:59:41 loss: 0.2593 loss_seg: 0.1605 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:22:02,806 INFO misc.py line 117 726] Train: [9/20][152/510] Data 1.927 (3.930) Batch 18.934 (28.280) Remain 46:52:56 loss: 0.2268 loss_seg: 0.1357 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:22:34,701 INFO misc.py line 117 726] Train: [9/20][153/510] Data 3.312 (3.925) Batch 31.894 (28.304) Remain 46:54:52 loss: 0.2302 loss_seg: 0.1352 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:23:03,164 INFO misc.py line 117 726] Train: [9/20][154/510] Data 5.478 (3.936) Batch 28.463 (28.305) Remain 46:54:30 loss: 0.3199 loss_seg: 0.2220 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:23:38,848 INFO misc.py line 117 726] Train: [9/20][155/510] Data 7.368 (3.958) Batch 35.684 (28.354) Remain 46:58:51 loss: 0.3455 loss_seg: 0.2417 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:24:02,067 INFO misc.py line 117 726] Train: [9/20][156/510] Data 2.738 (3.950) Batch 23.219 (28.320) Remain 46:55:02 loss: 0.2126 loss_seg: 0.1191 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:24:27,244 INFO misc.py line 117 726] Train: [9/20][157/510] Data 2.134 (3.939) Batch 25.177 (28.300) Remain 46:52:32 loss: 0.2422 loss_seg: 0.1493 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:24:50,632 INFO misc.py line 117 726] Train: [9/20][158/510] Data 2.270 (3.928) Batch 23.388 (28.268) Remain 46:48:55 loss: 0.2006 loss_seg: 0.1078 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:25:17,946 INFO misc.py line 117 726] Train: [9/20][159/510] Data 3.340 (3.924) Batch 27.314 (28.262) Remain 46:47:50 loss: 0.2125 loss_seg: 0.1217 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:25:48,896 INFO misc.py line 117 726] Train: [9/20][160/510] Data 3.297 (3.920) Batch 30.949 (28.279) Remain 46:49:04 loss: 0.2592 loss_seg: 0.1581 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:26:15,735 INFO misc.py line 117 726] Train: [9/20][161/510] Data 3.411 (3.917) Batch 26.840 (28.270) Remain 46:47:41 loss: 0.2298 loss_seg: 0.1355 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:26:43,228 INFO misc.py line 117 726] Train: [9/20][162/510] Data 3.234 (3.913) Batch 27.493 (28.265) Remain 46:46:44 loss: 0.2611 loss_seg: 0.1656 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:27:07,107 INFO misc.py line 117 726] Train: [9/20][163/510] Data 2.465 (3.903) Batch 23.879 (28.238) Remain 46:43:32 loss: 0.2159 loss_seg: 0.1241 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:27:32,630 INFO misc.py line 117 726] Train: [9/20][164/510] Data 2.476 (3.895) Batch 25.523 (28.221) Remain 46:41:24 loss: 0.3210 loss_seg: 0.2115 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:27:58,313 INFO misc.py line 117 726] Train: [9/20][165/510] Data 2.753 (3.888) Batch 25.683 (28.205) Remain 46:39:22 loss: 0.1970 loss_seg: 0.1081 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:28:17,171 INFO misc.py line 117 726] Train: [9/20][166/510] Data 1.891 (3.875) Batch 18.858 (28.148) Remain 46:33:13 loss: 0.2234 loss_seg: 0.1277 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:28:46,391 INFO misc.py line 117 726] Train: [9/20][167/510] Data 4.109 (3.877) Batch 29.220 (28.155) Remain 46:33:23 loss: 0.2303 loss_seg: 0.1384 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:29:14,477 INFO misc.py line 117 726] Train: [9/20][168/510] Data 4.624 (3.881) Batch 28.087 (28.154) Remain 46:32:53 loss: 0.2619 loss_seg: 0.1635 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:29:41,572 INFO misc.py line 117 726] Train: [9/20][169/510] Data 2.615 (3.874) Batch 27.094 (28.148) Remain 46:31:47 loss: 0.2276 loss_seg: 0.1313 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:30:13,676 INFO misc.py line 117 726] Train: [9/20][170/510] Data 5.564 (3.884) Batch 32.105 (28.171) Remain 46:33:39 loss: 0.1899 loss_seg: 0.1067 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:30:37,758 INFO misc.py line 117 726] Train: [9/20][171/510] Data 2.719 (3.877) Batch 24.082 (28.147) Remain 46:30:46 loss: 0.2800 loss_seg: 0.1773 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:31:01,748 INFO misc.py line 117 726] Train: [9/20][172/510] Data 2.530 (3.869) Batch 23.990 (28.122) Remain 46:27:52 loss: 0.2084 loss_seg: 0.1216 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:31:27,205 INFO misc.py line 117 726] Train: [9/20][173/510] Data 2.661 (3.862) Batch 25.457 (28.107) Remain 46:25:51 loss: 0.2428 loss_seg: 0.1452 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:32:06,376 INFO misc.py line 117 726] Train: [9/20][174/510] Data 12.314 (3.911) Batch 39.171 (28.172) Remain 46:31:47 loss: 0.3664 loss_seg: 0.2615 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:32:37,346 INFO misc.py line 117 726] Train: [9/20][175/510] Data 2.608 (3.904) Batch 30.969 (28.188) Remain 46:32:56 loss: 0.2505 loss_seg: 0.1551 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:32:59,154 INFO misc.py line 117 726] Train: [9/20][176/510] Data 1.849 (3.892) Batch 21.809 (28.151) Remain 46:28:48 loss: 0.2501 loss_seg: 0.1494 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:33:18,556 INFO misc.py line 117 726] Train: [9/20][177/510] Data 2.132 (3.882) Batch 19.402 (28.101) Remain 46:23:21 loss: 0.2281 loss_seg: 0.1321 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:33:53,882 INFO misc.py line 117 726] Train: [9/20][178/510] Data 3.884 (3.882) Batch 35.326 (28.142) Remain 46:26:59 loss: 0.2226 loss_seg: 0.1349 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0321 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:34:29,118 INFO misc.py line 117 726] Train: [9/20][179/510] Data 6.000 (3.894) Batch 35.236 (28.182) Remain 46:30:30 loss: 0.2281 loss_seg: 0.1387 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:34:54,946 INFO misc.py line 117 726] Train: [9/20][180/510] Data 2.473 (3.886) Batch 25.828 (28.169) Remain 46:28:43 loss: 0.2000 loss_seg: 0.1104 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:35:24,697 INFO misc.py line 117 726] Train: [9/20][181/510] Data 3.693 (3.885) Batch 29.751 (28.178) Remain 46:29:07 loss: 0.2821 loss_seg: 0.1802 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:35:52,682 INFO misc.py line 117 726] Train: [9/20][182/510] Data 6.162 (3.897) Batch 27.986 (28.177) Remain 46:28:33 loss: 0.2415 loss_seg: 0.1480 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:36:23,796 INFO misc.py line 117 726] Train: [9/20][183/510] Data 3.570 (3.895) Batch 31.113 (28.193) Remain 46:29:42 loss: 0.2345 loss_seg: 0.1393 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:36:58,897 INFO misc.py line 117 726] Train: [9/20][184/510] Data 4.264 (3.897) Batch 35.101 (28.231) Remain 46:33:00 loss: 0.3158 loss_seg: 0.2156 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:37:27,165 INFO misc.py line 117 726] Train: [9/20][185/510] Data 2.203 (3.888) Batch 28.269 (28.231) Remain 46:32:33 loss: 0.1968 loss_seg: 0.1121 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:37:59,905 INFO misc.py line 117 726] Train: [9/20][186/510] Data 4.141 (3.890) Batch 32.739 (28.256) Remain 46:34:31 loss: 0.2676 loss_seg: 0.1665 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:38:30,672 INFO misc.py line 117 726] Train: [9/20][187/510] Data 4.447 (3.893) Batch 30.768 (28.270) Remain 46:35:24 loss: 0.2379 loss_seg: 0.1422 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:38:54,700 INFO misc.py line 117 726] Train: [9/20][188/510] Data 2.480 (3.885) Batch 24.028 (28.247) Remain 46:32:39 loss: 0.2540 loss_seg: 0.1586 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:39:22,679 INFO misc.py line 117 726] Train: [9/20][189/510] Data 3.012 (3.880) Batch 27.979 (28.245) Remain 46:32:03 loss: 0.1908 loss_seg: 0.1020 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:39:55,445 INFO misc.py line 117 726] Train: [9/20][190/510] Data 3.912 (3.880) Batch 32.765 (28.269) Remain 46:33:58 loss: 0.3114 loss_seg: 0.2056 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:40:17,652 INFO misc.py line 117 726] Train: [9/20][191/510] Data 3.226 (3.877) Batch 22.207 (28.237) Remain 46:30:18 loss: 0.2154 loss_seg: 0.1253 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:40:41,718 INFO misc.py line 117 726] Train: [9/20][192/510] Data 2.516 (3.870) Batch 24.066 (28.215) Remain 46:27:39 loss: 0.3286 loss_seg: 0.2306 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:41:13,639 INFO misc.py line 117 726] Train: [9/20][193/510] Data 3.485 (3.868) Batch 31.921 (28.235) Remain 46:29:06 loss: 0.2309 loss_seg: 0.1327 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:41:44,933 INFO misc.py line 117 726] Train: [9/20][194/510] Data 3.121 (3.864) Batch 31.294 (28.251) Remain 46:30:13 loss: 0.2394 loss_seg: 0.1441 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:42:14,368 INFO misc.py line 117 726] Train: [9/20][195/510] Data 3.166 (3.860) Batch 29.435 (28.257) Remain 46:30:21 loss: 0.1691 loss_seg: 0.0865 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:42:43,349 INFO misc.py line 117 726] Train: [9/20][196/510] Data 3.960 (3.861) Batch 28.981 (28.261) Remain 46:30:15 loss: 0.2082 loss_seg: 0.1204 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:43:10,634 INFO misc.py line 117 726] Train: [9/20][197/510] Data 4.081 (3.862) Batch 27.285 (28.256) Remain 46:29:17 loss: 0.2138 loss_seg: 0.1212 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:43:41,009 INFO misc.py line 117 726] Train: [9/20][198/510] Data 4.674 (3.866) Batch 30.376 (28.266) Remain 46:29:54 loss: 0.2101 loss_seg: 0.1229 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:44:05,138 INFO misc.py line 117 726] Train: [9/20][199/510] Data 2.600 (3.860) Batch 24.129 (28.245) Remain 46:27:20 loss: 0.2213 loss_seg: 0.1296 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:44:31,764 INFO misc.py line 117 726] Train: [9/20][200/510] Data 3.860 (3.860) Batch 26.626 (28.237) Remain 46:26:03 loss: 0.4247 loss_seg: 0.3267 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:44:31,764 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 01:45:05,620 INFO misc.py line 117 726] Train: [9/20][201/510] Data 4.736 (3.864) Batch 33.857 (28.266) Remain 46:28:23 loss: 0.2239 loss_seg: 0.1307 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:45:17,978 INFO misc.py line 117 726] Train: [9/20][202/510] Data 1.339 (3.851) Batch 12.358 (28.186) Remain 46:20:02 loss: 0.3559 loss_seg: 0.2452 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:45:44,312 INFO misc.py line 117 726] Train: [9/20][203/510] Data 2.713 (3.846) Batch 26.334 (28.176) Remain 46:18:39 loss: 0.2372 loss_seg: 0.1428 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:46:26,137 INFO misc.py line 117 726] Train: [9/20][204/510] Data 12.979 (3.891) Batch 41.824 (28.244) Remain 46:24:52 loss: 0.3413 loss_seg: 0.2406 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:46:54,450 INFO misc.py line 117 726] Train: [9/20][205/510] Data 2.805 (3.886) Batch 28.313 (28.245) Remain 46:24:26 loss: 0.3085 loss_seg: 0.2056 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:47:18,871 INFO misc.py line 117 726] Train: [9/20][206/510] Data 2.896 (3.881) Batch 24.421 (28.226) Remain 46:22:06 loss: 0.2356 loss_seg: 0.1418 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:47:47,333 INFO misc.py line 117 726] Train: [9/20][207/510] Data 4.221 (3.882) Batch 28.462 (28.227) Remain 46:21:45 loss: 0.2650 loss_seg: 0.1755 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:48:11,493 INFO misc.py line 117 726] Train: [9/20][208/510] Data 3.817 (3.882) Batch 24.159 (28.207) Remain 46:19:20 loss: 0.3212 loss_seg: 0.2167 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:48:41,862 INFO misc.py line 117 726] Train: [9/20][209/510] Data 3.190 (3.879) Batch 30.369 (28.218) Remain 46:19:53 loss: 0.2420 loss_seg: 0.1503 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:49:06,717 INFO misc.py line 117 726] Train: [9/20][210/510] Data 2.725 (3.873) Batch 24.856 (28.201) Remain 46:17:49 loss: 0.3156 loss_seg: 0.2068 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:49:39,400 INFO misc.py line 117 726] Train: [9/20][211/510] Data 3.819 (3.873) Batch 32.683 (28.223) Remain 46:19:28 loss: 0.1923 loss_seg: 0.1056 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:50:10,303 INFO misc.py line 117 726] Train: [9/20][212/510] Data 3.417 (3.871) Batch 30.903 (28.236) Remain 46:20:16 loss: 0.2413 loss_seg: 0.1436 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:50:40,184 INFO misc.py line 117 726] Train: [9/20][213/510] Data 4.045 (3.872) Batch 29.881 (28.243) Remain 46:20:34 loss: 0.2191 loss_seg: 0.1293 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:51:01,685 INFO misc.py line 117 726] Train: [9/20][214/510] Data 2.280 (3.864) Batch 21.502 (28.212) Remain 46:16:57 loss: 0.2235 loss_seg: 0.1298 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:51:33,572 INFO misc.py line 117 726] Train: [9/20][215/510] Data 3.047 (3.860) Batch 31.887 (28.229) Remain 46:18:11 loss: 0.1796 loss_seg: 0.0987 loss_superpoint_edge: 0.0133 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:52:08,526 INFO misc.py line 117 726] Train: [9/20][216/510] Data 3.763 (3.860) Batch 34.954 (28.260) Remain 46:20:49 loss: 0.3902 loss_seg: 0.2865 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:52:32,386 INFO misc.py line 117 726] Train: [9/20][217/510] Data 2.436 (3.853) Batch 23.860 (28.240) Remain 46:18:20 loss: 0.1977 loss_seg: 0.1087 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:52:56,047 INFO misc.py line 117 726] Train: [9/20][218/510] Data 4.315 (3.855) Batch 23.662 (28.219) Remain 46:15:46 loss: 0.1970 loss_seg: 0.1085 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:53:19,461 INFO misc.py line 117 726] Train: [9/20][219/510] Data 2.707 (3.850) Batch 23.414 (28.196) Remain 46:13:06 loss: 0.2339 loss_seg: 0.1419 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:53:47,771 INFO misc.py line 117 726] Train: [9/20][220/510] Data 2.563 (3.844) Batch 28.309 (28.197) Remain 46:12:41 loss: 0.2282 loss_seg: 0.1375 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:54:22,555 INFO misc.py line 117 726] Train: [9/20][221/510] Data 3.710 (3.843) Batch 34.784 (28.227) Remain 46:15:11 loss: 0.2834 loss_seg: 0.1811 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:54:40,892 INFO misc.py line 117 726] Train: [9/20][222/510] Data 2.161 (3.836) Batch 18.337 (28.182) Remain 46:10:17 loss: 0.3378 loss_seg: 0.2373 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:55:09,675 INFO misc.py line 117 726] Train: [9/20][223/510] Data 3.497 (3.834) Batch 28.784 (28.185) Remain 46:10:04 loss: 0.2925 loss_seg: 0.2026 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:55:41,594 INFO misc.py line 117 726] Train: [9/20][224/510] Data 4.308 (3.836) Batch 31.918 (28.202) Remain 46:11:16 loss: 0.2694 loss_seg: 0.1688 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:56:10,067 INFO misc.py line 117 726] Train: [9/20][225/510] Data 3.693 (3.836) Batch 28.473 (28.203) Remain 46:10:55 loss: 0.2185 loss_seg: 0.1252 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:56:38,484 INFO misc.py line 117 726] Train: [9/20][226/510] Data 3.445 (3.834) Batch 28.418 (28.204) Remain 46:10:32 loss: 0.2386 loss_seg: 0.1434 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:57:03,252 INFO misc.py line 117 726] Train: [9/20][227/510] Data 2.898 (3.830) Batch 24.768 (28.188) Remain 46:08:34 loss: 0.2764 loss_seg: 0.1695 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:57:37,430 INFO misc.py line 117 726] Train: [9/20][228/510] Data 3.026 (3.826) Batch 34.177 (28.215) Remain 46:10:42 loss: 0.2159 loss_seg: 0.1279 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:58:10,900 INFO misc.py line 117 726] Train: [9/20][229/510] Data 5.163 (3.832) Batch 33.470 (28.238) Remain 46:12:31 loss: 0.2570 loss_seg: 0.1585 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:58:39,121 INFO misc.py line 117 726] Train: [9/20][230/510] Data 3.487 (3.831) Batch 28.221 (28.238) Remain 46:12:03 loss: 0.2318 loss_seg: 0.1331 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:58:57,119 INFO misc.py line 117 726] Train: [9/20][231/510] Data 2.250 (3.824) Batch 17.998 (28.193) Remain 46:07:10 loss: 0.1982 loss_seg: 0.1064 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:59:25,943 INFO misc.py line 117 726] Train: [9/20][232/510] Data 2.808 (3.819) Batch 28.824 (28.196) Remain 46:06:58 loss: 0.2483 loss_seg: 0.1508 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 01:59:55,303 INFO misc.py line 117 726] Train: [9/20][233/510] Data 4.636 (3.823) Batch 29.359 (28.201) Remain 46:06:59 loss: 0.2014 loss_seg: 0.1160 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:00:18,309 INFO misc.py line 117 726] Train: [9/20][234/510] Data 2.583 (3.817) Batch 23.007 (28.179) Remain 46:04:19 loss: 0.1994 loss_seg: 0.1125 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:00:53,837 INFO misc.py line 117 726] Train: [9/20][235/510] Data 7.030 (3.831) Batch 35.528 (28.210) Remain 46:06:57 loss: 0.3217 loss_seg: 0.2150 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:01:24,541 INFO misc.py line 117 726] Train: [9/20][236/510] Data 3.284 (3.829) Batch 30.703 (28.221) Remain 46:07:32 loss: 0.2747 loss_seg: 0.1747 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:01:58,088 INFO misc.py line 117 726] Train: [9/20][237/510] Data 4.079 (3.830) Batch 33.547 (28.244) Remain 46:09:18 loss: 0.3990 loss_seg: 0.2989 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:02:34,697 INFO misc.py line 117 726] Train: [9/20][238/510] Data 5.429 (3.837) Batch 36.610 (28.279) Remain 46:12:19 loss: 0.2380 loss_seg: 0.1420 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:03:00,260 INFO misc.py line 117 726] Train: [9/20][239/510] Data 2.909 (3.833) Batch 25.563 (28.268) Remain 46:10:43 loss: 0.2194 loss_seg: 0.1276 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:03:34,777 INFO misc.py line 117 726] Train: [9/20][240/510] Data 7.978 (3.850) Batch 34.517 (28.294) Remain 46:12:49 loss: 0.2263 loss_seg: 0.1389 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:04:12,016 INFO misc.py line 117 726] Train: [9/20][241/510] Data 6.699 (3.862) Batch 37.239 (28.332) Remain 46:16:02 loss: 0.2197 loss_seg: 0.1321 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:04:32,905 INFO misc.py line 117 726] Train: [9/20][242/510] Data 2.294 (3.856) Batch 20.889 (28.301) Remain 46:12:31 loss: 0.2957 loss_seg: 0.1960 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:04:59,765 INFO misc.py line 117 726] Train: [9/20][243/510] Data 2.952 (3.852) Batch 26.860 (28.295) Remain 46:11:27 loss: 0.2227 loss_seg: 0.1308 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:05:27,297 INFO misc.py line 117 726] Train: [9/20][244/510] Data 3.379 (3.850) Batch 27.532 (28.291) Remain 46:10:40 loss: 0.2547 loss_seg: 0.1625 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:05:59,374 INFO misc.py line 117 726] Train: [9/20][245/510] Data 6.688 (3.862) Batch 32.077 (28.307) Remain 46:11:44 loss: 0.4003 loss_seg: 0.2904 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:06:33,114 INFO misc.py line 117 726] Train: [9/20][246/510] Data 6.708 (3.873) Batch 33.741 (28.329) Remain 46:13:27 loss: 0.2166 loss_seg: 0.1267 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:07:03,853 INFO misc.py line 117 726] Train: [9/20][247/510] Data 3.301 (3.871) Batch 30.739 (28.339) Remain 46:13:57 loss: 0.2256 loss_seg: 0.1312 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:07:36,727 INFO misc.py line 117 726] Train: [9/20][248/510] Data 4.551 (3.874) Batch 32.874 (28.358) Remain 46:15:17 loss: 0.2501 loss_seg: 0.1495 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:08:15,745 INFO misc.py line 117 726] Train: [9/20][249/510] Data 6.963 (3.886) Batch 39.018 (28.401) Remain 46:19:03 loss: 0.2361 loss_seg: 0.1441 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:08:47,773 INFO misc.py line 117 726] Train: [9/20][250/510] Data 3.735 (3.886) Batch 32.028 (28.416) Remain 46:20:01 loss: 0.2319 loss_seg: 0.1389 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:08:47,774 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 02:09:12,737 INFO misc.py line 117 726] Train: [9/20][251/510] Data 2.901 (3.882) Batch 24.964 (28.402) Remain 46:18:11 loss: 0.1876 loss_seg: 0.1042 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:09:40,108 INFO misc.py line 117 726] Train: [9/20][252/510] Data 2.964 (3.878) Batch 27.371 (28.398) Remain 46:17:18 loss: 0.2100 loss_seg: 0.1186 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:10:03,141 INFO misc.py line 117 726] Train: [9/20][253/510] Data 2.356 (3.872) Batch 23.033 (28.376) Remain 46:14:44 loss: 0.2540 loss_seg: 0.1592 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:10:27,329 INFO misc.py line 117 726] Train: [9/20][254/510] Data 2.374 (3.866) Batch 24.189 (28.360) Remain 46:12:37 loss: 0.2663 loss_seg: 0.1690 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:10:54,053 INFO misc.py line 117 726] Train: [9/20][255/510] Data 3.580 (3.865) Batch 26.724 (28.353) Remain 46:11:31 loss: 0.2728 loss_seg: 0.1738 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:11:17,261 INFO misc.py line 117 726] Train: [9/20][256/510] Data 3.962 (3.865) Batch 23.207 (28.333) Remain 46:09:03 loss: 0.2254 loss_seg: 0.1348 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:11:44,535 INFO misc.py line 117 726] Train: [9/20][257/510] Data 3.674 (3.865) Batch 27.274 (28.329) Remain 46:08:11 loss: 0.2721 loss_seg: 0.1729 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:12:14,720 INFO misc.py line 117 726] Train: [9/20][258/510] Data 3.310 (3.862) Batch 30.185 (28.336) Remain 46:08:25 loss: 0.1999 loss_seg: 0.1093 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:12:39,436 INFO misc.py line 117 726] Train: [9/20][259/510] Data 2.865 (3.858) Batch 24.716 (28.322) Remain 46:06:34 loss: 0.2883 loss_seg: 0.1932 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:13:02,358 INFO misc.py line 117 726] Train: [9/20][260/510] Data 2.642 (3.854) Batch 22.922 (28.301) Remain 46:04:02 loss: 0.2200 loss_seg: 0.1292 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:13:33,397 INFO misc.py line 117 726] Train: [9/20][261/510] Data 3.726 (3.853) Batch 31.039 (28.311) Remain 46:04:36 loss: 0.2969 loss_seg: 0.1959 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:13:54,047 INFO misc.py line 117 726] Train: [9/20][262/510] Data 2.471 (3.848) Batch 20.650 (28.282) Remain 46:01:15 loss: 0.2592 loss_seg: 0.1593 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:14:22,863 INFO misc.py line 117 726] Train: [9/20][263/510] Data 2.919 (3.844) Batch 28.816 (28.284) Remain 46:00:58 loss: 0.2519 loss_seg: 0.1550 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:14:50,727 INFO misc.py line 117 726] Train: [9/20][264/510] Data 3.234 (3.842) Batch 27.864 (28.282) Remain 46:00:21 loss: 0.3256 loss_seg: 0.2258 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:15:20,628 INFO misc.py line 117 726] Train: [9/20][265/510] Data 2.743 (3.838) Batch 29.902 (28.288) Remain 46:00:29 loss: 0.2256 loss_seg: 0.1322 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:15:42,568 INFO misc.py line 117 726] Train: [9/20][266/510] Data 2.704 (3.833) Batch 21.939 (28.264) Remain 45:57:39 loss: 0.1883 loss_seg: 0.0980 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:16:03,005 INFO misc.py line 117 726] Train: [9/20][267/510] Data 1.695 (3.825) Batch 20.437 (28.235) Remain 45:54:17 loss: 0.1734 loss_seg: 0.0902 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:16:30,007 INFO misc.py line 117 726] Train: [9/20][268/510] Data 3.277 (3.823) Batch 27.000 (28.230) Remain 45:53:22 loss: 0.2415 loss_seg: 0.1520 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:16:55,707 INFO misc.py line 117 726] Train: [9/20][269/510] Data 3.130 (3.821) Batch 25.702 (28.221) Remain 45:51:58 loss: 0.2356 loss_seg: 0.1457 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:17:22,084 INFO misc.py line 117 726] Train: [9/20][270/510] Data 2.491 (3.816) Batch 26.376 (28.214) Remain 45:50:49 loss: 0.2598 loss_seg: 0.1650 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:17:54,118 INFO misc.py line 117 726] Train: [9/20][271/510] Data 3.452 (3.814) Batch 32.034 (28.228) Remain 45:51:44 loss: 0.3063 loss_seg: 0.2007 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:18:12,953 INFO misc.py line 117 726] Train: [9/20][272/510] Data 2.358 (3.809) Batch 18.835 (28.193) Remain 45:47:52 loss: 0.2578 loss_seg: 0.1610 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:18:38,926 INFO misc.py line 117 726] Train: [9/20][273/510] Data 3.381 (3.807) Batch 25.973 (28.185) Remain 45:46:36 loss: 0.2677 loss_seg: 0.1668 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:19:07,464 INFO misc.py line 117 726] Train: [9/20][274/510] Data 2.627 (3.803) Batch 28.538 (28.186) Remain 45:46:15 loss: 0.2272 loss_seg: 0.1365 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:19:25,133 INFO misc.py line 117 726] Train: [9/20][275/510] Data 2.515 (3.798) Batch 17.669 (28.147) Remain 45:42:01 loss: 0.3211 loss_seg: 0.2127 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:19:53,855 INFO misc.py line 117 726] Train: [9/20][276/510] Data 5.411 (3.804) Batch 28.722 (28.149) Remain 45:41:45 loss: 0.1874 loss_seg: 0.1029 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:20:19,804 INFO misc.py line 117 726] Train: [9/20][277/510] Data 6.926 (3.816) Batch 25.948 (28.141) Remain 45:40:30 loss: 0.2450 loss_seg: 0.1444 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0436 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:20:46,321 INFO misc.py line 117 726] Train: [9/20][278/510] Data 3.229 (3.813) Batch 26.518 (28.136) Remain 45:39:27 loss: 0.2220 loss_seg: 0.1275 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:21:25,125 INFO misc.py line 117 726] Train: [9/20][279/510] Data 6.930 (3.825) Batch 38.804 (28.174) Remain 45:42:45 loss: 0.3001 loss_seg: 0.1997 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:21:51,490 INFO misc.py line 117 726] Train: [9/20][280/510] Data 2.571 (3.820) Batch 26.365 (28.168) Remain 45:41:39 loss: 0.3106 loss_seg: 0.2102 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:22:22,441 INFO misc.py line 117 726] Train: [9/20][281/510] Data 3.159 (3.818) Batch 30.951 (28.178) Remain 45:42:09 loss: 0.3168 loss_seg: 0.2033 loss_superpoint_edge: 0.0432 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:22:55,135 INFO misc.py line 117 726] Train: [9/20][282/510] Data 3.287 (3.816) Batch 32.694 (28.194) Remain 45:43:15 loss: 0.2341 loss_seg: 0.1432 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:23:27,944 INFO misc.py line 117 726] Train: [9/20][283/510] Data 3.364 (3.814) Batch 32.809 (28.210) Remain 45:44:23 loss: 0.2498 loss_seg: 0.1545 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:24:03,645 INFO misc.py line 117 726] Train: [9/20][284/510] Data 3.903 (3.815) Batch 35.701 (28.237) Remain 45:46:31 loss: 0.1910 loss_seg: 0.1015 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:24:40,057 INFO misc.py line 117 726] Train: [9/20][285/510] Data 5.152 (3.819) Batch 36.412 (28.266) Remain 45:48:52 loss: 0.2168 loss_seg: 0.1262 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:25:11,248 INFO misc.py line 117 726] Train: [9/20][286/510] Data 4.780 (3.823) Batch 31.191 (28.276) Remain 45:49:24 loss: 0.1801 loss_seg: 0.0957 loss_superpoint_edge: 0.0148 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:25:35,260 INFO misc.py line 117 726] Train: [9/20][287/510] Data 4.055 (3.824) Batch 24.012 (28.261) Remain 45:47:28 loss: 0.1971 loss_seg: 0.1116 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:26:04,854 INFO misc.py line 117 726] Train: [9/20][288/510] Data 3.272 (3.822) Batch 29.594 (28.266) Remain 45:47:27 loss: 0.2549 loss_seg: 0.1560 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:26:30,771 INFO misc.py line 117 726] Train: [9/20][289/510] Data 1.997 (3.815) Batch 25.917 (28.258) Remain 45:46:11 loss: 0.2496 loss_seg: 0.1478 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:27:01,330 INFO misc.py line 117 726] Train: [9/20][290/510] Data 4.294 (3.817) Batch 30.559 (28.266) Remain 45:46:29 loss: 0.2886 loss_seg: 0.1943 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:27:31,919 INFO misc.py line 117 726] Train: [9/20][291/510] Data 5.037 (3.821) Batch 30.589 (28.274) Remain 45:46:48 loss: 0.3539 loss_seg: 0.2501 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:28:03,453 INFO misc.py line 117 726] Train: [9/20][292/510] Data 8.943 (3.839) Batch 31.534 (28.285) Remain 45:47:25 loss: 0.1758 loss_seg: 0.0924 loss_superpoint_edge: 0.0147 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:28:29,585 INFO misc.py line 117 726] Train: [9/20][293/510] Data 2.342 (3.834) Batch 26.131 (28.278) Remain 45:46:14 loss: 0.2719 loss_seg: 0.1703 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:28:55,841 INFO misc.py line 117 726] Train: [9/20][294/510] Data 3.752 (3.833) Batch 26.257 (28.271) Remain 45:45:05 loss: 0.2526 loss_seg: 0.1546 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:29:16,595 INFO misc.py line 117 726] Train: [9/20][295/510] Data 1.990 (3.827) Batch 20.754 (28.245) Remain 45:42:07 loss: 0.2616 loss_seg: 0.1606 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:29:42,303 INFO misc.py line 117 726] Train: [9/20][296/510] Data 2.965 (3.824) Batch 25.708 (28.236) Remain 45:40:48 loss: 0.1894 loss_seg: 0.1043 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:30:10,026 INFO misc.py line 117 726] Train: [9/20][297/510] Data 2.711 (3.820) Batch 27.723 (28.235) Remain 45:40:10 loss: 0.2368 loss_seg: 0.1361 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:30:41,788 INFO misc.py line 117 726] Train: [9/20][298/510] Data 4.823 (3.824) Batch 31.762 (28.247) Remain 45:40:51 loss: 0.2415 loss_seg: 0.1429 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:31:15,702 INFO misc.py line 117 726] Train: [9/20][299/510] Data 4.586 (3.826) Batch 33.914 (28.266) Remain 45:42:14 loss: 0.2943 loss_seg: 0.1951 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:31:51,597 INFO misc.py line 117 726] Train: [9/20][300/510] Data 5.135 (3.831) Batch 35.895 (28.291) Remain 45:44:15 loss: 0.2454 loss_seg: 0.1512 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:31:51,598 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 02:32:22,447 INFO misc.py line 117 726] Train: [9/20][301/510] Data 3.713 (3.830) Batch 30.850 (28.300) Remain 45:44:37 loss: 0.2011 loss_seg: 0.1081 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:32:57,079 INFO misc.py line 117 726] Train: [9/20][302/510] Data 4.950 (3.834) Batch 34.632 (28.321) Remain 45:46:12 loss: 0.2135 loss_seg: 0.1263 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:33:26,163 INFO misc.py line 117 726] Train: [9/20][303/510] Data 3.258 (3.832) Batch 29.084 (28.324) Remain 45:45:59 loss: 0.2733 loss_seg: 0.1740 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:33:51,388 INFO misc.py line 117 726] Train: [9/20][304/510] Data 2.320 (3.827) Batch 25.225 (28.313) Remain 45:44:30 loss: 0.2890 loss_seg: 0.1930 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:34:12,359 INFO misc.py line 117 726] Train: [9/20][305/510] Data 2.392 (3.822) Batch 20.971 (28.289) Remain 45:41:41 loss: 0.3140 loss_seg: 0.2223 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:34:36,404 INFO misc.py line 117 726] Train: [9/20][306/510] Data 2.483 (3.818) Batch 24.045 (28.275) Remain 45:39:51 loss: 0.1980 loss_seg: 0.1108 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:35:03,111 INFO misc.py line 117 726] Train: [9/20][307/510] Data 3.209 (3.816) Batch 26.707 (28.270) Remain 45:38:53 loss: 0.2414 loss_seg: 0.1432 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:35:33,060 INFO misc.py line 117 726] Train: [9/20][308/510] Data 3.157 (3.814) Batch 29.948 (28.275) Remain 45:38:56 loss: 0.2147 loss_seg: 0.1216 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:36:01,033 INFO misc.py line 117 726] Train: [9/20][309/510] Data 3.765 (3.814) Batch 27.973 (28.274) Remain 45:38:22 loss: 0.2952 loss_seg: 0.1934 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:36:35,271 INFO misc.py line 117 726] Train: [9/20][310/510] Data 4.852 (3.817) Batch 34.238 (28.294) Remain 45:39:47 loss: 0.2212 loss_seg: 0.1314 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:37:08,209 INFO misc.py line 117 726] Train: [9/20][311/510] Data 3.334 (3.816) Batch 32.938 (28.309) Remain 45:40:46 loss: 0.1879 loss_seg: 0.1014 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:37:39,410 INFO misc.py line 117 726] Train: [9/20][312/510] Data 3.374 (3.814) Batch 31.201 (28.318) Remain 45:41:12 loss: 0.2622 loss_seg: 0.1617 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:38:13,465 INFO misc.py line 117 726] Train: [9/20][313/510] Data 4.428 (3.816) Batch 34.055 (28.337) Remain 45:42:31 loss: 0.1925 loss_seg: 0.1062 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:38:40,520 INFO misc.py line 117 726] Train: [9/20][314/510] Data 3.811 (3.816) Batch 27.055 (28.333) Remain 45:41:39 loss: 0.2272 loss_seg: 0.1352 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:39:02,626 INFO misc.py line 117 726] Train: [9/20][315/510] Data 2.166 (3.811) Batch 22.106 (28.313) Remain 45:39:15 loss: 0.2933 loss_seg: 0.1873 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:39:32,719 INFO misc.py line 117 726] Train: [9/20][316/510] Data 4.273 (3.812) Batch 30.092 (28.318) Remain 45:39:20 loss: 0.2932 loss_seg: 0.1882 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:39:57,908 INFO misc.py line 117 726] Train: [9/20][317/510] Data 2.658 (3.809) Batch 25.189 (28.308) Remain 45:37:54 loss: 0.2399 loss_seg: 0.1437 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:40:30,037 INFO misc.py line 117 726] Train: [9/20][318/510] Data 5.346 (3.813) Batch 32.129 (28.321) Remain 45:38:36 loss: 0.2892 loss_seg: 0.1888 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:40:50,124 INFO misc.py line 117 726] Train: [9/20][319/510] Data 2.313 (3.809) Batch 20.087 (28.295) Remain 45:35:36 loss: 0.2453 loss_seg: 0.1480 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:41:08,319 INFO misc.py line 117 726] Train: [9/20][320/510] Data 2.480 (3.805) Batch 18.195 (28.263) Remain 45:32:03 loss: 0.2099 loss_seg: 0.1214 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:41:33,308 INFO misc.py line 117 726] Train: [9/20][321/510] Data 3.183 (3.803) Batch 24.989 (28.252) Remain 45:30:35 loss: 0.2776 loss_seg: 0.1753 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:41:45,429 INFO misc.py line 117 726] Train: [9/20][322/510] Data 1.573 (3.796) Batch 12.120 (28.202) Remain 45:25:14 loss: 0.2469 loss_seg: 0.1533 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:42:12,684 INFO misc.py line 117 726] Train: [9/20][323/510] Data 3.727 (3.795) Batch 27.256 (28.199) Remain 45:24:28 loss: 0.1851 loss_seg: 0.0975 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:42:43,840 INFO misc.py line 117 726] Train: [9/20][324/510] Data 5.786 (3.802) Batch 31.156 (28.208) Remain 45:24:53 loss: 0.2738 loss_seg: 0.1704 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:43:07,015 INFO misc.py line 117 726] Train: [9/20][325/510] Data 3.112 (3.799) Batch 23.175 (28.192) Remain 45:22:55 loss: 0.2560 loss_seg: 0.1593 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:43:26,408 INFO misc.py line 117 726] Train: [9/20][326/510] Data 2.956 (3.797) Batch 19.393 (28.165) Remain 45:19:49 loss: 0.2319 loss_seg: 0.1325 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0438 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:43:55,845 INFO misc.py line 117 726] Train: [9/20][327/510] Data 2.914 (3.794) Batch 29.437 (28.169) Remain 45:19:43 loss: 0.2688 loss_seg: 0.1719 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:44:23,691 INFO misc.py line 117 726] Train: [9/20][328/510] Data 3.540 (3.793) Batch 27.846 (28.168) Remain 45:19:09 loss: 0.1915 loss_seg: 0.1019 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:44:44,814 INFO misc.py line 117 726] Train: [9/20][329/510] Data 2.848 (3.790) Batch 21.123 (28.147) Remain 45:16:36 loss: 0.2031 loss_seg: 0.1137 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:45:20,290 INFO misc.py line 117 726] Train: [9/20][330/510] Data 3.877 (3.791) Batch 35.476 (28.169) Remain 45:18:18 loss: 0.2236 loss_seg: 0.1303 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:45:57,714 INFO misc.py line 117 726] Train: [9/20][331/510] Data 6.264 (3.798) Batch 37.424 (28.197) Remain 45:20:33 loss: 0.2908 loss_seg: 0.1875 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:46:34,237 INFO misc.py line 117 726] Train: [9/20][332/510] Data 6.267 (3.806) Batch 36.523 (28.222) Remain 45:22:31 loss: 0.2851 loss_seg: 0.1834 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:47:00,712 INFO misc.py line 117 726] Train: [9/20][333/510] Data 2.370 (3.801) Batch 26.474 (28.217) Remain 45:21:32 loss: 0.2036 loss_seg: 0.1149 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:47:26,558 INFO misc.py line 117 726] Train: [9/20][334/510] Data 3.456 (3.800) Batch 25.847 (28.210) Remain 45:20:23 loss: 0.1927 loss_seg: 0.1049 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:47:55,446 INFO misc.py line 117 726] Train: [9/20][335/510] Data 4.986 (3.804) Batch 28.888 (28.212) Remain 45:20:06 loss: 0.2202 loss_seg: 0.1251 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:48:27,375 INFO misc.py line 117 726] Train: [9/20][336/510] Data 2.490 (3.800) Batch 31.929 (28.223) Remain 45:20:42 loss: 0.2386 loss_seg: 0.1412 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:48:58,960 INFO misc.py line 117 726] Train: [9/20][337/510] Data 5.397 (3.805) Batch 31.585 (28.233) Remain 45:21:12 loss: 0.4969 loss_seg: 0.3829 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:49:10,712 INFO misc.py line 117 726] Train: [9/20][338/510] Data 1.596 (3.798) Batch 11.752 (28.184) Remain 45:16:00 loss: 0.2427 loss_seg: 0.1468 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:49:43,727 INFO misc.py line 117 726] Train: [9/20][339/510] Data 7.724 (3.810) Batch 33.016 (28.198) Remain 45:16:55 loss: 0.2114 loss_seg: 0.1214 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:50:16,845 INFO misc.py line 117 726] Train: [9/20][340/510] Data 4.569 (3.812) Batch 33.118 (28.213) Remain 45:17:51 loss: 0.2765 loss_seg: 0.1762 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:50:46,345 INFO misc.py line 117 726] Train: [9/20][341/510] Data 3.588 (3.811) Batch 29.500 (28.217) Remain 45:17:45 loss: 0.2118 loss_seg: 0.1220 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:51:03,111 INFO misc.py line 117 726] Train: [9/20][342/510] Data 2.384 (3.807) Batch 16.766 (28.183) Remain 45:14:01 loss: 0.3084 loss_seg: 0.2026 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:51:25,712 INFO misc.py line 117 726] Train: [9/20][343/510] Data 2.773 (3.804) Batch 22.601 (28.167) Remain 45:11:58 loss: 0.2416 loss_seg: 0.1508 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:51:51,201 INFO misc.py line 117 726] Train: [9/20][344/510] Data 2.996 (3.802) Batch 25.490 (28.159) Remain 45:10:45 loss: 0.2223 loss_seg: 0.1254 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:52:11,272 INFO misc.py line 117 726] Train: [9/20][345/510] Data 2.471 (3.798) Batch 20.070 (28.135) Remain 45:08:00 loss: 0.2392 loss_seg: 0.1466 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:52:42,253 INFO misc.py line 117 726] Train: [9/20][346/510] Data 3.695 (3.798) Batch 30.981 (28.143) Remain 45:08:20 loss: 0.2029 loss_seg: 0.1140 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:53:06,131 INFO misc.py line 117 726] Train: [9/20][347/510] Data 3.168 (3.796) Batch 23.879 (28.131) Remain 45:06:40 loss: 0.2581 loss_seg: 0.1645 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:53:41,278 INFO misc.py line 117 726] Train: [9/20][348/510] Data 4.290 (3.797) Batch 35.147 (28.151) Remain 45:08:09 loss: 0.2759 loss_seg: 0.1814 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:54:12,319 INFO misc.py line 117 726] Train: [9/20][349/510] Data 2.736 (3.794) Batch 31.040 (28.160) Remain 45:08:29 loss: 0.2256 loss_seg: 0.1298 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:54:40,988 INFO misc.py line 117 726] Train: [9/20][350/510] Data 4.818 (3.797) Batch 28.669 (28.161) Remain 45:08:10 loss: 0.2195 loss_seg: 0.1291 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:54:40,989 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 02:55:07,441 INFO misc.py line 117 726] Train: [9/20][351/510] Data 4.871 (3.800) Batch 26.453 (28.156) Remain 45:07:13 loss: 0.2392 loss_seg: 0.1457 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:55:27,322 INFO misc.py line 117 726] Train: [9/20][352/510] Data 2.624 (3.797) Batch 19.881 (28.133) Remain 45:04:28 loss: 0.2850 loss_seg: 0.1894 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:55:59,498 INFO misc.py line 117 726] Train: [9/20][353/510] Data 4.081 (3.798) Batch 32.176 (28.144) Remain 45:05:07 loss: 0.2638 loss_seg: 0.1786 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:56:32,306 INFO misc.py line 117 726] Train: [9/20][354/510] Data 2.977 (3.795) Batch 32.807 (28.157) Remain 45:05:55 loss: 0.2526 loss_seg: 0.1594 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:57:07,911 INFO misc.py line 117 726] Train: [9/20][355/510] Data 10.590 (3.815) Batch 35.605 (28.179) Remain 45:07:29 loss: 0.2789 loss_seg: 0.1769 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:57:37,833 INFO misc.py line 117 726] Train: [9/20][356/510] Data 4.386 (3.816) Batch 29.922 (28.184) Remain 45:07:29 loss: 0.2959 loss_seg: 0.1933 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:58:10,741 INFO misc.py line 117 726] Train: [9/20][357/510] Data 4.851 (3.819) Batch 32.908 (28.197) Remain 45:08:18 loss: 0.2862 loss_seg: 0.1899 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:58:42,093 INFO misc.py line 117 726] Train: [9/20][358/510] Data 4.203 (3.820) Batch 31.353 (28.206) Remain 45:08:41 loss: 0.2049 loss_seg: 0.1162 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:59:12,497 INFO misc.py line 117 726] Train: [9/20][359/510] Data 3.400 (3.819) Batch 30.403 (28.212) Remain 45:08:48 loss: 0.2814 loss_seg: 0.1767 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 02:59:41,971 INFO misc.py line 117 726] Train: [9/20][360/510] Data 3.472 (3.818) Batch 29.474 (28.215) Remain 45:08:41 loss: 0.2535 loss_seg: 0.1632 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:00:08,987 INFO misc.py line 117 726] Train: [9/20][361/510] Data 4.063 (3.819) Batch 27.016 (28.212) Remain 45:07:53 loss: 0.2681 loss_seg: 0.1688 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:00:40,356 INFO misc.py line 117 726] Train: [9/20][362/510] Data 7.084 (3.828) Batch 31.369 (28.221) Remain 45:08:15 loss: 0.2228 loss_seg: 0.1343 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:01:06,977 INFO misc.py line 117 726] Train: [9/20][363/510] Data 2.834 (3.825) Batch 26.621 (28.216) Remain 45:07:22 loss: 0.2692 loss_seg: 0.1683 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:01:29,655 INFO misc.py line 117 726] Train: [9/20][364/510] Data 2.304 (3.821) Batch 22.678 (28.201) Remain 45:05:25 loss: 0.2063 loss_seg: 0.1179 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:01:54,572 INFO misc.py line 117 726] Train: [9/20][365/510] Data 2.830 (3.818) Batch 24.917 (28.192) Remain 45:04:05 loss: 0.2186 loss_seg: 0.1265 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:02:22,155 INFO misc.py line 117 726] Train: [9/20][366/510] Data 2.635 (3.815) Batch 27.583 (28.190) Remain 45:03:27 loss: 0.2782 loss_seg: 0.1745 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:03:01,044 INFO misc.py line 117 726] Train: [9/20][367/510] Data 8.762 (3.828) Batch 38.889 (28.220) Remain 45:05:48 loss: 0.2129 loss_seg: 0.1251 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:03:36,318 INFO misc.py line 117 726] Train: [9/20][368/510] Data 4.055 (3.829) Batch 35.274 (28.239) Remain 45:07:11 loss: 0.2482 loss_seg: 0.1552 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:04:02,635 INFO misc.py line 117 726] Train: [9/20][369/510] Data 3.469 (3.828) Batch 26.316 (28.234) Remain 45:06:12 loss: 0.2506 loss_seg: 0.1555 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:04:26,981 INFO misc.py line 117 726] Train: [9/20][370/510] Data 2.691 (3.825) Batch 24.346 (28.223) Remain 45:04:43 loss: 0.2637 loss_seg: 0.1665 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:04:49,810 INFO misc.py line 117 726] Train: [9/20][371/510] Data 2.199 (3.821) Batch 22.829 (28.209) Remain 45:02:51 loss: 0.2373 loss_seg: 0.1418 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:05:16,135 INFO misc.py line 117 726] Train: [9/20][372/510] Data 3.735 (3.820) Batch 26.325 (28.203) Remain 45:01:53 loss: 0.2141 loss_seg: 0.1258 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:05:48,239 INFO misc.py line 117 726] Train: [9/20][373/510] Data 3.203 (3.819) Batch 32.104 (28.214) Remain 45:02:26 loss: 0.2430 loss_seg: 0.1469 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:06:23,569 INFO misc.py line 117 726] Train: [9/20][374/510] Data 4.917 (3.822) Batch 35.330 (28.233) Remain 45:03:48 loss: 0.2319 loss_seg: 0.1383 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:06:55,298 INFO misc.py line 117 726] Train: [9/20][375/510] Data 5.764 (3.827) Batch 31.729 (28.243) Remain 45:04:13 loss: 0.2568 loss_seg: 0.1636 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:07:21,367 INFO misc.py line 117 726] Train: [9/20][376/510] Data 2.908 (3.824) Batch 26.069 (28.237) Remain 45:03:12 loss: 0.1862 loss_seg: 0.0965 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:07:47,895 INFO misc.py line 117 726] Train: [9/20][377/510] Data 3.304 (3.823) Batch 26.527 (28.232) Remain 45:02:17 loss: 0.2104 loss_seg: 0.1204 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:08:14,223 INFO misc.py line 117 726] Train: [9/20][378/510] Data 2.783 (3.820) Batch 26.329 (28.227) Remain 45:01:20 loss: 0.2078 loss_seg: 0.1191 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:08:37,889 INFO misc.py line 117 726] Train: [9/20][379/510] Data 2.536 (3.817) Batch 23.665 (28.215) Remain 44:59:42 loss: 0.1964 loss_seg: 0.1094 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:09:12,664 INFO misc.py line 117 726] Train: [9/20][380/510] Data 6.282 (3.823) Batch 34.775 (28.232) Remain 45:00:53 loss: 0.2625 loss_seg: 0.1698 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:09:42,031 INFO misc.py line 117 726] Train: [9/20][381/510] Data 3.293 (3.822) Batch 29.368 (28.235) Remain 45:00:42 loss: 0.2554 loss_seg: 0.1594 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:10:06,043 INFO misc.py line 117 726] Train: [9/20][382/510] Data 2.638 (3.819) Batch 24.011 (28.224) Remain 44:59:10 loss: 0.2460 loss_seg: 0.1465 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:10:41,982 INFO misc.py line 117 726] Train: [9/20][383/510] Data 5.122 (3.822) Batch 35.940 (28.245) Remain 45:00:39 loss: 0.2011 loss_seg: 0.1135 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:11:12,143 INFO misc.py line 117 726] Train: [9/20][384/510] Data 3.086 (3.820) Batch 30.161 (28.250) Remain 45:00:39 loss: 0.2007 loss_seg: 0.1091 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:11:42,073 INFO misc.py line 117 726] Train: [9/20][385/510] Data 4.969 (3.823) Batch 29.929 (28.254) Remain 45:00:36 loss: 0.2880 loss_seg: 0.1900 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:12:12,424 INFO misc.py line 117 726] Train: [9/20][386/510] Data 3.460 (3.822) Batch 30.352 (28.259) Remain 45:00:39 loss: 0.1968 loss_seg: 0.1109 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:12:32,280 INFO misc.py line 117 726] Train: [9/20][387/510] Data 2.303 (3.818) Batch 19.856 (28.238) Remain 44:58:06 loss: 0.2112 loss_seg: 0.1229 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:12:56,739 INFO misc.py line 117 726] Train: [9/20][388/510] Data 2.442 (3.815) Batch 24.459 (28.228) Remain 44:56:41 loss: 0.2883 loss_seg: 0.1895 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:13:16,520 INFO misc.py line 117 726] Train: [9/20][389/510] Data 2.300 (3.811) Batch 19.781 (28.206) Remain 44:54:07 loss: 0.2161 loss_seg: 0.1287 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:13:47,962 INFO misc.py line 117 726] Train: [9/20][390/510] Data 3.402 (3.810) Batch 31.441 (28.214) Remain 44:54:27 loss: 0.2489 loss_seg: 0.1536 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:14:17,196 INFO misc.py line 117 726] Train: [9/20][391/510] Data 5.127 (3.813) Batch 29.234 (28.217) Remain 44:54:14 loss: 0.2218 loss_seg: 0.1311 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:14:40,055 INFO misc.py line 117 726] Train: [9/20][392/510] Data 2.707 (3.810) Batch 22.859 (28.203) Remain 44:52:27 loss: 0.2386 loss_seg: 0.1401 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:15:04,209 INFO misc.py line 117 726] Train: [9/20][393/510] Data 2.336 (3.807) Batch 24.155 (28.193) Remain 44:50:59 loss: 0.2833 loss_seg: 0.1824 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:15:24,813 INFO misc.py line 117 726] Train: [9/20][394/510] Data 2.041 (3.802) Batch 20.603 (28.173) Remain 44:48:40 loss: 0.3348 loss_seg: 0.2163 loss_superpoint_edge: 0.0490 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:16:04,994 INFO misc.py line 117 726] Train: [9/20][395/510] Data 7.342 (3.811) Batch 40.182 (28.204) Remain 44:51:07 loss: 0.4265 loss_seg: 0.3183 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:16:39,313 INFO misc.py line 117 726] Train: [9/20][396/510] Data 6.471 (3.818) Batch 34.319 (28.220) Remain 44:52:08 loss: 0.2416 loss_seg: 0.1494 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:17:07,241 INFO misc.py line 117 726] Train: [9/20][397/510] Data 7.408 (3.827) Batch 27.928 (28.219) Remain 44:51:35 loss: 0.2672 loss_seg: 0.1678 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:17:39,628 INFO misc.py line 117 726] Train: [9/20][398/510] Data 3.512 (3.826) Batch 32.387 (28.229) Remain 44:52:08 loss: 0.2444 loss_seg: 0.1474 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:18:02,386 INFO misc.py line 117 726] Train: [9/20][399/510] Data 2.652 (3.823) Batch 22.758 (28.215) Remain 44:50:20 loss: 0.1822 loss_seg: 0.0981 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:18:38,813 INFO misc.py line 117 726] Train: [9/20][400/510] Data 4.920 (3.826) Batch 36.426 (28.236) Remain 44:51:50 loss: 0.2273 loss_seg: 0.1382 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:18:38,813 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 03:18:59,006 INFO misc.py line 117 726] Train: [9/20][401/510] Data 2.403 (3.822) Batch 20.193 (28.216) Remain 44:49:27 loss: 0.1815 loss_seg: 0.0955 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:19:23,090 INFO misc.py line 117 726] Train: [9/20][402/510] Data 2.834 (3.820) Batch 24.084 (28.206) Remain 44:47:59 loss: 0.2069 loss_seg: 0.1145 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:19:44,427 INFO misc.py line 117 726] Train: [9/20][403/510] Data 2.524 (3.817) Batch 21.337 (28.188) Remain 44:45:53 loss: 0.2767 loss_seg: 0.1819 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:20:13,937 INFO misc.py line 117 726] Train: [9/20][404/510] Data 3.231 (3.815) Batch 29.509 (28.192) Remain 44:45:43 loss: 0.2212 loss_seg: 0.1288 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:20:44,958 INFO misc.py line 117 726] Train: [9/20][405/510] Data 4.770 (3.818) Batch 31.021 (28.199) Remain 44:45:56 loss: 0.2002 loss_seg: 0.1152 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:21:13,407 INFO misc.py line 117 726] Train: [9/20][406/510] Data 2.809 (3.815) Batch 28.449 (28.199) Remain 44:45:31 loss: 0.2162 loss_seg: 0.1276 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:21:35,573 INFO misc.py line 117 726] Train: [9/20][407/510] Data 2.794 (3.813) Batch 22.167 (28.184) Remain 44:43:37 loss: 0.2895 loss_seg: 0.1922 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:22:09,016 INFO misc.py line 117 726] Train: [9/20][408/510] Data 3.406 (3.812) Batch 33.443 (28.197) Remain 44:44:23 loss: 0.2242 loss_seg: 0.1343 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:22:36,692 INFO misc.py line 117 726] Train: [9/20][409/510] Data 5.731 (3.816) Batch 27.676 (28.196) Remain 44:43:48 loss: 0.2711 loss_seg: 0.1716 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:23:04,662 INFO misc.py line 117 726] Train: [9/20][410/510] Data 2.848 (3.814) Batch 27.970 (28.196) Remain 44:43:16 loss: 0.2290 loss_seg: 0.1348 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:23:31,119 INFO misc.py line 117 726] Train: [9/20][411/510] Data 3.066 (3.812) Batch 26.457 (28.191) Remain 44:42:24 loss: 0.2694 loss_seg: 0.1719 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:23:50,953 INFO misc.py line 117 726] Train: [9/20][412/510] Data 1.780 (3.807) Batch 19.834 (28.171) Remain 44:39:59 loss: 0.1954 loss_seg: 0.1073 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:24:13,825 INFO misc.py line 117 726] Train: [9/20][413/510] Data 2.877 (3.805) Batch 22.872 (28.158) Remain 44:38:17 loss: 0.3382 loss_seg: 0.2318 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:24:48,767 INFO misc.py line 117 726] Train: [9/20][414/510] Data 5.683 (3.809) Batch 34.941 (28.174) Remain 44:39:23 loss: 0.2684 loss_seg: 0.1688 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:25:16,747 INFO misc.py line 117 726] Train: [9/20][415/510] Data 6.786 (3.817) Batch 27.980 (28.174) Remain 44:38:52 loss: 0.2603 loss_seg: 0.1606 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:25:48,800 INFO misc.py line 117 726] Train: [9/20][416/510] Data 4.862 (3.819) Batch 32.053 (28.183) Remain 44:39:18 loss: 0.2465 loss_seg: 0.1538 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:26:24,436 INFO misc.py line 117 726] Train: [9/20][417/510] Data 10.526 (3.835) Batch 35.636 (28.201) Remain 44:40:32 loss: 0.2154 loss_seg: 0.1269 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:26:48,692 INFO misc.py line 117 726] Train: [9/20][418/510] Data 4.762 (3.838) Batch 24.257 (28.192) Remain 44:39:10 loss: 0.2998 loss_seg: 0.1945 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:27:11,971 INFO misc.py line 117 726] Train: [9/20][419/510] Data 2.116 (3.833) Batch 23.279 (28.180) Remain 44:37:34 loss: 0.2120 loss_seg: 0.1210 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:27:46,583 INFO misc.py line 117 726] Train: [9/20][420/510] Data 3.715 (3.833) Batch 34.612 (28.196) Remain 44:38:34 loss: 0.2389 loss_seg: 0.1434 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:28:14,272 INFO misc.py line 117 726] Train: [9/20][421/510] Data 3.148 (3.832) Batch 27.689 (28.194) Remain 44:37:59 loss: 0.2167 loss_seg: 0.1234 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:28:38,219 INFO misc.py line 117 726] Train: [9/20][422/510] Data 3.210 (3.830) Batch 23.947 (28.184) Remain 44:36:33 loss: 0.6382 loss_seg: 0.5036 loss_superpoint_edge: 0.0656 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:29:04,960 INFO misc.py line 117 726] Train: [9/20][423/510] Data 2.562 (3.827) Batch 26.741 (28.181) Remain 44:35:45 loss: 0.2488 loss_seg: 0.1519 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:29:26,930 INFO misc.py line 117 726] Train: [9/20][424/510] Data 2.420 (3.824) Batch 21.971 (28.166) Remain 44:33:53 loss: 0.1964 loss_seg: 0.1091 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:30:07,244 INFO misc.py line 117 726] Train: [9/20][425/510] Data 7.153 (3.832) Batch 40.313 (28.195) Remain 44:36:09 loss: 0.1928 loss_seg: 0.1055 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:30:37,002 INFO misc.py line 117 726] Train: [9/20][426/510] Data 4.135 (3.832) Batch 29.758 (28.198) Remain 44:36:02 loss: 0.2872 loss_seg: 0.1853 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:30:56,862 INFO misc.py line 117 726] Train: [9/20][427/510] Data 2.462 (3.829) Batch 19.861 (28.179) Remain 44:33:41 loss: 0.2028 loss_seg: 0.1131 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:31:17,790 INFO misc.py line 117 726] Train: [9/20][428/510] Data 2.048 (3.825) Batch 20.928 (28.162) Remain 44:31:36 loss: 0.2880 loss_seg: 0.1884 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:31:52,410 INFO misc.py line 117 726] Train: [9/20][429/510] Data 3.275 (3.824) Batch 34.619 (28.177) Remain 44:32:34 loss: 0.1964 loss_seg: 0.1112 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:32:24,114 INFO misc.py line 117 726] Train: [9/20][430/510] Data 4.267 (3.825) Batch 31.705 (28.185) Remain 44:32:53 loss: 0.1884 loss_seg: 0.1027 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:32:59,983 INFO misc.py line 117 726] Train: [9/20][431/510] Data 4.141 (3.825) Batch 35.868 (28.203) Remain 44:34:07 loss: 0.2186 loss_seg: 0.1245 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:33:28,076 INFO misc.py line 117 726] Train: [9/20][432/510] Data 2.847 (3.823) Batch 28.094 (28.203) Remain 44:33:37 loss: 0.2182 loss_seg: 0.1290 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:33:57,645 INFO misc.py line 117 726] Train: [9/20][433/510] Data 2.990 (3.821) Batch 29.569 (28.206) Remain 44:33:27 loss: 0.2340 loss_seg: 0.1378 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:34:17,977 INFO misc.py line 117 726] Train: [9/20][434/510] Data 2.076 (3.817) Batch 20.332 (28.188) Remain 44:31:15 loss: 0.2501 loss_seg: 0.1524 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:34:51,655 INFO misc.py line 117 726] Train: [9/20][435/510] Data 4.647 (3.819) Batch 33.677 (28.200) Remain 44:31:59 loss: 0.2764 loss_seg: 0.1726 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:35:27,664 INFO misc.py line 117 726] Train: [9/20][436/510] Data 4.558 (3.821) Batch 36.009 (28.219) Remain 44:33:14 loss: 0.3256 loss_seg: 0.2246 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:35:56,548 INFO misc.py line 117 726] Train: [9/20][437/510] Data 2.990 (3.819) Batch 28.884 (28.220) Remain 44:32:54 loss: 0.2567 loss_seg: 0.1570 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:36:29,753 INFO misc.py line 117 726] Train: [9/20][438/510] Data 3.473 (3.818) Batch 33.205 (28.232) Remain 44:33:31 loss: 0.2706 loss_seg: 0.1670 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:37:07,381 INFO misc.py line 117 726] Train: [9/20][439/510] Data 7.808 (3.827) Batch 37.628 (28.253) Remain 44:35:05 loss: 0.2896 loss_seg: 0.1987 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:37:35,375 INFO misc.py line 117 726] Train: [9/20][440/510] Data 2.745 (3.825) Batch 27.994 (28.252) Remain 44:34:33 loss: 0.2531 loss_seg: 0.1534 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:38:14,231 INFO misc.py line 117 726] Train: [9/20][441/510] Data 6.493 (3.831) Batch 38.856 (28.277) Remain 44:36:23 loss: 0.2354 loss_seg: 0.1512 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:38:44,407 INFO misc.py line 117 726] Train: [9/20][442/510] Data 3.723 (3.831) Batch 30.176 (28.281) Remain 44:36:19 loss: 0.3333 loss_seg: 0.2415 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:39:22,319 INFO misc.py line 117 726] Train: [9/20][443/510] Data 9.010 (3.842) Batch 37.912 (28.303) Remain 44:37:55 loss: 0.3857 loss_seg: 0.2753 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:39:51,245 INFO misc.py line 117 726] Train: [9/20][444/510] Data 7.576 (3.851) Batch 28.926 (28.304) Remain 44:37:35 loss: 0.2670 loss_seg: 0.1728 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:40:30,787 INFO misc.py line 117 726] Train: [9/20][445/510] Data 10.486 (3.866) Batch 39.543 (28.330) Remain 44:39:31 loss: 0.2973 loss_seg: 0.2028 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:40:59,559 INFO misc.py line 117 726] Train: [9/20][446/510] Data 4.835 (3.868) Batch 28.771 (28.331) Remain 44:39:08 loss: 0.2973 loss_seg: 0.1898 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:41:14,756 INFO misc.py line 117 726] Train: [9/20][447/510] Data 2.416 (3.865) Batch 15.197 (28.301) Remain 44:35:52 loss: 0.4926 loss_seg: 0.3762 loss_superpoint_edge: 0.0415 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:41:40,826 INFO misc.py line 117 726] Train: [9/20][448/510] Data 3.312 (3.863) Batch 26.070 (28.296) Remain 44:34:55 loss: 0.2654 loss_seg: 0.1638 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:42:10,468 INFO misc.py line 117 726] Train: [9/20][449/510] Data 3.166 (3.862) Batch 29.643 (28.299) Remain 44:34:44 loss: 0.2457 loss_seg: 0.1522 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:42:42,588 INFO misc.py line 117 726] Train: [9/20][450/510] Data 4.873 (3.864) Batch 32.120 (28.308) Remain 44:35:04 loss: 0.3374 loss_seg: 0.2404 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:42:42,589 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 03:43:06,927 INFO misc.py line 117 726] Train: [9/20][451/510] Data 3.366 (3.863) Batch 24.339 (28.299) Remain 44:33:46 loss: 0.2364 loss_seg: 0.1380 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:43:31,211 INFO misc.py line 117 726] Train: [9/20][452/510] Data 2.084 (3.859) Batch 24.284 (28.290) Remain 44:32:27 loss: 0.2383 loss_seg: 0.1470 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:43:58,238 INFO misc.py line 117 726] Train: [9/20][453/510] Data 2.726 (3.857) Batch 27.026 (28.287) Remain 44:31:42 loss: 0.2978 loss_seg: 0.1945 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:44:30,873 INFO misc.py line 117 726] Train: [9/20][454/510] Data 3.706 (3.856) Batch 32.635 (28.297) Remain 44:32:09 loss: 0.2360 loss_seg: 0.1421 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:45:04,166 INFO misc.py line 117 726] Train: [9/20][455/510] Data 4.212 (3.857) Batch 33.293 (28.308) Remain 44:32:43 loss: 0.2718 loss_seg: 0.1697 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:45:36,473 INFO misc.py line 117 726] Train: [9/20][456/510] Data 5.615 (3.861) Batch 32.308 (28.317) Remain 44:33:05 loss: 0.2324 loss_seg: 0.1446 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:46:10,166 INFO misc.py line 117 726] Train: [9/20][457/510] Data 4.992 (3.863) Batch 33.692 (28.328) Remain 44:33:44 loss: 0.2228 loss_seg: 0.1373 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:46:35,034 INFO misc.py line 117 726] Train: [9/20][458/510] Data 3.123 (3.862) Batch 24.868 (28.321) Remain 44:32:32 loss: 0.2246 loss_seg: 0.1356 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:47:08,983 INFO misc.py line 117 726] Train: [9/20][459/510] Data 4.025 (3.862) Batch 33.949 (28.333) Remain 44:33:14 loss: 0.1871 loss_seg: 0.1006 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:47:43,608 INFO misc.py line 117 726] Train: [9/20][460/510] Data 3.965 (3.862) Batch 34.625 (28.347) Remain 44:34:03 loss: 0.2321 loss_seg: 0.1390 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:48:03,285 INFO misc.py line 117 726] Train: [9/20][461/510] Data 2.068 (3.858) Batch 19.676 (28.328) Remain 44:31:48 loss: 0.2902 loss_seg: 0.1984 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:48:27,761 INFO misc.py line 117 726] Train: [9/20][462/510] Data 2.753 (3.856) Batch 24.476 (28.320) Remain 44:30:32 loss: 0.2170 loss_seg: 0.1290 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:48:54,214 INFO misc.py line 117 726] Train: [9/20][463/510] Data 3.458 (3.855) Batch 26.454 (28.316) Remain 44:29:41 loss: 0.1945 loss_seg: 0.1078 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:49:17,572 INFO misc.py line 117 726] Train: [9/20][464/510] Data 2.778 (3.853) Batch 23.358 (28.305) Remain 44:28:12 loss: 0.2875 loss_seg: 0.1763 loss_superpoint_edge: 0.0449 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:49:44,847 INFO misc.py line 117 726] Train: [9/20][465/510] Data 3.037 (3.851) Batch 27.275 (28.303) Remain 44:27:31 loss: 0.3214 loss_seg: 0.2243 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:50:13,214 INFO misc.py line 117 726] Train: [9/20][466/510] Data 3.615 (3.851) Batch 28.367 (28.303) Remain 44:27:03 loss: 0.2628 loss_seg: 0.1724 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:50:42,823 INFO misc.py line 117 726] Train: [9/20][467/510] Data 4.651 (3.852) Batch 29.608 (28.306) Remain 44:26:51 loss: 0.4998 loss_seg: 0.3743 loss_superpoint_edge: 0.0589 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:51:15,466 INFO misc.py line 117 726] Train: [9/20][468/510] Data 2.988 (3.850) Batch 32.644 (28.315) Remain 44:27:15 loss: 0.2366 loss_seg: 0.1454 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:51:40,839 INFO misc.py line 117 726] Train: [9/20][469/510] Data 2.778 (3.848) Batch 25.373 (28.309) Remain 44:26:11 loss: 0.2393 loss_seg: 0.1426 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:52:13,065 INFO misc.py line 117 726] Train: [9/20][470/510] Data 7.404 (3.856) Batch 32.226 (28.317) Remain 44:26:30 loss: 0.2205 loss_seg: 0.1290 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:52:42,077 INFO misc.py line 117 726] Train: [9/20][471/510] Data 2.632 (3.853) Batch 29.012 (28.318) Remain 44:26:10 loss: 0.2112 loss_seg: 0.1198 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:53:09,838 INFO misc.py line 117 726] Train: [9/20][472/510] Data 2.784 (3.851) Batch 27.761 (28.317) Remain 44:25:35 loss: 0.2208 loss_seg: 0.1269 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:53:40,429 INFO misc.py line 117 726] Train: [9/20][473/510] Data 3.523 (3.850) Batch 30.591 (28.322) Remain 44:25:34 loss: 0.2620 loss_seg: 0.1633 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:54:07,099 INFO misc.py line 117 726] Train: [9/20][474/510] Data 3.596 (3.850) Batch 26.670 (28.319) Remain 44:24:46 loss: 0.2661 loss_seg: 0.1696 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:54:43,498 INFO misc.py line 117 726] Train: [9/20][475/510] Data 8.774 (3.860) Batch 36.399 (28.336) Remain 44:25:55 loss: 0.2265 loss_seg: 0.1330 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:55:12,430 INFO misc.py line 117 726] Train: [9/20][476/510] Data 3.833 (3.860) Batch 28.931 (28.337) Remain 44:25:33 loss: 0.2449 loss_seg: 0.1528 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:55:41,772 INFO misc.py line 117 726] Train: [9/20][477/510] Data 3.715 (3.860) Batch 29.342 (28.339) Remain 44:25:17 loss: 0.2267 loss_seg: 0.1308 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:56:06,771 INFO misc.py line 117 726] Train: [9/20][478/510] Data 3.890 (3.860) Batch 24.999 (28.332) Remain 44:24:09 loss: 0.3152 loss_seg: 0.2249 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:56:31,164 INFO misc.py line 117 726] Train: [9/20][479/510] Data 2.260 (3.856) Batch 24.393 (28.324) Remain 44:22:54 loss: 0.1842 loss_seg: 0.1021 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:57:06,109 INFO misc.py line 117 726] Train: [9/20][480/510] Data 4.437 (3.858) Batch 34.945 (28.338) Remain 44:23:44 loss: 0.2625 loss_seg: 0.1724 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:57:29,639 INFO misc.py line 117 726] Train: [9/20][481/510] Data 2.526 (3.855) Batch 23.530 (28.328) Remain 44:22:19 loss: 0.2722 loss_seg: 0.1679 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:58:06,409 INFO misc.py line 117 726] Train: [9/20][482/510] Data 5.604 (3.858) Batch 36.770 (28.345) Remain 44:23:30 loss: 0.2374 loss_seg: 0.1402 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:58:26,798 INFO misc.py line 117 726] Train: [9/20][483/510] Data 1.718 (3.854) Batch 20.389 (28.329) Remain 44:21:28 loss: 0.2839 loss_seg: 0.1785 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:58:54,436 INFO misc.py line 117 726] Train: [9/20][484/510] Data 3.122 (3.853) Batch 27.638 (28.327) Remain 44:20:52 loss: 0.2105 loss_seg: 0.1181 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:59:26,142 INFO misc.py line 117 726] Train: [9/20][485/510] Data 3.723 (3.852) Batch 31.705 (28.334) Remain 44:21:03 loss: 0.2480 loss_seg: 0.1497 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 03:59:56,110 INFO misc.py line 117 726] Train: [9/20][486/510] Data 4.052 (3.853) Batch 29.968 (28.338) Remain 44:20:54 loss: 0.2598 loss_seg: 0.1631 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:00:11,587 INFO misc.py line 117 726] Train: [9/20][487/510] Data 1.830 (3.848) Batch 15.477 (28.311) Remain 44:17:56 loss: 0.3228 loss_seg: 0.2108 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:00:28,968 INFO misc.py line 117 726] Train: [9/20][488/510] Data 2.538 (3.846) Batch 17.380 (28.288) Remain 44:15:20 loss: 0.3378 loss_seg: 0.2361 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:00:59,001 INFO misc.py line 117 726] Train: [9/20][489/510] Data 3.285 (3.845) Batch 30.034 (28.292) Remain 44:15:12 loss: 0.3052 loss_seg: 0.1993 loss_superpoint_edge: 0.0421 loss_superpoint_contrast: 0.0319 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:01:27,976 INFO misc.py line 117 726] Train: [9/20][490/510] Data 3.336 (3.844) Batch 28.974 (28.293) Remain 44:14:52 loss: 0.2224 loss_seg: 0.1310 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:02:04,339 INFO misc.py line 117 726] Train: [9/20][491/510] Data 3.696 (3.843) Batch 36.364 (28.310) Remain 44:15:57 loss: 0.2292 loss_seg: 0.1334 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:02:29,721 INFO misc.py line 117 726] Train: [9/20][492/510] Data 3.599 (3.843) Batch 25.381 (28.304) Remain 44:14:55 loss: 0.2975 loss_seg: 0.2062 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:03:00,617 INFO misc.py line 117 726] Train: [9/20][493/510] Data 2.522 (3.840) Batch 30.896 (28.309) Remain 44:14:56 loss: 0.2721 loss_seg: 0.1796 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:03:35,824 INFO misc.py line 117 726] Train: [9/20][494/510] Data 4.175 (3.841) Batch 35.207 (28.323) Remain 44:15:47 loss: 0.2098 loss_seg: 0.1196 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:03:52,191 INFO misc.py line 117 726] Train: [9/20][495/510] Data 2.014 (3.837) Batch 16.367 (28.299) Remain 44:13:02 loss: 0.2883 loss_seg: 0.1958 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:04:26,088 INFO misc.py line 117 726] Train: [9/20][496/510] Data 6.020 (3.841) Batch 33.898 (28.310) Remain 44:13:37 loss: 0.2243 loss_seg: 0.1295 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:04:59,111 INFO misc.py line 117 726] Train: [9/20][497/510] Data 6.078 (3.846) Batch 33.023 (28.320) Remain 44:14:03 loss: 0.2189 loss_seg: 0.1288 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:05:22,695 INFO misc.py line 117 726] Train: [9/20][498/510] Data 2.755 (3.844) Batch 23.583 (28.310) Remain 44:12:41 loss: 0.3203 loss_seg: 0.2095 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:05:44,098 INFO misc.py line 117 726] Train: [9/20][499/510] Data 2.652 (3.841) Batch 21.404 (28.296) Remain 44:10:54 loss: 0.2923 loss_seg: 0.1942 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:06:09,337 INFO misc.py line 117 726] Train: [9/20][500/510] Data 2.846 (3.839) Batch 25.239 (28.290) Remain 44:09:51 loss: 0.2660 loss_seg: 0.1639 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:06:09,340 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 04:06:37,264 INFO misc.py line 117 726] Train: [9/20][501/510] Data 4.142 (3.840) Batch 27.927 (28.290) Remain 44:09:19 loss: 0.3035 loss_seg: 0.1972 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:07:03,502 INFO misc.py line 117 726] Train: [9/20][502/510] Data 3.187 (3.839) Batch 26.238 (28.285) Remain 44:08:27 loss: 0.2155 loss_seg: 0.1253 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:07:25,101 INFO misc.py line 117 726] Train: [9/20][503/510] Data 2.328 (3.836) Batch 21.599 (28.272) Remain 44:06:44 loss: 0.2854 loss_seg: 0.1822 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:07:53,076 INFO misc.py line 117 726] Train: [9/20][504/510] Data 3.356 (3.835) Batch 27.975 (28.272) Remain 44:06:12 loss: 0.2396 loss_seg: 0.1484 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:08:22,093 INFO misc.py line 117 726] Train: [9/20][505/510] Data 3.337 (3.834) Batch 29.017 (28.273) Remain 44:05:52 loss: 0.3223 loss_seg: 0.2119 loss_superpoint_edge: 0.0434 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:08:44,332 INFO misc.py line 117 726] Train: [9/20][506/510] Data 3.172 (3.832) Batch 22.239 (28.261) Remain 44:04:17 loss: 0.2544 loss_seg: 0.1596 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:09:01,759 INFO misc.py line 117 726] Train: [9/20][507/510] Data 1.710 (3.828) Batch 17.426 (28.240) Remain 44:01:48 loss: 0.2138 loss_seg: 0.1246 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:09:28,232 INFO misc.py line 117 726] Train: [9/20][508/510] Data 2.520 (3.826) Batch 26.474 (28.236) Remain 44:01:00 loss: 0.2518 loss_seg: 0.1531 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:09:53,608 INFO misc.py line 117 726] Train: [9/20][509/510] Data 2.400 (3.823) Batch 25.376 (28.230) Remain 44:00:00 loss: 0.2563 loss_seg: 0.1571 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:10:12,788 INFO misc.py line 117 726] Train: [9/20][510/510] Data 2.167 (3.820) Batch 19.180 (28.213) Remain 43:57:52 loss: 0.2381 loss_seg: 0.1399 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:10:12,790 INFO misc.py line 147 726] Train result: loss: 0.2534 loss_seg: 0.1578 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-11 04:10:12,790 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-11 04:10:28,487 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7008 [2026-06-11 04:10:44,792 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7075 [2026-06-11 04:12:00,458 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9340 [2026-06-11 04:12:41,330 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0497 [2026-06-11 04:13:00,926 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0235 [2026-06-11 04:13:37,103 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.0123 [2026-06-11 04:14:24,160 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1117 [2026-06-11 04:14:39,880 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2527 [2026-06-11 04:14:57,907 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9968 [2026-06-11 04:15:16,802 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3683 [2026-06-11 04:15:32,644 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4734 [2026-06-11 04:15:54,248 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.8069 [2026-06-11 04:16:20,177 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8246 [2026-06-11 04:16:31,668 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6467 [2026-06-11 04:17:03,212 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 0.9945 [2026-06-11 04:17:29,371 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3895 [2026-06-11 04:17:56,285 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.1953 [2026-06-11 04:18:39,474 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.0594 [2026-06-11 04:19:00,613 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4295 [2026-06-11 04:19:17,237 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8105 [2026-06-11 04:19:48,582 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.7963 [2026-06-11 04:20:04,889 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.3977 [2026-06-11 04:20:27,016 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2365 [2026-06-11 04:20:49,152 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.7836 [2026-06-11 04:21:02,935 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6455 [2026-06-11 04:21:30,949 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5322 [2026-06-11 04:22:12,767 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 1.8582 [2026-06-11 04:22:30,183 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5284 [2026-06-11 04:22:49,169 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.5260 [2026-06-11 04:23:06,134 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4578 [2026-06-11 04:23:31,548 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1677 [2026-06-11 04:23:50,024 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6379 [2026-06-11 04:24:07,783 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1028 [2026-06-11 04:24:32,460 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7242 [2026-06-11 04:24:32,477 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6659/0.7422/0.8950. [2026-06-11 04:24:32,477 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9223/0.9549 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9755/0.9880 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8361/0.9684 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0022/0.0160 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3561/0.4351 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.5884/0.6107 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5894/0.6749 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7912/0.8948 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9088/0.9521 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6570/0.7252 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7663/0.8515 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6677/0.8727 [2026-06-11 04:24:32,478 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5964/0.7050 [2026-06-11 04:24:32,478 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-11 04:24:32,479 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-11 04:24:32,479 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 04:25:00,096 INFO misc.py line 117 726] Train: [10/20][1/510] Data 3.145 (3.145) Batch 26.051 (26.051) Remain 40:35:18 loss: 0.2988 loss_seg: 0.1958 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:25:28,208 INFO misc.py line 117 726] Train: [10/20][2/510] Data 3.136 (3.136) Batch 28.112 (28.112) Remain 43:47:33 loss: 0.2663 loss_seg: 0.1670 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:25:56,057 INFO misc.py line 117 726] Train: [10/20][3/510] Data 5.734 (5.734) Batch 27.849 (27.849) Remain 43:22:31 loss: 0.2543 loss_seg: 0.1607 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:26:27,986 INFO misc.py line 117 726] Train: [10/20][4/510] Data 3.760 (3.760) Batch 31.929 (31.929) Remain 49:43:14 loss: 0.2511 loss_seg: 0.1527 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:26:54,441 INFO misc.py line 117 726] Train: [10/20][5/510] Data 2.840 (3.300) Batch 26.454 (29.192) Remain 45:26:59 loss: 0.2276 loss_seg: 0.1291 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:27:22,831 INFO misc.py line 117 726] Train: [10/20][6/510] Data 2.610 (3.070) Batch 28.390 (28.925) Remain 45:01:33 loss: 0.3990 loss_seg: 0.2812 loss_superpoint_edge: 0.0499 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:27:51,111 INFO misc.py line 117 726] Train: [10/20][7/510] Data 3.697 (3.227) Batch 28.280 (28.763) Remain 44:46:01 loss: 0.2579 loss_seg: 0.1572 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:28:27,670 INFO misc.py line 117 726] Train: [10/20][8/510] Data 5.414 (3.664) Batch 36.559 (30.323) Remain 47:11:06 loss: 0.2820 loss_seg: 0.1781 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:28:48,905 INFO misc.py line 117 726] Train: [10/20][9/510] Data 2.547 (3.478) Batch 21.235 (28.808) Remain 44:49:13 loss: 0.2165 loss_seg: 0.1230 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:29:25,142 INFO misc.py line 117 726] Train: [10/20][10/510] Data 5.249 (3.731) Batch 36.236 (29.869) Remain 46:27:47 loss: 0.2696 loss_seg: 0.1740 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:29:46,125 INFO misc.py line 117 726] Train: [10/20][11/510] Data 6.478 (4.075) Batch 20.983 (28.758) Remain 44:43:38 loss: 0.2362 loss_seg: 0.1354 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0466 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:30:11,597 INFO misc.py line 117 726] Train: [10/20][12/510] Data 3.254 (3.983) Batch 25.472 (28.393) Remain 44:09:05 loss: 0.2093 loss_seg: 0.1184 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:30:36,671 INFO misc.py line 117 726] Train: [10/20][13/510] Data 3.630 (3.948) Batch 25.075 (28.061) Remain 43:37:39 loss: 0.2669 loss_seg: 0.1668 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:31:02,719 INFO misc.py line 117 726] Train: [10/20][14/510] Data 3.674 (3.923) Batch 26.048 (27.878) Remain 43:20:07 loss: 0.2586 loss_seg: 0.1617 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:31:29,818 INFO misc.py line 117 726] Train: [10/20][15/510] Data 3.217 (3.864) Batch 27.099 (27.813) Remain 43:13:36 loss: 0.2334 loss_seg: 0.1417 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:31:54,265 INFO misc.py line 117 726] Train: [10/20][16/510] Data 3.071 (3.803) Batch 24.446 (27.554) Remain 42:48:59 loss: 0.2316 loss_seg: 0.1391 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:32:20,662 INFO misc.py line 117 726] Train: [10/20][17/510] Data 4.653 (3.864) Batch 26.397 (27.472) Remain 42:40:49 loss: 0.3256 loss_seg: 0.2218 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:32:55,599 INFO misc.py line 117 726] Train: [10/20][18/510] Data 4.287 (3.892) Batch 34.937 (27.969) Remain 43:26:44 loss: 0.2268 loss_seg: 0.1336 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:33:24,667 INFO misc.py line 117 726] Train: [10/20][19/510] Data 7.207 (4.099) Batch 29.068 (28.038) Remain 43:32:40 loss: 0.2061 loss_seg: 0.1098 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:33:45,674 INFO misc.py line 117 726] Train: [10/20][20/510] Data 2.998 (4.034) Batch 21.007 (27.624) Remain 42:53:40 loss: 0.3355 loss_seg: 0.2179 loss_superpoint_edge: 0.0496 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:34:12,656 INFO misc.py line 117 726] Train: [10/20][21/510] Data 3.474 (4.003) Batch 26.982 (27.589) Remain 42:49:53 loss: 0.1799 loss_seg: 0.0935 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:34:40,139 INFO misc.py line 117 726] Train: [10/20][22/510] Data 2.847 (3.942) Batch 27.483 (27.583) Remain 42:48:55 loss: 0.2149 loss_seg: 0.1215 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:35:10,567 INFO misc.py line 117 726] Train: [10/20][23/510] Data 3.546 (3.923) Batch 30.428 (27.725) Remain 43:01:42 loss: 0.2462 loss_seg: 0.1485 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:35:29,875 INFO misc.py line 117 726] Train: [10/20][24/510] Data 2.106 (3.836) Batch 19.308 (27.325) Remain 42:23:55 loss: 0.3637 loss_seg: 0.2573 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:35:55,954 INFO misc.py line 117 726] Train: [10/20][25/510] Data 4.336 (3.859) Batch 26.079 (27.268) Remain 42:18:11 loss: 0.2403 loss_seg: 0.1465 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:36:25,562 INFO misc.py line 117 726] Train: [10/20][26/510] Data 4.632 (3.892) Batch 29.609 (27.370) Remain 42:27:12 loss: 0.2514 loss_seg: 0.1544 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:36:57,523 INFO misc.py line 117 726] Train: [10/20][27/510] Data 7.525 (4.044) Batch 31.960 (27.561) Remain 42:44:33 loss: 0.2804 loss_seg: 0.1612 loss_superpoint_edge: 0.0454 loss_superpoint_contrast: 0.0430 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:37:31,964 INFO misc.py line 117 726] Train: [10/20][28/510] Data 5.646 (4.108) Batch 34.441 (27.836) Remain 43:09:42 loss: 0.2180 loss_seg: 0.1263 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:38:07,057 INFO misc.py line 117 726] Train: [10/20][29/510] Data 5.066 (4.145) Batch 35.093 (28.115) Remain 43:35:11 loss: 0.2474 loss_seg: 0.1492 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:38:48,254 INFO misc.py line 117 726] Train: [10/20][30/510] Data 9.366 (4.338) Batch 41.198 (28.600) Remain 44:19:47 loss: 0.2081 loss_seg: 0.1184 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:39:17,733 INFO misc.py line 117 726] Train: [10/20][31/510] Data 3.347 (4.303) Batch 29.479 (28.631) Remain 44:22:13 loss: 0.2848 loss_seg: 0.1832 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:39:46,554 INFO misc.py line 117 726] Train: [10/20][32/510] Data 3.037 (4.259) Batch 28.821 (28.638) Remain 44:22:21 loss: 0.2253 loss_seg: 0.1332 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:40:18,093 INFO misc.py line 117 726] Train: [10/20][33/510] Data 6.244 (4.325) Batch 31.539 (28.734) Remain 44:30:52 loss: 0.2026 loss_seg: 0.1114 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:40:34,123 INFO misc.py line 117 726] Train: [10/20][34/510] Data 2.206 (4.257) Batch 16.031 (28.325) Remain 43:52:18 loss: 0.2809 loss_seg: 0.1894 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:41:06,806 INFO misc.py line 117 726] Train: [10/20][35/510] Data 5.020 (4.281) Batch 32.683 (28.461) Remain 44:04:29 loss: 0.2567 loss_seg: 0.1602 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:41:28,447 INFO misc.py line 117 726] Train: [10/20][36/510] Data 3.176 (4.247) Batch 21.641 (28.254) Remain 43:44:49 loss: 0.2434 loss_seg: 0.1496 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:41:51,812 INFO misc.py line 117 726] Train: [10/20][37/510] Data 2.689 (4.201) Batch 23.365 (28.110) Remain 43:30:59 loss: 0.2407 loss_seg: 0.1452 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:42:14,316 INFO misc.py line 117 726] Train: [10/20][38/510] Data 2.095 (4.141) Batch 22.505 (27.950) Remain 43:15:38 loss: 0.2339 loss_seg: 0.1397 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:42:49,363 INFO misc.py line 117 726] Train: [10/20][39/510] Data 4.008 (4.138) Batch 35.047 (28.147) Remain 43:33:29 loss: 0.2804 loss_seg: 0.1802 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:43:12,361 INFO misc.py line 117 726] Train: [10/20][40/510] Data 2.823 (4.102) Batch 22.998 (28.008) Remain 43:20:05 loss: 0.2522 loss_seg: 0.1540 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:43:46,268 INFO misc.py line 117 726] Train: [10/20][41/510] Data 9.340 (4.240) Batch 33.907 (28.163) Remain 43:34:02 loss: 0.2821 loss_seg: 0.1771 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:44:10,839 INFO misc.py line 117 726] Train: [10/20][42/510] Data 4.024 (4.234) Batch 24.571 (28.071) Remain 43:25:01 loss: 0.2117 loss_seg: 0.1224 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:44:33,748 INFO misc.py line 117 726] Train: [10/20][43/510] Data 3.445 (4.215) Batch 22.909 (27.942) Remain 43:12:34 loss: 0.1811 loss_seg: 0.0922 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:44:59,503 INFO misc.py line 117 726] Train: [10/20][44/510] Data 3.385 (4.194) Batch 25.754 (27.889) Remain 43:07:09 loss: 0.2624 loss_seg: 0.1654 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:45:23,626 INFO misc.py line 117 726] Train: [10/20][45/510] Data 4.908 (4.211) Batch 24.123 (27.799) Remain 42:58:22 loss: 0.2400 loss_seg: 0.1487 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:45:48,458 INFO misc.py line 117 726] Train: [10/20][46/510] Data 3.594 (4.197) Batch 24.832 (27.730) Remain 42:51:31 loss: 0.2421 loss_seg: 0.1456 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:46:19,283 INFO misc.py line 117 726] Train: [10/20][47/510] Data 2.749 (4.164) Batch 30.824 (27.801) Remain 42:57:34 loss: 0.3494 loss_seg: 0.2460 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:46:56,106 INFO misc.py line 117 726] Train: [10/20][48/510] Data 9.003 (4.272) Batch 36.824 (28.001) Remain 43:15:42 loss: 0.3264 loss_seg: 0.2306 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:47:20,633 INFO misc.py line 117 726] Train: [10/20][49/510] Data 3.261 (4.250) Batch 24.527 (27.926) Remain 43:08:14 loss: 0.2190 loss_seg: 0.1260 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:47:46,452 INFO misc.py line 117 726] Train: [10/20][50/510] Data 3.400 (4.232) Batch 25.819 (27.881) Remain 43:03:36 loss: 0.2308 loss_seg: 0.1358 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:47:46,452 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 04:48:08,527 INFO misc.py line 117 726] Train: [10/20][51/510] Data 2.558 (4.197) Batch 22.075 (27.760) Remain 42:51:56 loss: 0.2557 loss_seg: 0.1582 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:48:45,622 INFO misc.py line 117 726] Train: [10/20][52/510] Data 8.544 (4.285) Batch 37.095 (27.950) Remain 43:09:07 loss: 0.2427 loss_seg: 0.1513 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:49:10,525 INFO misc.py line 117 726] Train: [10/20][53/510] Data 3.027 (4.260) Batch 24.904 (27.889) Remain 43:03:01 loss: 0.2551 loss_seg: 0.1573 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:49:39,820 INFO misc.py line 117 726] Train: [10/20][54/510] Data 3.582 (4.247) Batch 29.295 (27.917) Remain 43:05:06 loss: 0.2397 loss_seg: 0.1449 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:49:59,226 INFO misc.py line 117 726] Train: [10/20][55/510] Data 2.601 (4.215) Batch 19.407 (27.753) Remain 42:49:29 loss: 0.2054 loss_seg: 0.1167 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:50:31,024 INFO misc.py line 117 726] Train: [10/20][56/510] Data 3.594 (4.204) Batch 31.798 (27.830) Remain 42:56:05 loss: 0.2339 loss_seg: 0.1396 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:51:04,809 INFO misc.py line 117 726] Train: [10/20][57/510] Data 4.432 (4.208) Batch 33.785 (27.940) Remain 43:05:49 loss: 0.2359 loss_seg: 0.1429 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:51:45,632 INFO misc.py line 117 726] Train: [10/20][58/510] Data 9.924 (4.312) Batch 40.823 (28.174) Remain 43:27:02 loss: 0.2774 loss_seg: 0.1813 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:52:07,333 INFO misc.py line 117 726] Train: [10/20][59/510] Data 2.528 (4.280) Batch 21.701 (28.059) Remain 43:15:52 loss: 0.2038 loss_seg: 0.1112 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:52:39,779 INFO misc.py line 117 726] Train: [10/20][60/510] Data 2.945 (4.256) Batch 32.445 (28.135) Remain 43:22:31 loss: 0.2574 loss_seg: 0.1597 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:53:05,985 INFO misc.py line 117 726] Train: [10/20][61/510] Data 2.354 (4.224) Batch 26.206 (28.102) Remain 43:18:59 loss: 0.2137 loss_seg: 0.1192 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:53:31,723 INFO misc.py line 117 726] Train: [10/20][62/510] Data 3.059 (4.204) Batch 25.738 (28.062) Remain 43:14:48 loss: 0.2223 loss_seg: 0.1306 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:53:54,349 INFO misc.py line 117 726] Train: [10/20][63/510] Data 2.241 (4.171) Batch 22.626 (27.972) Remain 43:05:58 loss: 0.2330 loss_seg: 0.1350 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:54:25,001 INFO misc.py line 117 726] Train: [10/20][64/510] Data 3.315 (4.157) Batch 30.652 (28.015) Remain 43:09:33 loss: 0.2408 loss_seg: 0.1466 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:54:48,351 INFO misc.py line 117 726] Train: [10/20][65/510] Data 2.546 (4.131) Batch 23.350 (27.940) Remain 43:02:08 loss: 0.2894 loss_seg: 0.1814 loss_superpoint_edge: 0.0405 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:55:09,387 INFO misc.py line 117 726] Train: [10/20][66/510] Data 2.555 (4.106) Batch 21.036 (27.831) Remain 42:51:32 loss: 0.2244 loss_seg: 0.1350 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:55:35,524 INFO misc.py line 117 726] Train: [10/20][67/510] Data 3.015 (4.089) Batch 26.137 (27.804) Remain 42:48:38 loss: 0.2613 loss_seg: 0.1645 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:56:02,189 INFO misc.py line 117 726] Train: [10/20][68/510] Data 3.001 (4.072) Batch 26.665 (27.787) Remain 42:46:33 loss: 0.1868 loss_seg: 0.1015 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:56:34,594 INFO misc.py line 117 726] Train: [10/20][69/510] Data 3.843 (4.069) Batch 32.406 (27.857) Remain 42:52:33 loss: 0.3180 loss_seg: 0.2077 loss_superpoint_edge: 0.0436 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:57:09,049 INFO misc.py line 117 726] Train: [10/20][70/510] Data 4.427 (4.074) Batch 34.454 (27.955) Remain 43:01:11 loss: 0.2157 loss_seg: 0.1267 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:57:31,213 INFO misc.py line 117 726] Train: [10/20][71/510] Data 3.034 (4.059) Batch 22.165 (27.870) Remain 42:52:51 loss: 0.2263 loss_seg: 0.1330 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:58:01,173 INFO misc.py line 117 726] Train: [10/20][72/510] Data 5.604 (4.081) Batch 29.960 (27.900) Remain 42:55:11 loss: 0.2586 loss_seg: 0.1616 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:58:32,112 INFO misc.py line 117 726] Train: [10/20][73/510] Data 4.715 (4.090) Batch 30.939 (27.944) Remain 42:58:43 loss: 0.2305 loss_seg: 0.1321 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:59:09,677 INFO misc.py line 117 726] Train: [10/20][74/510] Data 5.098 (4.105) Batch 37.565 (28.079) Remain 43:10:46 loss: 0.2652 loss_seg: 0.1718 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 04:59:32,005 INFO misc.py line 117 726] Train: [10/20][75/510] Data 3.163 (4.091) Batch 22.328 (27.999) Remain 43:02:55 loss: 0.2086 loss_seg: 0.1202 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:00:03,045 INFO misc.py line 117 726] Train: [10/20][76/510] Data 3.279 (4.080) Batch 31.041 (28.041) Remain 43:06:18 loss: 0.2353 loss_seg: 0.1420 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:00:26,593 INFO misc.py line 117 726] Train: [10/20][77/510] Data 2.606 (4.060) Batch 23.547 (27.980) Remain 43:00:14 loss: 0.1916 loss_seg: 0.1058 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:01:00,777 INFO misc.py line 117 726] Train: [10/20][78/510] Data 4.878 (4.071) Batch 34.184 (28.063) Remain 43:07:24 loss: 0.2912 loss_seg: 0.1955 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:01:31,524 INFO misc.py line 117 726] Train: [10/20][79/510] Data 2.771 (4.054) Batch 30.747 (28.098) Remain 43:10:11 loss: 0.1763 loss_seg: 0.0919 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:01:52,400 INFO misc.py line 117 726] Train: [10/20][80/510] Data 2.490 (4.034) Batch 20.877 (28.004) Remain 43:01:04 loss: 0.2179 loss_seg: 0.1259 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:02:28,850 INFO misc.py line 117 726] Train: [10/20][81/510] Data 5.867 (4.057) Batch 36.450 (28.113) Remain 43:10:35 loss: 0.2533 loss_seg: 0.1538 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:02:56,575 INFO misc.py line 117 726] Train: [10/20][82/510] Data 4.640 (4.065) Batch 27.725 (28.108) Remain 43:09:39 loss: 0.3293 loss_seg: 0.2302 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:03:22,610 INFO misc.py line 117 726] Train: [10/20][83/510] Data 2.498 (4.045) Batch 26.035 (28.082) Remain 43:06:48 loss: 0.2273 loss_seg: 0.1350 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:03:42,221 INFO misc.py line 117 726] Train: [10/20][84/510] Data 2.041 (4.020) Batch 19.611 (27.977) Remain 42:56:42 loss: 0.2582 loss_seg: 0.1579 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:04:08,308 INFO misc.py line 117 726] Train: [10/20][85/510] Data 2.453 (4.001) Batch 26.088 (27.954) Remain 42:54:07 loss: 0.2591 loss_seg: 0.1617 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:04:36,164 INFO misc.py line 117 726] Train: [10/20][86/510] Data 3.179 (3.991) Batch 27.856 (27.953) Remain 42:53:32 loss: 0.2250 loss_seg: 0.1324 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:05:01,692 INFO misc.py line 117 726] Train: [10/20][87/510] Data 2.201 (3.970) Batch 25.528 (27.924) Remain 42:50:25 loss: 0.2263 loss_seg: 0.1353 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:05:27,349 INFO misc.py line 117 726] Train: [10/20][88/510] Data 3.762 (3.968) Batch 25.657 (27.898) Remain 42:47:30 loss: 0.3491 loss_seg: 0.2554 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:06:04,068 INFO misc.py line 117 726] Train: [10/20][89/510] Data 11.334 (4.053) Batch 36.719 (28.000) Remain 42:56:28 loss: 0.1954 loss_seg: 0.1088 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:06:38,355 INFO misc.py line 117 726] Train: [10/20][90/510] Data 5.559 (4.071) Batch 34.287 (28.072) Remain 43:02:39 loss: 0.2255 loss_seg: 0.1305 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:06:58,019 INFO misc.py line 117 726] Train: [10/20][91/510] Data 2.294 (4.050) Batch 19.664 (27.977) Remain 42:53:24 loss: 0.3129 loss_seg: 0.2008 loss_superpoint_edge: 0.0425 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:07:21,168 INFO misc.py line 117 726] Train: [10/20][92/510] Data 2.718 (4.035) Batch 23.149 (27.923) Remain 42:47:56 loss: 0.2410 loss_seg: 0.1474 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:07:47,615 INFO misc.py line 117 726] Train: [10/20][93/510] Data 5.056 (4.047) Batch 26.447 (27.906) Remain 42:45:58 loss: 0.3128 loss_seg: 0.2044 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:08:19,904 INFO misc.py line 117 726] Train: [10/20][94/510] Data 3.934 (4.046) Batch 32.290 (27.954) Remain 42:49:56 loss: 0.2637 loss_seg: 0.1632 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:08:46,964 INFO misc.py line 117 726] Train: [10/20][95/510] Data 2.881 (4.033) Batch 27.060 (27.945) Remain 42:48:34 loss: 0.2854 loss_seg: 0.1925 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:09:17,631 INFO misc.py line 117 726] Train: [10/20][96/510] Data 3.925 (4.032) Batch 30.667 (27.974) Remain 42:50:48 loss: 0.2665 loss_seg: 0.1683 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:09:45,038 INFO misc.py line 117 726] Train: [10/20][97/510] Data 3.554 (4.027) Batch 27.407 (27.968) Remain 42:49:46 loss: 0.2429 loss_seg: 0.1504 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:10:16,327 INFO misc.py line 117 726] Train: [10/20][98/510] Data 4.045 (4.027) Batch 31.289 (28.003) Remain 42:52:31 loss: 0.2453 loss_seg: 0.1517 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:10:43,118 INFO misc.py line 117 726] Train: [10/20][99/510] Data 2.705 (4.013) Batch 26.791 (27.990) Remain 42:50:54 loss: 0.2193 loss_seg: 0.1249 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:11:02,142 INFO misc.py line 117 726] Train: [10/20][100/510] Data 2.147 (3.994) Batch 19.023 (27.898) Remain 42:41:56 loss: 0.1922 loss_seg: 0.1055 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:11:02,142 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 05:11:33,098 INFO misc.py line 117 726] Train: [10/20][101/510] Data 4.873 (4.003) Batch 30.956 (27.929) Remain 42:44:20 loss: 0.2642 loss_seg: 0.1784 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:12:10,032 INFO misc.py line 117 726] Train: [10/20][102/510] Data 5.488 (4.018) Batch 36.934 (28.020) Remain 42:52:13 loss: 0.2392 loss_seg: 0.1442 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:12:28,954 INFO misc.py line 117 726] Train: [10/20][103/510] Data 2.214 (4.000) Batch 18.922 (27.929) Remain 42:43:24 loss: 0.2083 loss_seg: 0.1148 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:13:02,067 INFO misc.py line 117 726] Train: [10/20][104/510] Data 4.103 (4.001) Batch 33.113 (27.980) Remain 42:47:39 loss: 0.2528 loss_seg: 0.1628 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:13:36,293 INFO misc.py line 117 726] Train: [10/20][105/510] Data 4.047 (4.001) Batch 34.226 (28.042) Remain 42:52:48 loss: 0.3693 loss_seg: 0.2632 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:14:05,422 INFO misc.py line 117 726] Train: [10/20][106/510] Data 3.263 (3.994) Batch 29.128 (28.052) Remain 42:53:18 loss: 0.2132 loss_seg: 0.1197 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:14:36,998 INFO misc.py line 117 726] Train: [10/20][107/510] Data 3.537 (3.990) Batch 31.576 (28.086) Remain 42:55:57 loss: 0.2260 loss_seg: 0.1376 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:15:05,099 INFO misc.py line 117 726] Train: [10/20][108/510] Data 3.000 (3.980) Batch 28.101 (28.086) Remain 42:55:29 loss: 0.4313 loss_seg: 0.3150 loss_superpoint_edge: 0.0462 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:15:38,026 INFO misc.py line 117 726] Train: [10/20][109/510] Data 3.566 (3.976) Batch 32.927 (28.132) Remain 42:59:12 loss: 0.2606 loss_seg: 0.1602 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:16:03,302 INFO misc.py line 117 726] Train: [10/20][110/510] Data 2.863 (3.966) Batch 25.276 (28.105) Remain 42:56:17 loss: 0.1686 loss_seg: 0.0865 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:16:28,463 INFO misc.py line 117 726] Train: [10/20][111/510] Data 2.119 (3.949) Batch 25.161 (28.078) Remain 42:53:19 loss: 0.2195 loss_seg: 0.1250 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:16:55,369 INFO misc.py line 117 726] Train: [10/20][112/510] Data 3.022 (3.940) Batch 26.906 (28.067) Remain 42:51:52 loss: 0.2368 loss_seg: 0.1421 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:17:17,029 INFO misc.py line 117 726] Train: [10/20][113/510] Data 2.241 (3.925) Batch 21.660 (28.009) Remain 42:46:04 loss: 0.1770 loss_seg: 0.0924 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:17:46,003 INFO misc.py line 117 726] Train: [10/20][114/510] Data 3.641 (3.922) Batch 28.974 (28.018) Remain 42:46:24 loss: 0.2562 loss_seg: 0.1652 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:18:21,018 INFO misc.py line 117 726] Train: [10/20][115/510] Data 5.612 (3.937) Batch 35.015 (28.080) Remain 42:51:39 loss: 0.2567 loss_seg: 0.1630 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:18:39,276 INFO misc.py line 117 726] Train: [10/20][116/510] Data 1.979 (3.920) Batch 18.258 (27.993) Remain 42:43:13 loss: 0.2343 loss_seg: 0.1410 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:19:08,375 INFO misc.py line 117 726] Train: [10/20][117/510] Data 3.381 (3.915) Batch 29.099 (28.003) Remain 42:43:39 loss: 0.2011 loss_seg: 0.1142 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:19:37,478 INFO misc.py line 117 726] Train: [10/20][118/510] Data 3.705 (3.914) Batch 29.103 (28.012) Remain 42:44:03 loss: 0.2805 loss_seg: 0.1829 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:20:03,620 INFO misc.py line 117 726] Train: [10/20][119/510] Data 2.694 (3.903) Batch 26.142 (27.996) Remain 42:42:07 loss: 0.2907 loss_seg: 0.1853 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:20:33,089 INFO misc.py line 117 726] Train: [10/20][120/510] Data 5.117 (3.913) Batch 29.469 (28.009) Remain 42:42:48 loss: 0.4406 loss_seg: 0.3308 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:20:53,514 INFO misc.py line 117 726] Train: [10/20][121/510] Data 2.518 (3.902) Batch 20.425 (27.945) Remain 42:36:27 loss: 0.2181 loss_seg: 0.1285 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:21:12,013 INFO misc.py line 117 726] Train: [10/20][122/510] Data 2.149 (3.887) Batch 18.499 (27.865) Remain 42:28:44 loss: 0.3029 loss_seg: 0.2043 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:21:35,062 INFO misc.py line 117 726] Train: [10/20][123/510] Data 2.424 (3.875) Batch 23.049 (27.825) Remain 42:24:35 loss: 0.1708 loss_seg: 0.0884 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:22:12,937 INFO misc.py line 117 726] Train: [10/20][124/510] Data 11.132 (3.935) Batch 37.875 (27.908) Remain 42:31:43 loss: 0.3686 loss_seg: 0.2781 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:22:32,219 INFO misc.py line 117 726] Train: [10/20][125/510] Data 2.222 (3.921) Batch 19.283 (27.837) Remain 42:24:48 loss: 0.2480 loss_seg: 0.1471 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:23:03,451 INFO misc.py line 117 726] Train: [10/20][126/510] Data 3.892 (3.920) Batch 31.232 (27.865) Remain 42:26:51 loss: 0.3243 loss_seg: 0.2284 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:23:34,013 INFO misc.py line 117 726] Train: [10/20][127/510] Data 3.511 (3.917) Batch 30.562 (27.887) Remain 42:28:22 loss: 0.2107 loss_seg: 0.1232 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:23:59,548 INFO misc.py line 117 726] Train: [10/20][128/510] Data 3.272 (3.912) Batch 25.535 (27.868) Remain 42:26:11 loss: 0.2450 loss_seg: 0.1505 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:24:35,240 INFO misc.py line 117 726] Train: [10/20][129/510] Data 8.228 (3.946) Batch 35.692 (27.930) Remain 42:31:24 loss: 0.3919 loss_seg: 0.2655 loss_superpoint_edge: 0.0605 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:25:12,022 INFO misc.py line 117 726] Train: [10/20][130/510] Data 6.148 (3.963) Batch 36.782 (28.000) Remain 42:37:18 loss: 0.2678 loss_seg: 0.1658 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:25:45,162 INFO misc.py line 117 726] Train: [10/20][131/510] Data 3.432 (3.959) Batch 33.140 (28.040) Remain 42:40:30 loss: 0.2244 loss_seg: 0.1288 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:26:18,221 INFO misc.py line 117 726] Train: [10/20][132/510] Data 4.865 (3.966) Batch 33.058 (28.079) Remain 42:43:35 loss: 0.2039 loss_seg: 0.1138 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:26:52,406 INFO misc.py line 117 726] Train: [10/20][133/510] Data 3.821 (3.965) Batch 34.185 (28.126) Remain 42:47:24 loss: 0.2133 loss_seg: 0.1222 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:27:18,722 INFO misc.py line 117 726] Train: [10/20][134/510] Data 4.015 (3.966) Batch 26.316 (28.112) Remain 42:45:40 loss: 0.1993 loss_seg: 0.1097 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:27:48,859 INFO misc.py line 117 726] Train: [10/20][135/510] Data 4.528 (3.970) Batch 30.138 (28.127) Remain 42:46:36 loss: 0.2502 loss_seg: 0.1531 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:28:21,187 INFO misc.py line 117 726] Train: [10/20][136/510] Data 4.827 (3.976) Batch 32.327 (28.159) Remain 42:49:01 loss: 0.3029 loss_seg: 0.1974 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:28:47,886 INFO misc.py line 117 726] Train: [10/20][137/510] Data 2.865 (3.968) Batch 26.699 (28.148) Remain 42:47:33 loss: 0.2168 loss_seg: 0.1239 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:29:13,308 INFO misc.py line 117 726] Train: [10/20][138/510] Data 3.734 (3.966) Batch 25.422 (28.128) Remain 42:45:15 loss: 0.3134 loss_seg: 0.2086 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:29:48,825 INFO misc.py line 117 726] Train: [10/20][139/510] Data 4.858 (3.973) Batch 35.517 (28.182) Remain 42:49:44 loss: 0.2444 loss_seg: 0.1534 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:30:16,596 INFO misc.py line 117 726] Train: [10/20][140/510] Data 4.041 (3.973) Batch 27.771 (28.179) Remain 42:48:59 loss: 0.2951 loss_seg: 0.1987 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:30:44,308 INFO misc.py line 117 726] Train: [10/20][141/510] Data 3.176 (3.968) Batch 27.712 (28.176) Remain 42:48:13 loss: 0.2273 loss_seg: 0.1334 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:30:54,279 INFO misc.py line 117 726] Train: [10/20][142/510] Data 1.420 (3.949) Batch 9.970 (28.045) Remain 42:35:48 loss: 0.2124 loss_seg: 0.1261 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:31:28,069 INFO misc.py line 117 726] Train: [10/20][143/510] Data 6.765 (3.969) Batch 33.791 (28.086) Remain 42:39:05 loss: 0.2239 loss_seg: 0.1321 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:31:50,673 INFO misc.py line 117 726] Train: [10/20][144/510] Data 1.969 (3.955) Batch 22.604 (28.047) Remain 42:35:04 loss: 0.2502 loss_seg: 0.1549 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:32:22,243 INFO misc.py line 117 726] Train: [10/20][145/510] Data 5.397 (3.965) Batch 31.570 (28.072) Remain 42:36:51 loss: 0.2636 loss_seg: 0.1660 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:32:47,114 INFO misc.py line 117 726] Train: [10/20][146/510] Data 4.144 (3.967) Batch 24.871 (28.049) Remain 42:34:21 loss: 0.2246 loss_seg: 0.1288 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:33:16,219 INFO misc.py line 117 726] Train: [10/20][147/510] Data 5.150 (3.975) Batch 29.105 (28.057) Remain 42:34:33 loss: 0.1747 loss_seg: 0.0900 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:33:43,503 INFO misc.py line 117 726] Train: [10/20][148/510] Data 3.321 (3.970) Batch 27.284 (28.051) Remain 42:33:36 loss: 0.1867 loss_seg: 0.1017 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:34:09,933 INFO misc.py line 117 726] Train: [10/20][149/510] Data 2.731 (3.962) Batch 26.430 (28.040) Remain 42:32:07 loss: 0.2356 loss_seg: 0.1427 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:34:35,714 INFO misc.py line 117 726] Train: [10/20][150/510] Data 3.674 (3.960) Batch 25.781 (28.025) Remain 42:30:15 loss: 0.2733 loss_seg: 0.1681 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:34:35,715 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 05:35:19,080 INFO misc.py line 117 726] Train: [10/20][151/510] Data 13.066 (4.021) Batch 43.367 (28.129) Remain 42:39:13 loss: 0.2273 loss_seg: 0.1347 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:35:40,818 INFO misc.py line 117 726] Train: [10/20][152/510] Data 3.795 (4.020) Batch 21.737 (28.086) Remain 42:34:51 loss: 0.2006 loss_seg: 0.1048 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:36:16,501 INFO misc.py line 117 726] Train: [10/20][153/510] Data 7.785 (4.045) Batch 35.684 (28.136) Remain 42:38:59 loss: 0.2461 loss_seg: 0.1514 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:36:45,558 INFO misc.py line 117 726] Train: [10/20][154/510] Data 3.604 (4.042) Batch 29.056 (28.142) Remain 42:39:04 loss: 0.2675 loss_seg: 0.1636 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:37:06,153 INFO misc.py line 117 726] Train: [10/20][155/510] Data 2.332 (4.031) Batch 20.595 (28.093) Remain 42:34:05 loss: 0.2326 loss_seg: 0.1324 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:37:39,074 INFO misc.py line 117 726] Train: [10/20][156/510] Data 3.434 (4.027) Batch 32.921 (28.124) Remain 42:36:29 loss: 0.2518 loss_seg: 0.1685 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:38:08,113 INFO misc.py line 117 726] Train: [10/20][157/510] Data 3.422 (4.023) Batch 29.038 (28.130) Remain 42:36:34 loss: 0.2827 loss_seg: 0.1796 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:38:43,711 INFO misc.py line 117 726] Train: [10/20][158/510] Data 8.032 (4.049) Batch 35.599 (28.178) Remain 42:40:28 loss: 0.2513 loss_seg: 0.1614 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:39:08,730 INFO misc.py line 117 726] Train: [10/20][159/510] Data 2.488 (4.039) Batch 25.019 (28.158) Remain 42:38:10 loss: 0.2778 loss_seg: 0.1774 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:39:40,579 INFO misc.py line 117 726] Train: [10/20][160/510] Data 5.245 (4.046) Batch 31.849 (28.182) Remain 42:39:50 loss: 0.2868 loss_seg: 0.1865 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:40:11,853 INFO misc.py line 117 726] Train: [10/20][161/510] Data 2.803 (4.039) Batch 31.274 (28.201) Remain 42:41:08 loss: 0.2411 loss_seg: 0.1458 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:40:44,437 INFO misc.py line 117 726] Train: [10/20][162/510] Data 2.863 (4.031) Batch 32.583 (28.229) Remain 42:43:10 loss: 0.3312 loss_seg: 0.2312 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:41:01,335 INFO misc.py line 117 726] Train: [10/20][163/510] Data 1.764 (4.017) Batch 16.899 (28.158) Remain 42:36:16 loss: 0.2356 loss_seg: 0.1412 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:41:24,765 INFO misc.py line 117 726] Train: [10/20][164/510] Data 2.552 (4.008) Batch 23.430 (28.129) Remain 42:33:08 loss: 0.2557 loss_seg: 0.1618 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:41:51,948 INFO misc.py line 117 726] Train: [10/20][165/510] Data 2.824 (4.001) Batch 27.183 (28.123) Remain 42:32:08 loss: 0.2831 loss_seg: 0.1961 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:42:20,198 INFO misc.py line 117 726] Train: [10/20][166/510] Data 3.160 (3.995) Batch 28.249 (28.124) Remain 42:31:44 loss: 0.2612 loss_seg: 0.1655 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:42:52,624 INFO misc.py line 117 726] Train: [10/20][167/510] Data 4.299 (3.997) Batch 32.427 (28.150) Remain 42:33:39 loss: 0.3633 loss_seg: 0.2684 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:43:18,907 INFO misc.py line 117 726] Train: [10/20][168/510] Data 2.984 (3.991) Batch 26.283 (28.138) Remain 42:32:09 loss: 0.2367 loss_seg: 0.1398 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:43:47,781 INFO misc.py line 117 726] Train: [10/20][169/510] Data 3.190 (3.986) Batch 28.874 (28.143) Remain 42:32:05 loss: 0.3657 loss_seg: 0.2662 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:44:15,638 INFO misc.py line 117 726] Train: [10/20][170/510] Data 2.640 (3.978) Batch 27.857 (28.141) Remain 42:31:28 loss: 0.2467 loss_seg: 0.1536 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:44:48,085 INFO misc.py line 117 726] Train: [10/20][171/510] Data 4.673 (3.982) Batch 32.447 (28.167) Remain 42:33:19 loss: 0.2064 loss_seg: 0.1179 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:45:16,403 INFO misc.py line 117 726] Train: [10/20][172/510] Data 3.286 (3.978) Batch 28.318 (28.168) Remain 42:32:56 loss: 0.1936 loss_seg: 0.1051 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:45:52,616 INFO misc.py line 117 726] Train: [10/20][173/510] Data 9.890 (4.013) Batch 36.213 (28.215) Remain 42:36:45 loss: 0.2478 loss_seg: 0.1486 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0452 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:46:20,415 INFO misc.py line 117 726] Train: [10/20][174/510] Data 3.391 (4.009) Batch 27.799 (28.213) Remain 42:36:03 loss: 0.2381 loss_seg: 0.1433 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:46:44,452 INFO misc.py line 117 726] Train: [10/20][175/510] Data 2.747 (4.002) Batch 24.037 (28.188) Remain 42:33:23 loss: 0.2290 loss_seg: 0.1341 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:47:12,315 INFO misc.py line 117 726] Train: [10/20][176/510] Data 3.806 (4.001) Batch 27.863 (28.186) Remain 42:32:45 loss: 0.3570 loss_seg: 0.2421 loss_superpoint_edge: 0.0505 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:47:41,075 INFO misc.py line 117 726] Train: [10/20][177/510] Data 3.324 (3.997) Batch 28.760 (28.190) Remain 42:32:34 loss: 0.2664 loss_seg: 0.1706 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:48:16,356 INFO misc.py line 117 726] Train: [10/20][178/510] Data 4.113 (3.998) Batch 35.281 (28.230) Remain 42:35:46 loss: 0.2098 loss_seg: 0.1167 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:48:42,490 INFO misc.py line 117 726] Train: [10/20][179/510] Data 3.158 (3.993) Batch 26.133 (28.218) Remain 42:34:13 loss: 0.2273 loss_seg: 0.1416 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:49:11,670 INFO misc.py line 117 726] Train: [10/20][180/510] Data 3.504 (3.990) Batch 29.180 (28.224) Remain 42:34:15 loss: 0.2137 loss_seg: 0.1242 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:49:36,796 INFO misc.py line 117 726] Train: [10/20][181/510] Data 2.974 (3.985) Batch 25.126 (28.206) Remain 42:32:12 loss: 0.2340 loss_seg: 0.1407 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:50:07,021 INFO misc.py line 117 726] Train: [10/20][182/510] Data 3.425 (3.981) Batch 30.226 (28.218) Remain 42:32:45 loss: 0.3243 loss_seg: 0.2246 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:50:36,420 INFO misc.py line 117 726] Train: [10/20][183/510] Data 5.059 (3.987) Batch 29.398 (28.224) Remain 42:32:52 loss: 0.2222 loss_seg: 0.1325 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:51:03,389 INFO misc.py line 117 726] Train: [10/20][184/510] Data 3.207 (3.983) Batch 26.969 (28.217) Remain 42:31:47 loss: 0.1720 loss_seg: 0.0892 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:51:32,423 INFO misc.py line 117 726] Train: [10/20][185/510] Data 2.938 (3.977) Batch 29.034 (28.222) Remain 42:31:43 loss: 0.2144 loss_seg: 0.1244 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0317 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:52:01,596 INFO misc.py line 117 726] Train: [10/20][186/510] Data 3.704 (3.976) Batch 29.173 (28.227) Remain 42:31:43 loss: 0.2350 loss_seg: 0.1362 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:52:36,190 INFO misc.py line 117 726] Train: [10/20][187/510] Data 5.695 (3.985) Batch 34.594 (28.262) Remain 42:34:22 loss: 0.2091 loss_seg: 0.1168 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:53:07,125 INFO misc.py line 117 726] Train: [10/20][188/510] Data 5.116 (3.991) Batch 30.935 (28.276) Remain 42:35:12 loss: 0.1981 loss_seg: 0.1128 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:53:31,252 INFO misc.py line 117 726] Train: [10/20][189/510] Data 2.994 (3.986) Batch 24.127 (28.254) Remain 42:32:43 loss: 0.2183 loss_seg: 0.1268 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:53:59,525 INFO misc.py line 117 726] Train: [10/20][190/510] Data 4.632 (3.989) Batch 28.273 (28.254) Remain 42:32:15 loss: 0.2240 loss_seg: 0.1312 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:54:36,470 INFO misc.py line 117 726] Train: [10/20][191/510] Data 7.671 (4.009) Batch 36.944 (28.300) Remain 42:35:58 loss: 0.4320 loss_seg: 0.3272 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:55:12,072 INFO misc.py line 117 726] Train: [10/20][192/510] Data 5.194 (4.015) Batch 35.603 (28.339) Remain 42:38:59 loss: 0.2285 loss_seg: 0.1360 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:55:38,375 INFO misc.py line 117 726] Train: [10/20][193/510] Data 3.060 (4.010) Batch 26.303 (28.328) Remain 42:37:32 loss: 0.1786 loss_seg: 0.0941 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:55:59,882 INFO misc.py line 117 726] Train: [10/20][194/510] Data 2.995 (4.005) Batch 21.506 (28.292) Remain 42:33:50 loss: 0.2249 loss_seg: 0.1315 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:56:25,153 INFO misc.py line 117 726] Train: [10/20][195/510] Data 2.762 (3.998) Batch 25.271 (28.277) Remain 42:31:57 loss: 0.2483 loss_seg: 0.1548 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:56:45,322 INFO misc.py line 117 726] Train: [10/20][196/510] Data 2.612 (3.991) Batch 20.169 (28.235) Remain 42:27:41 loss: 0.2328 loss_seg: 0.1392 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:57:17,784 INFO misc.py line 117 726] Train: [10/20][197/510] Data 4.957 (3.996) Batch 32.462 (28.256) Remain 42:29:11 loss: 0.2424 loss_seg: 0.1518 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:57:46,205 INFO misc.py line 117 726] Train: [10/20][198/510] Data 3.093 (3.992) Batch 28.421 (28.257) Remain 42:28:47 loss: 0.2516 loss_seg: 0.1584 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:58:13,319 INFO misc.py line 117 726] Train: [10/20][199/510] Data 3.851 (3.991) Batch 27.114 (28.251) Remain 42:27:47 loss: 0.3634 loss_seg: 0.2570 loss_superpoint_edge: 0.0404 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:58:47,969 INFO misc.py line 117 726] Train: [10/20][200/510] Data 6.069 (4.001) Batch 34.650 (28.284) Remain 42:30:15 loss: 0.3244 loss_seg: 0.2289 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:58:47,970 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 05:59:18,080 INFO misc.py line 117 726] Train: [10/20][201/510] Data 4.087 (4.002) Batch 30.111 (28.293) Remain 42:30:37 loss: 0.2545 loss_seg: 0.1589 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 05:59:48,527 INFO misc.py line 117 726] Train: [10/20][202/510] Data 5.031 (4.007) Batch 30.446 (28.304) Remain 42:31:07 loss: 0.2891 loss_seg: 0.1899 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:00:21,411 INFO misc.py line 117 726] Train: [10/20][203/510] Data 4.784 (4.011) Batch 32.884 (28.327) Remain 42:32:42 loss: 0.2541 loss_seg: 0.1603 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:00:52,411 INFO misc.py line 117 726] Train: [10/20][204/510] Data 2.794 (4.005) Batch 31.000 (28.340) Remain 42:33:26 loss: 0.1921 loss_seg: 0.1050 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:01:22,683 INFO misc.py line 117 726] Train: [10/20][205/510] Data 3.850 (4.004) Batch 30.271 (28.350) Remain 42:33:49 loss: 0.1621 loss_seg: 0.0811 loss_superpoint_edge: 0.0129 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:01:57,756 INFO misc.py line 117 726] Train: [10/20][206/510] Data 3.930 (4.004) Batch 35.073 (28.383) Remain 42:36:20 loss: 0.2018 loss_seg: 0.1137 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:02:35,865 INFO misc.py line 117 726] Train: [10/20][207/510] Data 7.773 (4.022) Batch 38.109 (28.430) Remain 42:40:09 loss: 0.2920 loss_seg: 0.1956 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:03:12,662 INFO misc.py line 117 726] Train: [10/20][208/510] Data 4.154 (4.023) Batch 36.797 (28.471) Remain 42:43:21 loss: 0.2659 loss_seg: 0.1724 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:03:39,719 INFO misc.py line 117 726] Train: [10/20][209/510] Data 3.284 (4.019) Batch 27.057 (28.464) Remain 42:42:16 loss: 0.1850 loss_seg: 0.0977 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:04:00,397 INFO misc.py line 117 726] Train: [10/20][210/510] Data 2.274 (4.011) Batch 20.678 (28.427) Remain 42:38:24 loss: 0.2572 loss_seg: 0.1564 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:04:33,396 INFO misc.py line 117 726] Train: [10/20][211/510] Data 5.447 (4.018) Batch 32.999 (28.449) Remain 42:39:54 loss: 0.3562 loss_seg: 0.2533 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:05:05,412 INFO misc.py line 117 726] Train: [10/20][212/510] Data 4.723 (4.021) Batch 32.016 (28.466) Remain 42:40:58 loss: 0.4752 loss_seg: 0.3647 loss_superpoint_edge: 0.0450 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:05:44,863 INFO misc.py line 117 726] Train: [10/20][213/510] Data 6.536 (4.033) Batch 39.452 (28.518) Remain 42:45:12 loss: 0.2125 loss_seg: 0.1242 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:06:14,525 INFO misc.py line 117 726] Train: [10/20][214/510] Data 3.040 (4.028) Batch 29.662 (28.524) Remain 42:45:13 loss: 0.2498 loss_seg: 0.1531 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:06:43,964 INFO misc.py line 117 726] Train: [10/20][215/510] Data 3.831 (4.027) Batch 29.438 (28.528) Remain 42:45:07 loss: 0.3310 loss_seg: 0.2343 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:07:15,356 INFO misc.py line 117 726] Train: [10/20][216/510] Data 2.976 (4.022) Batch 31.393 (28.541) Remain 42:45:51 loss: 0.2112 loss_seg: 0.1244 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:07:44,008 INFO misc.py line 117 726] Train: [10/20][217/510] Data 4.766 (4.026) Batch 28.652 (28.542) Remain 42:45:26 loss: 0.4016 loss_seg: 0.2763 loss_superpoint_edge: 0.0551 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:08:08,801 INFO misc.py line 117 726] Train: [10/20][218/510] Data 2.432 (4.019) Batch 24.793 (28.524) Remain 42:43:23 loss: 0.1837 loss_seg: 0.0994 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:08:35,062 INFO misc.py line 117 726] Train: [10/20][219/510] Data 3.204 (4.015) Batch 26.262 (28.514) Remain 42:41:58 loss: 0.2228 loss_seg: 0.1342 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:09:07,328 INFO misc.py line 117 726] Train: [10/20][220/510] Data 3.319 (4.012) Batch 32.265 (28.531) Remain 42:43:03 loss: 0.2038 loss_seg: 0.1185 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:09:28,309 INFO misc.py line 117 726] Train: [10/20][221/510] Data 2.474 (4.005) Batch 20.981 (28.497) Remain 42:39:27 loss: 0.2466 loss_seg: 0.1621 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:09:59,602 INFO misc.py line 117 726] Train: [10/20][222/510] Data 4.391 (4.006) Batch 31.293 (28.509) Remain 42:40:08 loss: 0.3076 loss_seg: 0.2201 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:10:34,505 INFO misc.py line 117 726] Train: [10/20][223/510] Data 4.041 (4.006) Batch 34.904 (28.538) Remain 42:42:16 loss: 0.2448 loss_seg: 0.1495 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:10:59,942 INFO misc.py line 117 726] Train: [10/20][224/510] Data 3.088 (4.002) Batch 25.437 (28.524) Remain 42:40:32 loss: 0.3132 loss_seg: 0.2093 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:11:22,781 INFO misc.py line 117 726] Train: [10/20][225/510] Data 2.431 (3.995) Batch 22.839 (28.499) Remain 42:37:45 loss: 0.1904 loss_seg: 0.1016 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:11:48,925 INFO misc.py line 117 726] Train: [10/20][226/510] Data 3.106 (3.991) Batch 26.144 (28.488) Remain 42:36:20 loss: 0.2450 loss_seg: 0.1475 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:12:10,007 INFO misc.py line 117 726] Train: [10/20][227/510] Data 2.599 (3.985) Batch 21.082 (28.455) Remain 42:32:53 loss: 0.2419 loss_seg: 0.1497 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:12:39,498 INFO misc.py line 117 726] Train: [10/20][228/510] Data 2.587 (3.979) Batch 29.491 (28.460) Remain 42:32:50 loss: 0.2303 loss_seg: 0.1370 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:12:56,112 INFO misc.py line 117 726] Train: [10/20][229/510] Data 1.710 (3.969) Batch 16.614 (28.407) Remain 42:27:39 loss: 0.2627 loss_seg: 0.1696 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:13:25,957 INFO misc.py line 117 726] Train: [10/20][230/510] Data 4.276 (3.970) Batch 29.844 (28.414) Remain 42:27:45 loss: 0.2883 loss_seg: 0.1832 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:13:53,800 INFO misc.py line 117 726] Train: [10/20][231/510] Data 3.666 (3.969) Batch 27.844 (28.411) Remain 42:27:03 loss: 0.2290 loss_seg: 0.1344 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:14:21,094 INFO misc.py line 117 726] Train: [10/20][232/510] Data 2.917 (3.964) Batch 27.294 (28.406) Remain 42:26:08 loss: 0.2661 loss_seg: 0.1665 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:14:50,890 INFO misc.py line 117 726] Train: [10/20][233/510] Data 3.471 (3.962) Batch 29.796 (28.412) Remain 42:26:13 loss: 0.2313 loss_seg: 0.1370 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:15:22,335 INFO misc.py line 117 726] Train: [10/20][234/510] Data 4.427 (3.964) Batch 31.445 (28.425) Remain 42:26:55 loss: 0.2468 loss_seg: 0.1518 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:15:41,039 INFO misc.py line 117 726] Train: [10/20][235/510] Data 1.994 (3.956) Batch 18.703 (28.384) Remain 42:22:41 loss: 0.2345 loss_seg: 0.1392 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:16:08,003 INFO misc.py line 117 726] Train: [10/20][236/510] Data 3.272 (3.953) Batch 26.964 (28.377) Remain 42:21:40 loss: 0.2758 loss_seg: 0.1791 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:16:33,126 INFO misc.py line 117 726] Train: [10/20][237/510] Data 3.154 (3.949) Batch 25.123 (28.364) Remain 42:19:57 loss: 0.2260 loss_seg: 0.1359 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:16:56,815 INFO misc.py line 117 726] Train: [10/20][238/510] Data 2.849 (3.945) Batch 23.689 (28.344) Remain 42:17:42 loss: 0.2701 loss_seg: 0.1733 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:17:33,647 INFO misc.py line 117 726] Train: [10/20][239/510] Data 6.391 (3.955) Batch 36.833 (28.380) Remain 42:20:26 loss: 0.2785 loss_seg: 0.1751 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:17:54,099 INFO misc.py line 117 726] Train: [10/20][240/510] Data 2.405 (3.948) Batch 20.452 (28.346) Remain 42:16:58 loss: 0.1958 loss_seg: 0.1057 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:18:18,987 INFO misc.py line 117 726] Train: [10/20][241/510] Data 2.760 (3.943) Batch 24.888 (28.332) Remain 42:15:12 loss: 0.2829 loss_seg: 0.1872 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:18:47,871 INFO misc.py line 117 726] Train: [10/20][242/510] Data 3.205 (3.940) Batch 28.883 (28.334) Remain 42:14:56 loss: 0.2201 loss_seg: 0.1309 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:19:15,945 INFO misc.py line 117 726] Train: [10/20][243/510] Data 2.179 (3.933) Batch 28.074 (28.333) Remain 42:14:22 loss: 0.2442 loss_seg: 0.1456 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:19:35,102 INFO misc.py line 117 726] Train: [10/20][244/510] Data 2.089 (3.925) Batch 19.157 (28.295) Remain 42:10:29 loss: 0.1977 loss_seg: 0.1114 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:20:03,859 INFO misc.py line 117 726] Train: [10/20][245/510] Data 3.473 (3.923) Batch 28.757 (28.297) Remain 42:10:11 loss: 0.2007 loss_seg: 0.1161 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:20:35,503 INFO misc.py line 117 726] Train: [10/20][246/510] Data 4.671 (3.927) Batch 31.643 (28.310) Remain 42:10:57 loss: 0.2073 loss_seg: 0.1211 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:20:57,516 INFO misc.py line 117 726] Train: [10/20][247/510] Data 3.116 (3.923) Batch 22.013 (28.285) Remain 42:08:10 loss: 0.1948 loss_seg: 0.1073 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:21:27,051 INFO misc.py line 117 726] Train: [10/20][248/510] Data 5.016 (3.928) Batch 29.535 (28.290) Remain 42:08:09 loss: 0.3243 loss_seg: 0.2124 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:21:53,629 INFO misc.py line 117 726] Train: [10/20][249/510] Data 2.965 (3.924) Batch 26.578 (28.283) Remain 42:07:04 loss: 0.2057 loss_seg: 0.1145 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:22:31,447 INFO misc.py line 117 726] Train: [10/20][250/510] Data 9.930 (3.948) Batch 37.819 (28.321) Remain 42:10:02 loss: 0.3328 loss_seg: 0.2316 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:22:31,448 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 06:23:05,534 INFO misc.py line 117 726] Train: [10/20][251/510] Data 5.293 (3.953) Batch 34.087 (28.345) Remain 42:11:39 loss: 0.2867 loss_seg: 0.1915 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:23:33,908 INFO misc.py line 117 726] Train: [10/20][252/510] Data 2.676 (3.948) Batch 28.373 (28.345) Remain 42:11:11 loss: 0.2776 loss_seg: 0.1786 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:24:11,054 INFO misc.py line 117 726] Train: [10/20][253/510] Data 7.118 (3.961) Batch 37.146 (28.380) Remain 42:13:51 loss: 0.2086 loss_seg: 0.1228 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:24:40,051 INFO misc.py line 117 726] Train: [10/20][254/510] Data 3.023 (3.957) Batch 28.997 (28.382) Remain 42:13:36 loss: 0.2279 loss_seg: 0.1345 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:25:12,103 INFO misc.py line 117 726] Train: [10/20][255/510] Data 4.073 (3.958) Batch 32.052 (28.397) Remain 42:14:25 loss: 0.1948 loss_seg: 0.1075 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:25:41,848 INFO misc.py line 117 726] Train: [10/20][256/510] Data 3.113 (3.954) Batch 29.745 (28.402) Remain 42:14:26 loss: 0.2549 loss_seg: 0.1554 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:25:59,119 INFO misc.py line 117 726] Train: [10/20][257/510] Data 1.918 (3.946) Batch 17.271 (28.359) Remain 42:10:03 loss: 0.1688 loss_seg: 0.0852 loss_superpoint_edge: 0.0148 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:26:25,021 INFO misc.py line 117 726] Train: [10/20][258/510] Data 3.480 (3.945) Batch 25.901 (28.349) Remain 42:08:43 loss: 0.2495 loss_seg: 0.1531 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:26:48,463 INFO misc.py line 117 726] Train: [10/20][259/510] Data 2.673 (3.940) Batch 23.442 (28.330) Remain 42:06:32 loss: 0.2621 loss_seg: 0.1583 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:27:20,157 INFO misc.py line 117 726] Train: [10/20][260/510] Data 3.831 (3.939) Batch 31.693 (28.343) Remain 42:07:13 loss: 0.2161 loss_seg: 0.1231 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:27:43,498 INFO misc.py line 117 726] Train: [10/20][261/510] Data 2.646 (3.934) Batch 23.341 (28.323) Remain 42:05:01 loss: 0.2281 loss_seg: 0.1326 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:28:11,621 INFO misc.py line 117 726] Train: [10/20][262/510] Data 4.010 (3.934) Batch 28.124 (28.323) Remain 42:04:29 loss: 0.2735 loss_seg: 0.1654 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:28:30,220 INFO misc.py line 117 726] Train: [10/20][263/510] Data 2.055 (3.927) Batch 18.599 (28.285) Remain 42:00:41 loss: 0.2488 loss_seg: 0.1528 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:29:00,883 INFO misc.py line 117 726] Train: [10/20][264/510] Data 2.928 (3.923) Batch 30.663 (28.294) Remain 42:01:01 loss: 0.2125 loss_seg: 0.1251 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:29:39,533 INFO misc.py line 117 726] Train: [10/20][265/510] Data 8.069 (3.939) Batch 38.650 (28.334) Remain 42:04:04 loss: 0.3247 loss_seg: 0.2120 loss_superpoint_edge: 0.0458 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:30:04,560 INFO misc.py line 117 726] Train: [10/20][266/510] Data 4.851 (3.943) Batch 25.026 (28.321) Remain 42:02:29 loss: 0.2438 loss_seg: 0.1454 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:30:30,015 INFO misc.py line 117 726] Train: [10/20][267/510] Data 2.253 (3.936) Batch 25.455 (28.310) Remain 42:01:02 loss: 0.2410 loss_seg: 0.1467 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:31:05,795 INFO misc.py line 117 726] Train: [10/20][268/510] Data 5.349 (3.942) Batch 35.780 (28.339) Remain 42:03:04 loss: 0.2048 loss_seg: 0.1179 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:31:35,710 INFO misc.py line 117 726] Train: [10/20][269/510] Data 2.852 (3.938) Batch 29.915 (28.345) Remain 42:03:08 loss: 0.2214 loss_seg: 0.1293 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:31:53,431 INFO misc.py line 117 726] Train: [10/20][270/510] Data 1.669 (3.929) Batch 17.722 (28.305) Remain 41:59:07 loss: 0.3213 loss_seg: 0.2064 loss_superpoint_edge: 0.0444 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:32:29,728 INFO misc.py line 117 726] Train: [10/20][271/510] Data 4.849 (3.932) Batch 36.296 (28.335) Remain 42:01:18 loss: 0.2754 loss_seg: 0.1695 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:32:52,851 INFO misc.py line 117 726] Train: [10/20][272/510] Data 4.853 (3.936) Batch 23.124 (28.315) Remain 41:59:06 loss: 0.2567 loss_seg: 0.1609 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:33:13,569 INFO misc.py line 117 726] Train: [10/20][273/510] Data 2.619 (3.931) Batch 20.718 (28.287) Remain 41:56:08 loss: 0.3141 loss_seg: 0.2055 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:33:36,660 INFO misc.py line 117 726] Train: [10/20][274/510] Data 3.433 (3.929) Batch 23.091 (28.268) Remain 41:53:57 loss: 0.2116 loss_seg: 0.1209 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:34:04,347 INFO misc.py line 117 726] Train: [10/20][275/510] Data 3.361 (3.927) Batch 27.687 (28.266) Remain 41:53:17 loss: 0.2789 loss_seg: 0.1817 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0316 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:34:28,687 INFO misc.py line 117 726] Train: [10/20][276/510] Data 2.358 (3.921) Batch 24.340 (28.251) Remain 41:51:32 loss: 0.2506 loss_seg: 0.1542 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:35:07,790 INFO misc.py line 117 726] Train: [10/20][277/510] Data 10.601 (3.946) Batch 39.103 (28.291) Remain 41:54:35 loss: 0.2056 loss_seg: 0.1148 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:35:33,139 INFO misc.py line 117 726] Train: [10/20][278/510] Data 2.784 (3.941) Batch 25.349 (28.280) Remain 41:53:10 loss: 0.2898 loss_seg: 0.1806 loss_superpoint_edge: 0.0430 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:36:04,952 INFO misc.py line 117 726] Train: [10/20][279/510] Data 5.148 (3.946) Batch 31.813 (28.293) Remain 41:53:50 loss: 0.2647 loss_seg: 0.1639 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:36:36,325 INFO misc.py line 117 726] Train: [10/20][280/510] Data 3.227 (3.943) Batch 31.373 (28.304) Remain 41:54:21 loss: 0.2074 loss_seg: 0.1180 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:37:02,316 INFO misc.py line 117 726] Train: [10/20][281/510] Data 4.773 (3.946) Batch 25.991 (28.296) Remain 41:53:08 loss: 0.2450 loss_seg: 0.1450 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:37:30,678 INFO misc.py line 117 726] Train: [10/20][282/510] Data 4.038 (3.947) Batch 28.362 (28.296) Remain 41:52:41 loss: 0.3067 loss_seg: 0.2035 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:37:55,256 INFO misc.py line 117 726] Train: [10/20][283/510] Data 3.276 (3.944) Batch 24.579 (28.283) Remain 41:51:02 loss: 0.2419 loss_seg: 0.1436 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:38:30,322 INFO misc.py line 117 726] Train: [10/20][284/510] Data 4.629 (3.947) Batch 35.066 (28.307) Remain 41:52:43 loss: 0.2092 loss_seg: 0.1220 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:39:06,745 INFO misc.py line 117 726] Train: [10/20][285/510] Data 6.474 (3.956) Batch 36.423 (28.336) Remain 41:54:47 loss: 0.3608 loss_seg: 0.2506 loss_superpoint_edge: 0.0437 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:39:40,710 INFO misc.py line 117 726] Train: [10/20][286/510] Data 6.533 (3.965) Batch 33.965 (28.356) Remain 41:56:05 loss: 0.2031 loss_seg: 0.1138 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:40:11,224 INFO misc.py line 117 726] Train: [10/20][287/510] Data 3.014 (3.961) Batch 30.514 (28.363) Remain 41:56:17 loss: 0.2563 loss_seg: 0.1648 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:40:39,545 INFO misc.py line 117 726] Train: [10/20][288/510] Data 2.999 (3.958) Batch 28.321 (28.363) Remain 41:55:48 loss: 0.2456 loss_seg: 0.1493 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:41:01,521 INFO misc.py line 117 726] Train: [10/20][289/510] Data 2.346 (3.952) Batch 21.976 (28.341) Remain 41:53:21 loss: 0.1956 loss_seg: 0.1101 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:41:19,136 INFO misc.py line 117 726] Train: [10/20][290/510] Data 2.136 (3.946) Batch 17.615 (28.303) Remain 41:49:34 loss: 0.2172 loss_seg: 0.1236 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:41:46,019 INFO misc.py line 117 726] Train: [10/20][291/510] Data 3.544 (3.945) Batch 26.883 (28.298) Remain 41:48:39 loss: 0.2091 loss_seg: 0.1240 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:42:09,949 INFO misc.py line 117 726] Train: [10/20][292/510] Data 2.866 (3.941) Batch 23.929 (28.283) Remain 41:46:50 loss: 0.3112 loss_seg: 0.2019 loss_superpoint_edge: 0.0427 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:42:39,244 INFO misc.py line 117 726] Train: [10/20][293/510] Data 3.238 (3.938) Batch 29.296 (28.287) Remain 41:46:41 loss: 0.2607 loss_seg: 0.1574 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:43:18,274 INFO misc.py line 117 726] Train: [10/20][294/510] Data 6.845 (3.948) Batch 39.030 (28.324) Remain 41:49:29 loss: 0.3102 loss_seg: 0.2047 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:43:49,891 INFO misc.py line 117 726] Train: [10/20][295/510] Data 3.420 (3.947) Batch 31.618 (28.335) Remain 41:50:00 loss: 0.2939 loss_seg: 0.1951 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:44:12,404 INFO misc.py line 117 726] Train: [10/20][296/510] Data 3.145 (3.944) Batch 22.513 (28.315) Remain 41:47:46 loss: 0.3156 loss_seg: 0.2182 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:44:33,202 INFO misc.py line 117 726] Train: [10/20][297/510] Data 2.570 (3.939) Batch 20.798 (28.290) Remain 41:45:02 loss: 0.3791 loss_seg: 0.2715 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:45:05,618 INFO misc.py line 117 726] Train: [10/20][298/510] Data 4.158 (3.940) Batch 32.416 (28.304) Remain 41:45:48 loss: 0.2825 loss_seg: 0.1798 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:45:26,696 INFO misc.py line 117 726] Train: [10/20][299/510] Data 2.650 (3.936) Batch 21.078 (28.279) Remain 41:43:10 loss: 0.2505 loss_seg: 0.1512 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:45:59,119 INFO misc.py line 117 726] Train: [10/20][300/510] Data 4.328 (3.937) Batch 32.423 (28.293) Remain 41:43:56 loss: 0.2575 loss_seg: 0.1577 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:45:59,119 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 06:46:28,330 INFO misc.py line 117 726] Train: [10/20][301/510] Data 5.814 (3.943) Batch 29.211 (28.296) Remain 41:43:44 loss: 0.2168 loss_seg: 0.1270 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:46:53,597 INFO misc.py line 117 726] Train: [10/20][302/510] Data 2.762 (3.939) Batch 25.267 (28.286) Remain 41:42:22 loss: 0.1905 loss_seg: 0.1001 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:47:20,612 INFO misc.py line 117 726] Train: [10/20][303/510] Data 3.128 (3.937) Batch 27.016 (28.282) Remain 41:41:31 loss: 0.2179 loss_seg: 0.1273 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:47:48,635 INFO misc.py line 117 726] Train: [10/20][304/510] Data 2.687 (3.932) Batch 28.023 (28.281) Remain 41:40:58 loss: 0.1910 loss_seg: 0.1023 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:48:15,087 INFO misc.py line 117 726] Train: [10/20][305/510] Data 4.098 (3.933) Batch 26.452 (28.275) Remain 41:39:58 loss: 0.2454 loss_seg: 0.1562 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:48:49,668 INFO misc.py line 117 726] Train: [10/20][306/510] Data 4.546 (3.935) Batch 34.580 (28.296) Remain 41:41:20 loss: 0.2450 loss_seg: 0.1497 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:49:27,124 INFO misc.py line 117 726] Train: [10/20][307/510] Data 5.301 (3.939) Batch 37.457 (28.326) Remain 41:43:32 loss: 0.2581 loss_seg: 0.1680 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:49:48,392 INFO misc.py line 117 726] Train: [10/20][308/510] Data 2.395 (3.934) Batch 21.267 (28.303) Remain 41:41:01 loss: 0.2902 loss_seg: 0.1808 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:50:14,838 INFO misc.py line 117 726] Train: [10/20][309/510] Data 3.493 (3.933) Batch 26.446 (28.297) Remain 41:40:00 loss: 0.2692 loss_seg: 0.1683 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:50:46,464 INFO misc.py line 117 726] Train: [10/20][310/510] Data 4.457 (3.935) Batch 31.626 (28.308) Remain 41:40:29 loss: 0.2460 loss_seg: 0.1501 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:51:18,362 INFO misc.py line 117 726] Train: [10/20][311/510] Data 3.244 (3.932) Batch 31.898 (28.319) Remain 41:41:03 loss: 0.2726 loss_seg: 0.1766 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:51:46,453 INFO misc.py line 117 726] Train: [10/20][312/510] Data 5.951 (3.939) Batch 28.092 (28.318) Remain 41:40:31 loss: 0.3327 loss_seg: 0.2174 loss_superpoint_edge: 0.0461 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:52:20,166 INFO misc.py line 117 726] Train: [10/20][313/510] Data 4.270 (3.940) Batch 33.713 (28.336) Remain 41:41:34 loss: 0.2528 loss_seg: 0.1559 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:52:50,450 INFO misc.py line 117 726] Train: [10/20][314/510] Data 2.229 (3.935) Batch 30.284 (28.342) Remain 41:41:39 loss: 0.2607 loss_seg: 0.1630 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:53:18,441 INFO misc.py line 117 726] Train: [10/20][315/510] Data 2.549 (3.930) Batch 27.990 (28.341) Remain 41:41:05 loss: 0.2191 loss_seg: 0.1244 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:53:43,240 INFO misc.py line 117 726] Train: [10/20][316/510] Data 4.049 (3.930) Batch 24.800 (28.330) Remain 41:39:37 loss: 0.2768 loss_seg: 0.1764 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:54:13,194 INFO misc.py line 117 726] Train: [10/20][317/510] Data 5.189 (3.934) Batch 29.954 (28.335) Remain 41:39:36 loss: 0.2915 loss_seg: 0.1900 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:54:45,363 INFO misc.py line 117 726] Train: [10/20][318/510] Data 4.283 (3.936) Batch 32.169 (28.347) Remain 41:40:12 loss: 0.3756 loss_seg: 0.2660 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:55:07,122 INFO misc.py line 117 726] Train: [10/20][319/510] Data 2.780 (3.932) Batch 21.760 (28.326) Remain 41:37:53 loss: 0.2222 loss_seg: 0.1324 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:55:43,839 INFO misc.py line 117 726] Train: [10/20][320/510] Data 4.702 (3.934) Batch 36.717 (28.353) Remain 41:39:45 loss: 0.2009 loss_seg: 0.1148 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:56:07,590 INFO misc.py line 117 726] Train: [10/20][321/510] Data 1.980 (3.928) Batch 23.750 (28.338) Remain 41:38:00 loss: 0.2122 loss_seg: 0.1210 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:56:28,631 INFO misc.py line 117 726] Train: [10/20][322/510] Data 2.466 (3.924) Batch 21.041 (28.315) Remain 41:35:31 loss: 0.2481 loss_seg: 0.1497 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:56:51,847 INFO misc.py line 117 726] Train: [10/20][323/510] Data 2.562 (3.919) Batch 23.217 (28.299) Remain 41:33:38 loss: 0.2612 loss_seg: 0.1633 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:57:16,332 INFO misc.py line 117 726] Train: [10/20][324/510] Data 2.831 (3.916) Batch 24.484 (28.287) Remain 41:32:07 loss: 0.1824 loss_seg: 0.0994 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:57:46,417 INFO misc.py line 117 726] Train: [10/20][325/510] Data 6.369 (3.924) Batch 30.085 (28.293) Remain 41:32:08 loss: 0.3072 loss_seg: 0.2069 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:58:13,360 INFO misc.py line 117 726] Train: [10/20][326/510] Data 2.552 (3.919) Batch 26.943 (28.289) Remain 41:31:18 loss: 0.1877 loss_seg: 0.1047 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:58:36,902 INFO misc.py line 117 726] Train: [10/20][327/510] Data 2.520 (3.915) Batch 23.540 (28.274) Remain 41:29:32 loss: 0.1957 loss_seg: 0.1071 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:59:08,610 INFO misc.py line 117 726] Train: [10/20][328/510] Data 2.899 (3.912) Batch 31.710 (28.285) Remain 41:30:00 loss: 0.2520 loss_seg: 0.1550 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 06:59:34,141 INFO misc.py line 117 726] Train: [10/20][329/510] Data 4.312 (3.913) Batch 25.531 (28.276) Remain 41:28:47 loss: 0.2742 loss_seg: 0.1845 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:00:08,430 INFO misc.py line 117 726] Train: [10/20][330/510] Data 3.968 (3.913) Batch 34.289 (28.295) Remain 41:29:56 loss: 0.2349 loss_seg: 0.1408 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:00:40,446 INFO misc.py line 117 726] Train: [10/20][331/510] Data 3.637 (3.912) Batch 32.016 (28.306) Remain 41:30:27 loss: 0.2125 loss_seg: 0.1230 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:01:08,109 INFO misc.py line 117 726] Train: [10/20][332/510] Data 2.813 (3.909) Batch 27.663 (28.304) Remain 41:29:49 loss: 0.2160 loss_seg: 0.1286 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:01:28,266 INFO misc.py line 117 726] Train: [10/20][333/510] Data 2.475 (3.905) Batch 20.157 (28.279) Remain 41:27:10 loss: 0.3178 loss_seg: 0.2076 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:01:54,410 INFO misc.py line 117 726] Train: [10/20][334/510] Data 4.409 (3.906) Batch 26.144 (28.273) Remain 41:26:08 loss: 0.2801 loss_seg: 0.1878 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:02:20,745 INFO misc.py line 117 726] Train: [10/20][335/510] Data 5.172 (3.910) Batch 26.335 (28.267) Remain 41:25:09 loss: 0.2549 loss_seg: 0.1589 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:02:48,214 INFO misc.py line 117 726] Train: [10/20][336/510] Data 2.876 (3.907) Batch 27.469 (28.265) Remain 41:24:28 loss: 0.2038 loss_seg: 0.1170 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:03:10,728 INFO misc.py line 117 726] Train: [10/20][337/510] Data 2.817 (3.904) Batch 22.514 (28.248) Remain 41:22:29 loss: 0.3251 loss_seg: 0.2284 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:03:40,149 INFO misc.py line 117 726] Train: [10/20][338/510] Data 2.641 (3.900) Batch 29.420 (28.251) Remain 41:22:19 loss: 0.2223 loss_seg: 0.1316 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:03:58,419 INFO misc.py line 117 726] Train: [10/20][339/510] Data 2.639 (3.896) Batch 18.270 (28.221) Remain 41:19:14 loss: 0.2035 loss_seg: 0.1109 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:04:31,007 INFO misc.py line 117 726] Train: [10/20][340/510] Data 4.567 (3.898) Batch 32.588 (28.234) Remain 41:19:54 loss: 0.2362 loss_seg: 0.1459 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:05:01,526 INFO misc.py line 117 726] Train: [10/20][341/510] Data 3.557 (3.897) Batch 30.519 (28.241) Remain 41:20:01 loss: 0.2579 loss_seg: 0.1629 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:05:23,131 INFO misc.py line 117 726] Train: [10/20][342/510] Data 2.900 (3.894) Batch 21.605 (28.221) Remain 41:17:50 loss: 0.2628 loss_seg: 0.1601 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:05:55,110 INFO misc.py line 117 726] Train: [10/20][343/510] Data 3.723 (3.894) Batch 31.979 (28.233) Remain 41:18:20 loss: 0.1883 loss_seg: 0.1040 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:06:24,652 INFO misc.py line 117 726] Train: [10/20][344/510] Data 3.476 (3.893) Batch 29.542 (28.236) Remain 41:18:12 loss: 0.3052 loss_seg: 0.2115 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:06:57,040 INFO misc.py line 117 726] Train: [10/20][345/510] Data 3.478 (3.891) Batch 32.387 (28.248) Remain 41:18:48 loss: 0.2473 loss_seg: 0.1552 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:07:25,308 INFO misc.py line 117 726] Train: [10/20][346/510] Data 3.211 (3.889) Batch 28.267 (28.249) Remain 41:18:20 loss: 0.3369 loss_seg: 0.2274 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:07:55,673 INFO misc.py line 117 726] Train: [10/20][347/510] Data 3.342 (3.888) Batch 30.367 (28.255) Remain 41:18:24 loss: 0.2053 loss_seg: 0.1153 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:08:22,898 INFO misc.py line 117 726] Train: [10/20][348/510] Data 2.589 (3.884) Batch 27.224 (28.252) Remain 41:17:40 loss: 0.2416 loss_seg: 0.1449 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:08:54,236 INFO misc.py line 117 726] Train: [10/20][349/510] Data 4.234 (3.885) Batch 31.339 (28.261) Remain 41:17:59 loss: 0.2122 loss_seg: 0.1204 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:09:20,734 INFO misc.py line 117 726] Train: [10/20][350/510] Data 3.534 (3.884) Batch 26.497 (28.256) Remain 41:17:04 loss: 0.2430 loss_seg: 0.1509 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:09:20,736 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 07:09:52,161 INFO misc.py line 117 726] Train: [10/20][351/510] Data 5.029 (3.887) Batch 31.427 (28.265) Remain 41:17:23 loss: 0.2914 loss_seg: 0.1913 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:10:20,117 INFO misc.py line 117 726] Train: [10/20][352/510] Data 4.783 (3.890) Batch 27.956 (28.264) Remain 41:16:50 loss: 0.2179 loss_seg: 0.1250 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:10:37,178 INFO misc.py line 117 726] Train: [10/20][353/510] Data 2.579 (3.886) Batch 17.062 (28.232) Remain 41:13:34 loss: 0.1876 loss_seg: 0.1000 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:11:01,390 INFO misc.py line 117 726] Train: [10/20][354/510] Data 2.759 (3.883) Batch 24.212 (28.220) Remain 41:12:05 loss: 0.2346 loss_seg: 0.1407 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:11:33,645 INFO misc.py line 117 726] Train: [10/20][355/510] Data 3.706 (3.882) Batch 32.255 (28.232) Remain 41:12:38 loss: 0.2586 loss_seg: 0.1570 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:11:59,320 INFO misc.py line 117 726] Train: [10/20][356/510] Data 2.401 (3.878) Batch 25.675 (28.225) Remain 41:11:31 loss: 0.2075 loss_seg: 0.1178 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:12:31,437 INFO misc.py line 117 726] Train: [10/20][357/510] Data 3.586 (3.877) Batch 32.117 (28.236) Remain 41:12:01 loss: 0.2817 loss_seg: 0.1822 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:13:01,464 INFO misc.py line 117 726] Train: [10/20][358/510] Data 3.394 (3.876) Batch 30.027 (28.241) Remain 41:11:59 loss: 0.2403 loss_seg: 0.1428 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:13:32,680 INFO misc.py line 117 726] Train: [10/20][359/510] Data 3.860 (3.876) Batch 31.216 (28.249) Remain 41:12:15 loss: 0.2276 loss_seg: 0.1331 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:13:56,574 INFO misc.py line 117 726] Train: [10/20][360/510] Data 2.589 (3.872) Batch 23.894 (28.237) Remain 41:10:42 loss: 0.2490 loss_seg: 0.1537 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:14:29,916 INFO misc.py line 117 726] Train: [10/20][361/510] Data 3.866 (3.872) Batch 33.342 (28.251) Remain 41:11:29 loss: 0.3364 loss_seg: 0.2371 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:15:03,498 INFO misc.py line 117 726] Train: [10/20][362/510] Data 5.038 (3.876) Batch 33.582 (28.266) Remain 41:12:19 loss: 0.2482 loss_seg: 0.1552 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:15:29,391 INFO misc.py line 117 726] Train: [10/20][363/510] Data 3.458 (3.874) Batch 25.893 (28.259) Remain 41:11:16 loss: 0.2553 loss_seg: 0.1568 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:15:54,172 INFO misc.py line 117 726] Train: [10/20][364/510] Data 2.659 (3.871) Batch 24.781 (28.250) Remain 41:09:57 loss: 0.3230 loss_seg: 0.2280 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:16:18,422 INFO misc.py line 117 726] Train: [10/20][365/510] Data 2.617 (3.868) Batch 24.251 (28.239) Remain 41:08:31 loss: 0.2748 loss_seg: 0.1756 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:16:50,576 INFO misc.py line 117 726] Train: [10/20][366/510] Data 3.162 (3.866) Batch 32.154 (28.249) Remain 41:08:59 loss: 0.2278 loss_seg: 0.1362 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:17:18,337 INFO misc.py line 117 726] Train: [10/20][367/510] Data 2.901 (3.863) Batch 27.761 (28.248) Remain 41:08:24 loss: 0.3233 loss_seg: 0.2311 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:17:32,805 INFO misc.py line 117 726] Train: [10/20][368/510] Data 1.785 (3.857) Batch 14.468 (28.210) Remain 41:04:38 loss: 0.2834 loss_seg: 0.1745 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:17:52,285 INFO misc.py line 117 726] Train: [10/20][369/510] Data 2.506 (3.854) Batch 19.480 (28.186) Remain 41:02:04 loss: 0.2353 loss_seg: 0.1369 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:18:19,991 INFO misc.py line 117 726] Train: [10/20][370/510] Data 3.691 (3.853) Batch 27.706 (28.185) Remain 41:01:29 loss: 0.2105 loss_seg: 0.1214 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:18:45,474 INFO misc.py line 117 726] Train: [10/20][371/510] Data 2.691 (3.850) Batch 25.483 (28.178) Remain 41:00:23 loss: 0.1933 loss_seg: 0.1066 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:19:05,406 INFO misc.py line 117 726] Train: [10/20][372/510] Data 2.540 (3.846) Batch 19.932 (28.155) Remain 40:57:58 loss: 0.2426 loss_seg: 0.1462 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:19:19,884 INFO misc.py line 117 726] Train: [10/20][373/510] Data 1.702 (3.841) Batch 14.478 (28.118) Remain 40:54:16 loss: 0.3273 loss_seg: 0.2299 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:19:53,741 INFO misc.py line 117 726] Train: [10/20][374/510] Data 7.688 (3.851) Batch 33.857 (28.134) Remain 40:55:09 loss: 0.2164 loss_seg: 0.1225 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:20:26,657 INFO misc.py line 117 726] Train: [10/20][375/510] Data 5.027 (3.854) Batch 32.916 (28.147) Remain 40:55:48 loss: 0.2226 loss_seg: 0.1296 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:21:00,304 INFO misc.py line 117 726] Train: [10/20][376/510] Data 4.085 (3.855) Batch 33.647 (28.162) Remain 40:56:37 loss: 0.2158 loss_seg: 0.1264 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:21:24,239 INFO misc.py line 117 726] Train: [10/20][377/510] Data 4.223 (3.856) Batch 23.936 (28.150) Remain 40:55:10 loss: 0.2961 loss_seg: 0.1923 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:21:51,235 INFO misc.py line 117 726] Train: [10/20][378/510] Data 3.061 (3.854) Batch 26.996 (28.147) Remain 40:54:25 loss: 0.2162 loss_seg: 0.1259 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:22:16,879 INFO misc.py line 117 726] Train: [10/20][379/510] Data 3.240 (3.852) Batch 25.643 (28.140) Remain 40:53:22 loss: 0.2558 loss_seg: 0.1651 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:22:44,376 INFO misc.py line 117 726] Train: [10/20][380/510] Data 2.881 (3.849) Batch 27.498 (28.139) Remain 40:52:45 loss: 0.3380 loss_seg: 0.2375 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:23:04,863 INFO misc.py line 117 726] Train: [10/20][381/510] Data 3.815 (3.849) Batch 20.487 (28.119) Remain 40:50:31 loss: 0.3086 loss_seg: 0.2058 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:23:38,622 INFO misc.py line 117 726] Train: [10/20][382/510] Data 3.809 (3.849) Batch 33.759 (28.133) Remain 40:51:21 loss: 0.2319 loss_seg: 0.1425 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:24:09,979 INFO misc.py line 117 726] Train: [10/20][383/510] Data 4.855 (3.852) Batch 31.358 (28.142) Remain 40:51:37 loss: 0.2739 loss_seg: 0.1747 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:24:51,561 INFO misc.py line 117 726] Train: [10/20][384/510] Data 8.923 (3.865) Batch 41.581 (28.177) Remain 40:54:13 loss: 0.2817 loss_seg: 0.1889 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:25:17,897 INFO misc.py line 117 726] Train: [10/20][385/510] Data 3.978 (3.866) Batch 26.337 (28.172) Remain 40:53:20 loss: 0.2716 loss_seg: 0.1770 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:25:42,311 INFO misc.py line 117 726] Train: [10/20][386/510] Data 3.109 (3.864) Batch 24.414 (28.163) Remain 40:52:01 loss: 0.2057 loss_seg: 0.1159 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:26:13,831 INFO misc.py line 117 726] Train: [10/20][387/510] Data 3.478 (3.863) Batch 31.520 (28.171) Remain 40:52:18 loss: 0.2420 loss_seg: 0.1455 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:26:41,970 INFO misc.py line 117 726] Train: [10/20][388/510] Data 3.410 (3.861) Batch 28.139 (28.171) Remain 40:51:49 loss: 0.2102 loss_seg: 0.1224 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:27:06,269 INFO misc.py line 117 726] Train: [10/20][389/510] Data 2.502 (3.858) Batch 24.299 (28.161) Remain 40:50:29 loss: 0.1978 loss_seg: 0.1080 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:27:31,913 INFO misc.py line 117 726] Train: [10/20][390/510] Data 3.026 (3.856) Batch 25.644 (28.155) Remain 40:49:27 loss: 0.2116 loss_seg: 0.1211 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:28:03,644 INFO misc.py line 117 726] Train: [10/20][391/510] Data 3.946 (3.856) Batch 31.730 (28.164) Remain 40:49:47 loss: 0.2499 loss_seg: 0.1541 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:28:30,403 INFO misc.py line 117 726] Train: [10/20][392/510] Data 2.497 (3.852) Batch 26.759 (28.160) Remain 40:49:00 loss: 0.1517 loss_seg: 0.0710 loss_superpoint_edge: 0.0137 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:28:59,657 INFO misc.py line 117 726] Train: [10/20][393/510] Data 3.737 (3.852) Batch 29.255 (28.163) Remain 40:48:46 loss: 0.3293 loss_seg: 0.2274 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:29:35,933 INFO misc.py line 117 726] Train: [10/20][394/510] Data 5.245 (3.856) Batch 36.276 (28.184) Remain 40:50:06 loss: 0.2316 loss_seg: 0.1358 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:30:01,607 INFO misc.py line 117 726] Train: [10/20][395/510] Data 2.768 (3.853) Batch 25.674 (28.177) Remain 40:49:05 loss: 0.1986 loss_seg: 0.1084 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:30:33,498 INFO misc.py line 117 726] Train: [10/20][396/510] Data 2.976 (3.851) Batch 31.891 (28.187) Remain 40:49:26 loss: 0.2314 loss_seg: 0.1369 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:31:01,055 INFO misc.py line 117 726] Train: [10/20][397/510] Data 3.210 (3.849) Batch 27.556 (28.185) Remain 40:48:49 loss: 0.1821 loss_seg: 0.0972 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:31:20,011 INFO misc.py line 117 726] Train: [10/20][398/510] Data 2.236 (3.845) Batch 18.957 (28.162) Remain 40:46:19 loss: 0.2999 loss_seg: 0.1993 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:31:53,228 INFO misc.py line 117 726] Train: [10/20][399/510] Data 3.750 (3.845) Batch 33.217 (28.175) Remain 40:46:58 loss: 0.2169 loss_seg: 0.1269 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:32:28,247 INFO misc.py line 117 726] Train: [10/20][400/510] Data 7.120 (3.853) Batch 35.019 (28.192) Remain 40:47:59 loss: 0.2990 loss_seg: 0.1979 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:32:28,248 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 07:33:02,728 INFO misc.py line 117 726] Train: [10/20][401/510] Data 10.070 (3.869) Batch 34.481 (28.208) Remain 40:48:53 loss: 0.5883 loss_seg: 0.4228 loss_superpoint_edge: 0.0975 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:33:26,025 INFO misc.py line 117 726] Train: [10/20][402/510] Data 2.935 (3.866) Batch 23.297 (28.195) Remain 40:47:21 loss: 0.2236 loss_seg: 0.1318 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:33:48,433 INFO misc.py line 117 726] Train: [10/20][403/510] Data 2.935 (3.864) Batch 22.408 (28.181) Remain 40:45:38 loss: 0.3748 loss_seg: 0.2823 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:34:09,774 INFO misc.py line 117 726] Train: [10/20][404/510] Data 2.314 (3.860) Batch 21.341 (28.164) Remain 40:43:41 loss: 0.2779 loss_seg: 0.1744 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:34:37,515 INFO misc.py line 117 726] Train: [10/20][405/510] Data 3.816 (3.860) Batch 27.741 (28.163) Remain 40:43:07 loss: 0.2150 loss_seg: 0.1219 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:35:06,155 INFO misc.py line 117 726] Train: [10/20][406/510] Data 3.403 (3.859) Batch 28.641 (28.164) Remain 40:42:45 loss: 0.2290 loss_seg: 0.1354 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:35:31,734 INFO misc.py line 117 726] Train: [10/20][407/510] Data 3.410 (3.858) Batch 25.578 (28.158) Remain 40:41:44 loss: 0.3735 loss_seg: 0.2638 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:36:07,837 INFO misc.py line 117 726] Train: [10/20][408/510] Data 6.666 (3.865) Batch 36.103 (28.177) Remain 40:42:57 loss: 0.2886 loss_seg: 0.1823 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:36:32,082 INFO misc.py line 117 726] Train: [10/20][409/510] Data 2.887 (3.862) Batch 24.246 (28.168) Remain 40:41:39 loss: 0.3076 loss_seg: 0.2124 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:37:03,497 INFO misc.py line 117 726] Train: [10/20][410/510] Data 4.581 (3.864) Batch 31.414 (28.176) Remain 40:41:52 loss: 0.2555 loss_seg: 0.1597 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:37:25,922 INFO misc.py line 117 726] Train: [10/20][411/510] Data 2.096 (3.860) Batch 22.425 (28.161) Remain 40:40:11 loss: 0.2077 loss_seg: 0.1154 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:38:03,185 INFO misc.py line 117 726] Train: [10/20][412/510] Data 4.463 (3.861) Batch 37.263 (28.184) Remain 40:41:38 loss: 0.2726 loss_seg: 0.1725 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:38:28,254 INFO misc.py line 117 726] Train: [10/20][413/510] Data 2.732 (3.858) Batch 25.070 (28.176) Remain 40:40:31 loss: 0.3135 loss_seg: 0.2103 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:38:58,397 INFO misc.py line 117 726] Train: [10/20][414/510] Data 2.967 (3.856) Batch 30.143 (28.181) Remain 40:40:27 loss: 0.2174 loss_seg: 0.1234 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:39:36,115 INFO misc.py line 117 726] Train: [10/20][415/510] Data 6.534 (3.863) Batch 37.718 (28.204) Remain 40:41:59 loss: 0.2227 loss_seg: 0.1354 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:40:00,532 INFO misc.py line 117 726] Train: [10/20][416/510] Data 2.614 (3.860) Batch 24.417 (28.195) Remain 40:40:44 loss: 0.2479 loss_seg: 0.1538 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:40:22,238 INFO misc.py line 117 726] Train: [10/20][417/510] Data 1.745 (3.855) Batch 21.707 (28.179) Remain 40:38:54 loss: 0.1897 loss_seg: 0.1030 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:40:56,773 INFO misc.py line 117 726] Train: [10/20][418/510] Data 3.888 (3.855) Batch 34.534 (28.194) Remain 40:39:45 loss: 0.1759 loss_seg: 0.0930 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:41:17,177 INFO misc.py line 117 726] Train: [10/20][419/510] Data 2.600 (3.852) Batch 20.404 (28.176) Remain 40:37:40 loss: 0.2142 loss_seg: 0.1269 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:41:53,276 INFO misc.py line 117 726] Train: [10/20][420/510] Data 8.529 (3.863) Batch 36.100 (28.195) Remain 40:38:50 loss: 0.2069 loss_seg: 0.1187 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:42:22,206 INFO misc.py line 117 726] Train: [10/20][421/510] Data 3.229 (3.861) Batch 28.930 (28.197) Remain 40:38:31 loss: 0.2209 loss_seg: 0.1313 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:42:47,401 INFO misc.py line 117 726] Train: [10/20][422/510] Data 2.654 (3.858) Batch 25.194 (28.189) Remain 40:37:26 loss: 0.2806 loss_seg: 0.1738 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:43:20,460 INFO misc.py line 117 726] Train: [10/20][423/510] Data 3.816 (3.858) Batch 33.059 (28.201) Remain 40:37:58 loss: 0.2482 loss_seg: 0.1559 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:43:44,237 INFO misc.py line 117 726] Train: [10/20][424/510] Data 2.629 (3.855) Batch 23.777 (28.190) Remain 40:36:35 loss: 0.2411 loss_seg: 0.1473 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:44:14,129 INFO misc.py line 117 726] Train: [10/20][425/510] Data 3.429 (3.854) Batch 29.892 (28.194) Remain 40:36:28 loss: 0.2393 loss_seg: 0.1422 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:44:32,700 INFO misc.py line 117 726] Train: [10/20][426/510] Data 2.142 (3.850) Batch 18.571 (28.172) Remain 40:34:02 loss: 0.1935 loss_seg: 0.1048 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:45:07,521 INFO misc.py line 117 726] Train: [10/20][427/510] Data 4.124 (3.851) Batch 34.821 (28.187) Remain 40:34:55 loss: 0.2691 loss_seg: 0.1673 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:45:30,921 INFO misc.py line 117 726] Train: [10/20][428/510] Data 2.531 (3.848) Batch 23.400 (28.176) Remain 40:33:28 loss: 0.2059 loss_seg: 0.1143 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:46:04,842 INFO misc.py line 117 726] Train: [10/20][429/510] Data 4.220 (3.849) Batch 33.921 (28.190) Remain 40:34:10 loss: 0.2250 loss_seg: 0.1377 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:46:43,799 INFO misc.py line 117 726] Train: [10/20][430/510] Data 8.249 (3.859) Batch 38.957 (28.215) Remain 40:35:52 loss: 0.2780 loss_seg: 0.1855 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:47:12,284 INFO misc.py line 117 726] Train: [10/20][431/510] Data 3.379 (3.858) Batch 28.486 (28.215) Remain 40:35:27 loss: 0.2246 loss_seg: 0.1284 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:47:42,053 INFO misc.py line 117 726] Train: [10/20][432/510] Data 4.083 (3.859) Batch 29.769 (28.219) Remain 40:35:18 loss: 0.2340 loss_seg: 0.1417 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:48:06,169 INFO misc.py line 117 726] Train: [10/20][433/510] Data 2.669 (3.856) Batch 24.116 (28.210) Remain 40:34:00 loss: 0.2181 loss_seg: 0.1231 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:48:31,198 INFO misc.py line 117 726] Train: [10/20][434/510] Data 2.624 (3.853) Batch 25.028 (28.202) Remain 40:32:54 loss: 0.2355 loss_seg: 0.1389 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:48:54,097 INFO misc.py line 117 726] Train: [10/20][435/510] Data 2.339 (3.849) Batch 22.899 (28.190) Remain 40:31:22 loss: 0.2656 loss_seg: 0.1717 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:49:15,114 INFO misc.py line 117 726] Train: [10/20][436/510] Data 2.007 (3.845) Batch 21.017 (28.173) Remain 40:29:28 loss: 0.3622 loss_seg: 0.2573 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:49:43,515 INFO misc.py line 117 726] Train: [10/20][437/510] Data 3.021 (3.843) Batch 28.402 (28.174) Remain 40:29:03 loss: 0.1962 loss_seg: 0.1100 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:50:22,693 INFO misc.py line 117 726] Train: [10/20][438/510] Data 7.763 (3.852) Batch 39.177 (28.199) Remain 40:30:46 loss: 0.3196 loss_seg: 0.2287 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:50:42,060 INFO misc.py line 117 726] Train: [10/20][439/510] Data 2.172 (3.848) Batch 19.367 (28.179) Remain 40:28:33 loss: 0.2323 loss_seg: 0.1416 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:51:10,021 INFO misc.py line 117 726] Train: [10/20][440/510] Data 4.518 (3.850) Batch 27.961 (28.178) Remain 40:28:02 loss: 0.2906 loss_seg: 0.1902 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:51:37,136 INFO misc.py line 117 726] Train: [10/20][441/510] Data 3.672 (3.850) Batch 27.115 (28.176) Remain 40:27:21 loss: 0.2351 loss_seg: 0.1335 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:51:58,232 INFO misc.py line 117 726] Train: [10/20][442/510] Data 2.714 (3.847) Batch 21.095 (28.160) Remain 40:25:30 loss: 0.2386 loss_seg: 0.1457 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:52:27,457 INFO misc.py line 117 726] Train: [10/20][443/510] Data 5.197 (3.850) Batch 29.225 (28.162) Remain 40:25:14 loss: 0.2213 loss_seg: 0.1258 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:52:44,007 INFO misc.py line 117 726] Train: [10/20][444/510] Data 1.893 (3.846) Batch 16.550 (28.136) Remain 40:22:30 loss: 0.2620 loss_seg: 0.1715 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:53:08,623 INFO misc.py line 117 726] Train: [10/20][445/510] Data 2.862 (3.843) Batch 24.616 (28.128) Remain 40:21:20 loss: 0.2511 loss_seg: 0.1573 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:53:36,833 INFO misc.py line 117 726] Train: [10/20][446/510] Data 5.107 (3.846) Batch 28.211 (28.128) Remain 40:20:53 loss: 0.2827 loss_seg: 0.1849 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:54:03,972 INFO misc.py line 117 726] Train: [10/20][447/510] Data 2.694 (3.844) Batch 27.138 (28.126) Remain 40:20:14 loss: 0.2275 loss_seg: 0.1329 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:54:33,965 INFO misc.py line 117 726] Train: [10/20][448/510] Data 2.810 (3.841) Batch 29.993 (28.130) Remain 40:20:07 loss: 0.2020 loss_seg: 0.1123 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:54:52,921 INFO misc.py line 117 726] Train: [10/20][449/510] Data 2.330 (3.838) Batch 18.957 (28.110) Remain 40:17:53 loss: 0.2787 loss_seg: 0.1778 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:55:26,211 INFO misc.py line 117 726] Train: [10/20][450/510] Data 4.835 (3.840) Batch 33.290 (28.121) Remain 40:18:25 loss: 0.2545 loss_seg: 0.1540 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:55:26,212 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 07:56:04,359 INFO misc.py line 117 726] Train: [10/20][451/510] Data 8.054 (3.850) Batch 38.148 (28.144) Remain 40:19:52 loss: 0.2690 loss_seg: 0.1714 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:56:23,732 INFO misc.py line 117 726] Train: [10/20][452/510] Data 2.668 (3.847) Batch 19.373 (28.124) Remain 40:17:43 loss: 0.1790 loss_seg: 0.0909 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:56:50,504 INFO misc.py line 117 726] Train: [10/20][453/510] Data 3.985 (3.847) Batch 26.772 (28.121) Remain 40:16:59 loss: 0.2925 loss_seg: 0.1848 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:57:22,122 INFO misc.py line 117 726] Train: [10/20][454/510] Data 3.964 (3.847) Batch 31.618 (28.129) Remain 40:17:11 loss: 0.2686 loss_seg: 0.1688 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:57:44,566 INFO misc.py line 117 726] Train: [10/20][455/510] Data 3.569 (3.847) Batch 22.444 (28.116) Remain 40:15:38 loss: 0.2432 loss_seg: 0.1438 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:58:12,459 INFO misc.py line 117 726] Train: [10/20][456/510] Data 3.021 (3.845) Batch 27.893 (28.116) Remain 40:15:08 loss: 0.2700 loss_seg: 0.1645 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:58:37,371 INFO misc.py line 117 726] Train: [10/20][457/510] Data 2.691 (3.842) Batch 24.912 (28.109) Remain 40:14:03 loss: 0.2261 loss_seg: 0.1370 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:59:14,375 INFO misc.py line 117 726] Train: [10/20][458/510] Data 4.364 (3.844) Batch 37.004 (28.128) Remain 40:15:16 loss: 0.2733 loss_seg: 0.1740 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 07:59:41,083 INFO misc.py line 117 726] Train: [10/20][459/510] Data 2.868 (3.841) Batch 26.707 (28.125) Remain 40:14:32 loss: 0.2582 loss_seg: 0.1591 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:00:11,770 INFO misc.py line 117 726] Train: [10/20][460/510] Data 4.141 (3.842) Batch 30.688 (28.131) Remain 40:14:32 loss: 0.2174 loss_seg: 0.1223 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:00:32,875 INFO misc.py line 117 726] Train: [10/20][461/510] Data 1.979 (3.838) Batch 21.105 (28.115) Remain 40:12:45 loss: 0.2238 loss_seg: 0.1279 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:00:57,399 INFO misc.py line 117 726] Train: [10/20][462/510] Data 2.313 (3.835) Batch 24.523 (28.107) Remain 40:11:37 loss: 0.2350 loss_seg: 0.1374 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:01:29,030 INFO misc.py line 117 726] Train: [10/20][463/510] Data 3.165 (3.833) Batch 31.632 (28.115) Remain 40:11:48 loss: 0.2577 loss_seg: 0.1637 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:02:02,487 INFO misc.py line 117 726] Train: [10/20][464/510] Data 4.598 (3.835) Batch 33.457 (28.127) Remain 40:12:20 loss: 0.2715 loss_seg: 0.1738 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:02:27,864 INFO misc.py line 117 726] Train: [10/20][465/510] Data 3.395 (3.834) Batch 25.377 (28.121) Remain 40:11:21 loss: 0.2321 loss_seg: 0.1432 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:02:51,365 INFO misc.py line 117 726] Train: [10/20][466/510] Data 3.047 (3.832) Batch 23.500 (28.111) Remain 40:10:02 loss: 0.2618 loss_seg: 0.1660 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:03:16,688 INFO misc.py line 117 726] Train: [10/20][467/510] Data 2.407 (3.829) Batch 25.323 (28.105) Remain 40:09:03 loss: 0.2009 loss_seg: 0.1112 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:03:38,215 INFO misc.py line 117 726] Train: [10/20][468/510] Data 2.314 (3.826) Batch 21.527 (28.091) Remain 40:07:22 loss: 0.2870 loss_seg: 0.1911 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:04:16,818 INFO misc.py line 117 726] Train: [10/20][469/510] Data 6.057 (3.831) Batch 38.603 (28.113) Remain 40:08:50 loss: 0.2965 loss_seg: 0.1980 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:04:43,301 INFO misc.py line 117 726] Train: [10/20][470/510] Data 2.464 (3.828) Batch 26.483 (28.110) Remain 40:08:03 loss: 0.2579 loss_seg: 0.1575 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:05:12,232 INFO misc.py line 117 726] Train: [10/20][471/510] Data 2.684 (3.825) Batch 28.931 (28.111) Remain 40:07:44 loss: 0.2583 loss_seg: 0.1541 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:05:43,047 INFO misc.py line 117 726] Train: [10/20][472/510] Data 3.851 (3.825) Batch 30.814 (28.117) Remain 40:07:46 loss: 0.2605 loss_seg: 0.1603 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:06:09,733 INFO misc.py line 117 726] Train: [10/20][473/510] Data 2.909 (3.823) Batch 26.686 (28.114) Remain 40:07:02 loss: 0.2190 loss_seg: 0.1295 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:06:33,775 INFO misc.py line 117 726] Train: [10/20][474/510] Data 2.285 (3.820) Batch 24.042 (28.106) Remain 40:05:50 loss: 0.2358 loss_seg: 0.1415 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:06:54,099 INFO misc.py line 117 726] Train: [10/20][475/510] Data 2.916 (3.818) Batch 20.324 (28.089) Remain 40:03:57 loss: 0.2111 loss_seg: 0.1185 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:07:25,106 INFO misc.py line 117 726] Train: [10/20][476/510] Data 3.651 (3.818) Batch 31.007 (28.095) Remain 40:04:00 loss: 0.2290 loss_seg: 0.1340 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:07:54,776 INFO misc.py line 117 726] Train: [10/20][477/510] Data 2.353 (3.815) Batch 29.670 (28.099) Remain 40:03:49 loss: 0.1666 loss_seg: 0.0838 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:08:21,632 INFO misc.py line 117 726] Train: [10/20][478/510] Data 2.822 (3.813) Batch 26.857 (28.096) Remain 40:03:08 loss: 0.1936 loss_seg: 0.1061 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:08:46,414 INFO misc.py line 117 726] Train: [10/20][479/510] Data 2.442 (3.810) Batch 24.782 (28.089) Remain 40:02:04 loss: 0.2358 loss_seg: 0.1372 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:09:14,408 INFO misc.py line 117 726] Train: [10/20][480/510] Data 3.333 (3.809) Batch 27.994 (28.089) Remain 40:01:35 loss: 0.3103 loss_seg: 0.2118 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:09:34,541 INFO misc.py line 117 726] Train: [10/20][481/510] Data 2.071 (3.805) Batch 20.134 (28.072) Remain 39:59:42 loss: 0.2771 loss_seg: 0.1832 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:10:11,618 INFO misc.py line 117 726] Train: [10/20][482/510] Data 6.094 (3.810) Batch 37.076 (28.091) Remain 40:00:50 loss: 0.2810 loss_seg: 0.1894 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:10:42,961 INFO misc.py line 117 726] Train: [10/20][483/510] Data 5.476 (3.813) Batch 31.343 (28.098) Remain 40:00:56 loss: 0.3242 loss_seg: 0.2142 loss_superpoint_edge: 0.0412 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:11:05,621 INFO misc.py line 117 726] Train: [10/20][484/510] Data 2.670 (3.811) Batch 22.660 (28.086) Remain 39:59:30 loss: 0.3141 loss_seg: 0.2160 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:11:36,742 INFO misc.py line 117 726] Train: [10/20][485/510] Data 5.523 (3.815) Batch 31.121 (28.093) Remain 39:59:35 loss: 0.1977 loss_seg: 0.1118 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:11:56,503 INFO misc.py line 117 726] Train: [10/20][486/510] Data 2.706 (3.812) Batch 19.761 (28.075) Remain 39:57:38 loss: 0.2292 loss_seg: 0.1390 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:12:20,716 INFO misc.py line 117 726] Train: [10/20][487/510] Data 3.478 (3.812) Batch 24.213 (28.067) Remain 39:56:29 loss: 0.2758 loss_seg: 0.1726 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:12:42,663 INFO misc.py line 117 726] Train: [10/20][488/510] Data 2.944 (3.810) Batch 21.948 (28.055) Remain 39:54:56 loss: 0.3789 loss_seg: 0.2836 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:13:18,399 INFO misc.py line 117 726] Train: [10/20][489/510] Data 10.958 (3.825) Batch 35.736 (28.071) Remain 39:55:49 loss: 0.1563 loss_seg: 0.0736 loss_superpoint_edge: 0.0095 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:13:47,618 INFO misc.py line 117 726] Train: [10/20][490/510] Data 4.701 (3.826) Batch 29.219 (28.073) Remain 39:55:33 loss: 0.2709 loss_seg: 0.1693 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:14:09,812 INFO misc.py line 117 726] Train: [10/20][491/510] Data 2.299 (3.823) Batch 22.194 (28.061) Remain 39:54:04 loss: 0.2132 loss_seg: 0.1246 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:14:39,154 INFO misc.py line 117 726] Train: [10/20][492/510] Data 3.370 (3.822) Batch 29.342 (28.064) Remain 39:53:49 loss: 0.2310 loss_seg: 0.1332 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:15:03,614 INFO misc.py line 117 726] Train: [10/20][493/510] Data 2.277 (3.819) Batch 24.460 (28.056) Remain 39:52:43 loss: 0.1605 loss_seg: 0.0799 loss_superpoint_edge: 0.0142 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:15:32,424 INFO misc.py line 117 726] Train: [10/20][494/510] Data 4.932 (3.821) Batch 28.810 (28.058) Remain 39:52:23 loss: 0.2212 loss_seg: 0.1290 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:16:04,632 INFO misc.py line 117 726] Train: [10/20][495/510] Data 3.656 (3.821) Batch 32.208 (28.066) Remain 39:52:38 loss: 0.4003 loss_seg: 0.2864 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:16:32,382 INFO misc.py line 117 726] Train: [10/20][496/510] Data 3.408 (3.820) Batch 27.750 (28.066) Remain 39:52:07 loss: 0.2597 loss_seg: 0.1592 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:17:13,340 INFO misc.py line 117 726] Train: [10/20][497/510] Data 11.858 (3.837) Batch 40.957 (28.092) Remain 39:53:52 loss: 0.2924 loss_seg: 0.1931 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:17:32,564 INFO misc.py line 117 726] Train: [10/20][498/510] Data 2.577 (3.834) Batch 19.225 (28.074) Remain 39:51:53 loss: 0.3116 loss_seg: 0.2097 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:17:54,724 INFO misc.py line 117 726] Train: [10/20][499/510] Data 3.586 (3.833) Batch 22.160 (28.062) Remain 39:50:23 loss: 0.3214 loss_seg: 0.2220 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:18:24,662 INFO misc.py line 117 726] Train: [10/20][500/510] Data 3.471 (3.833) Batch 29.937 (28.066) Remain 39:50:15 loss: 0.2514 loss_seg: 0.1581 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:18:24,662 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 08:18:52,620 INFO misc.py line 117 726] Train: [10/20][501/510] Data 4.852 (3.835) Batch 27.958 (28.065) Remain 39:49:46 loss: 0.2018 loss_seg: 0.1158 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:19:21,919 INFO misc.py line 117 726] Train: [10/20][502/510] Data 3.481 (3.834) Batch 29.299 (28.068) Remain 39:49:30 loss: 0.2752 loss_seg: 0.1744 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:19:51,417 INFO misc.py line 117 726] Train: [10/20][503/510] Data 2.857 (3.832) Batch 29.498 (28.071) Remain 39:49:17 loss: 0.1829 loss_seg: 0.0981 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:20:22,476 INFO misc.py line 117 726] Train: [10/20][504/510] Data 3.387 (3.831) Batch 31.060 (28.077) Remain 39:49:19 loss: 0.1927 loss_seg: 0.1034 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:20:47,999 INFO misc.py line 117 726] Train: [10/20][505/510] Data 2.802 (3.829) Batch 25.523 (28.072) Remain 39:48:25 loss: 0.2655 loss_seg: 0.1651 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:21:22,505 INFO misc.py line 117 726] Train: [10/20][506/510] Data 3.712 (3.829) Batch 34.506 (28.084) Remain 39:49:02 loss: 0.2256 loss_seg: 0.1329 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:21:41,150 INFO misc.py line 117 726] Train: [10/20][507/510] Data 2.122 (3.826) Batch 18.644 (28.066) Remain 39:46:59 loss: 0.1961 loss_seg: 0.1085 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:22:05,288 INFO misc.py line 117 726] Train: [10/20][508/510] Data 2.557 (3.823) Batch 24.138 (28.058) Remain 39:45:51 loss: 0.2181 loss_seg: 0.1275 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:22:22,472 INFO misc.py line 117 726] Train: [10/20][509/510] Data 1.785 (3.819) Batch 17.184 (28.036) Remain 39:43:33 loss: 0.2699 loss_seg: 0.1783 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:22:50,169 INFO misc.py line 117 726] Train: [10/20][510/510] Data 2.942 (3.817) Batch 27.696 (28.036) Remain 39:43:02 loss: 0.1969 loss_seg: 0.1106 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:22:50,170 INFO misc.py line 147 726] Train result: loss: 0.2519 loss_seg: 0.1565 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-11 08:22:50,170 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-11 08:23:05,540 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7329 [2026-06-11 08:23:21,377 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6765 [2026-06-11 08:24:36,800 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9595 [2026-06-11 08:25:16,726 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0278 [2026-06-11 08:25:35,835 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9244 [2026-06-11 08:26:11,709 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.1126 [2026-06-11 08:26:57,917 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.0494 [2026-06-11 08:27:13,260 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2879 [2026-06-11 08:27:31,005 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9780 [2026-06-11 08:27:49,675 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4084 [2026-06-11 08:28:05,330 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5018 [2026-06-11 08:28:26,728 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7878 [2026-06-11 08:28:52,351 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9000 [2026-06-11 08:29:03,599 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7193 [2026-06-11 08:29:34,725 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0308 [2026-06-11 08:30:00,693 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.2087 [2026-06-11 08:30:27,309 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3085 [2026-06-11 08:31:10,183 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1055 [2026-06-11 08:31:31,115 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4296 [2026-06-11 08:31:47,536 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8326 [2026-06-11 08:32:18,449 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.7103 [2026-06-11 08:32:34,635 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4870 [2026-06-11 08:32:56,561 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.1981 [2026-06-11 08:33:18,328 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8814 [2026-06-11 08:33:32,055 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6033 [2026-06-11 08:33:59,662 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.4729 [2026-06-11 08:34:40,886 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1414 [2026-06-11 08:34:58,078 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5287 [2026-06-11 08:35:16,555 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.5007 [2026-06-11 08:35:33,421 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.5325 [2026-06-11 08:35:58,158 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2149 [2026-06-11 08:36:16,325 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6757 [2026-06-11 08:36:33,609 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.0746 [2026-06-11 08:36:57,747 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6602 [2026-06-11 08:36:57,761 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6681/0.7398/0.8950. [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9243/0.9568 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9761/0.9877 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8366/0.9709 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0013/0.0107 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3280/0.4094 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.5811/0.6054 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5755/0.6702 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7847/0.8956 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9188/0.9603 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6854/0.7408 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7674/0.8459 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7062/0.8565 [2026-06-11 08:36:57,761 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5999/0.7075 [2026-06-11 08:36:57,761 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-11 08:36:57,762 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-11 08:36:57,762 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 08:37:27,451 INFO misc.py line 117 726] Train: [11/20][1/510] Data 3.743 (3.743) Batch 28.149 (28.149) Remain 39:52:12 loss: 0.3392 loss_seg: 0.2338 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:37:57,039 INFO misc.py line 117 726] Train: [11/20][2/510] Data 3.582 (3.582) Batch 29.588 (29.588) Remain 41:53:57 loss: 0.2267 loss_seg: 0.1339 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:38:23,630 INFO misc.py line 117 726] Train: [11/20][3/510] Data 3.018 (3.018) Batch 26.591 (26.591) Remain 37:38:53 loss: 0.3108 loss_seg: 0.2087 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:38:46,847 INFO misc.py line 117 726] Train: [11/20][4/510] Data 3.144 (3.144) Batch 23.218 (23.218) Remain 32:51:57 loss: 0.2484 loss_seg: 0.1503 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:39:10,292 INFO misc.py line 117 726] Train: [11/20][5/510] Data 2.612 (2.878) Batch 23.445 (23.331) Remain 33:01:12 loss: 0.2568 loss_seg: 0.1617 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:39:33,241 INFO misc.py line 117 726] Train: [11/20][6/510] Data 3.008 (2.922) Batch 22.949 (23.204) Remain 32:49:59 loss: 0.2092 loss_seg: 0.1176 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:39:55,112 INFO misc.py line 117 726] Train: [11/20][7/510] Data 2.423 (2.797) Batch 21.871 (22.871) Remain 32:21:19 loss: 0.2467 loss_seg: 0.1471 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:40:20,014 INFO misc.py line 117 726] Train: [11/20][8/510] Data 3.337 (2.905) Batch 24.902 (23.277) Remain 32:55:25 loss: 0.2317 loss_seg: 0.1378 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:40:35,158 INFO misc.py line 117 726] Train: [11/20][9/510] Data 1.909 (2.739) Batch 15.144 (21.921) Remain 31:00:01 loss: 0.2645 loss_seg: 0.1635 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:41:02,883 INFO misc.py line 117 726] Train: [11/20][10/510] Data 2.995 (2.776) Batch 27.725 (22.750) Remain 32:09:59 loss: 0.2159 loss_seg: 0.1265 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:41:30,887 INFO misc.py line 117 726] Train: [11/20][11/510] Data 2.998 (2.803) Batch 28.004 (23.407) Remain 33:05:18 loss: 0.1948 loss_seg: 0.1078 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:42:04,355 INFO misc.py line 117 726] Train: [11/20][12/510] Data 3.801 (2.914) Batch 33.468 (24.525) Remain 34:39:42 loss: 0.2239 loss_seg: 0.1312 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:42:35,036 INFO misc.py line 117 726] Train: [11/20][13/510] Data 2.882 (2.911) Batch 30.682 (25.141) Remain 35:31:30 loss: 0.2832 loss_seg: 0.1850 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:43:08,236 INFO misc.py line 117 726] Train: [11/20][14/510] Data 4.947 (3.096) Batch 33.200 (25.873) Remain 36:33:11 loss: 0.2831 loss_seg: 0.1787 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:43:42,911 INFO misc.py line 117 726] Train: [11/20][15/510] Data 4.649 (3.226) Batch 34.675 (26.607) Remain 37:34:55 loss: 0.2321 loss_seg: 0.1408 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:44:05,183 INFO misc.py line 117 726] Train: [11/20][16/510] Data 3.975 (3.283) Batch 22.272 (26.273) Remain 37:06:13 loss: 0.2777 loss_seg: 0.1743 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:44:22,286 INFO misc.py line 117 726] Train: [11/20][17/510] Data 1.658 (3.167) Batch 17.103 (25.618) Remain 36:10:17 loss: 0.2156 loss_seg: 0.1215 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:44:52,132 INFO misc.py line 117 726] Train: [11/20][18/510] Data 3.572 (3.194) Batch 29.846 (25.900) Remain 36:33:44 loss: 0.2104 loss_seg: 0.1212 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:45:07,418 INFO misc.py line 117 726] Train: [11/20][19/510] Data 2.116 (3.127) Batch 15.286 (25.237) Remain 35:37:08 loss: 0.2284 loss_seg: 0.1328 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:45:27,737 INFO misc.py line 117 726] Train: [11/20][20/510] Data 2.329 (3.080) Batch 20.319 (24.947) Remain 35:12:13 loss: 0.2563 loss_seg: 0.1585 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:45:56,353 INFO misc.py line 117 726] Train: [11/20][21/510] Data 3.458 (3.101) Batch 28.616 (25.151) Remain 35:29:03 loss: 0.3335 loss_seg: 0.2228 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:46:23,471 INFO misc.py line 117 726] Train: [11/20][22/510] Data 5.043 (3.203) Batch 27.118 (25.255) Remain 35:37:23 loss: 0.4960 loss_seg: 0.3764 loss_superpoint_edge: 0.0467 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0340 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:46:56,840 INFO misc.py line 117 726] Train: [11/20][23/510] Data 5.829 (3.334) Batch 33.369 (25.660) Remain 36:11:18 loss: 0.2565 loss_seg: 0.1592 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:47:19,582 INFO misc.py line 117 726] Train: [11/20][24/510] Data 2.831 (3.310) Batch 22.742 (25.522) Remain 35:59:07 loss: 0.2216 loss_seg: 0.1318 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:47:40,506 INFO misc.py line 117 726] Train: [11/20][25/510] Data 2.569 (3.277) Batch 20.924 (25.313) Remain 35:41:01 loss: 0.1976 loss_seg: 0.1046 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:48:09,629 INFO misc.py line 117 726] Train: [11/20][26/510] Data 2.926 (3.261) Batch 29.123 (25.478) Remain 35:54:36 loss: 0.2441 loss_seg: 0.1499 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:48:35,914 INFO misc.py line 117 726] Train: [11/20][27/510] Data 2.915 (3.247) Batch 26.285 (25.512) Remain 35:57:01 loss: 0.2873 loss_seg: 0.1983 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:49:15,455 INFO misc.py line 117 726] Train: [11/20][28/510] Data 6.122 (3.362) Batch 39.541 (26.073) Remain 36:44:02 loss: 0.2746 loss_seg: 0.1824 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:49:43,152 INFO misc.py line 117 726] Train: [11/20][29/510] Data 3.545 (3.369) Batch 27.697 (26.135) Remain 36:48:52 loss: 0.2503 loss_seg: 0.1570 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:50:06,242 INFO misc.py line 117 726] Train: [11/20][30/510] Data 3.055 (3.357) Batch 23.090 (26.023) Remain 36:38:54 loss: 0.2140 loss_seg: 0.1259 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:50:41,611 INFO misc.py line 117 726] Train: [11/20][31/510] Data 3.491 (3.362) Batch 35.369 (26.356) Remain 37:06:40 loss: 0.2349 loss_seg: 0.1427 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:51:11,394 INFO misc.py line 117 726] Train: [11/20][32/510] Data 3.524 (3.368) Batch 29.783 (26.475) Remain 37:16:13 loss: 0.2320 loss_seg: 0.1430 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:51:33,655 INFO misc.py line 117 726] Train: [11/20][33/510] Data 2.150 (3.327) Batch 22.260 (26.334) Remain 37:03:55 loss: 0.2541 loss_seg: 0.1577 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:52:06,385 INFO misc.py line 117 726] Train: [11/20][34/510] Data 3.372 (3.329) Batch 32.730 (26.540) Remain 37:20:53 loss: 0.2552 loss_seg: 0.1513 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:52:33,883 INFO misc.py line 117 726] Train: [11/20][35/510] Data 3.020 (3.319) Batch 27.499 (26.570) Remain 37:22:59 loss: 0.2567 loss_seg: 0.1586 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:52:53,986 INFO misc.py line 117 726] Train: [11/20][36/510] Data 2.832 (3.304) Batch 20.103 (26.374) Remain 37:06:00 loss: 0.2296 loss_seg: 0.1334 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:53:24,733 INFO misc.py line 117 726] Train: [11/20][37/510] Data 3.232 (3.302) Batch 30.747 (26.503) Remain 37:16:24 loss: 0.2307 loss_seg: 0.1335 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:53:50,265 INFO misc.py line 117 726] Train: [11/20][38/510] Data 3.862 (3.318) Batch 25.532 (26.475) Remain 37:13:37 loss: 0.2228 loss_seg: 0.1339 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:54:14,790 INFO misc.py line 117 726] Train: [11/20][39/510] Data 2.728 (3.302) Batch 24.526 (26.421) Remain 37:08:37 loss: 0.2745 loss_seg: 0.1739 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:54:49,754 INFO misc.py line 117 726] Train: [11/20][40/510] Data 8.135 (3.432) Batch 34.964 (26.652) Remain 37:27:39 loss: 0.1775 loss_seg: 0.0925 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:55:13,816 INFO misc.py line 117 726] Train: [11/20][41/510] Data 2.393 (3.405) Batch 24.062 (26.584) Remain 37:21:27 loss: 0.3265 loss_seg: 0.2271 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:55:44,997 INFO misc.py line 117 726] Train: [11/20][42/510] Data 3.001 (3.395) Batch 31.181 (26.702) Remain 37:30:57 loss: 0.2219 loss_seg: 0.1301 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:56:04,628 INFO misc.py line 117 726] Train: [11/20][43/510] Data 1.968 (3.359) Batch 19.631 (26.525) Remain 37:15:36 loss: 0.2504 loss_seg: 0.1516 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:56:32,031 INFO misc.py line 117 726] Train: [11/20][44/510] Data 3.184 (3.355) Batch 27.403 (26.546) Remain 37:16:58 loss: 0.3947 loss_seg: 0.2911 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:57:05,090 INFO misc.py line 117 726] Train: [11/20][45/510] Data 6.624 (3.433) Batch 33.059 (26.701) Remain 37:29:35 loss: 0.3375 loss_seg: 0.2415 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:57:26,742 INFO misc.py line 117 726] Train: [11/20][46/510] Data 2.398 (3.408) Batch 21.652 (26.584) Remain 37:19:15 loss: 0.2099 loss_seg: 0.1225 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:57:57,762 INFO misc.py line 117 726] Train: [11/20][47/510] Data 4.190 (3.426) Batch 31.020 (26.685) Remain 37:27:18 loss: 0.2007 loss_seg: 0.1122 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:58:25,882 INFO misc.py line 117 726] Train: [11/20][48/510] Data 5.772 (3.478) Batch 28.120 (26.717) Remain 37:29:32 loss: 0.2338 loss_seg: 0.1374 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:59:01,336 INFO misc.py line 117 726] Train: [11/20][49/510] Data 8.574 (3.589) Batch 35.454 (26.907) Remain 37:45:05 loss: 0.2759 loss_seg: 0.1778 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:59:33,714 INFO misc.py line 117 726] Train: [11/20][50/510] Data 3.495 (3.587) Batch 32.378 (27.023) Remain 37:54:26 loss: 0.2115 loss_seg: 0.1228 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 08:59:33,714 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 08:59:55,410 INFO misc.py line 117 726] Train: [11/20][51/510] Data 2.971 (3.574) Batch 21.696 (26.912) Remain 37:44:39 loss: 0.2331 loss_seg: 0.1411 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:00:22,038 INFO misc.py line 117 726] Train: [11/20][52/510] Data 2.343 (3.549) Batch 26.629 (26.906) Remain 37:43:42 loss: 0.2912 loss_seg: 0.1855 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:00:58,333 INFO misc.py line 117 726] Train: [11/20][53/510] Data 5.813 (3.594) Batch 36.295 (27.094) Remain 37:59:03 loss: 0.2199 loss_seg: 0.1250 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:01:38,122 INFO misc.py line 117 726] Train: [11/20][54/510] Data 8.256 (3.686) Batch 39.789 (27.343) Remain 38:19:32 loss: 0.2358 loss_seg: 0.1403 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:02:01,190 INFO misc.py line 117 726] Train: [11/20][55/510] Data 3.301 (3.678) Batch 23.067 (27.261) Remain 38:12:10 loss: 0.1855 loss_seg: 0.0991 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:02:25,845 INFO misc.py line 117 726] Train: [11/20][56/510] Data 2.799 (3.662) Batch 24.656 (27.212) Remain 38:07:35 loss: 0.2133 loss_seg: 0.1169 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0437 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:02:56,883 INFO misc.py line 117 726] Train: [11/20][57/510] Data 4.008 (3.668) Batch 31.038 (27.282) Remain 38:13:05 loss: 0.2498 loss_seg: 0.1531 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:03:26,887 INFO misc.py line 117 726] Train: [11/20][58/510] Data 2.953 (3.655) Batch 30.003 (27.332) Remain 38:16:47 loss: 0.1976 loss_seg: 0.1080 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:04:01,517 INFO misc.py line 117 726] Train: [11/20][59/510] Data 4.691 (3.674) Batch 34.630 (27.462) Remain 38:27:17 loss: 0.2619 loss_seg: 0.1640 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:04:26,884 INFO misc.py line 117 726] Train: [11/20][60/510] Data 2.609 (3.655) Batch 25.367 (27.426) Remain 38:23:44 loss: 0.2560 loss_seg: 0.1647 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:04:55,128 INFO misc.py line 117 726] Train: [11/20][61/510] Data 2.731 (3.639) Batch 28.245 (27.440) Remain 38:24:28 loss: 0.2547 loss_seg: 0.1549 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:05:19,557 INFO misc.py line 117 726] Train: [11/20][62/510] Data 2.653 (3.622) Batch 24.429 (27.389) Remain 38:19:43 loss: 0.2844 loss_seg: 0.1825 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:05:48,324 INFO misc.py line 117 726] Train: [11/20][63/510] Data 2.943 (3.611) Batch 28.767 (27.412) Remain 38:21:12 loss: 0.2087 loss_seg: 0.1188 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:06:16,813 INFO misc.py line 117 726] Train: [11/20][64/510] Data 3.062 (3.602) Batch 28.489 (27.429) Remain 38:22:13 loss: 0.2934 loss_seg: 0.2011 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:06:54,925 INFO misc.py line 117 726] Train: [11/20][65/510] Data 4.837 (3.622) Batch 38.111 (27.602) Remain 38:36:13 loss: 0.2953 loss_seg: 0.1889 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:07:29,195 INFO misc.py line 117 726] Train: [11/20][66/510] Data 5.186 (3.647) Batch 34.270 (27.707) Remain 38:44:38 loss: 0.2831 loss_seg: 0.1936 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:07:53,809 INFO misc.py line 117 726] Train: [11/20][67/510] Data 2.862 (3.635) Batch 24.613 (27.659) Remain 38:40:07 loss: 0.2437 loss_seg: 0.1501 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:08:29,518 INFO misc.py line 117 726] Train: [11/20][68/510] Data 6.794 (3.683) Batch 35.710 (27.783) Remain 38:50:03 loss: 0.2795 loss_seg: 0.1873 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:08:49,015 INFO misc.py line 117 726] Train: [11/20][69/510] Data 1.853 (3.655) Batch 19.496 (27.657) Remain 38:39:04 loss: 0.2848 loss_seg: 0.1799 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:09:20,789 INFO misc.py line 117 726] Train: [11/20][70/510] Data 6.285 (3.695) Batch 31.775 (27.719) Remain 38:43:45 loss: 0.3060 loss_seg: 0.1989 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:09:48,678 INFO misc.py line 117 726] Train: [11/20][71/510] Data 3.091 (3.686) Batch 27.888 (27.721) Remain 38:43:30 loss: 0.3358 loss_seg: 0.2221 loss_superpoint_edge: 0.0471 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:10:09,607 INFO misc.py line 117 726] Train: [11/20][72/510] Data 2.019 (3.662) Batch 20.929 (27.623) Remain 38:34:47 loss: 0.2368 loss_seg: 0.1409 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:10:40,690 INFO misc.py line 117 726] Train: [11/20][73/510] Data 4.417 (3.672) Batch 31.083 (27.672) Remain 38:38:28 loss: 0.2436 loss_seg: 0.1493 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:11:06,617 INFO misc.py line 117 726] Train: [11/20][74/510] Data 2.659 (3.658) Batch 25.927 (27.648) Remain 38:35:57 loss: 0.2402 loss_seg: 0.1434 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:11:33,526 INFO misc.py line 117 726] Train: [11/20][75/510] Data 2.812 (3.646) Batch 26.909 (27.637) Remain 38:34:38 loss: 0.3054 loss_seg: 0.1945 loss_superpoint_edge: 0.0421 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:12:00,276 INFO misc.py line 117 726] Train: [11/20][76/510] Data 2.337 (3.628) Batch 26.751 (27.625) Remain 38:33:09 loss: 0.2430 loss_seg: 0.1446 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:12:21,614 INFO misc.py line 117 726] Train: [11/20][77/510] Data 3.013 (3.620) Batch 21.338 (27.540) Remain 38:25:35 loss: 0.2527 loss_seg: 0.1550 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:12:50,961 INFO misc.py line 117 726] Train: [11/20][78/510] Data 5.134 (3.640) Batch 29.346 (27.564) Remain 38:27:08 loss: 0.2657 loss_seg: 0.1683 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:13:11,094 INFO misc.py line 117 726] Train: [11/20][79/510] Data 2.621 (3.627) Batch 20.133 (27.467) Remain 38:18:29 loss: 0.2630 loss_seg: 0.1494 loss_superpoint_edge: 0.0455 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:13:39,626 INFO misc.py line 117 726] Train: [11/20][80/510] Data 3.266 (3.622) Batch 28.533 (27.480) Remain 38:19:11 loss: 0.2687 loss_seg: 0.1668 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:13:56,973 INFO misc.py line 117 726] Train: [11/20][81/510] Data 1.932 (3.601) Batch 17.347 (27.351) Remain 38:07:52 loss: 0.3140 loss_seg: 0.2047 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:14:27,166 INFO misc.py line 117 726] Train: [11/20][82/510] Data 3.616 (3.601) Batch 30.192 (27.387) Remain 38:10:25 loss: 0.1575 loss_seg: 0.0769 loss_superpoint_edge: 0.0130 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:14:44,234 INFO misc.py line 117 726] Train: [11/20][83/510] Data 2.215 (3.583) Batch 17.069 (27.258) Remain 37:59:11 loss: 0.2007 loss_seg: 0.1112 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:15:04,605 INFO misc.py line 117 726] Train: [11/20][84/510] Data 2.605 (3.571) Batch 20.371 (27.173) Remain 37:51:37 loss: 0.2318 loss_seg: 0.1385 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:15:33,148 INFO misc.py line 117 726] Train: [11/20][85/510] Data 3.313 (3.568) Batch 28.543 (27.189) Remain 37:52:34 loss: 0.2366 loss_seg: 0.1377 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:15:56,739 INFO misc.py line 117 726] Train: [11/20][86/510] Data 2.836 (3.559) Batch 23.591 (27.146) Remain 37:48:29 loss: 0.1944 loss_seg: 0.1061 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:16:30,045 INFO misc.py line 117 726] Train: [11/20][87/510] Data 3.806 (3.562) Batch 33.306 (27.219) Remain 37:54:09 loss: 0.2359 loss_seg: 0.1451 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:17:00,921 INFO misc.py line 117 726] Train: [11/20][88/510] Data 3.092 (3.557) Batch 30.876 (27.262) Remain 37:57:18 loss: 0.2427 loss_seg: 0.1465 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:17:37,362 INFO misc.py line 117 726] Train: [11/20][89/510] Data 3.807 (3.560) Batch 36.441 (27.369) Remain 38:05:45 loss: 0.2677 loss_seg: 0.1757 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:18:07,297 INFO misc.py line 117 726] Train: [11/20][90/510] Data 3.971 (3.564) Batch 29.935 (27.398) Remain 38:07:46 loss: 0.3081 loss_seg: 0.2129 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:18:30,250 INFO misc.py line 117 726] Train: [11/20][91/510] Data 3.091 (3.559) Batch 22.953 (27.348) Remain 38:03:05 loss: 0.2080 loss_seg: 0.1193 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:18:58,445 INFO misc.py line 117 726] Train: [11/20][92/510] Data 3.198 (3.555) Batch 28.195 (27.357) Remain 38:03:26 loss: 0.2843 loss_seg: 0.1741 loss_superpoint_edge: 0.0439 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:19:36,945 INFO misc.py line 117 726] Train: [11/20][93/510] Data 7.222 (3.596) Batch 38.500 (27.481) Remain 38:13:18 loss: 0.3869 loss_seg: 0.2852 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:20:10,911 INFO misc.py line 117 726] Train: [11/20][94/510] Data 3.311 (3.593) Batch 33.965 (27.553) Remain 38:18:47 loss: 0.2533 loss_seg: 0.1557 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:20:45,006 INFO misc.py line 117 726] Train: [11/20][95/510] Data 4.120 (3.598) Batch 34.095 (27.624) Remain 38:24:16 loss: 0.2269 loss_seg: 0.1366 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:21:14,229 INFO misc.py line 117 726] Train: [11/20][96/510] Data 4.264 (3.606) Batch 29.223 (27.641) Remain 38:25:14 loss: 0.2527 loss_seg: 0.1545 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:21:39,938 INFO misc.py line 117 726] Train: [11/20][97/510] Data 2.498 (3.594) Batch 25.708 (27.620) Remain 38:23:04 loss: 0.1877 loss_seg: 0.1032 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:21:59,848 INFO misc.py line 117 726] Train: [11/20][98/510] Data 1.848 (3.575) Batch 19.911 (27.539) Remain 38:15:50 loss: 0.2538 loss_seg: 0.1561 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:22:34,247 INFO misc.py line 117 726] Train: [11/20][99/510] Data 4.352 (3.583) Batch 34.399 (27.611) Remain 38:21:20 loss: 0.3401 loss_seg: 0.2493 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:23:00,542 INFO misc.py line 117 726] Train: [11/20][100/510] Data 3.231 (3.580) Batch 26.295 (27.597) Remain 38:19:45 loss: 0.2176 loss_seg: 0.1288 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:23:00,542 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 09:23:23,968 INFO misc.py line 117 726] Train: [11/20][101/510] Data 2.827 (3.572) Batch 23.426 (27.554) Remain 38:15:44 loss: 0.2154 loss_seg: 0.1232 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:23:55,793 INFO misc.py line 117 726] Train: [11/20][102/510] Data 4.115 (3.578) Batch 31.825 (27.598) Remain 38:18:52 loss: 0.2417 loss_seg: 0.1515 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:24:21,293 INFO misc.py line 117 726] Train: [11/20][103/510] Data 2.828 (3.570) Batch 25.499 (27.577) Remain 38:16:40 loss: 0.2446 loss_seg: 0.1460 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:24:50,337 INFO misc.py line 117 726] Train: [11/20][104/510] Data 3.088 (3.565) Batch 29.045 (27.591) Remain 38:17:25 loss: 0.2508 loss_seg: 0.1555 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:25:19,552 INFO misc.py line 117 726] Train: [11/20][105/510] Data 3.145 (3.561) Batch 29.215 (27.607) Remain 38:18:17 loss: 0.2315 loss_seg: 0.1347 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:25:46,794 INFO misc.py line 117 726] Train: [11/20][106/510] Data 2.613 (3.552) Batch 27.242 (27.604) Remain 38:17:32 loss: 0.2057 loss_seg: 0.1153 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:26:06,130 INFO misc.py line 117 726] Train: [11/20][107/510] Data 2.511 (3.542) Batch 19.336 (27.524) Remain 38:10:27 loss: 0.3109 loss_seg: 0.1997 loss_superpoint_edge: 0.0449 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:26:34,426 INFO misc.py line 117 726] Train: [11/20][108/510] Data 2.832 (3.535) Batch 28.296 (27.531) Remain 38:10:36 loss: 0.3099 loss_seg: 0.2049 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:27:03,117 INFO misc.py line 117 726] Train: [11/20][109/510] Data 3.595 (3.536) Batch 28.691 (27.542) Remain 38:11:03 loss: 0.1752 loss_seg: 0.0922 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:27:28,718 INFO misc.py line 117 726] Train: [11/20][110/510] Data 2.971 (3.531) Batch 25.601 (27.524) Remain 38:09:05 loss: 0.2159 loss_seg: 0.1217 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:27:50,051 INFO misc.py line 117 726] Train: [11/20][111/510] Data 2.066 (3.517) Batch 21.333 (27.467) Remain 38:03:52 loss: 0.1931 loss_seg: 0.1100 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:28:15,397 INFO misc.py line 117 726] Train: [11/20][112/510] Data 2.946 (3.512) Batch 25.346 (27.447) Remain 38:01:47 loss: 0.2005 loss_seg: 0.1122 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:28:38,842 INFO misc.py line 117 726] Train: [11/20][113/510] Data 4.298 (3.519) Batch 23.445 (27.411) Remain 37:58:18 loss: 0.2257 loss_seg: 0.1313 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:28:59,836 INFO misc.py line 117 726] Train: [11/20][114/510] Data 2.565 (3.510) Batch 20.994 (27.353) Remain 37:53:03 loss: 0.2506 loss_seg: 0.1582 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:29:24,708 INFO misc.py line 117 726] Train: [11/20][115/510] Data 2.626 (3.502) Batch 24.873 (27.331) Remain 37:50:45 loss: 0.2209 loss_seg: 0.1276 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:29:55,107 INFO misc.py line 117 726] Train: [11/20][116/510] Data 3.436 (3.502) Batch 30.400 (27.358) Remain 37:52:33 loss: 0.2303 loss_seg: 0.1381 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:30:24,943 INFO misc.py line 117 726] Train: [11/20][117/510] Data 8.028 (3.542) Batch 29.836 (27.380) Remain 37:53:54 loss: 0.3124 loss_seg: 0.2129 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:30:48,480 INFO misc.py line 117 726] Train: [11/20][118/510] Data 2.431 (3.532) Batch 23.537 (27.347) Remain 37:50:40 loss: 0.1668 loss_seg: 0.0837 loss_superpoint_edge: 0.0147 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:31:15,404 INFO misc.py line 117 726] Train: [11/20][119/510] Data 3.713 (3.533) Batch 26.924 (27.343) Remain 37:49:54 loss: 0.1865 loss_seg: 0.1022 loss_superpoint_edge: 0.0136 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:31:53,006 INFO misc.py line 117 726] Train: [11/20][120/510] Data 7.987 (3.571) Batch 37.602 (27.431) Remain 37:56:44 loss: 0.4572 loss_seg: 0.3489 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:32:29,899 INFO misc.py line 117 726] Train: [11/20][121/510] Data 5.541 (3.588) Batch 36.893 (27.511) Remain 38:02:56 loss: 0.2482 loss_seg: 0.1510 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:32:50,210 INFO misc.py line 117 726] Train: [11/20][122/510] Data 1.966 (3.575) Batch 20.311 (27.450) Remain 37:57:27 loss: 0.2825 loss_seg: 0.1824 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:33:16,473 INFO misc.py line 117 726] Train: [11/20][123/510] Data 2.748 (3.568) Batch 26.263 (27.440) Remain 37:56:10 loss: 0.1668 loss_seg: 0.0805 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:33:38,310 INFO misc.py line 117 726] Train: [11/20][124/510] Data 4.368 (3.574) Batch 21.837 (27.394) Remain 37:51:52 loss: 0.2436 loss_seg: 0.1516 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:34:06,840 INFO misc.py line 117 726] Train: [11/20][125/510] Data 4.752 (3.584) Batch 28.530 (27.403) Remain 37:52:11 loss: 0.2563 loss_seg: 0.1616 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:34:39,464 INFO misc.py line 117 726] Train: [11/20][126/510] Data 6.080 (3.604) Batch 32.624 (27.446) Remain 37:55:15 loss: 0.2365 loss_seg: 0.1392 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:35:10,372 INFO misc.py line 117 726] Train: [11/20][127/510] Data 5.057 (3.616) Batch 30.908 (27.474) Remain 37:57:06 loss: 0.2030 loss_seg: 0.1130 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:35:38,668 INFO misc.py line 117 726] Train: [11/20][128/510] Data 3.134 (3.612) Batch 28.296 (27.480) Remain 37:57:12 loss: 0.2147 loss_seg: 0.1267 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:36:08,628 INFO misc.py line 117 726] Train: [11/20][129/510] Data 3.763 (3.613) Batch 29.960 (27.500) Remain 37:58:22 loss: 0.2817 loss_seg: 0.1845 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:36:38,925 INFO misc.py line 117 726] Train: [11/20][130/510] Data 5.530 (3.628) Batch 30.296 (27.522) Remain 37:59:44 loss: 0.2289 loss_seg: 0.1377 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:37:14,948 INFO misc.py line 117 726] Train: [11/20][131/510] Data 8.481 (3.666) Batch 36.024 (27.588) Remain 38:04:46 loss: 0.2568 loss_seg: 0.1600 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:37:48,338 INFO misc.py line 117 726] Train: [11/20][132/510] Data 4.777 (3.675) Batch 33.389 (27.633) Remain 38:08:02 loss: 0.2513 loss_seg: 0.1599 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:38:14,814 INFO misc.py line 117 726] Train: [11/20][133/510] Data 2.633 (3.667) Batch 26.476 (27.624) Remain 38:06:50 loss: 0.2474 loss_seg: 0.1517 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:38:48,581 INFO misc.py line 117 726] Train: [11/20][134/510] Data 5.853 (3.684) Batch 33.767 (27.671) Remain 38:10:16 loss: 0.2004 loss_seg: 0.1105 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:39:20,425 INFO misc.py line 117 726] Train: [11/20][135/510] Data 3.493 (3.682) Batch 31.844 (27.703) Remain 38:12:25 loss: 0.3642 loss_seg: 0.2671 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:39:49,473 INFO misc.py line 117 726] Train: [11/20][136/510] Data 2.851 (3.676) Batch 29.048 (27.713) Remain 38:12:47 loss: 0.2484 loss_seg: 0.1490 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:40:19,776 INFO misc.py line 117 726] Train: [11/20][137/510] Data 3.777 (3.677) Batch 30.303 (27.732) Remain 38:13:56 loss: 0.3068 loss_seg: 0.1913 loss_superpoint_edge: 0.0481 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:40:50,449 INFO misc.py line 117 726] Train: [11/20][138/510] Data 4.159 (3.680) Batch 30.672 (27.754) Remain 38:15:16 loss: 0.2379 loss_seg: 0.1437 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:41:17,084 INFO misc.py line 117 726] Train: [11/20][139/510] Data 2.350 (3.670) Batch 26.636 (27.746) Remain 38:14:07 loss: 0.2095 loss_seg: 0.1195 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:41:46,970 INFO misc.py line 117 726] Train: [11/20][140/510] Data 3.349 (3.668) Batch 29.886 (27.762) Remain 38:14:57 loss: 0.2005 loss_seg: 0.1133 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:42:12,576 INFO misc.py line 117 726] Train: [11/20][141/510] Data 2.138 (3.657) Batch 25.606 (27.746) Remain 38:13:12 loss: 0.2117 loss_seg: 0.1223 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:42:37,455 INFO misc.py line 117 726] Train: [11/20][142/510] Data 2.238 (3.647) Batch 24.879 (27.725) Remain 38:11:02 loss: 0.2129 loss_seg: 0.1225 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:43:05,124 INFO misc.py line 117 726] Train: [11/20][143/510] Data 3.160 (3.643) Batch 27.669 (27.725) Remain 38:10:32 loss: 0.2323 loss_seg: 0.1386 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:43:33,609 INFO misc.py line 117 726] Train: [11/20][144/510] Data 3.156 (3.640) Batch 28.484 (27.730) Remain 38:10:31 loss: 0.2640 loss_seg: 0.1644 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:44:02,432 INFO misc.py line 117 726] Train: [11/20][145/510] Data 5.035 (3.650) Batch 28.823 (27.738) Remain 38:10:41 loss: 0.3560 loss_seg: 0.2650 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:44:20,373 INFO misc.py line 117 726] Train: [11/20][146/510] Data 2.555 (3.642) Batch 17.941 (27.670) Remain 38:04:34 loss: 0.2363 loss_seg: 0.1393 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:44:47,783 INFO misc.py line 117 726] Train: [11/20][147/510] Data 4.534 (3.648) Batch 27.410 (27.668) Remain 38:03:58 loss: 0.2185 loss_seg: 0.1290 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:45:09,016 INFO misc.py line 117 726] Train: [11/20][148/510] Data 1.958 (3.637) Batch 21.233 (27.623) Remain 37:59:50 loss: 0.2346 loss_seg: 0.1381 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:45:45,729 INFO misc.py line 117 726] Train: [11/20][149/510] Data 6.235 (3.654) Batch 36.714 (27.686) Remain 38:04:31 loss: 0.3010 loss_seg: 0.2038 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:46:18,550 INFO misc.py line 117 726] Train: [11/20][150/510] Data 3.700 (3.655) Batch 32.820 (27.721) Remain 38:06:56 loss: 0.2474 loss_seg: 0.1490 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:46:18,550 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 09:46:38,287 INFO misc.py line 117 726] Train: [11/20][151/510] Data 3.048 (3.651) Batch 19.738 (27.667) Remain 38:02:02 loss: 0.2483 loss_seg: 0.1541 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:47:07,632 INFO misc.py line 117 726] Train: [11/20][152/510] Data 5.517 (3.663) Batch 29.344 (27.678) Remain 38:02:30 loss: 0.1735 loss_seg: 0.0903 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:47:46,064 INFO misc.py line 117 726] Train: [11/20][153/510] Data 6.010 (3.679) Batch 38.433 (27.750) Remain 38:07:57 loss: 0.2294 loss_seg: 0.1363 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:48:05,661 INFO misc.py line 117 726] Train: [11/20][154/510] Data 2.647 (3.672) Batch 19.597 (27.696) Remain 38:03:02 loss: 0.2719 loss_seg: 0.1718 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:48:31,434 INFO misc.py line 117 726] Train: [11/20][155/510] Data 2.863 (3.667) Batch 25.772 (27.683) Remain 38:01:32 loss: 0.1980 loss_seg: 0.1110 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:49:13,788 INFO misc.py line 117 726] Train: [11/20][156/510] Data 11.234 (3.716) Batch 42.354 (27.779) Remain 38:08:58 loss: 0.2099 loss_seg: 0.1177 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:49:40,184 INFO misc.py line 117 726] Train: [11/20][157/510] Data 3.388 (3.714) Batch 26.396 (27.770) Remain 38:07:46 loss: 0.1922 loss_seg: 0.1074 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:50:10,562 INFO misc.py line 117 726] Train: [11/20][158/510] Data 3.445 (3.712) Batch 30.378 (27.787) Remain 38:08:41 loss: 0.2379 loss_seg: 0.1412 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:50:37,561 INFO misc.py line 117 726] Train: [11/20][159/510] Data 4.093 (3.715) Batch 26.999 (27.782) Remain 38:07:48 loss: 0.2257 loss_seg: 0.1349 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:50:59,238 INFO misc.py line 117 726] Train: [11/20][160/510] Data 3.103 (3.711) Batch 21.676 (27.743) Remain 38:04:09 loss: 0.2142 loss_seg: 0.1221 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:51:24,592 INFO misc.py line 117 726] Train: [11/20][161/510] Data 3.848 (3.712) Batch 25.354 (27.728) Remain 38:02:26 loss: 0.3188 loss_seg: 0.2202 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:51:53,769 INFO misc.py line 117 726] Train: [11/20][162/510] Data 3.905 (3.713) Batch 29.177 (27.737) Remain 38:02:43 loss: 0.3058 loss_seg: 0.2148 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:52:19,601 INFO misc.py line 117 726] Train: [11/20][163/510] Data 3.013 (3.708) Batch 25.832 (27.725) Remain 38:01:17 loss: 0.2294 loss_seg: 0.1357 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:52:53,245 INFO misc.py line 117 726] Train: [11/20][164/510] Data 4.644 (3.714) Batch 33.643 (27.762) Remain 38:03:51 loss: 0.2352 loss_seg: 0.1405 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:53:20,908 INFO misc.py line 117 726] Train: [11/20][165/510] Data 2.740 (3.708) Batch 27.664 (27.761) Remain 38:03:20 loss: 0.2014 loss_seg: 0.1140 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:53:50,076 INFO misc.py line 117 726] Train: [11/20][166/510] Data 2.874 (3.703) Batch 29.168 (27.770) Remain 38:03:35 loss: 0.3419 loss_seg: 0.2322 loss_superpoint_edge: 0.0443 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:54:05,754 INFO misc.py line 117 726] Train: [11/20][167/510] Data 2.090 (3.693) Batch 15.678 (27.696) Remain 37:57:03 loss: 0.2161 loss_seg: 0.1258 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:54:37,406 INFO misc.py line 117 726] Train: [11/20][168/510] Data 2.979 (3.689) Batch 31.652 (27.720) Remain 37:58:34 loss: 0.1979 loss_seg: 0.1092 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:54:59,153 INFO misc.py line 117 726] Train: [11/20][169/510] Data 2.854 (3.684) Batch 21.747 (27.684) Remain 37:55:09 loss: 0.1789 loss_seg: 0.0957 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:55:20,964 INFO misc.py line 117 726] Train: [11/20][170/510] Data 2.732 (3.678) Batch 21.811 (27.649) Remain 37:51:48 loss: 0.3230 loss_seg: 0.2216 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:55:50,944 INFO misc.py line 117 726] Train: [11/20][171/510] Data 4.122 (3.681) Batch 29.980 (27.663) Remain 37:52:28 loss: 0.3253 loss_seg: 0.2221 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:56:13,043 INFO misc.py line 117 726] Train: [11/20][172/510] Data 2.574 (3.674) Batch 22.099 (27.630) Remain 37:49:18 loss: 0.3101 loss_seg: 0.2147 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:56:42,489 INFO misc.py line 117 726] Train: [11/20][173/510] Data 3.741 (3.675) Batch 29.445 (27.640) Remain 37:49:43 loss: 0.2385 loss_seg: 0.1447 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:57:09,935 INFO misc.py line 117 726] Train: [11/20][174/510] Data 2.856 (3.670) Batch 27.447 (27.639) Remain 37:49:10 loss: 0.2791 loss_seg: 0.1815 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:57:36,213 INFO misc.py line 117 726] Train: [11/20][175/510] Data 2.976 (3.666) Batch 26.278 (27.631) Remain 37:48:04 loss: 0.2282 loss_seg: 0.1363 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:58:01,485 INFO misc.py line 117 726] Train: [11/20][176/510] Data 2.165 (3.657) Batch 25.272 (27.618) Remain 37:46:29 loss: 0.2065 loss_seg: 0.1145 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:58:23,070 INFO misc.py line 117 726] Train: [11/20][177/510] Data 2.320 (3.649) Batch 21.585 (27.583) Remain 37:43:11 loss: 0.2485 loss_seg: 0.1491 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:58:54,976 INFO misc.py line 117 726] Train: [11/20][178/510] Data 6.205 (3.664) Batch 31.906 (27.608) Remain 37:44:45 loss: 0.2400 loss_seg: 0.1499 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 09:59:32,365 INFO misc.py line 117 726] Train: [11/20][179/510] Data 5.365 (3.674) Batch 37.389 (27.663) Remain 37:48:50 loss: 0.3053 loss_seg: 0.2001 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:00:07,800 INFO misc.py line 117 726] Train: [11/20][180/510] Data 9.024 (3.704) Batch 35.435 (27.707) Remain 37:51:59 loss: 0.3721 loss_seg: 0.2810 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:00:28,528 INFO misc.py line 117 726] Train: [11/20][181/510] Data 2.687 (3.698) Batch 20.728 (27.668) Remain 37:48:18 loss: 0.2151 loss_seg: 0.1245 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:01:00,503 INFO misc.py line 117 726] Train: [11/20][182/510] Data 5.439 (3.708) Batch 31.974 (27.692) Remain 37:49:49 loss: 0.2195 loss_seg: 0.1265 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:01:31,060 INFO misc.py line 117 726] Train: [11/20][183/510] Data 3.525 (3.707) Batch 30.557 (27.708) Remain 37:50:39 loss: 0.2470 loss_seg: 0.1584 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:02:09,271 INFO misc.py line 117 726] Train: [11/20][184/510] Data 5.755 (3.718) Batch 38.210 (27.766) Remain 37:54:57 loss: 0.2704 loss_seg: 0.1616 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:02:46,130 INFO misc.py line 117 726] Train: [11/20][185/510] Data 3.809 (3.719) Batch 36.860 (27.816) Remain 37:58:35 loss: 0.1758 loss_seg: 0.0911 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:03:15,751 INFO misc.py line 117 726] Train: [11/20][186/510] Data 2.811 (3.714) Batch 29.621 (27.826) Remain 37:58:55 loss: 0.2486 loss_seg: 0.1482 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:03:39,822 INFO misc.py line 117 726] Train: [11/20][187/510] Data 2.654 (3.708) Batch 24.071 (27.805) Remain 37:56:47 loss: 0.2100 loss_seg: 0.1196 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:04:19,178 INFO misc.py line 117 726] Train: [11/20][188/510] Data 11.387 (3.750) Batch 39.356 (27.868) Remain 38:01:26 loss: 0.2889 loss_seg: 0.1878 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:05:00,789 INFO misc.py line 117 726] Train: [11/20][189/510] Data 9.960 (3.783) Batch 41.611 (27.942) Remain 38:07:01 loss: 0.1918 loss_seg: 0.1037 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:05:43,608 INFO misc.py line 117 726] Train: [11/20][190/510] Data 9.957 (3.816) Batch 42.819 (28.021) Remain 38:13:04 loss: 0.2640 loss_seg: 0.1613 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:06:11,394 INFO misc.py line 117 726] Train: [11/20][191/510] Data 4.632 (3.820) Batch 27.786 (28.020) Remain 38:12:30 loss: 0.3374 loss_seg: 0.2400 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:06:38,513 INFO misc.py line 117 726] Train: [11/20][192/510] Data 3.710 (3.820) Batch 27.120 (28.015) Remain 38:11:38 loss: 0.2638 loss_seg: 0.1676 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:07:07,200 INFO misc.py line 117 726] Train: [11/20][193/510] Data 3.251 (3.817) Batch 28.687 (28.019) Remain 38:11:28 loss: 0.2517 loss_seg: 0.1510 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:07:33,077 INFO misc.py line 117 726] Train: [11/20][194/510] Data 4.518 (3.820) Batch 25.877 (28.008) Remain 38:10:05 loss: 0.2905 loss_seg: 0.1892 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:08:01,171 INFO misc.py line 117 726] Train: [11/20][195/510] Data 2.697 (3.815) Batch 28.094 (28.008) Remain 38:09:39 loss: 0.2300 loss_seg: 0.1361 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:08:24,383 INFO misc.py line 117 726] Train: [11/20][196/510] Data 2.751 (3.809) Batch 23.212 (27.983) Remain 38:07:09 loss: 0.2012 loss_seg: 0.1116 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:08:53,855 INFO misc.py line 117 726] Train: [11/20][197/510] Data 3.311 (3.806) Batch 29.472 (27.991) Remain 38:07:19 loss: 0.2049 loss_seg: 0.1174 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:09:18,409 INFO misc.py line 117 726] Train: [11/20][198/510] Data 2.440 (3.799) Batch 24.555 (27.973) Remain 38:05:24 loss: 0.2959 loss_seg: 0.1863 loss_superpoint_edge: 0.0424 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:09:48,957 INFO misc.py line 117 726] Train: [11/20][199/510] Data 3.881 (3.800) Batch 30.548 (27.986) Remain 38:06:01 loss: 0.2430 loss_seg: 0.1539 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:10:17,630 INFO misc.py line 117 726] Train: [11/20][200/510] Data 3.079 (3.796) Batch 28.672 (27.990) Remain 38:05:50 loss: 0.2663 loss_seg: 0.1649 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:10:17,630 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 10:10:48,311 INFO misc.py line 117 726] Train: [11/20][201/510] Data 3.811 (3.796) Batch 30.681 (28.003) Remain 38:06:28 loss: 0.2285 loss_seg: 0.1318 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:11:10,633 INFO misc.py line 117 726] Train: [11/20][202/510] Data 2.190 (3.788) Batch 22.322 (27.975) Remain 38:03:40 loss: 0.2569 loss_seg: 0.1611 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:11:37,557 INFO misc.py line 117 726] Train: [11/20][203/510] Data 2.971 (3.784) Batch 26.924 (27.970) Remain 38:02:47 loss: 0.2670 loss_seg: 0.1718 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:12:01,553 INFO misc.py line 117 726] Train: [11/20][204/510] Data 2.771 (3.779) Batch 23.997 (27.950) Remain 38:00:42 loss: 0.2898 loss_seg: 0.1851 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:12:38,954 INFO misc.py line 117 726] Train: [11/20][205/510] Data 7.297 (3.797) Batch 37.401 (27.997) Remain 38:04:03 loss: 0.3101 loss_seg: 0.2055 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:13:08,864 INFO misc.py line 117 726] Train: [11/20][206/510] Data 3.328 (3.794) Batch 29.910 (28.006) Remain 38:04:21 loss: 0.2409 loss_seg: 0.1485 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:13:39,543 INFO misc.py line 117 726] Train: [11/20][207/510] Data 3.021 (3.790) Batch 30.679 (28.019) Remain 38:04:57 loss: 0.2373 loss_seg: 0.1424 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:13:59,720 INFO misc.py line 117 726] Train: [11/20][208/510] Data 2.476 (3.784) Batch 20.177 (27.981) Remain 38:01:22 loss: 0.1814 loss_seg: 0.0907 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:14:24,994 INFO misc.py line 117 726] Train: [11/20][209/510] Data 4.582 (3.788) Batch 25.273 (27.968) Remain 37:59:50 loss: 0.5151 loss_seg: 0.4150 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:14:54,349 INFO misc.py line 117 726] Train: [11/20][210/510] Data 3.675 (3.787) Batch 29.356 (27.974) Remain 37:59:55 loss: 0.2555 loss_seg: 0.1602 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:15:15,936 INFO misc.py line 117 726] Train: [11/20][211/510] Data 2.099 (3.779) Batch 21.587 (27.944) Remain 37:56:57 loss: 0.2143 loss_seg: 0.1228 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:15:41,036 INFO misc.py line 117 726] Train: [11/20][212/510] Data 2.912 (3.775) Batch 25.100 (27.930) Remain 37:55:22 loss: 0.2692 loss_seg: 0.1683 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:16:07,878 INFO misc.py line 117 726] Train: [11/20][213/510] Data 5.352 (3.783) Batch 26.842 (27.925) Remain 37:54:29 loss: 0.1812 loss_seg: 0.0956 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:16:33,833 INFO misc.py line 117 726] Train: [11/20][214/510] Data 2.553 (3.777) Batch 25.955 (27.916) Remain 37:53:15 loss: 0.2686 loss_seg: 0.1725 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:17:05,477 INFO misc.py line 117 726] Train: [11/20][215/510] Data 3.189 (3.774) Batch 31.644 (27.933) Remain 37:54:13 loss: 0.2083 loss_seg: 0.1188 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:17:40,404 INFO misc.py line 117 726] Train: [11/20][216/510] Data 3.927 (3.775) Batch 34.927 (27.966) Remain 37:56:26 loss: 0.3088 loss_seg: 0.1994 loss_superpoint_edge: 0.0427 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:18:08,308 INFO misc.py line 117 726] Train: [11/20][217/510] Data 3.873 (3.775) Batch 27.904 (27.966) Remain 37:55:56 loss: 0.3019 loss_seg: 0.1921 loss_superpoint_edge: 0.0434 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:18:39,999 INFO misc.py line 117 726] Train: [11/20][218/510] Data 4.719 (3.780) Batch 31.691 (27.983) Remain 37:56:53 loss: 0.2483 loss_seg: 0.1573 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:19:04,174 INFO misc.py line 117 726] Train: [11/20][219/510] Data 2.849 (3.775) Batch 24.176 (27.965) Remain 37:54:59 loss: 0.3128 loss_seg: 0.2198 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:19:32,160 INFO misc.py line 117 726] Train: [11/20][220/510] Data 2.742 (3.770) Batch 27.985 (27.966) Remain 37:54:31 loss: 0.2187 loss_seg: 0.1274 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:20:01,744 INFO misc.py line 117 726] Train: [11/20][221/510] Data 4.152 (3.772) Batch 29.584 (27.973) Remain 37:54:40 loss: 0.3241 loss_seg: 0.2297 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:20:16,453 INFO misc.py line 117 726] Train: [11/20][222/510] Data 2.154 (3.765) Batch 14.709 (27.912) Remain 37:49:16 loss: 0.1891 loss_seg: 0.1002 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:20:47,978 INFO misc.py line 117 726] Train: [11/20][223/510] Data 3.301 (3.763) Batch 31.525 (27.929) Remain 37:50:09 loss: 0.2472 loss_seg: 0.1507 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0320 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:21:17,379 INFO misc.py line 117 726] Train: [11/20][224/510] Data 5.197 (3.769) Batch 29.401 (27.936) Remain 37:50:13 loss: 0.3197 loss_seg: 0.2108 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:21:40,672 INFO misc.py line 117 726] Train: [11/20][225/510] Data 3.257 (3.767) Batch 23.293 (27.915) Remain 37:48:03 loss: 0.2644 loss_seg: 0.1640 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:22:01,473 INFO misc.py line 117 726] Train: [11/20][226/510] Data 2.185 (3.760) Batch 20.801 (27.883) Remain 37:45:00 loss: 0.1797 loss_seg: 0.0969 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:22:32,735 INFO misc.py line 117 726] Train: [11/20][227/510] Data 3.803 (3.760) Batch 31.262 (27.898) Remain 37:45:45 loss: 0.2867 loss_seg: 0.1866 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:22:59,301 INFO misc.py line 117 726] Train: [11/20][228/510] Data 4.144 (3.762) Batch 26.567 (27.892) Remain 37:44:49 loss: 0.2281 loss_seg: 0.1338 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:23:26,442 INFO misc.py line 117 726] Train: [11/20][229/510] Data 2.343 (3.755) Batch 27.140 (27.889) Remain 37:44:05 loss: 0.3793 loss_seg: 0.2642 loss_superpoint_edge: 0.0456 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:23:51,229 INFO misc.py line 117 726] Train: [11/20][230/510] Data 2.713 (3.751) Batch 24.787 (27.875) Remain 37:42:30 loss: 0.2201 loss_seg: 0.1287 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:24:28,164 INFO misc.py line 117 726] Train: [11/20][231/510] Data 4.554 (3.754) Batch 36.935 (27.915) Remain 37:45:16 loss: 0.2322 loss_seg: 0.1409 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:24:49,305 INFO misc.py line 117 726] Train: [11/20][232/510] Data 2.448 (3.749) Batch 21.141 (27.885) Remain 37:42:24 loss: 0.2619 loss_seg: 0.1612 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:25:21,310 INFO misc.py line 117 726] Train: [11/20][233/510] Data 5.394 (3.756) Batch 32.004 (27.903) Remain 37:43:23 loss: 0.2529 loss_seg: 0.1567 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:25:46,948 INFO misc.py line 117 726] Train: [11/20][234/510] Data 2.210 (3.749) Batch 25.639 (27.893) Remain 37:42:08 loss: 0.2207 loss_seg: 0.1228 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:26:06,242 INFO misc.py line 117 726] Train: [11/20][235/510] Data 2.417 (3.743) Batch 19.293 (27.856) Remain 37:38:39 loss: 0.2431 loss_seg: 0.1434 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:26:28,226 INFO misc.py line 117 726] Train: [11/20][236/510] Data 3.113 (3.741) Batch 21.984 (27.831) Remain 37:36:09 loss: 0.2021 loss_seg: 0.1147 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:27:01,332 INFO misc.py line 117 726] Train: [11/20][237/510] Data 4.359 (3.743) Batch 33.106 (27.853) Remain 37:37:31 loss: 0.2387 loss_seg: 0.1461 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:27:31,858 INFO misc.py line 117 726] Train: [11/20][238/510] Data 3.480 (3.742) Batch 30.526 (27.865) Remain 37:37:58 loss: 0.2425 loss_seg: 0.1489 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:28:01,394 INFO misc.py line 117 726] Train: [11/20][239/510] Data 2.610 (3.737) Batch 29.536 (27.872) Remain 37:38:05 loss: 0.1821 loss_seg: 0.0992 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:28:34,791 INFO misc.py line 117 726] Train: [11/20][240/510] Data 3.662 (3.737) Batch 33.397 (27.895) Remain 37:39:30 loss: 0.1927 loss_seg: 0.1054 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:29:07,256 INFO misc.py line 117 726] Train: [11/20][241/510] Data 4.479 (3.740) Batch 32.464 (27.914) Remain 37:40:36 loss: 0.2600 loss_seg: 0.1625 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:29:40,648 INFO misc.py line 117 726] Train: [11/20][242/510] Data 7.253 (3.755) Batch 33.393 (27.937) Remain 37:41:59 loss: 0.1997 loss_seg: 0.1137 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:29:57,650 INFO misc.py line 117 726] Train: [11/20][243/510] Data 1.822 (3.747) Batch 17.002 (27.892) Remain 37:37:50 loss: 0.2513 loss_seg: 0.1532 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:30:18,926 INFO misc.py line 117 726] Train: [11/20][244/510] Data 1.393 (3.737) Batch 21.276 (27.864) Remain 37:35:09 loss: 0.2964 loss_seg: 0.1903 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:30:49,073 INFO misc.py line 117 726] Train: [11/20][245/510] Data 4.301 (3.739) Batch 30.147 (27.874) Remain 37:35:26 loss: 0.2042 loss_seg: 0.1152 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:31:23,509 INFO misc.py line 117 726] Train: [11/20][246/510] Data 9.920 (3.765) Batch 34.436 (27.901) Remain 37:37:10 loss: 0.2940 loss_seg: 0.1884 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:31:50,449 INFO misc.py line 117 726] Train: [11/20][247/510] Data 4.238 (3.767) Batch 26.941 (27.897) Remain 37:36:23 loss: 0.1838 loss_seg: 0.0979 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:32:14,185 INFO misc.py line 117 726] Train: [11/20][248/510] Data 2.947 (3.763) Batch 23.735 (27.880) Remain 37:34:32 loss: 0.3289 loss_seg: 0.2332 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:32:43,038 INFO misc.py line 117 726] Train: [11/20][249/510] Data 3.291 (3.762) Batch 28.853 (27.884) Remain 37:34:24 loss: 0.1971 loss_seg: 0.1124 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:33:08,871 INFO misc.py line 117 726] Train: [11/20][250/510] Data 2.877 (3.758) Batch 25.833 (27.875) Remain 37:33:16 loss: 0.2007 loss_seg: 0.1135 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:33:08,871 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 10:33:34,901 INFO misc.py line 117 726] Train: [11/20][251/510] Data 3.097 (3.755) Batch 26.030 (27.868) Remain 37:32:12 loss: 0.3140 loss_seg: 0.2095 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:34:05,621 INFO misc.py line 117 726] Train: [11/20][252/510] Data 4.407 (3.758) Batch 30.720 (27.879) Remain 37:32:39 loss: 0.2459 loss_seg: 0.1529 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:34:40,308 INFO misc.py line 117 726] Train: [11/20][253/510] Data 7.893 (3.774) Batch 34.688 (27.907) Remain 37:34:23 loss: 0.2378 loss_seg: 0.1478 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:35:07,091 INFO misc.py line 117 726] Train: [11/20][254/510] Data 3.135 (3.772) Batch 26.783 (27.902) Remain 37:33:34 loss: 0.2213 loss_seg: 0.1287 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:35:37,179 INFO misc.py line 117 726] Train: [11/20][255/510] Data 3.816 (3.772) Batch 30.087 (27.911) Remain 37:33:48 loss: 0.2190 loss_seg: 0.1278 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:36:08,956 INFO misc.py line 117 726] Train: [11/20][256/510] Data 4.662 (3.776) Batch 31.777 (27.926) Remain 37:34:34 loss: 0.2044 loss_seg: 0.1176 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:36:33,812 INFO misc.py line 117 726] Train: [11/20][257/510] Data 2.520 (3.771) Batch 24.857 (27.914) Remain 37:33:07 loss: 0.2880 loss_seg: 0.1811 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:37:03,816 INFO misc.py line 117 726] Train: [11/20][258/510] Data 4.912 (3.775) Batch 30.003 (27.922) Remain 37:33:19 loss: 0.3492 loss_seg: 0.2369 loss_superpoint_edge: 0.0443 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:37:34,419 INFO misc.py line 117 726] Train: [11/20][259/510] Data 3.870 (3.775) Batch 30.603 (27.933) Remain 37:33:42 loss: 0.2317 loss_seg: 0.1402 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:38:00,346 INFO misc.py line 117 726] Train: [11/20][260/510] Data 2.909 (3.772) Batch 25.927 (27.925) Remain 37:32:36 loss: 0.2247 loss_seg: 0.1338 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:38:22,801 INFO misc.py line 117 726] Train: [11/20][261/510] Data 2.780 (3.768) Batch 22.455 (27.904) Remain 37:30:26 loss: 0.3053 loss_seg: 0.1950 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:38:42,447 INFO misc.py line 117 726] Train: [11/20][262/510] Data 2.414 (3.763) Batch 19.646 (27.872) Remain 37:27:24 loss: 0.2455 loss_seg: 0.1500 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:39:14,436 INFO misc.py line 117 726] Train: [11/20][263/510] Data 4.957 (3.768) Batch 31.989 (27.888) Remain 37:28:12 loss: 0.3080 loss_seg: 0.2029 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:39:44,425 INFO misc.py line 117 726] Train: [11/20][264/510] Data 4.052 (3.769) Batch 29.989 (27.896) Remain 37:28:23 loss: 0.2329 loss_seg: 0.1406 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:40:09,427 INFO misc.py line 117 726] Train: [11/20][265/510] Data 2.344 (3.763) Batch 25.002 (27.885) Remain 37:27:02 loss: 0.3161 loss_seg: 0.2036 loss_superpoint_edge: 0.0466 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:40:37,967 INFO misc.py line 117 726] Train: [11/20][266/510] Data 4.478 (3.766) Batch 28.539 (27.887) Remain 37:26:46 loss: 0.2446 loss_seg: 0.1481 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:41:03,737 INFO misc.py line 117 726] Train: [11/20][267/510] Data 3.073 (3.763) Batch 25.771 (27.879) Remain 37:25:40 loss: 0.3022 loss_seg: 0.2012 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:41:28,990 INFO misc.py line 117 726] Train: [11/20][268/510] Data 4.143 (3.765) Batch 25.253 (27.869) Remain 37:24:24 loss: 0.2217 loss_seg: 0.1308 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:41:58,111 INFO misc.py line 117 726] Train: [11/20][269/510] Data 3.421 (3.764) Batch 29.120 (27.874) Remain 37:24:19 loss: 0.2572 loss_seg: 0.1605 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:42:23,861 INFO misc.py line 117 726] Train: [11/20][270/510] Data 2.800 (3.760) Batch 25.751 (27.866) Remain 37:23:12 loss: 0.2657 loss_seg: 0.1626 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:42:51,689 INFO misc.py line 117 726] Train: [11/20][271/510] Data 2.975 (3.757) Batch 27.827 (27.866) Remain 37:22:44 loss: 0.2161 loss_seg: 0.1269 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:43:21,535 INFO misc.py line 117 726] Train: [11/20][272/510] Data 3.605 (3.756) Batch 29.846 (27.873) Remain 37:22:52 loss: 0.2507 loss_seg: 0.1562 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:43:41,344 INFO misc.py line 117 726] Train: [11/20][273/510] Data 1.904 (3.750) Batch 19.809 (27.843) Remain 37:20:00 loss: 0.2899 loss_seg: 0.1968 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:44:16,776 INFO misc.py line 117 726] Train: [11/20][274/510] Data 6.631 (3.760) Batch 35.432 (27.871) Remain 37:21:47 loss: 0.2305 loss_seg: 0.1324 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:44:41,978 INFO misc.py line 117 726] Train: [11/20][275/510] Data 2.462 (3.755) Batch 25.202 (27.862) Remain 37:20:32 loss: 0.2336 loss_seg: 0.1384 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:45:14,993 INFO misc.py line 117 726] Train: [11/20][276/510] Data 5.309 (3.761) Batch 33.014 (27.880) Remain 37:21:35 loss: 0.2389 loss_seg: 0.1447 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:45:43,164 INFO misc.py line 117 726] Train: [11/20][277/510] Data 2.993 (3.758) Batch 28.172 (27.882) Remain 37:21:12 loss: 0.2827 loss_seg: 0.1891 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:46:08,756 INFO misc.py line 117 726] Train: [11/20][278/510] Data 2.981 (3.755) Batch 25.592 (27.873) Remain 37:20:04 loss: 0.2248 loss_seg: 0.1353 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:46:39,318 INFO misc.py line 117 726] Train: [11/20][279/510] Data 3.928 (3.756) Batch 30.562 (27.883) Remain 37:20:23 loss: 0.3142 loss_seg: 0.2044 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:47:11,323 INFO misc.py line 117 726] Train: [11/20][280/510] Data 5.148 (3.761) Batch 32.005 (27.898) Remain 37:21:07 loss: 0.3175 loss_seg: 0.2224 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:47:47,774 INFO misc.py line 117 726] Train: [11/20][281/510] Data 5.066 (3.766) Batch 36.450 (27.929) Remain 37:23:07 loss: 0.1895 loss_seg: 0.1042 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:48:16,626 INFO misc.py line 117 726] Train: [11/20][282/510] Data 2.894 (3.763) Batch 28.852 (27.932) Remain 37:22:55 loss: 0.2964 loss_seg: 0.1970 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:48:50,165 INFO misc.py line 117 726] Train: [11/20][283/510] Data 5.423 (3.769) Batch 33.540 (27.952) Remain 37:24:04 loss: 0.4560 loss_seg: 0.3518 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:49:15,556 INFO misc.py line 117 726] Train: [11/20][284/510] Data 2.883 (3.765) Batch 25.390 (27.943) Remain 37:22:52 loss: 0.1731 loss_seg: 0.0912 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:49:40,637 INFO misc.py line 117 726] Train: [11/20][285/510] Data 2.480 (3.761) Batch 25.082 (27.933) Remain 37:21:35 loss: 0.2465 loss_seg: 0.1481 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:50:07,565 INFO misc.py line 117 726] Train: [11/20][286/510] Data 3.073 (3.758) Batch 26.928 (27.929) Remain 37:20:50 loss: 0.2351 loss_seg: 0.1398 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:50:31,721 INFO misc.py line 117 726] Train: [11/20][287/510] Data 2.029 (3.752) Batch 24.156 (27.916) Remain 37:19:18 loss: 0.2248 loss_seg: 0.1307 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:50:55,495 INFO misc.py line 117 726] Train: [11/20][288/510] Data 2.476 (3.748) Batch 23.775 (27.901) Remain 37:17:40 loss: 0.2517 loss_seg: 0.1580 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:51:23,810 INFO misc.py line 117 726] Train: [11/20][289/510] Data 2.778 (3.745) Batch 28.315 (27.903) Remain 37:17:20 loss: 0.3216 loss_seg: 0.2132 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:51:40,928 INFO misc.py line 117 726] Train: [11/20][290/510] Data 1.525 (3.737) Batch 17.118 (27.865) Remain 37:13:51 loss: 0.2012 loss_seg: 0.1128 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:52:08,965 INFO misc.py line 117 726] Train: [11/20][291/510] Data 3.426 (3.736) Batch 28.036 (27.866) Remain 37:13:26 loss: 0.3402 loss_seg: 0.2279 loss_superpoint_edge: 0.0451 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0341 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:52:45,036 INFO misc.py line 117 726] Train: [11/20][292/510] Data 6.537 (3.745) Batch 36.071 (27.894) Remain 37:15:15 loss: 0.2201 loss_seg: 0.1308 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:53:15,817 INFO misc.py line 117 726] Train: [11/20][293/510] Data 2.863 (3.742) Batch 30.781 (27.904) Remain 37:15:34 loss: 0.2118 loss_seg: 0.1208 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:53:44,281 INFO misc.py line 117 726] Train: [11/20][294/510] Data 3.468 (3.741) Batch 28.464 (27.906) Remain 37:15:16 loss: 0.2788 loss_seg: 0.1927 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:54:17,878 INFO misc.py line 117 726] Train: [11/20][295/510] Data 4.437 (3.744) Batch 33.597 (27.926) Remain 37:16:22 loss: 0.2584 loss_seg: 0.1622 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:54:41,543 INFO misc.py line 117 726] Train: [11/20][296/510] Data 2.402 (3.739) Batch 23.665 (27.911) Remain 37:14:44 loss: 0.2543 loss_seg: 0.1538 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:55:06,565 INFO misc.py line 117 726] Train: [11/20][297/510] Data 4.192 (3.741) Batch 25.021 (27.901) Remain 37:13:29 loss: 0.3839 loss_seg: 0.2859 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:55:37,981 INFO misc.py line 117 726] Train: [11/20][298/510] Data 3.193 (3.739) Batch 31.417 (27.913) Remain 37:13:58 loss: 0.1958 loss_seg: 0.1073 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:56:01,040 INFO misc.py line 117 726] Train: [11/20][299/510] Data 3.037 (3.737) Batch 23.059 (27.897) Remain 37:12:11 loss: 0.3280 loss_seg: 0.2278 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:56:27,625 INFO misc.py line 117 726] Train: [11/20][300/510] Data 3.267 (3.735) Batch 26.584 (27.892) Remain 37:11:22 loss: 0.2031 loss_seg: 0.1143 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:56:27,626 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 10:56:49,205 INFO misc.py line 117 726] Train: [11/20][301/510] Data 2.652 (3.731) Batch 21.580 (27.871) Remain 37:09:13 loss: 0.2401 loss_seg: 0.1356 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:57:19,994 INFO misc.py line 117 726] Train: [11/20][302/510] Data 3.942 (3.732) Batch 30.789 (27.881) Remain 37:09:32 loss: 0.1996 loss_seg: 0.1098 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:57:46,461 INFO misc.py line 117 726] Train: [11/20][303/510] Data 4.865 (3.736) Batch 26.467 (27.876) Remain 37:08:41 loss: 0.2357 loss_seg: 0.1476 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:58:06,906 INFO misc.py line 117 726] Train: [11/20][304/510] Data 2.783 (3.733) Batch 20.446 (27.851) Remain 37:06:15 loss: 0.2038 loss_seg: 0.1124 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:58:33,959 INFO misc.py line 117 726] Train: [11/20][305/510] Data 2.876 (3.730) Batch 27.053 (27.849) Remain 37:05:34 loss: 0.2648 loss_seg: 0.1668 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:59:02,278 INFO misc.py line 117 726] Train: [11/20][306/510] Data 2.877 (3.727) Batch 28.318 (27.850) Remain 37:05:14 loss: 0.2219 loss_seg: 0.1306 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:59:30,630 INFO misc.py line 117 726] Train: [11/20][307/510] Data 3.700 (3.727) Batch 28.352 (27.852) Remain 37:04:54 loss: 0.2366 loss_seg: 0.1410 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 10:59:59,971 INFO misc.py line 117 726] Train: [11/20][308/510] Data 5.804 (3.734) Batch 29.341 (27.857) Remain 37:04:50 loss: 0.4455 loss_seg: 0.3467 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:00:33,066 INFO misc.py line 117 726] Train: [11/20][309/510] Data 3.428 (3.733) Batch 33.096 (27.874) Remain 37:05:44 loss: 0.2324 loss_seg: 0.1372 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:01:09,444 INFO misc.py line 117 726] Train: [11/20][310/510] Data 6.833 (3.743) Batch 36.378 (27.902) Remain 37:07:29 loss: 0.2778 loss_seg: 0.1720 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:01:31,515 INFO misc.py line 117 726] Train: [11/20][311/510] Data 1.860 (3.737) Batch 22.071 (27.883) Remain 37:05:30 loss: 0.3296 loss_seg: 0.2299 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:02:13,110 INFO misc.py line 117 726] Train: [11/20][312/510] Data 7.749 (3.750) Batch 41.595 (27.927) Remain 37:08:35 loss: 0.2922 loss_seg: 0.1930 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:02:44,133 INFO misc.py line 117 726] Train: [11/20][313/510] Data 3.297 (3.748) Batch 31.023 (27.937) Remain 37:08:54 loss: 0.2124 loss_seg: 0.1233 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:03:16,329 INFO misc.py line 117 726] Train: [11/20][314/510] Data 5.991 (3.755) Batch 32.195 (27.951) Remain 37:09:32 loss: 0.2347 loss_seg: 0.1423 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0443 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:03:51,702 INFO misc.py line 117 726] Train: [11/20][315/510] Data 5.352 (3.761) Batch 35.373 (27.975) Remain 37:10:58 loss: 0.2763 loss_seg: 0.1805 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:04:22,287 INFO misc.py line 117 726] Train: [11/20][316/510] Data 3.591 (3.760) Batch 30.586 (27.983) Remain 37:11:10 loss: 0.2305 loss_seg: 0.1384 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:04:52,368 INFO misc.py line 117 726] Train: [11/20][317/510] Data 5.566 (3.766) Batch 30.081 (27.990) Remain 37:11:14 loss: 0.2693 loss_seg: 0.1735 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:05:15,314 INFO misc.py line 117 726] Train: [11/20][318/510] Data 3.284 (3.764) Batch 22.946 (27.974) Remain 37:09:29 loss: 0.2155 loss_seg: 0.1246 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:05:42,177 INFO misc.py line 117 726] Train: [11/20][319/510] Data 2.985 (3.762) Batch 26.863 (27.970) Remain 37:08:44 loss: 0.3090 loss_seg: 0.2045 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:06:12,730 INFO misc.py line 117 726] Train: [11/20][320/510] Data 5.343 (3.767) Batch 30.553 (27.978) Remain 37:08:55 loss: 0.4661 loss_seg: 0.3481 loss_superpoint_edge: 0.0482 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:06:33,856 INFO misc.py line 117 726] Train: [11/20][321/510] Data 2.049 (3.761) Batch 21.126 (27.957) Remain 37:06:44 loss: 0.1906 loss_seg: 0.1064 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:07:09,267 INFO misc.py line 117 726] Train: [11/20][322/510] Data 10.413 (3.782) Batch 35.411 (27.980) Remain 37:08:08 loss: 0.2107 loss_seg: 0.1212 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:07:38,819 INFO misc.py line 117 726] Train: [11/20][323/510] Data 3.416 (3.781) Batch 29.552 (27.985) Remain 37:08:04 loss: 0.2464 loss_seg: 0.1535 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:08:01,812 INFO misc.py line 117 726] Train: [11/20][324/510] Data 3.210 (3.779) Batch 22.993 (27.969) Remain 37:06:21 loss: 0.1864 loss_seg: 0.0943 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:08:26,715 INFO misc.py line 117 726] Train: [11/20][325/510] Data 3.336 (3.778) Batch 24.903 (27.960) Remain 37:05:08 loss: 0.2215 loss_seg: 0.1285 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:09:00,068 INFO misc.py line 117 726] Train: [11/20][326/510] Data 4.807 (3.781) Batch 33.353 (27.977) Remain 37:06:00 loss: 0.3647 loss_seg: 0.2642 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:09:34,547 INFO misc.py line 117 726] Train: [11/20][327/510] Data 7.895 (3.794) Batch 34.479 (27.997) Remain 37:07:08 loss: 0.2170 loss_seg: 0.1286 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:10:01,205 INFO misc.py line 117 726] Train: [11/20][328/510] Data 4.841 (3.797) Batch 26.657 (27.993) Remain 37:06:20 loss: 0.2725 loss_seg: 0.1785 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:10:30,830 INFO misc.py line 117 726] Train: [11/20][329/510] Data 4.473 (3.799) Batch 29.626 (27.998) Remain 37:06:16 loss: 0.1949 loss_seg: 0.1067 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:10:57,093 INFO misc.py line 117 726] Train: [11/20][330/510] Data 3.928 (3.799) Batch 26.264 (27.992) Remain 37:05:22 loss: 0.2885 loss_seg: 0.1925 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:11:19,210 INFO misc.py line 117 726] Train: [11/20][331/510] Data 6.769 (3.809) Batch 22.117 (27.974) Remain 37:03:29 loss: 0.2026 loss_seg: 0.1089 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0446 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:11:40,879 INFO misc.py line 117 726] Train: [11/20][332/510] Data 2.567 (3.805) Batch 21.668 (27.955) Remain 37:01:30 loss: 0.2120 loss_seg: 0.1226 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:12:03,485 INFO misc.py line 117 726] Train: [11/20][333/510] Data 2.151 (3.800) Batch 22.607 (27.939) Remain 36:59:44 loss: 0.2461 loss_seg: 0.1514 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:12:32,869 INFO misc.py line 117 726] Train: [11/20][334/510] Data 5.039 (3.803) Batch 29.383 (27.943) Remain 36:59:37 loss: 0.3099 loss_seg: 0.2046 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:12:50,763 INFO misc.py line 117 726] Train: [11/20][335/510] Data 2.280 (3.799) Batch 17.895 (27.913) Remain 36:56:45 loss: 0.1739 loss_seg: 0.0870 loss_superpoint_edge: 0.0136 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:13:27,501 INFO misc.py line 117 726] Train: [11/20][336/510] Data 7.521 (3.810) Batch 36.738 (27.940) Remain 36:58:24 loss: 0.3039 loss_seg: 0.2103 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:14:02,129 INFO misc.py line 117 726] Train: [11/20][337/510] Data 3.429 (3.809) Batch 34.629 (27.960) Remain 36:59:31 loss: 0.2691 loss_seg: 0.1730 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:14:32,442 INFO misc.py line 117 726] Train: [11/20][338/510] Data 3.620 (3.808) Batch 30.313 (27.967) Remain 36:59:36 loss: 0.2351 loss_seg: 0.1465 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:15:06,588 INFO misc.py line 117 726] Train: [11/20][339/510] Data 3.743 (3.808) Batch 34.146 (27.985) Remain 37:00:36 loss: 0.2294 loss_seg: 0.1375 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:15:40,766 INFO misc.py line 117 726] Train: [11/20][340/510] Data 9.142 (3.824) Batch 34.177 (28.003) Remain 37:01:36 loss: 0.2846 loss_seg: 0.1856 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:16:13,840 INFO misc.py line 117 726] Train: [11/20][341/510] Data 5.952 (3.830) Batch 33.074 (28.018) Remain 37:02:19 loss: 0.2962 loss_seg: 0.1990 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:16:41,192 INFO misc.py line 117 726] Train: [11/20][342/510] Data 2.919 (3.828) Batch 27.353 (28.016) Remain 37:01:42 loss: 0.2327 loss_seg: 0.1397 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0321 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:17:15,286 INFO misc.py line 117 726] Train: [11/20][343/510] Data 5.385 (3.832) Batch 34.094 (28.034) Remain 37:02:39 loss: 0.2333 loss_seg: 0.1434 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:17:50,220 INFO misc.py line 117 726] Train: [11/20][344/510] Data 3.641 (3.832) Batch 34.933 (28.055) Remain 37:03:47 loss: 0.2147 loss_seg: 0.1245 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:18:20,689 INFO misc.py line 117 726] Train: [11/20][345/510] Data 3.336 (3.830) Batch 30.470 (28.062) Remain 37:03:52 loss: 0.2627 loss_seg: 0.1624 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:18:57,320 INFO misc.py line 117 726] Train: [11/20][346/510] Data 5.959 (3.836) Batch 36.630 (28.087) Remain 37:05:23 loss: 0.2471 loss_seg: 0.1479 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:19:20,893 INFO misc.py line 117 726] Train: [11/20][347/510] Data 2.789 (3.833) Batch 23.573 (28.073) Remain 37:03:53 loss: 0.2833 loss_seg: 0.1835 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:19:43,221 INFO misc.py line 117 726] Train: [11/20][348/510] Data 3.023 (3.831) Batch 22.329 (28.057) Remain 37:02:05 loss: 0.2153 loss_seg: 0.1266 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:20:10,801 INFO misc.py line 117 726] Train: [11/20][349/510] Data 3.820 (3.831) Batch 27.580 (28.055) Remain 37:01:31 loss: 0.3287 loss_seg: 0.2227 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:20:37,899 INFO misc.py line 117 726] Train: [11/20][350/510] Data 3.332 (3.830) Batch 27.098 (28.053) Remain 37:00:50 loss: 0.2438 loss_seg: 0.1487 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:20:37,900 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 11:21:12,205 INFO misc.py line 117 726] Train: [11/20][351/510] Data 4.583 (3.832) Batch 34.306 (28.071) Remain 37:01:47 loss: 0.2593 loss_seg: 0.1642 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:21:43,135 INFO misc.py line 117 726] Train: [11/20][352/510] Data 4.062 (3.832) Batch 30.930 (28.079) Remain 37:01:58 loss: 0.1729 loss_seg: 0.0913 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:22:07,215 INFO misc.py line 117 726] Train: [11/20][353/510] Data 3.251 (3.831) Batch 24.080 (28.067) Remain 37:00:35 loss: 0.2274 loss_seg: 0.1372 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:22:29,126 INFO misc.py line 117 726] Train: [11/20][354/510] Data 2.496 (3.827) Batch 21.912 (28.050) Remain 36:58:44 loss: 0.2031 loss_seg: 0.1110 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:22:54,180 INFO misc.py line 117 726] Train: [11/20][355/510] Data 4.963 (3.830) Batch 25.054 (28.041) Remain 36:57:36 loss: 0.3941 loss_seg: 0.2930 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:23:14,919 INFO misc.py line 117 726] Train: [11/20][356/510] Data 2.649 (3.827) Batch 20.739 (28.021) Remain 36:55:29 loss: 0.2477 loss_seg: 0.1541 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:23:37,359 INFO misc.py line 117 726] Train: [11/20][357/510] Data 2.436 (3.823) Batch 22.440 (28.005) Remain 36:53:47 loss: 0.2631 loss_seg: 0.1661 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:24:10,327 INFO misc.py line 117 726] Train: [11/20][358/510] Data 4.229 (3.824) Batch 32.969 (28.019) Remain 36:54:25 loss: 0.3428 loss_seg: 0.2440 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:24:40,364 INFO misc.py line 117 726] Train: [11/20][359/510] Data 3.230 (3.822) Batch 30.037 (28.025) Remain 36:54:24 loss: 0.2185 loss_seg: 0.1308 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:25:02,404 INFO misc.py line 117 726] Train: [11/20][360/510] Data 2.339 (3.818) Batch 22.040 (28.008) Remain 36:52:36 loss: 0.2103 loss_seg: 0.1182 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:25:33,425 INFO misc.py line 117 726] Train: [11/20][361/510] Data 3.615 (3.818) Batch 31.021 (28.016) Remain 36:52:48 loss: 0.3045 loss_seg: 0.2004 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:26:03,509 INFO misc.py line 117 726] Train: [11/20][362/510] Data 5.055 (3.821) Batch 30.084 (28.022) Remain 36:52:47 loss: 0.2602 loss_seg: 0.1670 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:26:23,701 INFO misc.py line 117 726] Train: [11/20][363/510] Data 2.539 (3.817) Batch 20.192 (28.000) Remain 36:50:36 loss: 0.1783 loss_seg: 0.0924 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:26:50,452 INFO misc.py line 117 726] Train: [11/20][364/510] Data 3.128 (3.816) Batch 26.752 (27.997) Remain 36:49:52 loss: 0.2386 loss_seg: 0.1429 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:27:06,880 INFO misc.py line 117 726] Train: [11/20][365/510] Data 2.530 (3.812) Batch 16.428 (27.965) Remain 36:46:53 loss: 0.2979 loss_seg: 0.1908 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:27:20,306 INFO misc.py line 117 726] Train: [11/20][366/510] Data 1.419 (3.805) Batch 13.425 (27.925) Remain 36:43:15 loss: 0.2389 loss_seg: 0.1470 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:27:49,143 INFO misc.py line 117 726] Train: [11/20][367/510] Data 3.900 (3.806) Batch 28.837 (27.927) Remain 36:42:59 loss: 0.2664 loss_seg: 0.1694 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:28:15,658 INFO misc.py line 117 726] Train: [11/20][368/510] Data 5.278 (3.810) Batch 26.516 (27.923) Remain 36:42:13 loss: 0.2208 loss_seg: 0.1264 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:28:38,379 INFO misc.py line 117 726] Train: [11/20][369/510] Data 2.601 (3.806) Batch 22.720 (27.909) Remain 36:40:38 loss: 0.2339 loss_seg: 0.1406 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:28:59,509 INFO misc.py line 117 726] Train: [11/20][370/510] Data 2.009 (3.802) Batch 21.130 (27.891) Remain 36:38:42 loss: 0.2412 loss_seg: 0.1434 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:29:23,202 INFO misc.py line 117 726] Train: [11/20][371/510] Data 2.474 (3.798) Batch 23.693 (27.879) Remain 36:37:21 loss: 0.2257 loss_seg: 0.1320 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:29:58,077 INFO misc.py line 117 726] Train: [11/20][372/510] Data 4.512 (3.800) Batch 34.875 (27.898) Remain 36:38:22 loss: 0.2379 loss_seg: 0.1476 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:30:23,711 INFO misc.py line 117 726] Train: [11/20][373/510] Data 3.914 (3.800) Batch 25.634 (27.892) Remain 36:37:26 loss: 0.2215 loss_seg: 0.1270 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:30:45,427 INFO misc.py line 117 726] Train: [11/20][374/510] Data 2.688 (3.797) Batch 21.716 (27.875) Remain 36:35:39 loss: 0.2774 loss_seg: 0.1796 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:31:08,609 INFO misc.py line 117 726] Train: [11/20][375/510] Data 2.478 (3.794) Batch 23.182 (27.863) Remain 36:34:11 loss: 0.1956 loss_seg: 0.1051 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:31:40,191 INFO misc.py line 117 726] Train: [11/20][376/510] Data 4.056 (3.794) Batch 31.582 (27.873) Remain 36:34:31 loss: 0.2253 loss_seg: 0.1325 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:32:04,728 INFO misc.py line 117 726] Train: [11/20][377/510] Data 2.425 (3.791) Batch 24.537 (27.864) Remain 36:33:21 loss: 0.2301 loss_seg: 0.1339 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:32:32,759 INFO misc.py line 117 726] Train: [11/20][378/510] Data 3.198 (3.789) Batch 28.031 (27.864) Remain 36:32:55 loss: 0.2682 loss_seg: 0.1639 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:33:01,158 INFO misc.py line 117 726] Train: [11/20][379/510] Data 3.491 (3.788) Batch 28.399 (27.866) Remain 36:32:34 loss: 0.2359 loss_seg: 0.1460 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:33:41,277 INFO misc.py line 117 726] Train: [11/20][380/510] Data 7.095 (3.797) Batch 40.119 (27.898) Remain 36:34:39 loss: 0.3874 loss_seg: 0.2801 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:34:06,857 INFO misc.py line 117 726] Train: [11/20][381/510] Data 2.711 (3.794) Batch 25.580 (27.892) Remain 36:33:42 loss: 0.2912 loss_seg: 0.1999 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:34:38,549 INFO misc.py line 117 726] Train: [11/20][382/510] Data 3.169 (3.793) Batch 31.692 (27.902) Remain 36:34:02 loss: 0.2098 loss_seg: 0.1187 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:35:09,471 INFO misc.py line 117 726] Train: [11/20][383/510] Data 2.956 (3.790) Batch 30.922 (27.910) Remain 36:34:11 loss: 0.2149 loss_seg: 0.1259 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:35:31,960 INFO misc.py line 117 726] Train: [11/20][384/510] Data 2.757 (3.788) Batch 22.490 (27.896) Remain 36:32:36 loss: 0.1977 loss_seg: 0.1061 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:36:04,119 INFO misc.py line 117 726] Train: [11/20][385/510] Data 3.601 (3.787) Batch 32.159 (27.907) Remain 36:33:01 loss: 0.2529 loss_seg: 0.1554 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:36:34,845 INFO misc.py line 117 726] Train: [11/20][386/510] Data 5.697 (3.792) Batch 30.726 (27.914) Remain 36:33:08 loss: 0.2616 loss_seg: 0.1699 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:37:06,232 INFO misc.py line 117 726] Train: [11/20][387/510] Data 3.787 (3.792) Batch 31.387 (27.923) Remain 36:33:23 loss: 0.3160 loss_seg: 0.2170 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:37:42,531 INFO misc.py line 117 726] Train: [11/20][388/510] Data 6.498 (3.799) Batch 36.299 (27.945) Remain 36:34:37 loss: 0.1860 loss_seg: 0.0974 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:38:05,625 INFO misc.py line 117 726] Train: [11/20][389/510] Data 3.354 (3.798) Batch 23.094 (27.933) Remain 36:33:10 loss: 0.2516 loss_seg: 0.1543 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:38:32,637 INFO misc.py line 117 726] Train: [11/20][390/510] Data 4.316 (3.799) Batch 27.013 (27.930) Remain 36:32:31 loss: 0.3100 loss_seg: 0.2073 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:38:59,976 INFO misc.py line 117 726] Train: [11/20][391/510] Data 2.849 (3.797) Batch 27.339 (27.929) Remain 36:31:56 loss: 0.2633 loss_seg: 0.1640 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:39:26,109 INFO misc.py line 117 726] Train: [11/20][392/510] Data 2.555 (3.794) Batch 26.132 (27.924) Remain 36:31:06 loss: 0.2939 loss_seg: 0.1890 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:39:55,797 INFO misc.py line 117 726] Train: [11/20][393/510] Data 2.687 (3.791) Batch 29.688 (27.929) Remain 36:31:00 loss: 0.2394 loss_seg: 0.1473 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:40:17,589 INFO misc.py line 117 726] Train: [11/20][394/510] Data 2.338 (3.787) Batch 21.792 (27.913) Remain 36:29:18 loss: 0.2562 loss_seg: 0.1615 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:40:46,405 INFO misc.py line 117 726] Train: [11/20][395/510] Data 4.472 (3.789) Batch 28.816 (27.915) Remain 36:29:01 loss: 0.2659 loss_seg: 0.1713 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:41:13,149 INFO misc.py line 117 726] Train: [11/20][396/510] Data 4.806 (3.791) Batch 26.744 (27.912) Remain 36:28:19 loss: 0.2627 loss_seg: 0.1654 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:41:28,984 INFO misc.py line 117 726] Train: [11/20][397/510] Data 2.040 (3.787) Batch 15.835 (27.882) Remain 36:25:27 loss: 0.1604 loss_seg: 0.0781 loss_superpoint_edge: 0.0085 loss_superpoint_contrast: 0.0438 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:41:55,062 INFO misc.py line 117 726] Train: [11/20][398/510] Data 3.029 (3.785) Batch 26.078 (27.877) Remain 36:24:37 loss: 0.1806 loss_seg: 0.0983 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:42:12,835 INFO misc.py line 117 726] Train: [11/20][399/510] Data 2.220 (3.781) Batch 17.773 (27.852) Remain 36:22:10 loss: 0.1887 loss_seg: 0.1018 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:42:49,550 INFO misc.py line 117 726] Train: [11/20][400/510] Data 3.950 (3.782) Batch 36.715 (27.874) Remain 36:23:27 loss: 0.1833 loss_seg: 0.0960 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:42:49,551 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 11:43:23,840 INFO misc.py line 117 726] Train: [11/20][401/510] Data 7.034 (3.790) Batch 34.290 (27.890) Remain 36:24:14 loss: 0.3074 loss_seg: 0.2038 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:43:47,641 INFO misc.py line 117 726] Train: [11/20][402/510] Data 2.446 (3.786) Batch 23.801 (27.880) Remain 36:22:58 loss: 0.2624 loss_seg: 0.1657 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:44:18,053 INFO misc.py line 117 726] Train: [11/20][403/510] Data 3.427 (3.785) Batch 30.412 (27.886) Remain 36:23:00 loss: 0.2768 loss_seg: 0.1791 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:44:55,230 INFO misc.py line 117 726] Train: [11/20][404/510] Data 6.735 (3.793) Batch 37.177 (27.909) Remain 36:24:21 loss: 0.3132 loss_seg: 0.2115 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:45:10,881 INFO misc.py line 117 726] Train: [11/20][405/510] Data 1.980 (3.788) Batch 15.651 (27.879) Remain 36:21:30 loss: 0.2556 loss_seg: 0.1586 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:45:37,403 INFO misc.py line 117 726] Train: [11/20][406/510] Data 3.510 (3.788) Batch 26.522 (27.875) Remain 36:20:46 loss: 0.2646 loss_seg: 0.1622 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:46:03,509 INFO misc.py line 117 726] Train: [11/20][407/510] Data 3.517 (3.787) Batch 26.106 (27.871) Remain 36:19:58 loss: 0.2427 loss_seg: 0.1448 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:46:36,548 INFO misc.py line 117 726] Train: [11/20][408/510] Data 3.634 (3.787) Batch 33.039 (27.884) Remain 36:20:30 loss: 0.2128 loss_seg: 0.1253 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:47:02,716 INFO misc.py line 117 726] Train: [11/20][409/510] Data 3.338 (3.785) Batch 26.168 (27.880) Remain 36:19:42 loss: 0.2869 loss_seg: 0.1808 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:47:23,273 INFO misc.py line 117 726] Train: [11/20][410/510] Data 2.704 (3.783) Batch 20.557 (27.862) Remain 36:17:50 loss: 0.3469 loss_seg: 0.2432 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:47:52,477 INFO misc.py line 117 726] Train: [11/20][411/510] Data 3.083 (3.781) Batch 29.204 (27.865) Remain 36:17:38 loss: 0.2336 loss_seg: 0.1386 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:48:25,242 INFO misc.py line 117 726] Train: [11/20][412/510] Data 4.095 (3.782) Batch 32.765 (27.877) Remain 36:18:06 loss: 0.2444 loss_seg: 0.1437 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:49:00,605 INFO misc.py line 117 726] Train: [11/20][413/510] Data 3.650 (3.782) Batch 35.363 (27.895) Remain 36:19:04 loss: 0.2710 loss_seg: 0.1720 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:49:31,413 INFO misc.py line 117 726] Train: [11/20][414/510] Data 6.956 (3.789) Batch 30.809 (27.902) Remain 36:19:09 loss: 0.4046 loss_seg: 0.2881 loss_superpoint_edge: 0.0484 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:50:02,857 INFO misc.py line 117 726] Train: [11/20][415/510] Data 3.477 (3.789) Batch 31.444 (27.911) Remain 36:19:21 loss: 0.2386 loss_seg: 0.1403 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:50:18,733 INFO misc.py line 117 726] Train: [11/20][416/510] Data 1.536 (3.783) Batch 15.876 (27.882) Remain 36:16:37 loss: 0.2404 loss_seg: 0.1436 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:50:38,816 INFO misc.py line 117 726] Train: [11/20][417/510] Data 2.549 (3.780) Batch 20.083 (27.863) Remain 36:14:41 loss: 0.3108 loss_seg: 0.1980 loss_superpoint_edge: 0.0465 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:50:58,130 INFO misc.py line 117 726] Train: [11/20][418/510] Data 2.309 (3.777) Batch 19.315 (27.842) Remain 36:12:37 loss: 0.2263 loss_seg: 0.1315 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:51:24,409 INFO misc.py line 117 726] Train: [11/20][419/510] Data 2.905 (3.774) Batch 26.279 (27.838) Remain 36:11:51 loss: 0.3256 loss_seg: 0.2166 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:51:54,699 INFO misc.py line 117 726] Train: [11/20][420/510] Data 2.774 (3.772) Batch 30.290 (27.844) Remain 36:11:51 loss: 0.2434 loss_seg: 0.1465 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:52:23,711 INFO misc.py line 117 726] Train: [11/20][421/510] Data 3.324 (3.771) Batch 29.012 (27.847) Remain 36:11:36 loss: 0.2485 loss_seg: 0.1514 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:52:52,089 INFO misc.py line 117 726] Train: [11/20][422/510] Data 5.576 (3.775) Batch 28.378 (27.848) Remain 36:11:14 loss: 0.2558 loss_seg: 0.1591 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:53:18,447 INFO misc.py line 117 726] Train: [11/20][423/510] Data 3.018 (3.773) Batch 26.357 (27.845) Remain 36:10:30 loss: 0.3436 loss_seg: 0.2419 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:53:56,764 INFO misc.py line 117 726] Train: [11/20][424/510] Data 5.582 (3.778) Batch 38.317 (27.870) Remain 36:11:58 loss: 0.3452 loss_seg: 0.2478 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:54:28,721 INFO misc.py line 117 726] Train: [11/20][425/510] Data 5.256 (3.781) Batch 31.957 (27.879) Remain 36:12:16 loss: 0.3029 loss_seg: 0.1963 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:54:56,937 INFO misc.py line 117 726] Train: [11/20][426/510] Data 3.729 (3.781) Batch 28.217 (27.880) Remain 36:11:51 loss: 0.2647 loss_seg: 0.1729 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:55:28,162 INFO misc.py line 117 726] Train: [11/20][427/510] Data 4.947 (3.784) Batch 31.225 (27.888) Remain 36:12:00 loss: 0.2120 loss_seg: 0.1206 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:55:55,144 INFO misc.py line 117 726] Train: [11/20][428/510] Data 3.185 (3.782) Batch 26.982 (27.886) Remain 36:11:22 loss: 0.2405 loss_seg: 0.1438 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:56:15,523 INFO misc.py line 117 726] Train: [11/20][429/510] Data 2.598 (3.780) Batch 20.379 (27.868) Remain 36:09:32 loss: 0.2361 loss_seg: 0.1410 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:56:44,921 INFO misc.py line 117 726] Train: [11/20][430/510] Data 2.815 (3.777) Batch 29.398 (27.872) Remain 36:09:21 loss: 0.3076 loss_seg: 0.2121 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:57:14,307 INFO misc.py line 117 726] Train: [11/20][431/510] Data 2.743 (3.775) Batch 29.386 (27.875) Remain 36:09:10 loss: 0.2305 loss_seg: 0.1356 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:57:52,596 INFO misc.py line 117 726] Train: [11/20][432/510] Data 5.576 (3.779) Batch 38.289 (27.900) Remain 36:10:35 loss: 0.2660 loss_seg: 0.1621 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:58:26,934 INFO misc.py line 117 726] Train: [11/20][433/510] Data 5.444 (3.783) Batch 34.338 (27.915) Remain 36:11:17 loss: 0.2000 loss_seg: 0.1104 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:58:52,454 INFO misc.py line 117 726] Train: [11/20][434/510] Data 2.982 (3.781) Batch 25.520 (27.909) Remain 36:10:23 loss: 0.2015 loss_seg: 0.1135 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:59:12,217 INFO misc.py line 117 726] Train: [11/20][435/510] Data 2.294 (3.778) Batch 19.763 (27.890) Remain 36:08:27 loss: 0.1935 loss_seg: 0.1055 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:59:29,169 INFO misc.py line 117 726] Train: [11/20][436/510] Data 2.083 (3.774) Batch 16.952 (27.865) Remain 36:06:02 loss: 0.2417 loss_seg: 0.1448 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 11:59:47,303 INFO misc.py line 117 726] Train: [11/20][437/510] Data 2.052 (3.770) Batch 18.134 (27.843) Remain 36:03:49 loss: 0.2578 loss_seg: 0.1617 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:00:20,161 INFO misc.py line 117 726] Train: [11/20][438/510] Data 4.219 (3.771) Batch 32.858 (27.854) Remain 36:04:15 loss: 0.2319 loss_seg: 0.1422 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:00:37,166 INFO misc.py line 117 726] Train: [11/20][439/510] Data 1.827 (3.766) Batch 17.005 (27.829) Remain 36:01:51 loss: 0.2832 loss_seg: 0.1948 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:01:10,726 INFO misc.py line 117 726] Train: [11/20][440/510] Data 3.578 (3.766) Batch 33.560 (27.842) Remain 36:02:25 loss: 0.2346 loss_seg: 0.1377 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:01:39,002 INFO misc.py line 117 726] Train: [11/20][441/510] Data 2.832 (3.764) Batch 28.277 (27.843) Remain 36:02:01 loss: 0.2440 loss_seg: 0.1476 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:02:11,348 INFO misc.py line 117 726] Train: [11/20][442/510] Data 7.358 (3.772) Batch 32.345 (27.854) Remain 36:02:21 loss: 0.2187 loss_seg: 0.1321 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:02:43,954 INFO misc.py line 117 726] Train: [11/20][443/510] Data 6.044 (3.777) Batch 32.607 (27.864) Remain 36:02:44 loss: 0.2089 loss_seg: 0.1196 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:03:06,244 INFO misc.py line 117 726] Train: [11/20][444/510] Data 2.623 (3.775) Batch 22.290 (27.852) Remain 36:01:17 loss: 0.2393 loss_seg: 0.1407 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:03:35,831 INFO misc.py line 117 726] Train: [11/20][445/510] Data 3.156 (3.773) Batch 29.586 (27.856) Remain 36:01:08 loss: 0.1977 loss_seg: 0.1114 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:04:04,677 INFO misc.py line 117 726] Train: [11/20][446/510] Data 3.175 (3.772) Batch 28.846 (27.858) Remain 36:00:50 loss: 0.2792 loss_seg: 0.1832 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:04:33,191 INFO misc.py line 117 726] Train: [11/20][447/510] Data 3.207 (3.771) Batch 28.513 (27.859) Remain 36:00:29 loss: 0.2266 loss_seg: 0.1339 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:05:10,769 INFO misc.py line 117 726] Train: [11/20][448/510] Data 7.212 (3.778) Batch 37.578 (27.881) Remain 36:01:43 loss: 0.2415 loss_seg: 0.1537 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:05:37,383 INFO misc.py line 117 726] Train: [11/20][449/510] Data 2.893 (3.776) Batch 26.614 (27.878) Remain 36:01:02 loss: 0.2618 loss_seg: 0.1562 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:06:08,110 INFO misc.py line 117 726] Train: [11/20][450/510] Data 4.482 (3.778) Batch 30.726 (27.885) Remain 36:01:04 loss: 0.3116 loss_seg: 0.2069 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:06:08,110 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 12:06:47,705 INFO misc.py line 117 726] Train: [11/20][451/510] Data 8.161 (3.788) Batch 39.595 (27.911) Remain 36:02:37 loss: 0.2017 loss_seg: 0.1139 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:07:05,698 INFO misc.py line 117 726] Train: [11/20][452/510] Data 2.564 (3.785) Batch 17.994 (27.889) Remain 36:00:27 loss: 0.2086 loss_seg: 0.1199 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:07:37,908 INFO misc.py line 117 726] Train: [11/20][453/510] Data 5.817 (3.790) Batch 32.210 (27.898) Remain 36:00:43 loss: 0.3257 loss_seg: 0.2196 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:08:03,643 INFO misc.py line 117 726] Train: [11/20][454/510] Data 2.679 (3.787) Batch 25.735 (27.894) Remain 35:59:53 loss: 0.2785 loss_seg: 0.1830 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:08:35,506 INFO misc.py line 117 726] Train: [11/20][455/510] Data 4.100 (3.788) Batch 31.863 (27.902) Remain 36:00:06 loss: 0.2548 loss_seg: 0.1562 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:08:59,805 INFO misc.py line 117 726] Train: [11/20][456/510] Data 3.007 (3.786) Batch 24.300 (27.894) Remain 35:59:01 loss: 0.2021 loss_seg: 0.1120 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:09:35,323 INFO misc.py line 117 726] Train: [11/20][457/510] Data 4.901 (3.788) Batch 35.518 (27.911) Remain 35:59:51 loss: 0.2070 loss_seg: 0.1199 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:10:03,291 INFO misc.py line 117 726] Train: [11/20][458/510] Data 4.260 (3.790) Batch 27.968 (27.911) Remain 35:59:24 loss: 0.2121 loss_seg: 0.1315 loss_superpoint_edge: 0.0136 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:10:31,299 INFO misc.py line 117 726] Train: [11/20][459/510] Data 3.298 (3.788) Batch 28.007 (27.912) Remain 35:58:57 loss: 0.1514 loss_seg: 0.0730 loss_superpoint_edge: 0.0125 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0295 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:10:59,824 INFO misc.py line 117 726] Train: [11/20][460/510] Data 2.788 (3.786) Batch 28.526 (27.913) Remain 35:58:35 loss: 0.2316 loss_seg: 0.1349 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:11:19,401 INFO misc.py line 117 726] Train: [11/20][461/510] Data 2.282 (3.783) Batch 19.577 (27.895) Remain 35:56:43 loss: 0.2762 loss_seg: 0.1745 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:11:47,075 INFO misc.py line 117 726] Train: [11/20][462/510] Data 3.895 (3.783) Batch 27.674 (27.894) Remain 35:56:13 loss: 0.2235 loss_seg: 0.1324 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:12:21,370 INFO misc.py line 117 726] Train: [11/20][463/510] Data 3.510 (3.783) Batch 34.295 (27.908) Remain 35:56:49 loss: 0.2723 loss_seg: 0.1755 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:12:49,692 INFO misc.py line 117 726] Train: [11/20][464/510] Data 6.198 (3.788) Batch 28.322 (27.909) Remain 35:56:26 loss: 0.2046 loss_seg: 0.1143 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:13:16,414 INFO misc.py line 117 726] Train: [11/20][465/510] Data 2.586 (3.785) Batch 26.722 (27.906) Remain 35:55:46 loss: 0.2192 loss_seg: 0.1266 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:13:58,640 INFO misc.py line 117 726] Train: [11/20][466/510] Data 13.050 (3.805) Batch 42.226 (27.937) Remain 35:57:41 loss: 0.2078 loss_seg: 0.1172 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:14:22,827 INFO misc.py line 117 726] Train: [11/20][467/510] Data 3.081 (3.804) Batch 24.187 (27.929) Remain 35:56:36 loss: 0.2774 loss_seg: 0.1739 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:14:48,979 INFO misc.py line 117 726] Train: [11/20][468/510] Data 3.155 (3.802) Batch 26.153 (27.925) Remain 35:55:50 loss: 0.2041 loss_seg: 0.1137 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:15:21,730 INFO misc.py line 117 726] Train: [11/20][469/510] Data 2.762 (3.800) Batch 32.751 (27.936) Remain 35:56:10 loss: 0.2505 loss_seg: 0.1566 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:15:57,983 INFO misc.py line 117 726] Train: [11/20][470/510] Data 4.754 (3.802) Batch 36.252 (27.954) Remain 35:57:05 loss: 0.2519 loss_seg: 0.1571 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:16:35,686 INFO misc.py line 117 726] Train: [11/20][471/510] Data 8.558 (3.812) Batch 37.704 (27.974) Remain 35:58:13 loss: 0.1873 loss_seg: 0.1013 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:17:12,928 INFO misc.py line 117 726] Train: [11/20][472/510] Data 5.848 (3.817) Batch 37.242 (27.994) Remain 35:59:17 loss: 0.2821 loss_seg: 0.1799 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:17:44,015 INFO misc.py line 117 726] Train: [11/20][473/510] Data 3.664 (3.816) Batch 31.087 (28.001) Remain 35:59:19 loss: 0.2315 loss_seg: 0.1402 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:18:09,275 INFO misc.py line 117 726] Train: [11/20][474/510] Data 2.428 (3.813) Batch 25.260 (27.995) Remain 35:58:24 loss: 0.3037 loss_seg: 0.2104 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:18:42,672 INFO misc.py line 117 726] Train: [11/20][475/510] Data 5.708 (3.817) Batch 33.396 (28.006) Remain 35:58:49 loss: 0.2553 loss_seg: 0.1580 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:19:10,992 INFO misc.py line 117 726] Train: [11/20][476/510] Data 3.255 (3.816) Batch 28.321 (28.007) Remain 35:58:24 loss: 0.1924 loss_seg: 0.1041 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:19:39,549 INFO misc.py line 117 726] Train: [11/20][477/510] Data 3.014 (3.814) Batch 28.557 (28.008) Remain 35:58:02 loss: 0.2454 loss_seg: 0.1472 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:20:08,262 INFO misc.py line 117 726] Train: [11/20][478/510] Data 2.857 (3.812) Batch 28.713 (28.010) Remain 35:57:41 loss: 0.2440 loss_seg: 0.1455 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:20:31,625 INFO misc.py line 117 726] Train: [11/20][479/510] Data 5.459 (3.816) Batch 23.363 (28.000) Remain 35:56:27 loss: 0.1748 loss_seg: 0.0865 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:20:56,939 INFO misc.py line 117 726] Train: [11/20][480/510] Data 5.989 (3.820) Batch 25.314 (27.994) Remain 35:55:33 loss: 0.2133 loss_seg: 0.1261 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:21:20,118 INFO misc.py line 117 726] Train: [11/20][481/510] Data 3.333 (3.819) Batch 23.180 (27.984) Remain 35:54:19 loss: 0.2890 loss_seg: 0.1897 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:21:37,549 INFO misc.py line 117 726] Train: [11/20][482/510] Data 2.040 (3.816) Batch 17.431 (27.962) Remain 35:52:09 loss: 0.2781 loss_seg: 0.1760 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:22:02,528 INFO misc.py line 117 726] Train: [11/20][483/510] Data 2.566 (3.813) Batch 24.979 (27.956) Remain 35:51:13 loss: 0.1722 loss_seg: 0.0878 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:22:33,506 INFO misc.py line 117 726] Train: [11/20][484/510] Data 3.746 (3.813) Batch 30.978 (27.962) Remain 35:51:14 loss: 0.2584 loss_seg: 0.1588 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:23:05,623 INFO misc.py line 117 726] Train: [11/20][485/510] Data 4.403 (3.814) Batch 32.117 (27.971) Remain 35:51:25 loss: 0.1994 loss_seg: 0.1148 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:23:30,073 INFO misc.py line 117 726] Train: [11/20][486/510] Data 2.610 (3.812) Batch 24.450 (27.964) Remain 35:50:24 loss: 0.2615 loss_seg: 0.1605 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:23:50,846 INFO misc.py line 117 726] Train: [11/20][487/510] Data 1.958 (3.808) Batch 20.773 (27.949) Remain 35:48:47 loss: 0.1933 loss_seg: 0.1039 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:24:21,761 INFO misc.py line 117 726] Train: [11/20][488/510] Data 3.202 (3.807) Batch 30.914 (27.955) Remain 35:48:48 loss: 0.2075 loss_seg: 0.1137 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:24:44,275 INFO misc.py line 117 726] Train: [11/20][489/510] Data 2.551 (3.804) Batch 22.514 (27.944) Remain 35:47:28 loss: 0.2717 loss_seg: 0.1690 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:25:11,743 INFO misc.py line 117 726] Train: [11/20][490/510] Data 7.753 (3.812) Batch 27.468 (27.943) Remain 35:46:56 loss: 0.2433 loss_seg: 0.1492 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:25:38,418 INFO misc.py line 117 726] Train: [11/20][491/510] Data 3.615 (3.812) Batch 26.675 (27.940) Remain 35:46:16 loss: 0.1859 loss_seg: 0.0995 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:26:06,888 INFO misc.py line 117 726] Train: [11/20][492/510] Data 3.383 (3.811) Batch 28.470 (27.941) Remain 35:45:53 loss: 0.2177 loss_seg: 0.1261 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:26:22,908 INFO misc.py line 117 726] Train: [11/20][493/510] Data 2.393 (3.808) Batch 16.020 (27.917) Remain 35:43:33 loss: 0.2219 loss_seg: 0.1249 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:26:59,096 INFO misc.py line 117 726] Train: [11/20][494/510] Data 4.430 (3.809) Batch 36.187 (27.934) Remain 35:44:22 loss: 0.2310 loss_seg: 0.1403 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:27:31,470 INFO misc.py line 117 726] Train: [11/20][495/510] Data 3.926 (3.810) Batch 32.374 (27.943) Remain 35:44:36 loss: 0.2774 loss_seg: 0.1768 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:27:58,376 INFO misc.py line 117 726] Train: [11/20][496/510] Data 2.892 (3.808) Batch 26.907 (27.941) Remain 35:43:58 loss: 0.2002 loss_seg: 0.1098 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:28:26,643 INFO misc.py line 117 726] Train: [11/20][497/510] Data 2.482 (3.805) Batch 28.266 (27.941) Remain 35:43:33 loss: 0.2318 loss_seg: 0.1353 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:28:50,114 INFO misc.py line 117 726] Train: [11/20][498/510] Data 3.296 (3.804) Batch 23.472 (27.932) Remain 35:42:24 loss: 0.2128 loss_seg: 0.1177 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:29:25,051 INFO misc.py line 117 726] Train: [11/20][499/510] Data 10.200 (3.817) Batch 34.937 (27.946) Remain 35:43:01 loss: 0.1853 loss_seg: 0.0997 loss_superpoint_edge: 0.0139 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:29:59,362 INFO misc.py line 117 726] Train: [11/20][500/510] Data 8.721 (3.827) Batch 34.312 (27.959) Remain 35:43:32 loss: 0.2980 loss_seg: 0.1962 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:29:59,363 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 12:30:30,701 INFO misc.py line 117 726] Train: [11/20][501/510] Data 3.770 (3.827) Batch 31.338 (27.966) Remain 35:43:35 loss: 0.2199 loss_seg: 0.1280 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:31:00,271 INFO misc.py line 117 726] Train: [11/20][502/510] Data 5.443 (3.830) Batch 29.571 (27.969) Remain 35:43:22 loss: 0.2082 loss_seg: 0.1190 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:31:33,845 INFO misc.py line 117 726] Train: [11/20][503/510] Data 3.644 (3.829) Batch 33.574 (27.980) Remain 35:43:46 loss: 0.2973 loss_seg: 0.1897 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:31:54,937 INFO misc.py line 117 726] Train: [11/20][504/510] Data 2.146 (3.826) Batch 21.092 (27.967) Remain 35:42:14 loss: 0.2322 loss_seg: 0.1368 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:32:15,482 INFO misc.py line 117 726] Train: [11/20][505/510] Data 2.299 (3.823) Batch 20.545 (27.952) Remain 35:40:38 loss: 0.2037 loss_seg: 0.1130 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:32:39,341 INFO misc.py line 117 726] Train: [11/20][506/510] Data 2.872 (3.821) Batch 23.859 (27.944) Remain 35:39:33 loss: 0.2130 loss_seg: 0.1199 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:33:10,934 INFO misc.py line 117 726] Train: [11/20][507/510] Data 3.396 (3.820) Batch 31.593 (27.951) Remain 35:39:38 loss: 0.2173 loss_seg: 0.1252 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:33:24,383 INFO misc.py line 117 726] Train: [11/20][508/510] Data 1.821 (3.816) Batch 13.449 (27.922) Remain 35:36:59 loss: 0.3536 loss_seg: 0.2531 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:33:58,623 INFO misc.py line 117 726] Train: [11/20][509/510] Data 3.889 (3.817) Batch 34.241 (27.935) Remain 35:37:28 loss: 0.2737 loss_seg: 0.1683 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:34:27,420 INFO misc.py line 117 726] Train: [11/20][510/510] Data 2.926 (3.815) Batch 28.796 (27.936) Remain 35:37:08 loss: 0.2848 loss_seg: 0.1815 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:34:27,421 INFO misc.py line 147 726] Train result: loss: 0.2514 loss_seg: 0.1561 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-11 12:34:27,422 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-11 12:34:42,970 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7280 [2026-06-11 12:34:58,985 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7033 [2026-06-11 12:36:13,737 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8681 [2026-06-11 12:36:53,961 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9819 [2026-06-11 12:37:13,334 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0158 [2026-06-11 12:37:49,136 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.0095 [2026-06-11 12:38:35,726 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.0917 [2026-06-11 12:38:51,117 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2617 [2026-06-11 12:39:08,854 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.8525 [2026-06-11 12:39:27,514 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3331 [2026-06-11 12:39:43,209 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5145 [2026-06-11 12:40:04,731 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7439 [2026-06-11 12:40:30,493 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8001 [2026-06-11 12:40:41,920 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7476 [2026-06-11 12:41:13,419 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0594 [2026-06-11 12:41:39,442 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3339 [2026-06-11 12:42:05,853 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.1571 [2026-06-11 12:42:48,366 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.0934 [2026-06-11 12:43:09,307 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4064 [2026-06-11 12:43:25,815 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.7830 [2026-06-11 12:43:56,667 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.7709 [2026-06-11 12:44:12,840 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4938 [2026-06-11 12:44:34,521 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2234 [2026-06-11 12:44:55,985 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8240 [2026-06-11 12:45:09,272 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6607 [2026-06-11 12:45:37,104 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5357 [2026-06-11 12:46:18,454 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.2022 [2026-06-11 12:46:35,617 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5374 [2026-06-11 12:46:54,082 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4961 [2026-06-11 12:47:10,780 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3446 [2026-06-11 12:47:35,826 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1935 [2026-06-11 12:47:53,972 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5772 [2026-06-11 12:48:11,387 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1507 [2026-06-11 12:48:35,691 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6664 [2026-06-11 12:48:35,710 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6738/0.7481/0.8978. [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9278/0.9598 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9762/0.9881 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8411/0.9697 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0013/0.0092 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3516/0.4243 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6032/0.6292 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6121/0.7020 [2026-06-11 12:48:35,710 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7856/0.8975 [2026-06-11 12:48:35,711 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9157/0.9579 [2026-06-11 12:48:35,711 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6875/0.7663 [2026-06-11 12:48:35,711 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7629/0.8451 [2026-06-11 12:48:35,711 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6910/0.8650 [2026-06-11 12:48:35,711 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.6031/0.7107 [2026-06-11 12:48:35,711 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-11 12:48:35,712 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-11 12:48:35,712 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 12:49:03,197 INFO misc.py line 117 726] Train: [12/20][1/510] Data 2.862 (2.862) Batch 25.950 (25.950) Remain 33:04:45 loss: 0.1706 loss_seg: 0.0892 loss_superpoint_edge: 0.0146 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:49:43,688 INFO misc.py line 117 726] Train: [12/20][2/510] Data 9.716 (9.716) Batch 40.492 (40.492) Remain 51:36:16 loss: 0.3880 loss_seg: 0.2880 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:50:07,278 INFO misc.py line 117 726] Train: [12/20][3/510] Data 2.877 (2.877) Batch 23.589 (23.589) Remain 30:03:23 loss: 0.3033 loss_seg: 0.2145 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:50:39,271 INFO misc.py line 117 726] Train: [12/20][4/510] Data 4.256 (4.256) Batch 31.994 (31.994) Remain 40:45:23 loss: 0.2783 loss_seg: 0.1730 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:51:14,555 INFO misc.py line 117 726] Train: [12/20][5/510] Data 5.621 (4.938) Batch 35.284 (33.639) Remain 42:50:34 loss: 0.2642 loss_seg: 0.1650 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:51:40,455 INFO misc.py line 117 726] Train: [12/20][6/510] Data 2.770 (4.215) Batch 25.900 (31.059) Remain 39:32:55 loss: 0.1771 loss_seg: 0.0933 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:52:04,354 INFO misc.py line 117 726] Train: [12/20][7/510] Data 3.024 (3.918) Batch 23.899 (29.269) Remain 37:15:40 loss: 0.2777 loss_seg: 0.1722 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:52:29,394 INFO misc.py line 117 726] Train: [12/20][8/510] Data 2.152 (3.565) Batch 25.039 (28.423) Remain 36:10:34 loss: 0.2578 loss_seg: 0.1590 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:53:06,297 INFO misc.py line 117 726] Train: [12/20][9/510] Data 5.267 (3.848) Batch 36.904 (29.837) Remain 37:58:01 loss: 0.2360 loss_seg: 0.1434 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:53:30,118 INFO misc.py line 117 726] Train: [12/20][10/510] Data 2.719 (3.687) Batch 23.821 (28.977) Remain 36:51:55 loss: 0.1977 loss_seg: 0.1089 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:54:07,692 INFO misc.py line 117 726] Train: [12/20][11/510] Data 4.447 (3.782) Batch 37.574 (30.052) Remain 38:13:27 loss: 0.1803 loss_seg: 0.0973 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:54:37,651 INFO misc.py line 117 726] Train: [12/20][12/510] Data 5.261 (3.946) Batch 29.959 (30.041) Remain 38:12:09 loss: 0.2513 loss_seg: 0.1510 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:54:56,744 INFO misc.py line 117 726] Train: [12/20][13/510] Data 1.790 (3.731) Batch 19.093 (28.947) Remain 36:48:08 loss: 0.2322 loss_seg: 0.1358 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:55:21,048 INFO misc.py line 117 726] Train: [12/20][14/510] Data 2.816 (3.648) Batch 24.304 (28.525) Remain 36:15:28 loss: 0.2346 loss_seg: 0.1442 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:55:51,211 INFO misc.py line 117 726] Train: [12/20][15/510] Data 3.935 (3.672) Batch 30.164 (28.661) Remain 36:25:24 loss: 0.1867 loss_seg: 0.1058 loss_superpoint_edge: 0.0139 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:56:11,129 INFO misc.py line 117 726] Train: [12/20][16/510] Data 2.475 (3.580) Batch 19.918 (27.989) Remain 35:33:39 loss: 0.2112 loss_seg: 0.1181 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:56:30,187 INFO misc.py line 117 726] Train: [12/20][17/510] Data 2.773 (3.522) Batch 19.058 (27.351) Remain 34:44:34 loss: 0.2472 loss_seg: 0.1475 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0435 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:56:59,242 INFO misc.py line 117 726] Train: [12/20][18/510] Data 3.040 (3.490) Batch 29.055 (27.464) Remain 34:52:46 loss: 0.2330 loss_seg: 0.1451 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:57:18,686 INFO misc.py line 117 726] Train: [12/20][19/510] Data 2.090 (3.402) Batch 19.444 (26.963) Remain 34:14:08 loss: 0.2334 loss_seg: 0.1375 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:57:48,539 INFO misc.py line 117 726] Train: [12/20][20/510] Data 3.463 (3.406) Batch 29.853 (27.133) Remain 34:26:37 loss: 0.2175 loss_seg: 0.1257 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:58:16,017 INFO misc.py line 117 726] Train: [12/20][21/510] Data 2.862 (3.376) Batch 27.477 (27.152) Remain 34:27:38 loss: 0.2182 loss_seg: 0.1256 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:58:42,647 INFO misc.py line 117 726] Train: [12/20][22/510] Data 2.298 (3.319) Batch 26.631 (27.125) Remain 34:25:05 loss: 0.2237 loss_seg: 0.1315 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:59:18,541 INFO misc.py line 117 726] Train: [12/20][23/510] Data 4.166 (3.361) Batch 35.894 (27.563) Remain 34:58:01 loss: 0.2246 loss_seg: 0.1285 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 12:59:47,637 INFO misc.py line 117 726] Train: [12/20][24/510] Data 2.427 (3.317) Batch 29.096 (27.636) Remain 35:03:06 loss: 0.2504 loss_seg: 0.1548 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:00:22,354 INFO misc.py line 117 726] Train: [12/20][25/510] Data 5.879 (3.433) Batch 34.716 (27.958) Remain 35:27:08 loss: 0.2259 loss_seg: 0.1446 loss_superpoint_edge: 0.0147 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:00:50,776 INFO misc.py line 117 726] Train: [12/20][26/510] Data 5.153 (3.508) Batch 28.422 (27.978) Remain 35:28:12 loss: 0.2220 loss_seg: 0.1297 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:01:26,215 INFO misc.py line 117 726] Train: [12/20][27/510] Data 5.494 (3.591) Batch 35.439 (28.289) Remain 35:51:22 loss: 0.2325 loss_seg: 0.1408 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:01:59,016 INFO misc.py line 117 726] Train: [12/20][28/510] Data 3.508 (3.588) Batch 32.801 (28.470) Remain 36:04:38 loss: 0.2493 loss_seg: 0.1544 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:02:29,951 INFO misc.py line 117 726] Train: [12/20][29/510] Data 2.627 (3.551) Batch 30.935 (28.564) Remain 36:11:22 loss: 0.2061 loss_seg: 0.1164 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:02:48,656 INFO misc.py line 117 726] Train: [12/20][30/510] Data 2.625 (3.516) Batch 18.704 (28.199) Remain 35:43:08 loss: 0.2193 loss_seg: 0.1219 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:03:14,608 INFO misc.py line 117 726] Train: [12/20][31/510] Data 3.212 (3.505) Batch 25.953 (28.119) Remain 35:36:34 loss: 0.2650 loss_seg: 0.1681 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:03:38,612 INFO misc.py line 117 726] Train: [12/20][32/510] Data 2.898 (3.484) Batch 24.004 (27.977) Remain 35:25:19 loss: 0.2781 loss_seg: 0.1752 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:04:07,256 INFO misc.py line 117 726] Train: [12/20][33/510] Data 5.432 (3.549) Batch 28.644 (27.999) Remain 35:26:32 loss: 0.1913 loss_seg: 0.1037 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:04:39,207 INFO misc.py line 117 726] Train: [12/20][34/510] Data 4.523 (3.581) Batch 31.951 (28.127) Remain 35:35:45 loss: 0.2070 loss_seg: 0.1147 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:05:17,099 INFO misc.py line 117 726] Train: [12/20][35/510] Data 5.632 (3.645) Batch 37.891 (28.432) Remain 35:58:27 loss: 0.2603 loss_seg: 0.1602 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:05:47,304 INFO misc.py line 117 726] Train: [12/20][36/510] Data 3.416 (3.638) Batch 30.206 (28.486) Remain 36:02:03 loss: 0.2437 loss_seg: 0.1425 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:06:08,346 INFO misc.py line 117 726] Train: [12/20][37/510] Data 2.444 (3.603) Batch 21.041 (28.267) Remain 35:44:58 loss: 0.2468 loss_seg: 0.1496 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:06:46,204 INFO misc.py line 117 726] Train: [12/20][38/510] Data 6.306 (3.680) Batch 37.858 (28.541) Remain 36:05:17 loss: 0.2752 loss_seg: 0.1742 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:07:19,726 INFO misc.py line 117 726] Train: [12/20][39/510] Data 5.048 (3.718) Batch 33.522 (28.679) Remain 36:15:18 loss: 0.2884 loss_seg: 0.1886 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:07:48,378 INFO misc.py line 117 726] Train: [12/20][40/510] Data 4.879 (3.749) Batch 28.652 (28.678) Remain 36:14:46 loss: 0.2500 loss_seg: 0.1491 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:08:13,116 INFO misc.py line 117 726] Train: [12/20][41/510] Data 2.650 (3.721) Batch 24.739 (28.575) Remain 36:06:26 loss: 0.2978 loss_seg: 0.1958 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:08:49,316 INFO misc.py line 117 726] Train: [12/20][42/510] Data 5.805 (3.774) Batch 36.200 (28.770) Remain 36:20:46 loss: 0.2471 loss_seg: 0.1500 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:09:08,923 INFO misc.py line 117 726] Train: [12/20][43/510] Data 2.505 (3.742) Batch 19.607 (28.541) Remain 36:02:56 loss: 0.2331 loss_seg: 0.1379 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:09:29,367 INFO misc.py line 117 726] Train: [12/20][44/510] Data 1.879 (3.697) Batch 20.443 (28.344) Remain 35:47:30 loss: 0.2415 loss_seg: 0.1447 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:09:57,322 INFO misc.py line 117 726] Train: [12/20][45/510] Data 6.349 (3.760) Batch 27.956 (28.334) Remain 35:46:19 loss: 0.2968 loss_seg: 0.1972 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:10:30,909 INFO misc.py line 117 726] Train: [12/20][46/510] Data 5.390 (3.798) Batch 33.587 (28.457) Remain 35:55:06 loss: 0.2121 loss_seg: 0.1206 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:10:57,501 INFO misc.py line 117 726] Train: [12/20][47/510] Data 2.633 (3.771) Batch 26.592 (28.414) Remain 35:51:25 loss: 0.3085 loss_seg: 0.1985 loss_superpoint_edge: 0.0438 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:11:20,477 INFO misc.py line 117 726] Train: [12/20][48/510] Data 2.838 (3.751) Batch 22.975 (28.293) Remain 35:41:48 loss: 0.3437 loss_seg: 0.2410 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:11:55,323 INFO misc.py line 117 726] Train: [12/20][49/510] Data 4.130 (3.759) Batch 34.847 (28.436) Remain 35:52:06 loss: 0.2357 loss_seg: 0.1490 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:12:29,775 INFO misc.py line 117 726] Train: [12/20][50/510] Data 4.540 (3.776) Batch 34.452 (28.564) Remain 36:01:19 loss: 0.2038 loss_seg: 0.1164 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:12:29,776 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 13:12:53,529 INFO misc.py line 117 726] Train: [12/20][51/510] Data 3.005 (3.759) Batch 23.754 (28.464) Remain 35:53:16 loss: 0.3242 loss_seg: 0.2317 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:13:15,364 INFO misc.py line 117 726] Train: [12/20][52/510] Data 2.622 (3.736) Batch 21.835 (28.328) Remain 35:42:33 loss: 0.2428 loss_seg: 0.1480 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:13:49,937 INFO misc.py line 117 726] Train: [12/20][53/510] Data 9.005 (3.842) Batch 34.573 (28.453) Remain 35:51:32 loss: 0.2133 loss_seg: 0.1204 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:14:20,935 INFO misc.py line 117 726] Train: [12/20][54/510] Data 4.223 (3.849) Batch 30.998 (28.503) Remain 35:54:49 loss: 0.1972 loss_seg: 0.1091 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:14:45,435 INFO misc.py line 117 726] Train: [12/20][55/510] Data 2.028 (3.814) Batch 24.500 (28.426) Remain 35:48:32 loss: 0.2277 loss_seg: 0.1332 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:15:20,256 INFO misc.py line 117 726] Train: [12/20][56/510] Data 5.638 (3.848) Batch 34.821 (28.547) Remain 35:57:11 loss: 0.2424 loss_seg: 0.1474 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:15:51,483 INFO misc.py line 117 726] Train: [12/20][57/510] Data 4.210 (3.855) Batch 31.227 (28.596) Remain 36:00:27 loss: 0.1912 loss_seg: 0.1045 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:16:14,308 INFO misc.py line 117 726] Train: [12/20][58/510] Data 2.392 (3.829) Batch 22.825 (28.491) Remain 35:52:03 loss: 0.1799 loss_seg: 0.0971 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:16:40,286 INFO misc.py line 117 726] Train: [12/20][59/510] Data 3.589 (3.824) Batch 25.978 (28.447) Remain 35:48:11 loss: 0.2574 loss_seg: 0.1614 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:17:07,396 INFO misc.py line 117 726] Train: [12/20][60/510] Data 2.613 (3.803) Batch 27.111 (28.423) Remain 35:45:56 loss: 0.2198 loss_seg: 0.1260 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:17:37,428 INFO misc.py line 117 726] Train: [12/20][61/510] Data 3.992 (3.806) Batch 30.031 (28.451) Remain 35:47:33 loss: 0.5387 loss_seg: 0.4064 loss_superpoint_edge: 0.0625 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:18:05,159 INFO misc.py line 117 726] Train: [12/20][62/510] Data 4.203 (3.813) Batch 27.731 (28.439) Remain 35:46:10 loss: 0.2128 loss_seg: 0.1174 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:18:35,095 INFO misc.py line 117 726] Train: [12/20][63/510] Data 3.894 (3.814) Batch 29.936 (28.464) Remain 35:47:34 loss: 0.2252 loss_seg: 0.1348 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:19:03,906 INFO misc.py line 117 726] Train: [12/20][64/510] Data 3.290 (3.806) Batch 28.811 (28.469) Remain 35:47:32 loss: 0.2228 loss_seg: 0.1333 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:19:33,443 INFO misc.py line 117 726] Train: [12/20][65/510] Data 3.987 (3.809) Batch 29.536 (28.487) Remain 35:48:21 loss: 0.2664 loss_seg: 0.1671 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:19:56,838 INFO misc.py line 117 726] Train: [12/20][66/510] Data 2.630 (3.790) Batch 23.396 (28.406) Remain 35:41:47 loss: 0.2594 loss_seg: 0.1578 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:20:25,926 INFO misc.py line 117 726] Train: [12/20][67/510] Data 4.134 (3.795) Batch 29.088 (28.416) Remain 35:42:07 loss: 0.2477 loss_seg: 0.1528 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:20:54,075 INFO misc.py line 117 726] Train: [12/20][68/510] Data 3.369 (3.789) Batch 28.149 (28.412) Remain 35:41:20 loss: 0.2455 loss_seg: 0.1506 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:21:20,528 INFO misc.py line 117 726] Train: [12/20][69/510] Data 2.857 (3.775) Batch 26.452 (28.383) Remain 35:38:37 loss: 0.2133 loss_seg: 0.1239 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:21:37,322 INFO misc.py line 117 726] Train: [12/20][70/510] Data 2.215 (3.751) Batch 16.794 (28.210) Remain 35:25:07 loss: 0.2331 loss_seg: 0.1370 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:22:04,270 INFO misc.py line 117 726] Train: [12/20][71/510] Data 4.275 (3.759) Batch 26.948 (28.191) Remain 35:23:15 loss: 0.2300 loss_seg: 0.1345 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:22:27,126 INFO misc.py line 117 726] Train: [12/20][72/510] Data 2.883 (3.746) Batch 22.856 (28.114) Remain 35:16:57 loss: 0.2613 loss_seg: 0.1622 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:22:56,600 INFO misc.py line 117 726] Train: [12/20][73/510] Data 6.080 (3.780) Batch 29.474 (28.133) Remain 35:17:57 loss: 0.2311 loss_seg: 0.1353 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:23:20,109 INFO misc.py line 117 726] Train: [12/20][74/510] Data 2.018 (3.755) Batch 23.509 (28.068) Remain 35:12:35 loss: 0.2601 loss_seg: 0.1535 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:23:37,439 INFO misc.py line 117 726] Train: [12/20][75/510] Data 2.347 (3.735) Batch 17.330 (27.919) Remain 35:00:53 loss: 0.2344 loss_seg: 0.1384 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:24:02,836 INFO misc.py line 117 726] Train: [12/20][76/510] Data 4.504 (3.746) Batch 25.397 (27.884) Remain 34:57:50 loss: 0.2085 loss_seg: 0.1206 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:24:31,074 INFO misc.py line 117 726] Train: [12/20][77/510] Data 2.677 (3.731) Batch 28.237 (27.889) Remain 34:57:43 loss: 0.2015 loss_seg: 0.1120 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:25:01,669 INFO misc.py line 117 726] Train: [12/20][78/510] Data 3.300 (3.726) Batch 30.595 (27.925) Remain 34:59:58 loss: 0.2218 loss_seg: 0.1293 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:25:28,649 INFO misc.py line 117 726] Train: [12/20][79/510] Data 2.611 (3.711) Batch 26.981 (27.913) Remain 34:58:34 loss: 0.3132 loss_seg: 0.2184 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:25:56,654 INFO misc.py line 117 726] Train: [12/20][80/510] Data 3.197 (3.704) Batch 28.005 (27.914) Remain 34:58:12 loss: 0.2524 loss_seg: 0.1549 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:26:10,417 INFO misc.py line 117 726] Train: [12/20][81/510] Data 1.993 (3.682) Batch 13.763 (27.733) Remain 34:44:06 loss: 0.2588 loss_seg: 0.1622 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0482 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:26:30,738 INFO misc.py line 117 726] Train: [12/20][82/510] Data 1.772 (3.658) Batch 20.321 (27.639) Remain 34:36:35 loss: 0.2455 loss_seg: 0.1488 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:27:05,790 INFO misc.py line 117 726] Train: [12/20][83/510] Data 4.793 (3.672) Batch 35.051 (27.731) Remain 34:43:05 loss: 0.2155 loss_seg: 0.1231 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:27:26,011 INFO misc.py line 117 726] Train: [12/20][84/510] Data 2.780 (3.661) Batch 20.221 (27.639) Remain 34:35:39 loss: 0.2691 loss_seg: 0.1682 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:27:58,165 INFO misc.py line 117 726] Train: [12/20][85/510] Data 3.236 (3.656) Batch 32.154 (27.694) Remain 34:39:20 loss: 0.2325 loss_seg: 0.1393 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:28:22,647 INFO misc.py line 117 726] Train: [12/20][86/510] Data 2.969 (3.648) Batch 24.482 (27.655) Remain 34:35:58 loss: 0.2489 loss_seg: 0.1517 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:28:53,557 INFO misc.py line 117 726] Train: [12/20][87/510] Data 3.490 (3.646) Batch 30.910 (27.694) Remain 34:38:25 loss: 0.3363 loss_seg: 0.2389 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:29:19,468 INFO misc.py line 117 726] Train: [12/20][88/510] Data 3.634 (3.646) Batch 25.910 (27.673) Remain 34:36:23 loss: 0.2739 loss_seg: 0.1741 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:29:43,806 INFO misc.py line 117 726] Train: [12/20][89/510] Data 2.340 (3.631) Batch 24.339 (27.634) Remain 34:33:00 loss: 0.2046 loss_seg: 0.1143 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:30:06,330 INFO misc.py line 117 726] Train: [12/20][90/510] Data 3.002 (3.624) Batch 22.524 (27.575) Remain 34:28:08 loss: 0.2240 loss_seg: 0.1307 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:30:34,677 INFO misc.py line 117 726] Train: [12/20][91/510] Data 2.998 (3.616) Batch 28.347 (27.584) Remain 34:28:20 loss: 0.2266 loss_seg: 0.1291 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:31:11,141 INFO misc.py line 117 726] Train: [12/20][92/510] Data 9.021 (3.677) Batch 36.464 (27.684) Remain 34:35:21 loss: 0.1993 loss_seg: 0.1092 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:31:40,281 INFO misc.py line 117 726] Train: [12/20][93/510] Data 2.869 (3.668) Batch 29.141 (27.700) Remain 34:36:07 loss: 0.2342 loss_seg: 0.1376 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:32:08,296 INFO misc.py line 117 726] Train: [12/20][94/510] Data 3.010 (3.661) Batch 28.015 (27.703) Remain 34:35:54 loss: 0.2478 loss_seg: 0.1547 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:32:39,380 INFO misc.py line 117 726] Train: [12/20][95/510] Data 3.229 (3.656) Batch 31.084 (27.740) Remain 34:38:12 loss: 0.2387 loss_seg: 0.1437 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:33:15,979 INFO misc.py line 117 726] Train: [12/20][96/510] Data 5.631 (3.677) Batch 36.599 (27.835) Remain 34:44:52 loss: 0.1878 loss_seg: 0.1037 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:33:45,333 INFO misc.py line 117 726] Train: [12/20][97/510] Data 2.973 (3.670) Batch 29.354 (27.852) Remain 34:45:37 loss: 0.2228 loss_seg: 0.1286 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:34:03,281 INFO misc.py line 117 726] Train: [12/20][98/510] Data 2.327 (3.656) Batch 17.948 (27.747) Remain 34:37:21 loss: 0.2640 loss_seg: 0.1658 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:34:35,063 INFO misc.py line 117 726] Train: [12/20][99/510] Data 2.997 (3.649) Batch 31.782 (27.789) Remain 34:40:02 loss: 0.2320 loss_seg: 0.1344 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:35:08,979 INFO misc.py line 117 726] Train: [12/20][100/510] Data 3.510 (3.648) Batch 33.916 (27.853) Remain 34:44:18 loss: 0.3165 loss_seg: 0.2198 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:35:08,979 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 13:35:28,008 INFO misc.py line 117 726] Train: [12/20][101/510] Data 2.920 (3.640) Batch 19.030 (27.763) Remain 34:37:06 loss: 0.1798 loss_seg: 0.0966 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:36:04,315 INFO misc.py line 117 726] Train: [12/20][102/510] Data 6.092 (3.665) Batch 36.307 (27.849) Remain 34:43:05 loss: 0.2735 loss_seg: 0.1781 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:36:33,811 INFO misc.py line 117 726] Train: [12/20][103/510] Data 3.143 (3.660) Batch 29.496 (27.865) Remain 34:43:51 loss: 0.1905 loss_seg: 0.1080 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:37:09,223 INFO misc.py line 117 726] Train: [12/20][104/510] Data 7.695 (3.700) Batch 35.412 (27.940) Remain 34:48:59 loss: 0.1926 loss_seg: 0.1041 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:37:35,481 INFO misc.py line 117 726] Train: [12/20][105/510] Data 2.617 (3.689) Batch 26.258 (27.924) Remain 34:47:17 loss: 0.2445 loss_seg: 0.1425 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:38:02,232 INFO misc.py line 117 726] Train: [12/20][106/510] Data 2.708 (3.679) Batch 26.751 (27.912) Remain 34:45:58 loss: 0.2093 loss_seg: 0.1183 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:38:33,569 INFO misc.py line 117 726] Train: [12/20][107/510] Data 4.720 (3.689) Batch 31.336 (27.945) Remain 34:47:57 loss: 0.2840 loss_seg: 0.1830 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:38:55,204 INFO misc.py line 117 726] Train: [12/20][108/510] Data 2.582 (3.679) Batch 21.636 (27.885) Remain 34:43:00 loss: 0.2690 loss_seg: 0.1620 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:39:19,098 INFO misc.py line 117 726] Train: [12/20][109/510] Data 2.617 (3.669) Batch 23.893 (27.847) Remain 34:39:44 loss: 0.2102 loss_seg: 0.1197 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:39:45,687 INFO misc.py line 117 726] Train: [12/20][110/510] Data 3.061 (3.663) Batch 26.589 (27.836) Remain 34:38:23 loss: 0.2122 loss_seg: 0.1190 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:40:09,020 INFO misc.py line 117 726] Train: [12/20][111/510] Data 2.667 (3.654) Batch 23.333 (27.794) Remain 34:34:48 loss: 0.2603 loss_seg: 0.1577 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:40:46,263 INFO misc.py line 117 726] Train: [12/20][112/510] Data 5.466 (3.671) Batch 37.243 (27.881) Remain 34:40:49 loss: 0.3128 loss_seg: 0.2058 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:41:08,605 INFO misc.py line 117 726] Train: [12/20][113/510] Data 2.300 (3.658) Batch 22.342 (27.830) Remain 34:36:36 loss: 0.2211 loss_seg: 0.1335 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:41:34,401 INFO misc.py line 117 726] Train: [12/20][114/510] Data 3.078 (3.653) Batch 25.796 (27.812) Remain 34:34:46 loss: 0.2076 loss_seg: 0.1175 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:41:59,279 INFO misc.py line 117 726] Train: [12/20][115/510] Data 2.706 (3.644) Batch 24.878 (27.786) Remain 34:32:21 loss: 0.2087 loss_seg: 0.1213 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:42:36,369 INFO misc.py line 117 726] Train: [12/20][116/510] Data 4.067 (3.648) Batch 37.090 (27.868) Remain 34:38:01 loss: 0.2966 loss_seg: 0.1915 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:43:01,628 INFO misc.py line 117 726] Train: [12/20][117/510] Data 3.205 (3.644) Batch 25.259 (27.845) Remain 34:35:51 loss: 0.2361 loss_seg: 0.1397 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:43:28,715 INFO misc.py line 117 726] Train: [12/20][118/510] Data 3.365 (3.642) Batch 27.087 (27.839) Remain 34:34:54 loss: 0.2466 loss_seg: 0.1500 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:44:01,729 INFO misc.py line 117 726] Train: [12/20][119/510] Data 4.393 (3.648) Batch 33.014 (27.883) Remain 34:37:45 loss: 0.3122 loss_seg: 0.2209 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:44:20,353 INFO misc.py line 117 726] Train: [12/20][120/510] Data 2.518 (3.639) Batch 18.624 (27.804) Remain 34:31:24 loss: 0.2270 loss_seg: 0.1379 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:44:46,542 INFO misc.py line 117 726] Train: [12/20][121/510] Data 3.360 (3.636) Batch 26.189 (27.790) Remain 34:29:55 loss: 0.3309 loss_seg: 0.2331 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:45:14,382 INFO misc.py line 117 726] Train: [12/20][122/510] Data 3.139 (3.632) Batch 27.840 (27.791) Remain 34:29:29 loss: 0.2474 loss_seg: 0.1543 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:45:45,382 INFO misc.py line 117 726] Train: [12/20][123/510] Data 3.864 (3.634) Batch 31.000 (27.818) Remain 34:31:00 loss: 0.2994 loss_seg: 0.1917 loss_superpoint_edge: 0.0415 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:46:12,119 INFO misc.py line 117 726] Train: [12/20][124/510] Data 2.612 (3.626) Batch 26.737 (27.809) Remain 34:29:53 loss: 0.2402 loss_seg: 0.1423 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:46:44,197 INFO misc.py line 117 726] Train: [12/20][125/510] Data 4.370 (3.632) Batch 32.078 (27.844) Remain 34:32:01 loss: 0.1937 loss_seg: 0.1049 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:47:13,403 INFO misc.py line 117 726] Train: [12/20][126/510] Data 3.444 (3.630) Batch 29.206 (27.855) Remain 34:32:23 loss: 0.3717 loss_seg: 0.2682 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:47:43,047 INFO misc.py line 117 726] Train: [12/20][127/510] Data 4.472 (3.637) Batch 29.644 (27.869) Remain 34:32:59 loss: 0.2386 loss_seg: 0.1455 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:48:12,098 INFO misc.py line 117 726] Train: [12/20][128/510] Data 3.443 (3.635) Batch 29.051 (27.879) Remain 34:33:14 loss: 0.2418 loss_seg: 0.1446 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:48:40,481 INFO misc.py line 117 726] Train: [12/20][129/510] Data 4.733 (3.644) Batch 28.383 (27.883) Remain 34:33:04 loss: 0.1985 loss_seg: 0.1104 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:48:59,906 INFO misc.py line 117 726] Train: [12/20][130/510] Data 1.927 (3.631) Batch 19.425 (27.816) Remain 34:27:39 loss: 0.2235 loss_seg: 0.1332 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:49:26,047 INFO misc.py line 117 726] Train: [12/20][131/510] Data 2.423 (3.621) Batch 26.142 (27.803) Remain 34:26:13 loss: 0.2083 loss_seg: 0.1177 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:49:52,397 INFO misc.py line 117 726] Train: [12/20][132/510] Data 2.847 (3.615) Batch 26.350 (27.792) Remain 34:24:55 loss: 0.2165 loss_seg: 0.1263 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:50:17,018 INFO misc.py line 117 726] Train: [12/20][133/510] Data 3.112 (3.611) Batch 24.621 (27.767) Remain 34:22:38 loss: 0.1845 loss_seg: 0.0979 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:50:44,187 INFO misc.py line 117 726] Train: [12/20][134/510] Data 3.073 (3.607) Batch 27.169 (27.763) Remain 34:21:50 loss: 0.2246 loss_seg: 0.1336 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:51:14,751 INFO misc.py line 117 726] Train: [12/20][135/510] Data 5.327 (3.620) Batch 30.565 (27.784) Remain 34:22:57 loss: 0.3425 loss_seg: 0.2333 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:51:35,505 INFO misc.py line 117 726] Train: [12/20][136/510] Data 2.751 (3.614) Batch 20.754 (27.731) Remain 34:18:34 loss: 0.2148 loss_seg: 0.1232 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:52:00,370 INFO misc.py line 117 726] Train: [12/20][137/510] Data 2.897 (3.608) Batch 24.864 (27.710) Remain 34:16:31 loss: 0.1866 loss_seg: 0.1018 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:52:33,337 INFO misc.py line 117 726] Train: [12/20][138/510] Data 3.787 (3.610) Batch 32.967 (27.749) Remain 34:18:56 loss: 0.2332 loss_seg: 0.1377 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:53:04,839 INFO misc.py line 117 726] Train: [12/20][139/510] Data 3.400 (3.608) Batch 31.502 (27.776) Remain 34:20:31 loss: 0.2108 loss_seg: 0.1224 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:53:30,717 INFO misc.py line 117 726] Train: [12/20][140/510] Data 2.274 (3.598) Batch 25.877 (27.762) Remain 34:19:02 loss: 0.2024 loss_seg: 0.1146 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:54:05,409 INFO misc.py line 117 726] Train: [12/20][141/510] Data 8.869 (3.637) Batch 34.693 (27.813) Remain 34:22:18 loss: 0.2561 loss_seg: 0.1540 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:54:41,013 INFO misc.py line 117 726] Train: [12/20][142/510] Data 5.382 (3.649) Batch 35.603 (27.869) Remain 34:25:59 loss: 0.2891 loss_seg: 0.1994 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:55:06,912 INFO misc.py line 117 726] Train: [12/20][143/510] Data 3.590 (3.649) Batch 25.900 (27.855) Remain 34:24:29 loss: 0.2415 loss_seg: 0.1498 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:55:38,162 INFO misc.py line 117 726] Train: [12/20][144/510] Data 3.102 (3.645) Batch 31.250 (27.879) Remain 34:25:48 loss: 0.2041 loss_seg: 0.1148 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:56:09,887 INFO misc.py line 117 726] Train: [12/20][145/510] Data 5.031 (3.655) Batch 31.725 (27.906) Remain 34:27:20 loss: 0.3592 loss_seg: 0.2611 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:56:37,993 INFO misc.py line 117 726] Train: [12/20][146/510] Data 4.596 (3.661) Batch 28.106 (27.907) Remain 34:26:59 loss: 0.2275 loss_seg: 0.1350 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:56:56,730 INFO misc.py line 117 726] Train: [12/20][147/510] Data 1.872 (3.649) Batch 18.737 (27.843) Remain 34:21:48 loss: 0.3408 loss_seg: 0.2357 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:57:14,410 INFO misc.py line 117 726] Train: [12/20][148/510] Data 2.089 (3.638) Batch 17.680 (27.773) Remain 34:16:09 loss: 0.1886 loss_seg: 0.1033 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:57:42,902 INFO misc.py line 117 726] Train: [12/20][149/510] Data 3.383 (3.636) Batch 28.492 (27.778) Remain 34:16:03 loss: 0.2293 loss_seg: 0.1379 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:58:07,821 INFO misc.py line 117 726] Train: [12/20][150/510] Data 3.001 (3.632) Batch 24.919 (27.759) Remain 34:14:09 loss: 0.2007 loss_seg: 0.1087 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:58:07,821 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 13:58:40,354 INFO misc.py line 117 726] Train: [12/20][151/510] Data 4.837 (3.640) Batch 32.533 (27.791) Remain 34:16:04 loss: 0.2188 loss_seg: 0.1287 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:59:14,425 INFO misc.py line 117 726] Train: [12/20][152/510] Data 3.870 (3.642) Batch 34.071 (27.833) Remain 34:18:43 loss: 0.2846 loss_seg: 0.1827 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 13:59:42,694 INFO misc.py line 117 726] Train: [12/20][153/510] Data 4.076 (3.645) Batch 28.269 (27.836) Remain 34:18:28 loss: 0.2514 loss_seg: 0.1539 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:00:11,159 INFO misc.py line 117 726] Train: [12/20][154/510] Data 2.806 (3.639) Batch 28.465 (27.840) Remain 34:18:19 loss: 0.2885 loss_seg: 0.1883 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:00:39,117 INFO misc.py line 117 726] Train: [12/20][155/510] Data 2.796 (3.633) Batch 27.957 (27.841) Remain 34:17:55 loss: 0.2837 loss_seg: 0.1751 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:01:22,903 INFO misc.py line 117 726] Train: [12/20][156/510] Data 12.895 (3.694) Batch 43.787 (27.945) Remain 34:25:09 loss: 0.3885 loss_seg: 0.2874 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:01:54,597 INFO misc.py line 117 726] Train: [12/20][157/510] Data 3.901 (3.695) Batch 31.694 (27.970) Remain 34:26:29 loss: 0.2556 loss_seg: 0.1597 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:02:17,365 INFO misc.py line 117 726] Train: [12/20][158/510] Data 3.445 (3.694) Batch 22.768 (27.936) Remain 34:23:32 loss: 0.2009 loss_seg: 0.1101 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:02:50,161 INFO misc.py line 117 726] Train: [12/20][159/510] Data 3.464 (3.692) Batch 32.796 (27.967) Remain 34:25:22 loss: 0.2248 loss_seg: 0.1325 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:03:14,412 INFO misc.py line 117 726] Train: [12/20][160/510] Data 2.457 (3.684) Batch 24.251 (27.944) Remain 34:23:09 loss: 0.2395 loss_seg: 0.1449 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:03:43,419 INFO misc.py line 117 726] Train: [12/20][161/510] Data 5.072 (3.693) Batch 29.007 (27.950) Remain 34:23:11 loss: 0.2071 loss_seg: 0.1176 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:04:11,768 INFO misc.py line 117 726] Train: [12/20][162/510] Data 2.714 (3.687) Batch 28.348 (27.953) Remain 34:22:54 loss: 0.2896 loss_seg: 0.1831 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:04:36,815 INFO misc.py line 117 726] Train: [12/20][163/510] Data 2.581 (3.680) Batch 25.047 (27.935) Remain 34:21:06 loss: 0.2196 loss_seg: 0.1267 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:05:02,992 INFO misc.py line 117 726] Train: [12/20][164/510] Data 3.720 (3.680) Batch 26.177 (27.924) Remain 34:19:50 loss: 0.2947 loss_seg: 0.1921 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:05:23,629 INFO misc.py line 117 726] Train: [12/20][165/510] Data 1.593 (3.667) Batch 20.637 (27.879) Remain 34:16:03 loss: 0.2447 loss_seg: 0.1452 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:05:49,941 INFO misc.py line 117 726] Train: [12/20][166/510] Data 1.982 (3.657) Batch 26.312 (27.869) Remain 34:14:52 loss: 0.1902 loss_seg: 0.1041 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:06:07,505 INFO misc.py line 117 726] Train: [12/20][167/510] Data 2.320 (3.649) Batch 17.564 (27.806) Remain 34:09:47 loss: 0.2604 loss_seg: 0.1594 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:06:32,797 INFO misc.py line 117 726] Train: [12/20][168/510] Data 5.661 (3.661) Batch 25.292 (27.791) Remain 34:08:11 loss: 0.2537 loss_seg: 0.1568 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:07:04,352 INFO misc.py line 117 726] Train: [12/20][169/510] Data 3.290 (3.659) Batch 31.554 (27.814) Remain 34:09:24 loss: 0.2797 loss_seg: 0.1856 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:07:40,073 INFO misc.py line 117 726] Train: [12/20][170/510] Data 5.506 (3.670) Batch 35.721 (27.861) Remain 34:12:25 loss: 0.2957 loss_seg: 0.1979 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:07:57,218 INFO misc.py line 117 726] Train: [12/20][171/510] Data 1.840 (3.659) Batch 17.145 (27.797) Remain 34:07:16 loss: 0.2528 loss_seg: 0.1515 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:08:22,446 INFO misc.py line 117 726] Train: [12/20][172/510] Data 3.138 (3.656) Batch 25.228 (27.782) Remain 34:05:41 loss: 0.1934 loss_seg: 0.1058 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:08:52,499 INFO misc.py line 117 726] Train: [12/20][173/510] Data 5.153 (3.665) Batch 30.053 (27.795) Remain 34:06:12 loss: 0.3013 loss_seg: 0.1963 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:09:17,165 INFO misc.py line 117 726] Train: [12/20][174/510] Data 3.102 (3.662) Batch 24.666 (27.777) Remain 34:04:23 loss: 0.2596 loss_seg: 0.1606 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:09:39,192 INFO misc.py line 117 726] Train: [12/20][175/510] Data 2.051 (3.652) Batch 22.027 (27.744) Remain 34:01:28 loss: 0.3095 loss_seg: 0.2072 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:10:08,328 INFO misc.py line 117 726] Train: [12/20][176/510] Data 3.247 (3.650) Batch 29.136 (27.752) Remain 34:01:36 loss: 0.2223 loss_seg: 0.1343 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:10:47,845 INFO misc.py line 117 726] Train: [12/20][177/510] Data 6.531 (3.666) Batch 39.517 (27.819) Remain 34:06:06 loss: 0.2430 loss_seg: 0.1549 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:11:18,038 INFO misc.py line 117 726] Train: [12/20][178/510] Data 3.047 (3.663) Batch 30.193 (27.833) Remain 34:06:38 loss: 0.2806 loss_seg: 0.1957 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:11:45,538 INFO misc.py line 117 726] Train: [12/20][179/510] Data 2.864 (3.658) Batch 27.500 (27.831) Remain 34:06:02 loss: 0.2422 loss_seg: 0.1454 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:12:11,543 INFO misc.py line 117 726] Train: [12/20][180/510] Data 2.244 (3.650) Batch 26.004 (27.821) Remain 34:04:49 loss: 0.1968 loss_seg: 0.1092 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:12:46,158 INFO misc.py line 117 726] Train: [12/20][181/510] Data 4.825 (3.657) Batch 34.616 (27.859) Remain 34:07:09 loss: 0.1945 loss_seg: 0.1072 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:13:10,359 INFO misc.py line 117 726] Train: [12/20][182/510] Data 3.364 (3.655) Batch 24.200 (27.838) Remain 34:05:11 loss: 0.2341 loss_seg: 0.1390 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:13:42,974 INFO misc.py line 117 726] Train: [12/20][183/510] Data 3.529 (3.655) Batch 32.616 (27.865) Remain 34:06:40 loss: 0.3133 loss_seg: 0.2177 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:14:10,922 INFO misc.py line 117 726] Train: [12/20][184/510] Data 8.644 (3.682) Batch 27.947 (27.865) Remain 34:06:15 loss: 0.2140 loss_seg: 0.1256 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:14:38,550 INFO misc.py line 117 726] Train: [12/20][185/510] Data 2.781 (3.677) Batch 27.628 (27.864) Remain 34:05:41 loss: 0.1943 loss_seg: 0.1093 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:15:05,985 INFO misc.py line 117 726] Train: [12/20][186/510] Data 3.152 (3.674) Batch 27.436 (27.862) Remain 34:05:03 loss: 0.2402 loss_seg: 0.1405 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:15:31,619 INFO misc.py line 117 726] Train: [12/20][187/510] Data 2.779 (3.669) Batch 25.634 (27.850) Remain 34:03:42 loss: 0.2063 loss_seg: 0.1173 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:16:00,222 INFO misc.py line 117 726] Train: [12/20][188/510] Data 3.519 (3.669) Batch 28.603 (27.854) Remain 34:03:32 loss: 0.2923 loss_seg: 0.1925 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:16:19,492 INFO misc.py line 117 726] Train: [12/20][189/510] Data 2.480 (3.662) Batch 19.270 (27.808) Remain 33:59:41 loss: 0.2211 loss_seg: 0.1252 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:16:50,858 INFO misc.py line 117 726] Train: [12/20][190/510] Data 5.754 (3.673) Batch 31.365 (27.827) Remain 34:00:37 loss: 0.1657 loss_seg: 0.0841 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:17:15,629 INFO misc.py line 117 726] Train: [12/20][191/510] Data 4.313 (3.677) Batch 24.771 (27.810) Remain 33:58:57 loss: 0.2597 loss_seg: 0.1643 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:17:45,307 INFO misc.py line 117 726] Train: [12/20][192/510] Data 5.403 (3.686) Batch 29.678 (27.820) Remain 33:59:13 loss: 0.4942 loss_seg: 0.3918 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:18:03,985 INFO misc.py line 117 726] Train: [12/20][193/510] Data 2.716 (3.681) Batch 18.679 (27.772) Remain 33:55:14 loss: 0.2349 loss_seg: 0.1379 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:18:35,025 INFO misc.py line 117 726] Train: [12/20][194/510] Data 3.632 (3.681) Batch 31.040 (27.789) Remain 33:56:01 loss: 0.2417 loss_seg: 0.1456 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:19:02,088 INFO misc.py line 117 726] Train: [12/20][195/510] Data 2.814 (3.676) Batch 27.063 (27.785) Remain 33:55:17 loss: 0.2879 loss_seg: 0.1849 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:19:37,320 INFO misc.py line 117 726] Train: [12/20][196/510] Data 4.641 (3.681) Batch 35.232 (27.824) Remain 33:57:38 loss: 0.2754 loss_seg: 0.1768 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:20:06,068 INFO misc.py line 117 726] Train: [12/20][197/510] Data 3.217 (3.679) Batch 28.748 (27.829) Remain 33:57:31 loss: 0.1918 loss_seg: 0.1013 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:20:33,069 INFO misc.py line 117 726] Train: [12/20][198/510] Data 3.185 (3.676) Batch 27.001 (27.825) Remain 33:56:45 loss: 0.2542 loss_seg: 0.1558 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:21:00,770 INFO misc.py line 117 726] Train: [12/20][199/510] Data 3.935 (3.677) Batch 27.701 (27.824) Remain 33:56:14 loss: 0.2917 loss_seg: 0.1831 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:21:22,730 INFO misc.py line 117 726] Train: [12/20][200/510] Data 3.047 (3.674) Batch 21.959 (27.794) Remain 33:53:36 loss: 0.2942 loss_seg: 0.1901 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:21:22,730 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 14:21:54,650 INFO misc.py line 117 726] Train: [12/20][201/510] Data 8.607 (3.699) Batch 31.920 (27.815) Remain 33:54:40 loss: 0.2837 loss_seg: 0.1833 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:22:30,213 INFO misc.py line 117 726] Train: [12/20][202/510] Data 3.905 (3.700) Batch 35.563 (27.854) Remain 33:57:03 loss: 0.2318 loss_seg: 0.1365 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:22:55,536 INFO misc.py line 117 726] Train: [12/20][203/510] Data 2.764 (3.696) Batch 25.323 (27.841) Remain 33:55:39 loss: 0.2575 loss_seg: 0.1608 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:23:12,351 INFO misc.py line 117 726] Train: [12/20][204/510] Data 2.366 (3.689) Batch 16.815 (27.786) Remain 33:51:11 loss: 0.2341 loss_seg: 0.1400 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:23:30,126 INFO misc.py line 117 726] Train: [12/20][205/510] Data 2.528 (3.683) Batch 17.775 (27.737) Remain 33:47:06 loss: 0.2840 loss_seg: 0.1902 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:23:59,802 INFO misc.py line 117 726] Train: [12/20][206/510] Data 5.681 (3.693) Batch 29.676 (27.746) Remain 33:47:20 loss: 0.2837 loss_seg: 0.1840 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:24:27,625 INFO misc.py line 117 726] Train: [12/20][207/510] Data 4.785 (3.698) Batch 27.823 (27.747) Remain 33:46:54 loss: 0.2238 loss_seg: 0.1283 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:24:53,729 INFO misc.py line 117 726] Train: [12/20][208/510] Data 2.717 (3.694) Batch 26.104 (27.739) Remain 33:45:51 loss: 0.1968 loss_seg: 0.1103 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:25:23,005 INFO misc.py line 117 726] Train: [12/20][209/510] Data 2.859 (3.690) Batch 29.276 (27.746) Remain 33:45:56 loss: 0.1970 loss_seg: 0.1099 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:25:58,214 INFO misc.py line 117 726] Train: [12/20][210/510] Data 10.027 (3.720) Batch 35.209 (27.782) Remain 33:48:06 loss: 0.1646 loss_seg: 0.0798 loss_superpoint_edge: 0.0114 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:26:24,100 INFO misc.py line 117 726] Train: [12/20][211/510] Data 4.294 (3.723) Batch 25.886 (27.773) Remain 33:46:58 loss: 0.2442 loss_seg: 0.1469 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:26:54,006 INFO misc.py line 117 726] Train: [12/20][212/510] Data 3.795 (3.723) Batch 29.906 (27.783) Remain 33:47:15 loss: 0.3748 loss_seg: 0.2741 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:27:26,917 INFO misc.py line 117 726] Train: [12/20][213/510] Data 3.582 (3.723) Batch 32.910 (27.808) Remain 33:48:34 loss: 0.2242 loss_seg: 0.1299 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:28:09,710 INFO misc.py line 117 726] Train: [12/20][214/510] Data 11.811 (3.761) Batch 42.793 (27.879) Remain 33:53:17 loss: 0.2639 loss_seg: 0.1616 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0445 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:28:31,686 INFO misc.py line 117 726] Train: [12/20][215/510] Data 2.676 (3.756) Batch 21.976 (27.851) Remain 33:50:48 loss: 0.2626 loss_seg: 0.1686 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:29:00,872 INFO misc.py line 117 726] Train: [12/20][216/510] Data 3.447 (3.754) Batch 29.186 (27.857) Remain 33:50:47 loss: 0.2617 loss_seg: 0.1670 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:29:30,073 INFO misc.py line 117 726] Train: [12/20][217/510] Data 2.653 (3.749) Batch 29.201 (27.864) Remain 33:50:47 loss: 0.1869 loss_seg: 0.1004 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:29:51,670 INFO misc.py line 117 726] Train: [12/20][218/510] Data 2.612 (3.744) Batch 21.597 (27.834) Remain 33:48:11 loss: 0.2945 loss_seg: 0.2040 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:30:23,103 INFO misc.py line 117 726] Train: [12/20][219/510] Data 3.226 (3.742) Batch 31.433 (27.851) Remain 33:48:56 loss: 0.2303 loss_seg: 0.1397 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:30:45,596 INFO misc.py line 117 726] Train: [12/20][220/510] Data 2.287 (3.735) Batch 22.493 (27.826) Remain 33:46:41 loss: 0.1575 loss_seg: 0.0758 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:31:18,452 INFO misc.py line 117 726] Train: [12/20][221/510] Data 5.912 (3.745) Batch 32.856 (27.849) Remain 33:47:54 loss: 0.3040 loss_seg: 0.2141 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:31:55,447 INFO misc.py line 117 726] Train: [12/20][222/510] Data 10.601 (3.776) Batch 36.995 (27.891) Remain 33:50:28 loss: 0.2429 loss_seg: 0.1507 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:32:22,696 INFO misc.py line 117 726] Train: [12/20][223/510] Data 2.504 (3.770) Batch 27.248 (27.888) Remain 33:49:48 loss: 0.1878 loss_seg: 0.0988 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:32:51,271 INFO misc.py line 117 726] Train: [12/20][224/510] Data 2.596 (3.765) Batch 28.575 (27.891) Remain 33:49:33 loss: 0.2534 loss_seg: 0.1581 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:33:19,150 INFO misc.py line 117 726] Train: [12/20][225/510] Data 2.973 (3.761) Batch 27.880 (27.891) Remain 33:49:05 loss: 0.2837 loss_seg: 0.1834 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:33:53,227 INFO misc.py line 117 726] Train: [12/20][226/510] Data 5.034 (3.767) Batch 34.077 (27.919) Remain 33:50:38 loss: 0.2473 loss_seg: 0.1545 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:34:32,495 INFO misc.py line 117 726] Train: [12/20][227/510] Data 7.642 (3.784) Batch 39.268 (27.970) Remain 33:53:51 loss: 0.2730 loss_seg: 0.1728 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:34:55,111 INFO misc.py line 117 726] Train: [12/20][228/510] Data 4.053 (3.786) Batch 22.616 (27.946) Remain 33:51:40 loss: 0.2347 loss_seg: 0.1419 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:35:22,578 INFO misc.py line 117 726] Train: [12/20][229/510] Data 2.974 (3.782) Batch 27.467 (27.944) Remain 33:51:02 loss: 0.1974 loss_seg: 0.1085 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:35:32,914 INFO misc.py line 117 726] Train: [12/20][230/510] Data 1.592 (3.772) Batch 10.336 (27.866) Remain 33:44:56 loss: 0.4245 loss_seg: 0.2980 loss_superpoint_edge: 0.0570 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:35:57,510 INFO misc.py line 117 726] Train: [12/20][231/510] Data 3.201 (3.770) Batch 24.596 (27.852) Remain 33:43:26 loss: 0.2338 loss_seg: 0.1391 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:36:22,777 INFO misc.py line 117 726] Train: [12/20][232/510] Data 4.866 (3.775) Batch 25.267 (27.841) Remain 33:42:09 loss: 0.3950 loss_seg: 0.2819 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:36:53,725 INFO misc.py line 117 726] Train: [12/20][233/510] Data 4.450 (3.778) Batch 30.949 (27.854) Remain 33:42:40 loss: 0.2748 loss_seg: 0.1723 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:37:18,905 INFO misc.py line 117 726] Train: [12/20][234/510] Data 4.957 (3.783) Batch 25.180 (27.843) Remain 33:41:22 loss: 0.3394 loss_seg: 0.2508 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:37:54,105 INFO misc.py line 117 726] Train: [12/20][235/510] Data 4.493 (3.786) Batch 35.200 (27.874) Remain 33:43:12 loss: 0.2101 loss_seg: 0.1187 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:38:17,507 INFO misc.py line 117 726] Train: [12/20][236/510] Data 2.824 (3.782) Batch 23.402 (27.855) Remain 33:41:20 loss: 0.2795 loss_seg: 0.1865 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:38:44,876 INFO misc.py line 117 726] Train: [12/20][237/510] Data 3.122 (3.779) Batch 27.370 (27.853) Remain 33:40:44 loss: 0.2628 loss_seg: 0.1673 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:39:10,399 INFO misc.py line 117 726] Train: [12/20][238/510] Data 3.464 (3.777) Batch 25.523 (27.843) Remain 33:39:33 loss: 0.3164 loss_seg: 0.2133 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:39:42,167 INFO misc.py line 117 726] Train: [12/20][239/510] Data 3.538 (3.776) Batch 31.767 (27.860) Remain 33:40:17 loss: 0.2096 loss_seg: 0.1174 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:40:09,460 INFO misc.py line 117 726] Train: [12/20][240/510] Data 3.030 (3.773) Batch 27.294 (27.857) Remain 33:39:39 loss: 0.2742 loss_seg: 0.1687 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:40:38,140 INFO misc.py line 117 726] Train: [12/20][241/510] Data 3.063 (3.770) Batch 28.680 (27.861) Remain 33:39:26 loss: 0.2283 loss_seg: 0.1367 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:41:09,778 INFO misc.py line 117 726] Train: [12/20][242/510] Data 3.964 (3.771) Batch 31.638 (27.877) Remain 33:40:07 loss: 0.2693 loss_seg: 0.1709 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:41:43,236 INFO misc.py line 117 726] Train: [12/20][243/510] Data 4.608 (3.775) Batch 33.458 (27.900) Remain 33:41:20 loss: 0.2145 loss_seg: 0.1230 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:42:05,481 INFO misc.py line 117 726] Train: [12/20][244/510] Data 2.343 (3.769) Batch 22.245 (27.876) Remain 33:39:10 loss: 0.2509 loss_seg: 0.1601 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:42:27,805 INFO misc.py line 117 726] Train: [12/20][245/510] Data 2.379 (3.763) Batch 22.324 (27.853) Remain 33:37:03 loss: 0.2391 loss_seg: 0.1465 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:42:53,840 INFO misc.py line 117 726] Train: [12/20][246/510] Data 5.788 (3.771) Batch 26.035 (27.846) Remain 33:36:02 loss: 0.2231 loss_seg: 0.1349 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:43:12,630 INFO misc.py line 117 726] Train: [12/20][247/510] Data 2.568 (3.766) Batch 18.790 (27.809) Remain 33:32:53 loss: 0.3204 loss_seg: 0.2213 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:43:48,315 INFO misc.py line 117 726] Train: [12/20][248/510] Data 5.733 (3.774) Batch 35.684 (27.841) Remain 33:34:45 loss: 0.2683 loss_seg: 0.1712 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:44:14,341 INFO misc.py line 117 726] Train: [12/20][249/510] Data 3.346 (3.773) Batch 26.027 (27.834) Remain 33:33:45 loss: 0.2155 loss_seg: 0.1291 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:44:41,261 INFO misc.py line 117 726] Train: [12/20][250/510] Data 5.138 (3.778) Batch 26.920 (27.830) Remain 33:33:01 loss: 0.3186 loss_seg: 0.2231 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:44:41,262 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 14:45:12,586 INFO misc.py line 117 726] Train: [12/20][251/510] Data 4.371 (3.781) Batch 31.325 (27.844) Remain 33:33:35 loss: 0.2426 loss_seg: 0.1518 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:45:39,236 INFO misc.py line 117 726] Train: [12/20][252/510] Data 2.789 (3.777) Batch 26.650 (27.839) Remain 33:32:46 loss: 0.2165 loss_seg: 0.1253 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:46:15,458 INFO misc.py line 117 726] Train: [12/20][253/510] Data 10.353 (3.803) Batch 36.222 (27.873) Remain 33:34:43 loss: 0.2422 loss_seg: 0.1603 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:46:45,917 INFO misc.py line 117 726] Train: [12/20][254/510] Data 2.845 (3.799) Batch 30.459 (27.883) Remain 33:35:00 loss: 0.2116 loss_seg: 0.1228 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:47:10,987 INFO misc.py line 117 726] Train: [12/20][255/510] Data 3.273 (3.797) Batch 25.070 (27.872) Remain 33:33:44 loss: 0.2098 loss_seg: 0.1165 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:47:42,420 INFO misc.py line 117 726] Train: [12/20][256/510] Data 5.800 (3.805) Batch 31.433 (27.886) Remain 33:34:17 loss: 0.2982 loss_seg: 0.1950 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:48:14,795 INFO misc.py line 117 726] Train: [12/20][257/510] Data 4.010 (3.806) Batch 32.375 (27.904) Remain 33:35:06 loss: 0.1893 loss_seg: 0.1035 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:48:36,821 INFO misc.py line 117 726] Train: [12/20][258/510] Data 2.192 (3.799) Batch 22.027 (27.881) Remain 33:32:58 loss: 0.2544 loss_seg: 0.1551 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:49:07,116 INFO misc.py line 117 726] Train: [12/20][259/510] Data 3.432 (3.798) Batch 30.295 (27.890) Remain 33:33:11 loss: 0.1925 loss_seg: 0.1052 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:49:33,101 INFO misc.py line 117 726] Train: [12/20][260/510] Data 2.366 (3.792) Batch 25.985 (27.883) Remain 33:32:11 loss: 0.2379 loss_seg: 0.1478 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:50:10,119 INFO misc.py line 117 726] Train: [12/20][261/510] Data 7.983 (3.809) Batch 37.018 (27.918) Remain 33:34:16 loss: 0.2108 loss_seg: 0.1214 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:50:38,335 INFO misc.py line 117 726] Train: [12/20][262/510] Data 3.238 (3.806) Batch 28.216 (27.919) Remain 33:33:54 loss: 0.2878 loss_seg: 0.1824 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:51:11,230 INFO misc.py line 117 726] Train: [12/20][263/510] Data 4.970 (3.811) Batch 32.895 (27.938) Remain 33:34:48 loss: 0.1985 loss_seg: 0.1094 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:51:31,137 INFO misc.py line 117 726] Train: [12/20][264/510] Data 2.384 (3.805) Batch 19.907 (27.908) Remain 33:32:07 loss: 0.2242 loss_seg: 0.1347 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:51:55,371 INFO misc.py line 117 726] Train: [12/20][265/510] Data 2.075 (3.799) Batch 24.234 (27.893) Remain 33:30:39 loss: 0.2241 loss_seg: 0.1285 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:52:25,589 INFO misc.py line 117 726] Train: [12/20][266/510] Data 3.701 (3.798) Batch 30.218 (27.902) Remain 33:30:49 loss: 0.1929 loss_seg: 0.1031 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:52:59,645 INFO misc.py line 117 726] Train: [12/20][267/510] Data 3.694 (3.798) Batch 34.056 (27.926) Remain 33:32:02 loss: 0.2978 loss_seg: 0.1962 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:53:32,127 INFO misc.py line 117 726] Train: [12/20][268/510] Data 4.648 (3.801) Batch 32.481 (27.943) Remain 33:32:48 loss: 0.2816 loss_seg: 0.1795 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:53:54,580 INFO misc.py line 117 726] Train: [12/20][269/510] Data 2.235 (3.795) Batch 22.453 (27.922) Remain 33:30:51 loss: 0.2148 loss_seg: 0.1268 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:54:26,297 INFO misc.py line 117 726] Train: [12/20][270/510] Data 4.865 (3.799) Batch 31.717 (27.936) Remain 33:31:25 loss: 0.2499 loss_seg: 0.1526 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:54:52,577 INFO misc.py line 117 726] Train: [12/20][271/510] Data 3.463 (3.798) Batch 26.280 (27.930) Remain 33:30:30 loss: 0.2407 loss_seg: 0.1439 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:55:17,447 INFO misc.py line 117 726] Train: [12/20][272/510] Data 3.456 (3.797) Batch 24.870 (27.919) Remain 33:29:13 loss: 0.1716 loss_seg: 0.0887 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:55:35,590 INFO misc.py line 117 726] Train: [12/20][273/510] Data 2.860 (3.793) Batch 18.143 (27.883) Remain 33:26:09 loss: 0.2657 loss_seg: 0.1772 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:56:01,352 INFO misc.py line 117 726] Train: [12/20][274/510] Data 3.930 (3.794) Batch 25.762 (27.875) Remain 33:25:07 loss: 0.2208 loss_seg: 0.1262 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:56:25,964 INFO misc.py line 117 726] Train: [12/20][275/510] Data 3.081 (3.791) Batch 24.613 (27.863) Remain 33:23:48 loss: 0.2447 loss_seg: 0.1499 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:56:52,539 INFO misc.py line 117 726] Train: [12/20][276/510] Data 2.077 (3.785) Batch 26.574 (27.858) Remain 33:22:59 loss: 0.1944 loss_seg: 0.1079 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:57:19,426 INFO misc.py line 117 726] Train: [12/20][277/510] Data 2.219 (3.779) Batch 26.887 (27.855) Remain 33:22:16 loss: 0.2939 loss_seg: 0.1901 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:57:44,140 INFO misc.py line 117 726] Train: [12/20][278/510] Data 3.171 (3.777) Batch 24.714 (27.843) Remain 33:20:59 loss: 0.2418 loss_seg: 0.1480 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:58:14,276 INFO misc.py line 117 726] Train: [12/20][279/510] Data 2.985 (3.774) Batch 30.137 (27.851) Remain 33:21:07 loss: 0.1767 loss_seg: 0.0916 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:58:45,688 INFO misc.py line 117 726] Train: [12/20][280/510] Data 3.428 (3.773) Batch 31.411 (27.864) Remain 33:21:35 loss: 0.2410 loss_seg: 0.1413 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:59:17,402 INFO misc.py line 117 726] Train: [12/20][281/510] Data 4.286 (3.775) Batch 31.715 (27.878) Remain 33:22:06 loss: 0.2662 loss_seg: 0.1694 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 14:59:52,899 INFO misc.py line 117 726] Train: [12/20][282/510] Data 6.207 (3.783) Batch 35.496 (27.905) Remain 33:23:36 loss: 0.2266 loss_seg: 0.1342 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:00:18,254 INFO misc.py line 117 726] Train: [12/20][283/510] Data 3.186 (3.781) Batch 25.356 (27.896) Remain 33:22:29 loss: 0.2553 loss_seg: 0.1626 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:00:44,558 INFO misc.py line 117 726] Train: [12/20][284/510] Data 2.357 (3.776) Batch 26.304 (27.891) Remain 33:21:37 loss: 0.2852 loss_seg: 0.1860 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:01:19,949 INFO misc.py line 117 726] Train: [12/20][285/510] Data 3.995 (3.777) Batch 35.391 (27.917) Remain 33:23:03 loss: 0.2059 loss_seg: 0.1198 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:01:49,881 INFO misc.py line 117 726] Train: [12/20][286/510] Data 3.900 (3.778) Batch 29.932 (27.924) Remain 33:23:06 loss: 0.3239 loss_seg: 0.2268 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:02:18,510 INFO misc.py line 117 726] Train: [12/20][287/510] Data 3.322 (3.776) Batch 28.630 (27.927) Remain 33:22:49 loss: 0.2364 loss_seg: 0.1421 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:02:47,372 INFO misc.py line 117 726] Train: [12/20][288/510] Data 6.787 (3.786) Batch 28.861 (27.930) Remain 33:22:35 loss: 0.2788 loss_seg: 0.1833 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:03:16,603 INFO misc.py line 117 726] Train: [12/20][289/510] Data 6.146 (3.795) Batch 29.231 (27.935) Remain 33:22:27 loss: 0.2302 loss_seg: 0.1335 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:03:44,087 INFO misc.py line 117 726] Train: [12/20][290/510] Data 2.342 (3.790) Batch 27.484 (27.933) Remain 33:21:52 loss: 0.2256 loss_seg: 0.1285 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:04:10,648 INFO misc.py line 117 726] Train: [12/20][291/510] Data 2.896 (3.787) Batch 26.561 (27.928) Remain 33:21:04 loss: 0.3014 loss_seg: 0.2049 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:04:44,013 INFO misc.py line 117 726] Train: [12/20][292/510] Data 4.978 (3.791) Batch 33.365 (27.947) Remain 33:21:56 loss: 0.2779 loss_seg: 0.1830 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:05:18,328 INFO misc.py line 117 726] Train: [12/20][293/510] Data 4.078 (3.792) Batch 34.315 (27.969) Remain 33:23:03 loss: 0.2054 loss_seg: 0.1159 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:05:39,251 INFO misc.py line 117 726] Train: [12/20][294/510] Data 1.908 (3.785) Batch 20.923 (27.945) Remain 33:20:51 loss: 0.3411 loss_seg: 0.2268 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:05:59,782 INFO misc.py line 117 726] Train: [12/20][295/510] Data 2.964 (3.782) Batch 20.531 (27.920) Remain 33:18:34 loss: 0.2637 loss_seg: 0.1687 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:06:23,964 INFO misc.py line 117 726] Train: [12/20][296/510] Data 2.240 (3.777) Batch 24.182 (27.907) Remain 33:17:11 loss: 0.2333 loss_seg: 0.1430 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:06:51,529 INFO misc.py line 117 726] Train: [12/20][297/510] Data 4.209 (3.779) Batch 27.565 (27.906) Remain 33:16:38 loss: 0.2020 loss_seg: 0.1162 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:07:13,000 INFO misc.py line 117 726] Train: [12/20][298/510] Data 2.366 (3.774) Batch 21.471 (27.884) Remain 33:14:37 loss: 0.2402 loss_seg: 0.1475 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:07:40,114 INFO misc.py line 117 726] Train: [12/20][299/510] Data 3.312 (3.772) Batch 27.114 (27.881) Remain 33:13:58 loss: 0.2296 loss_seg: 0.1347 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:08:10,424 INFO misc.py line 117 726] Train: [12/20][300/510] Data 4.130 (3.773) Batch 30.310 (27.889) Remain 33:14:05 loss: 0.4190 loss_seg: 0.3202 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:08:10,424 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 15:08:35,667 INFO misc.py line 117 726] Train: [12/20][301/510] Data 3.300 (3.772) Batch 25.243 (27.880) Remain 33:12:59 loss: 0.2530 loss_seg: 0.1573 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:09:05,508 INFO misc.py line 117 726] Train: [12/20][302/510] Data 4.353 (3.774) Batch 29.841 (27.887) Remain 33:12:59 loss: 0.2487 loss_seg: 0.1537 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:09:21,186 INFO misc.py line 117 726] Train: [12/20][303/510] Data 1.841 (3.767) Batch 15.679 (27.846) Remain 33:09:37 loss: 0.2267 loss_seg: 0.1297 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:09:40,199 INFO misc.py line 117 726] Train: [12/20][304/510] Data 1.834 (3.761) Batch 19.013 (27.817) Remain 33:07:03 loss: 0.2050 loss_seg: 0.1182 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:09:56,582 INFO misc.py line 117 726] Train: [12/20][305/510] Data 1.599 (3.754) Batch 16.383 (27.779) Remain 33:03:53 loss: 0.2638 loss_seg: 0.1657 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:10:27,259 INFO misc.py line 117 726] Train: [12/20][306/510] Data 6.252 (3.762) Batch 30.678 (27.789) Remain 33:04:06 loss: 0.2796 loss_seg: 0.1828 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:11:06,956 INFO misc.py line 117 726] Train: [12/20][307/510] Data 6.298 (3.770) Batch 39.696 (27.828) Remain 33:06:26 loss: 0.2462 loss_seg: 0.1535 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:11:39,097 INFO misc.py line 117 726] Train: [12/20][308/510] Data 5.132 (3.775) Batch 32.141 (27.842) Remain 33:06:59 loss: 0.1967 loss_seg: 0.1087 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:12:10,094 INFO misc.py line 117 726] Train: [12/20][309/510] Data 3.760 (3.775) Batch 30.996 (27.852) Remain 33:07:15 loss: 0.1886 loss_seg: 0.1027 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:12:43,006 INFO misc.py line 117 726] Train: [12/20][310/510] Data 3.553 (3.774) Batch 32.912 (27.869) Remain 33:07:58 loss: 0.2238 loss_seg: 0.1358 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:13:12,508 INFO misc.py line 117 726] Train: [12/20][311/510] Data 2.995 (3.772) Batch 29.503 (27.874) Remain 33:07:53 loss: 0.2829 loss_seg: 0.1943 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:13:43,805 INFO misc.py line 117 726] Train: [12/20][312/510] Data 3.151 (3.770) Batch 31.297 (27.885) Remain 33:08:12 loss: 0.2914 loss_seg: 0.1865 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:14:33,293 INFO misc.py line 117 726] Train: [12/20][313/510] Data 16.827 (3.812) Batch 49.487 (27.955) Remain 33:12:43 loss: 0.1991 loss_seg: 0.1151 loss_superpoint_edge: 0.0126 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:15:07,456 INFO misc.py line 117 726] Train: [12/20][314/510] Data 3.426 (3.810) Batch 34.163 (27.975) Remain 33:13:40 loss: 0.2138 loss_seg: 0.1256 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:15:34,087 INFO misc.py line 117 726] Train: [12/20][315/510] Data 1.790 (3.804) Batch 26.631 (27.971) Remain 33:12:54 loss: 0.2144 loss_seg: 0.1224 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:16:03,551 INFO misc.py line 117 726] Train: [12/20][316/510] Data 2.074 (3.798) Batch 29.464 (27.975) Remain 33:12:46 loss: 0.2226 loss_seg: 0.1272 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:16:41,263 INFO misc.py line 117 726] Train: [12/20][317/510] Data 8.591 (3.814) Batch 37.712 (28.006) Remain 33:14:31 loss: 0.2666 loss_seg: 0.1740 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:17:04,304 INFO misc.py line 117 726] Train: [12/20][318/510] Data 2.869 (3.811) Batch 23.041 (27.991) Remain 33:12:55 loss: 0.2415 loss_seg: 0.1489 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:17:31,596 INFO misc.py line 117 726] Train: [12/20][319/510] Data 2.583 (3.807) Batch 27.291 (27.988) Remain 33:12:18 loss: 0.2080 loss_seg: 0.1155 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:18:00,064 INFO misc.py line 117 726] Train: [12/20][320/510] Data 2.829 (3.804) Batch 28.468 (27.990) Remain 33:11:56 loss: 0.2458 loss_seg: 0.1461 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:18:29,048 INFO misc.py line 117 726] Train: [12/20][321/510] Data 3.827 (3.804) Batch 28.985 (27.993) Remain 33:11:42 loss: 0.2499 loss_seg: 0.1534 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:19:04,867 INFO misc.py line 117 726] Train: [12/20][322/510] Data 5.150 (3.808) Batch 35.819 (28.018) Remain 33:12:58 loss: 0.2270 loss_seg: 0.1296 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:19:36,056 INFO misc.py line 117 726] Train: [12/20][323/510] Data 3.715 (3.808) Batch 31.189 (28.027) Remain 33:13:13 loss: 0.2788 loss_seg: 0.1810 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:20:04,433 INFO misc.py line 117 726] Train: [12/20][324/510] Data 4.099 (3.809) Batch 28.376 (28.029) Remain 33:12:49 loss: 0.4195 loss_seg: 0.3111 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:20:42,282 INFO misc.py line 117 726] Train: [12/20][325/510] Data 6.151 (3.816) Batch 37.849 (28.059) Remain 33:14:31 loss: 0.2575 loss_seg: 0.1643 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:21:10,254 INFO misc.py line 117 726] Train: [12/20][326/510] Data 5.041 (3.820) Batch 27.972 (28.059) Remain 33:14:02 loss: 0.2124 loss_seg: 0.1194 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:21:39,386 INFO misc.py line 117 726] Train: [12/20][327/510] Data 3.327 (3.818) Batch 29.132 (28.062) Remain 33:13:48 loss: 0.2897 loss_seg: 0.1914 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:22:06,124 INFO misc.py line 117 726] Train: [12/20][328/510] Data 2.942 (3.815) Batch 26.738 (28.058) Remain 33:13:03 loss: 0.2372 loss_seg: 0.1383 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:22:35,242 INFO misc.py line 117 726] Train: [12/20][329/510] Data 3.441 (3.814) Batch 29.118 (28.061) Remain 33:12:48 loss: 0.2503 loss_seg: 0.1532 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:22:55,933 INFO misc.py line 117 726] Train: [12/20][330/510] Data 2.531 (3.810) Batch 20.691 (28.039) Remain 33:10:44 loss: 0.2417 loss_seg: 0.1476 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:23:20,365 INFO misc.py line 117 726] Train: [12/20][331/510] Data 2.744 (3.807) Batch 24.432 (28.028) Remain 33:09:29 loss: 0.2462 loss_seg: 0.1477 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:23:48,671 INFO misc.py line 117 726] Train: [12/20][332/510] Data 4.512 (3.809) Batch 28.306 (28.029) Remain 33:09:05 loss: 0.2033 loss_seg: 0.1150 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:24:23,624 INFO misc.py line 117 726] Train: [12/20][333/510] Data 4.220 (3.811) Batch 34.953 (28.050) Remain 33:10:06 loss: 0.2245 loss_seg: 0.1303 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:24:55,504 INFO misc.py line 117 726] Train: [12/20][334/510] Data 3.164 (3.809) Batch 31.880 (28.061) Remain 33:10:28 loss: 0.2401 loss_seg: 0.1442 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:25:30,903 INFO misc.py line 117 726] Train: [12/20][335/510] Data 3.749 (3.808) Batch 35.398 (28.083) Remain 33:11:34 loss: 0.2528 loss_seg: 0.1517 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:26:03,277 INFO misc.py line 117 726] Train: [12/20][336/510] Data 4.442 (3.810) Batch 32.375 (28.096) Remain 33:12:00 loss: 0.2168 loss_seg: 0.1233 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:26:29,163 INFO misc.py line 117 726] Train: [12/20][337/510] Data 3.498 (3.809) Batch 25.886 (28.089) Remain 33:11:04 loss: 0.2125 loss_seg: 0.1194 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:26:47,292 INFO misc.py line 117 726] Train: [12/20][338/510] Data 2.632 (3.806) Batch 18.128 (28.060) Remain 33:08:30 loss: 0.2022 loss_seg: 0.1128 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:27:14,057 INFO misc.py line 117 726] Train: [12/20][339/510] Data 3.624 (3.805) Batch 26.765 (28.056) Remain 33:07:45 loss: 0.2374 loss_seg: 0.1432 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:27:34,280 INFO misc.py line 117 726] Train: [12/20][340/510] Data 1.679 (3.799) Batch 20.223 (28.033) Remain 33:05:38 loss: 0.2749 loss_seg: 0.1829 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:28:14,323 INFO misc.py line 117 726] Train: [12/20][341/510] Data 11.240 (3.821) Batch 40.043 (28.068) Remain 33:07:41 loss: 0.2056 loss_seg: 0.1204 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:28:39,002 INFO misc.py line 117 726] Train: [12/20][342/510] Data 2.562 (3.817) Batch 24.679 (28.058) Remain 33:06:31 loss: 0.2421 loss_seg: 0.1473 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:29:01,009 INFO misc.py line 117 726] Train: [12/20][343/510] Data 2.770 (3.814) Batch 22.007 (28.040) Remain 33:04:47 loss: 0.2284 loss_seg: 0.1354 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:29:23,941 INFO misc.py line 117 726] Train: [12/20][344/510] Data 2.230 (3.810) Batch 22.932 (28.025) Remain 33:03:15 loss: 0.2283 loss_seg: 0.1337 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:29:51,114 INFO misc.py line 117 726] Train: [12/20][345/510] Data 2.521 (3.806) Batch 27.174 (28.023) Remain 33:02:37 loss: 0.1918 loss_seg: 0.1051 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:30:15,065 INFO misc.py line 117 726] Train: [12/20][346/510] Data 2.741 (3.803) Batch 23.951 (28.011) Remain 33:01:18 loss: 0.2023 loss_seg: 0.1159 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:30:49,066 INFO misc.py line 117 726] Train: [12/20][347/510] Data 6.174 (3.810) Batch 34.001 (28.028) Remain 33:02:04 loss: 0.2130 loss_seg: 0.1207 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:31:18,852 INFO misc.py line 117 726] Train: [12/20][348/510] Data 2.916 (3.807) Batch 29.785 (28.034) Remain 33:01:58 loss: 0.2481 loss_seg: 0.1570 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:31:40,478 INFO misc.py line 117 726] Train: [12/20][349/510] Data 2.593 (3.803) Batch 21.627 (28.015) Remain 33:00:11 loss: 0.2029 loss_seg: 0.1164 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:32:08,920 INFO misc.py line 117 726] Train: [12/20][350/510] Data 5.818 (3.809) Batch 28.441 (28.016) Remain 32:59:48 loss: 0.2458 loss_seg: 0.1529 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:32:08,921 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 15:32:31,468 INFO misc.py line 117 726] Train: [12/20][351/510] Data 3.092 (3.807) Batch 22.548 (28.001) Remain 32:58:14 loss: 0.2458 loss_seg: 0.1486 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:32:59,199 INFO misc.py line 117 726] Train: [12/20][352/510] Data 3.419 (3.806) Batch 27.732 (28.000) Remain 32:57:43 loss: 0.2514 loss_seg: 0.1559 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:33:34,247 INFO misc.py line 117 726] Train: [12/20][353/510] Data 5.528 (3.811) Batch 35.047 (28.020) Remain 32:58:40 loss: 0.2593 loss_seg: 0.1678 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:34:18,789 INFO misc.py line 117 726] Train: [12/20][354/510] Data 10.172 (3.829) Batch 44.543 (28.067) Remain 33:01:31 loss: 0.2595 loss_seg: 0.1618 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:34:49,868 INFO misc.py line 117 726] Train: [12/20][355/510] Data 3.877 (3.829) Batch 31.079 (28.076) Remain 33:01:39 loss: 0.2246 loss_seg: 0.1333 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:35:14,754 INFO misc.py line 117 726] Train: [12/20][356/510] Data 3.723 (3.829) Batch 24.887 (28.067) Remain 33:00:33 loss: 0.2427 loss_seg: 0.1459 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:35:44,556 INFO misc.py line 117 726] Train: [12/20][357/510] Data 4.068 (3.830) Batch 29.802 (28.071) Remain 33:00:26 loss: 0.2741 loss_seg: 0.1693 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:36:01,244 INFO misc.py line 117 726] Train: [12/20][358/510] Data 2.229 (3.825) Batch 16.688 (28.039) Remain 32:57:42 loss: 0.2276 loss_seg: 0.1359 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:36:24,579 INFO misc.py line 117 726] Train: [12/20][359/510] Data 2.311 (3.821) Batch 23.336 (28.026) Remain 32:56:18 loss: 0.2416 loss_seg: 0.1446 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:36:47,685 INFO misc.py line 117 726] Train: [12/20][360/510] Data 2.429 (3.817) Batch 23.106 (28.012) Remain 32:54:52 loss: 0.2904 loss_seg: 0.1912 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:37:19,196 INFO misc.py line 117 726] Train: [12/20][361/510] Data 3.256 (3.815) Batch 31.510 (28.022) Remain 32:55:05 loss: 0.1925 loss_seg: 0.1063 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0322 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:37:39,409 INFO misc.py line 117 726] Train: [12/20][362/510] Data 3.175 (3.814) Batch 20.213 (28.000) Remain 32:53:05 loss: 0.2659 loss_seg: 0.1703 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:38:14,196 INFO misc.py line 117 726] Train: [12/20][363/510] Data 4.259 (3.815) Batch 34.787 (28.019) Remain 32:53:57 loss: 0.2001 loss_seg: 0.1145 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:38:36,430 INFO misc.py line 117 726] Train: [12/20][364/510] Data 3.152 (3.813) Batch 22.234 (28.003) Remain 32:52:21 loss: 0.2608 loss_seg: 0.1595 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:39:03,066 INFO misc.py line 117 726] Train: [12/20][365/510] Data 3.535 (3.812) Batch 26.635 (27.999) Remain 32:51:37 loss: 0.2224 loss_seg: 0.1277 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:39:34,243 INFO misc.py line 117 726] Train: [12/20][366/510] Data 2.845 (3.810) Batch 31.177 (28.008) Remain 32:51:46 loss: 0.2123 loss_seg: 0.1209 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:40:08,182 INFO misc.py line 117 726] Train: [12/20][367/510] Data 4.271 (3.811) Batch 33.939 (28.024) Remain 32:52:27 loss: 0.2614 loss_seg: 0.1631 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:40:38,983 INFO misc.py line 117 726] Train: [12/20][368/510] Data 3.939 (3.811) Batch 30.800 (28.032) Remain 32:52:31 loss: 0.2559 loss_seg: 0.1560 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:41:09,555 INFO misc.py line 117 726] Train: [12/20][369/510] Data 3.926 (3.812) Batch 30.572 (28.039) Remain 32:52:32 loss: 0.2268 loss_seg: 0.1334 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:41:39,811 INFO misc.py line 117 726] Train: [12/20][370/510] Data 3.632 (3.811) Batch 30.256 (28.045) Remain 32:52:30 loss: 0.2637 loss_seg: 0.1679 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:42:10,555 INFO misc.py line 117 726] Train: [12/20][371/510] Data 3.345 (3.810) Batch 30.744 (28.052) Remain 32:52:33 loss: 0.2522 loss_seg: 0.1593 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:42:43,947 INFO misc.py line 117 726] Train: [12/20][372/510] Data 3.584 (3.809) Batch 33.392 (28.067) Remain 32:53:05 loss: 0.2819 loss_seg: 0.1758 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:43:06,719 INFO misc.py line 117 726] Train: [12/20][373/510] Data 3.143 (3.807) Batch 22.771 (28.053) Remain 32:51:37 loss: 0.2193 loss_seg: 0.1278 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:43:30,193 INFO misc.py line 117 726] Train: [12/20][374/510] Data 3.279 (3.806) Batch 23.475 (28.040) Remain 32:50:17 loss: 0.2296 loss_seg: 0.1391 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:43:59,915 INFO misc.py line 117 726] Train: [12/20][375/510] Data 4.610 (3.808) Batch 29.722 (28.045) Remain 32:50:08 loss: 0.3018 loss_seg: 0.2069 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:44:27,137 INFO misc.py line 117 726] Train: [12/20][376/510] Data 2.738 (3.805) Batch 27.222 (28.043) Remain 32:49:31 loss: 0.1830 loss_seg: 0.0996 loss_superpoint_edge: 0.0145 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:45:01,364 INFO misc.py line 117 726] Train: [12/20][377/510] Data 5.812 (3.811) Batch 34.227 (28.059) Remain 32:50:12 loss: 0.2635 loss_seg: 0.1768 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:45:20,229 INFO misc.py line 117 726] Train: [12/20][378/510] Data 2.431 (3.807) Batch 18.865 (28.035) Remain 32:48:01 loss: 0.2242 loss_seg: 0.1325 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:45:48,508 INFO misc.py line 117 726] Train: [12/20][379/510] Data 3.117 (3.805) Batch 28.279 (28.035) Remain 32:47:36 loss: 0.2083 loss_seg: 0.1189 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:46:15,266 INFO misc.py line 117 726] Train: [12/20][380/510] Data 3.819 (3.805) Batch 26.758 (28.032) Remain 32:46:53 loss: 0.1718 loss_seg: 0.0905 loss_superpoint_edge: 0.0135 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:46:43,735 INFO misc.py line 117 726] Train: [12/20][381/510] Data 3.654 (3.805) Batch 28.469 (28.033) Remain 32:46:30 loss: 0.2572 loss_seg: 0.1702 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:47:16,177 INFO misc.py line 117 726] Train: [12/20][382/510] Data 6.706 (3.812) Batch 32.442 (28.045) Remain 32:46:51 loss: 0.3662 loss_seg: 0.2669 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:47:46,539 INFO misc.py line 117 726] Train: [12/20][383/510] Data 3.935 (3.813) Batch 30.362 (28.051) Remain 32:46:49 loss: 0.2800 loss_seg: 0.1825 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:48:19,600 INFO misc.py line 117 726] Train: [12/20][384/510] Data 3.702 (3.812) Batch 33.060 (28.064) Remain 32:47:16 loss: 0.2479 loss_seg: 0.1521 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:48:52,979 INFO misc.py line 117 726] Train: [12/20][385/510] Data 3.342 (3.811) Batch 33.379 (28.078) Remain 32:47:46 loss: 0.3128 loss_seg: 0.2047 loss_superpoint_edge: 0.0446 loss_superpoint_contrast: 0.0314 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:49:14,212 INFO misc.py line 117 726] Train: [12/20][386/510] Data 2.789 (3.809) Batch 21.233 (28.060) Remain 32:46:03 loss: 0.2506 loss_seg: 0.1535 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:49:50,814 INFO misc.py line 117 726] Train: [12/20][387/510] Data 6.054 (3.814) Batch 36.602 (28.082) Remain 32:47:09 loss: 0.2523 loss_seg: 0.1549 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:50:17,345 INFO misc.py line 117 726] Train: [12/20][388/510] Data 2.452 (3.811) Batch 26.532 (28.078) Remain 32:46:24 loss: 0.2252 loss_seg: 0.1294 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:50:53,428 INFO misc.py line 117 726] Train: [12/20][389/510] Data 3.707 (3.811) Batch 36.083 (28.099) Remain 32:47:23 loss: 0.2976 loss_seg: 0.1991 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:51:17,839 INFO misc.py line 117 726] Train: [12/20][390/510] Data 2.198 (3.806) Batch 24.411 (28.089) Remain 32:46:15 loss: 0.1844 loss_seg: 0.0990 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:51:43,048 INFO misc.py line 117 726] Train: [12/20][391/510] Data 3.446 (3.805) Batch 25.209 (28.082) Remain 32:45:15 loss: 0.1975 loss_seg: 0.1121 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:52:19,261 INFO misc.py line 117 726] Train: [12/20][392/510] Data 3.702 (3.805) Batch 36.213 (28.103) Remain 32:46:15 loss: 0.2698 loss_seg: 0.1725 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:52:52,601 INFO misc.py line 117 726] Train: [12/20][393/510] Data 3.984 (3.806) Batch 33.340 (28.116) Remain 32:46:43 loss: 0.2320 loss_seg: 0.1372 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:53:16,245 INFO misc.py line 117 726] Train: [12/20][394/510] Data 3.928 (3.806) Batch 23.644 (28.105) Remain 32:45:27 loss: 0.1909 loss_seg: 0.0924 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0452 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:53:48,142 INFO misc.py line 117 726] Train: [12/20][395/510] Data 3.408 (3.805) Batch 31.896 (28.114) Remain 32:45:40 loss: 0.2532 loss_seg: 0.1537 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:54:08,322 INFO misc.py line 117 726] Train: [12/20][396/510] Data 1.828 (3.800) Batch 20.181 (28.094) Remain 32:43:47 loss: 0.1864 loss_seg: 0.1001 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:54:33,977 INFO misc.py line 117 726] Train: [12/20][397/510] Data 4.141 (3.801) Batch 25.655 (28.088) Remain 32:42:53 loss: 0.2476 loss_seg: 0.1544 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:55:12,484 INFO misc.py line 117 726] Train: [12/20][398/510] Data 4.038 (3.801) Batch 38.507 (28.114) Remain 32:44:15 loss: 0.2379 loss_seg: 0.1441 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:55:45,341 INFO misc.py line 117 726] Train: [12/20][399/510] Data 4.142 (3.802) Batch 32.857 (28.126) Remain 32:44:37 loss: 0.3037 loss_seg: 0.1954 loss_superpoint_edge: 0.0440 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:56:15,379 INFO misc.py line 117 726] Train: [12/20][400/510] Data 3.300 (3.801) Batch 30.039 (28.131) Remain 32:44:29 loss: 0.2198 loss_seg: 0.1289 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:56:15,380 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 15:56:44,044 INFO misc.py line 117 726] Train: [12/20][401/510] Data 5.726 (3.806) Batch 28.664 (28.133) Remain 32:44:07 loss: 0.6268 loss_seg: 0.4899 loss_superpoint_edge: 0.0683 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:57:15,167 INFO misc.py line 117 726] Train: [12/20][402/510] Data 3.456 (3.805) Batch 31.123 (28.140) Remain 32:44:10 loss: 0.1923 loss_seg: 0.1050 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:57:35,150 INFO misc.py line 117 726] Train: [12/20][403/510] Data 2.955 (3.803) Batch 19.983 (28.120) Remain 32:42:17 loss: 0.3842 loss_seg: 0.2671 loss_superpoint_edge: 0.0465 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:58:08,632 INFO misc.py line 117 726] Train: [12/20][404/510] Data 7.071 (3.811) Batch 33.482 (28.133) Remain 32:42:44 loss: 0.4065 loss_seg: 0.2879 loss_superpoint_edge: 0.0501 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:58:41,795 INFO misc.py line 117 726] Train: [12/20][405/510] Data 4.731 (3.813) Batch 33.163 (28.146) Remain 32:43:09 loss: 0.2555 loss_seg: 0.1625 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:59:09,604 INFO misc.py line 117 726] Train: [12/20][406/510] Data 3.801 (3.813) Batch 27.809 (28.145) Remain 32:42:37 loss: 0.2628 loss_seg: 0.1651 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 15:59:37,934 INFO misc.py line 117 726] Train: [12/20][407/510] Data 3.516 (3.812) Batch 28.330 (28.145) Remain 32:42:11 loss: 0.2730 loss_seg: 0.1754 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:00:08,685 INFO misc.py line 117 726] Train: [12/20][408/510] Data 2.748 (3.810) Batch 30.751 (28.152) Remain 32:42:10 loss: 0.2663 loss_seg: 0.1672 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:00:44,048 INFO misc.py line 117 726] Train: [12/20][409/510] Data 6.854 (3.817) Batch 35.364 (28.169) Remain 32:42:56 loss: 0.2681 loss_seg: 0.1753 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:01:16,035 INFO misc.py line 117 726] Train: [12/20][410/510] Data 9.376 (3.831) Batch 31.987 (28.179) Remain 32:43:07 loss: 0.2704 loss_seg: 0.1738 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:01:45,141 INFO misc.py line 117 726] Train: [12/20][411/510] Data 3.260 (3.830) Batch 29.106 (28.181) Remain 32:42:48 loss: 0.2420 loss_seg: 0.1451 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:02:11,684 INFO misc.py line 117 726] Train: [12/20][412/510] Data 3.244 (3.828) Batch 26.543 (28.177) Remain 32:42:03 loss: 0.3163 loss_seg: 0.2133 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:02:38,192 INFO misc.py line 117 726] Train: [12/20][413/510] Data 4.192 (3.829) Batch 26.508 (28.173) Remain 32:41:18 loss: 0.2908 loss_seg: 0.1984 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:02:57,774 INFO misc.py line 117 726] Train: [12/20][414/510] Data 2.623 (3.826) Batch 19.582 (28.152) Remain 32:39:22 loss: 0.2329 loss_seg: 0.1399 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:03:24,138 INFO misc.py line 117 726] Train: [12/20][415/510] Data 2.953 (3.824) Batch 26.364 (28.148) Remain 32:38:36 loss: 0.2132 loss_seg: 0.1203 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:03:54,456 INFO misc.py line 117 726] Train: [12/20][416/510] Data 3.153 (3.822) Batch 30.317 (28.153) Remain 32:38:30 loss: 0.2382 loss_seg: 0.1432 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:04:32,711 INFO misc.py line 117 726] Train: [12/20][417/510] Data 6.344 (3.828) Batch 38.255 (28.177) Remain 32:39:44 loss: 0.2794 loss_seg: 0.1830 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:05:04,327 INFO misc.py line 117 726] Train: [12/20][418/510] Data 3.319 (3.827) Batch 31.616 (28.186) Remain 32:39:50 loss: 0.2430 loss_seg: 0.1441 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:05:31,319 INFO misc.py line 117 726] Train: [12/20][419/510] Data 2.816 (3.825) Batch 26.992 (28.183) Remain 32:39:10 loss: 0.2012 loss_seg: 0.1152 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:05:59,296 INFO misc.py line 117 726] Train: [12/20][420/510] Data 3.238 (3.823) Batch 27.977 (28.182) Remain 32:38:40 loss: 0.2213 loss_seg: 0.1313 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:06:23,225 INFO misc.py line 117 726] Train: [12/20][421/510] Data 2.720 (3.821) Batch 23.930 (28.172) Remain 32:37:29 loss: 0.2016 loss_seg: 0.1130 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:06:45,521 INFO misc.py line 117 726] Train: [12/20][422/510] Data 2.526 (3.818) Batch 22.295 (28.158) Remain 32:36:02 loss: 0.2333 loss_seg: 0.1378 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:07:05,980 INFO misc.py line 117 726] Train: [12/20][423/510] Data 2.058 (3.814) Batch 20.459 (28.140) Remain 32:34:18 loss: 0.2707 loss_seg: 0.1696 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:07:31,871 INFO misc.py line 117 726] Train: [12/20][424/510] Data 3.114 (3.812) Batch 25.892 (28.134) Remain 32:33:28 loss: 0.2196 loss_seg: 0.1323 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:08:01,865 INFO misc.py line 117 726] Train: [12/20][425/510] Data 3.111 (3.810) Batch 29.994 (28.139) Remain 32:33:18 loss: 0.2146 loss_seg: 0.1263 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:08:26,168 INFO misc.py line 117 726] Train: [12/20][426/510] Data 3.377 (3.809) Batch 24.302 (28.130) Remain 32:32:12 loss: 0.3058 loss_seg: 0.2032 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:09:00,087 INFO misc.py line 117 726] Train: [12/20][427/510] Data 3.591 (3.809) Batch 33.920 (28.143) Remain 32:32:41 loss: 0.2755 loss_seg: 0.1772 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:09:23,780 INFO misc.py line 117 726] Train: [12/20][428/510] Data 3.146 (3.807) Batch 23.692 (28.133) Remain 32:31:29 loss: 0.2470 loss_seg: 0.1481 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:09:48,819 INFO misc.py line 117 726] Train: [12/20][429/510] Data 3.186 (3.806) Batch 25.040 (28.126) Remain 32:30:30 loss: 0.2315 loss_seg: 0.1428 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:10:20,958 INFO misc.py line 117 726] Train: [12/20][430/510] Data 4.463 (3.807) Batch 32.139 (28.135) Remain 32:30:41 loss: 0.2348 loss_seg: 0.1415 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:10:53,493 INFO misc.py line 117 726] Train: [12/20][431/510] Data 3.342 (3.806) Batch 32.535 (28.145) Remain 32:30:56 loss: 0.2461 loss_seg: 0.1460 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:11:17,938 INFO misc.py line 117 726] Train: [12/20][432/510] Data 3.107 (3.804) Batch 24.445 (28.137) Remain 32:29:52 loss: 0.2726 loss_seg: 0.1715 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:11:46,305 INFO misc.py line 117 726] Train: [12/20][433/510] Data 2.992 (3.803) Batch 28.368 (28.137) Remain 32:29:26 loss: 0.1718 loss_seg: 0.0842 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:12:13,685 INFO misc.py line 117 726] Train: [12/20][434/510] Data 2.625 (3.800) Batch 27.380 (28.136) Remain 32:28:51 loss: 0.2409 loss_seg: 0.1483 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:12:46,211 INFO misc.py line 117 726] Train: [12/20][435/510] Data 8.289 (3.810) Batch 32.526 (28.146) Remain 32:29:05 loss: 0.4208 loss_seg: 0.2938 loss_superpoint_edge: 0.0583 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0345 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:13:15,417 INFO misc.py line 117 726] Train: [12/20][436/510] Data 3.503 (3.810) Batch 29.206 (28.148) Remain 32:28:47 loss: 0.2153 loss_seg: 0.1266 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:13:38,667 INFO misc.py line 117 726] Train: [12/20][437/510] Data 2.675 (3.807) Batch 23.250 (28.137) Remain 32:27:32 loss: 0.2054 loss_seg: 0.1152 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:13:53,698 INFO misc.py line 117 726] Train: [12/20][438/510] Data 1.609 (3.802) Batch 15.031 (28.107) Remain 32:24:59 loss: 0.2041 loss_seg: 0.1132 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:14:18,314 INFO misc.py line 117 726] Train: [12/20][439/510] Data 2.565 (3.799) Batch 24.616 (28.099) Remain 32:23:57 loss: 0.3811 loss_seg: 0.2687 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:14:43,199 INFO misc.py line 117 726] Train: [12/20][440/510] Data 2.742 (3.797) Batch 24.885 (28.091) Remain 32:22:59 loss: 0.3089 loss_seg: 0.2075 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:15:12,508 INFO misc.py line 117 726] Train: [12/20][441/510] Data 3.411 (3.796) Batch 29.309 (28.094) Remain 32:22:42 loss: 0.2664 loss_seg: 0.1690 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:15:36,196 INFO misc.py line 117 726] Train: [12/20][442/510] Data 4.512 (3.797) Batch 23.687 (28.084) Remain 32:21:32 loss: 0.2046 loss_seg: 0.1193 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:16:01,651 INFO misc.py line 117 726] Train: [12/20][443/510] Data 5.216 (3.801) Batch 25.453 (28.078) Remain 32:20:39 loss: 0.2195 loss_seg: 0.1302 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:16:24,965 INFO misc.py line 117 726] Train: [12/20][444/510] Data 2.347 (3.797) Batch 23.316 (28.067) Remain 32:19:27 loss: 0.2053 loss_seg: 0.1148 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:16:51,919 INFO misc.py line 117 726] Train: [12/20][445/510] Data 2.427 (3.794) Batch 26.954 (28.065) Remain 32:18:48 loss: 0.2434 loss_seg: 0.1464 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:17:32,825 INFO misc.py line 117 726] Train: [12/20][446/510] Data 11.349 (3.811) Batch 40.906 (28.094) Remain 32:20:20 loss: 0.2687 loss_seg: 0.1641 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:17:59,218 INFO misc.py line 117 726] Train: [12/20][447/510] Data 3.251 (3.810) Batch 26.393 (28.090) Remain 32:19:36 loss: 0.3034 loss_seg: 0.2086 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:18:27,928 INFO misc.py line 117 726] Train: [12/20][448/510] Data 4.794 (3.812) Batch 28.710 (28.091) Remain 32:19:14 loss: 0.2227 loss_seg: 0.1303 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:18:54,296 INFO misc.py line 117 726] Train: [12/20][449/510] Data 3.012 (3.810) Batch 26.368 (28.087) Remain 32:18:30 loss: 0.2134 loss_seg: 0.1241 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:19:17,293 INFO misc.py line 117 726] Train: [12/20][450/510] Data 2.192 (3.807) Batch 22.997 (28.076) Remain 32:17:15 loss: 0.2070 loss_seg: 0.1187 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:19:17,294 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 16:19:47,807 INFO misc.py line 117 726] Train: [12/20][451/510] Data 3.927 (3.807) Batch 30.514 (28.082) Remain 32:17:09 loss: 0.2972 loss_seg: 0.1950 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:20:13,717 INFO misc.py line 117 726] Train: [12/20][452/510] Data 4.403 (3.808) Batch 25.910 (28.077) Remain 32:16:21 loss: 0.2628 loss_seg: 0.1654 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:20:37,626 INFO misc.py line 117 726] Train: [12/20][453/510] Data 1.980 (3.804) Batch 23.909 (28.067) Remain 32:15:14 loss: 0.2099 loss_seg: 0.1199 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:21:12,453 INFO misc.py line 117 726] Train: [12/20][454/510] Data 5.157 (3.807) Batch 34.828 (28.082) Remain 32:15:48 loss: 0.2512 loss_seg: 0.1564 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:21:42,353 INFO misc.py line 117 726] Train: [12/20][455/510] Data 3.393 (3.806) Batch 29.900 (28.086) Remain 32:15:37 loss: 0.3495 loss_seg: 0.2511 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:22:09,691 INFO misc.py line 117 726] Train: [12/20][456/510] Data 2.931 (3.804) Batch 27.338 (28.085) Remain 32:15:02 loss: 0.2138 loss_seg: 0.1229 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:22:35,214 INFO misc.py line 117 726] Train: [12/20][457/510] Data 3.567 (3.804) Batch 25.523 (28.079) Remain 32:14:11 loss: 0.2144 loss_seg: 0.1243 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:23:02,433 INFO misc.py line 117 726] Train: [12/20][458/510] Data 4.020 (3.804) Batch 27.219 (28.077) Remain 32:13:35 loss: 0.2648 loss_seg: 0.1695 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:23:28,630 INFO misc.py line 117 726] Train: [12/20][459/510] Data 2.883 (3.802) Batch 26.197 (28.073) Remain 32:12:50 loss: 0.2742 loss_seg: 0.1759 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:23:55,730 INFO misc.py line 117 726] Train: [12/20][460/510] Data 5.559 (3.806) Batch 27.100 (28.071) Remain 32:12:13 loss: 0.2152 loss_seg: 0.1280 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:24:16,206 INFO misc.py line 117 726] Train: [12/20][461/510] Data 2.688 (3.804) Batch 20.476 (28.054) Remain 32:10:36 loss: 0.1946 loss_seg: 0.1092 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:24:50,723 INFO misc.py line 117 726] Train: [12/20][462/510] Data 4.435 (3.805) Batch 34.517 (28.069) Remain 32:11:06 loss: 0.2254 loss_seg: 0.1318 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:25:10,564 INFO misc.py line 117 726] Train: [12/20][463/510] Data 2.344 (3.802) Batch 19.842 (28.051) Remain 32:09:24 loss: 0.2223 loss_seg: 0.1314 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:25:40,133 INFO misc.py line 117 726] Train: [12/20][464/510] Data 3.765 (3.802) Batch 29.568 (28.054) Remain 32:09:10 loss: 0.2591 loss_seg: 0.1632 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:26:09,139 INFO misc.py line 117 726] Train: [12/20][465/510] Data 3.091 (3.800) Batch 29.006 (28.056) Remain 32:08:50 loss: 0.2464 loss_seg: 0.1481 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:26:30,940 INFO misc.py line 117 726] Train: [12/20][466/510] Data 2.534 (3.798) Batch 21.801 (28.042) Remain 32:07:27 loss: 0.3315 loss_seg: 0.2358 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:26:47,792 INFO misc.py line 117 726] Train: [12/20][467/510] Data 1.509 (3.793) Batch 16.852 (28.018) Remain 32:05:19 loss: 0.3379 loss_seg: 0.2254 loss_superpoint_edge: 0.0444 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:27:20,251 INFO misc.py line 117 726] Train: [12/20][468/510] Data 4.880 (3.795) Batch 32.460 (28.028) Remain 32:05:30 loss: 0.2169 loss_seg: 0.1310 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:27:42,002 INFO misc.py line 117 726] Train: [12/20][469/510] Data 2.608 (3.792) Batch 21.750 (28.014) Remain 32:04:07 loss: 0.2805 loss_seg: 0.1790 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:28:14,912 INFO misc.py line 117 726] Train: [12/20][470/510] Data 4.623 (3.794) Batch 32.911 (28.025) Remain 32:04:22 loss: 0.4044 loss_seg: 0.2914 loss_superpoint_edge: 0.0428 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:28:40,551 INFO misc.py line 117 726] Train: [12/20][471/510] Data 2.281 (3.791) Batch 25.638 (28.020) Remain 32:03:33 loss: 0.2136 loss_seg: 0.1241 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:29:05,918 INFO misc.py line 117 726] Train: [12/20][472/510] Data 4.038 (3.792) Batch 25.368 (28.014) Remain 32:02:42 loss: 0.2607 loss_seg: 0.1625 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:29:32,253 INFO misc.py line 117 726] Train: [12/20][473/510] Data 2.432 (3.789) Batch 26.334 (28.011) Remain 32:01:59 loss: 0.2848 loss_seg: 0.1754 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:29:58,366 INFO misc.py line 117 726] Train: [12/20][474/510] Data 2.697 (3.786) Batch 26.114 (28.007) Remain 32:01:14 loss: 0.2494 loss_seg: 0.1471 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:30:23,029 INFO misc.py line 117 726] Train: [12/20][475/510] Data 3.143 (3.785) Batch 24.662 (27.999) Remain 32:00:17 loss: 0.2632 loss_seg: 0.1634 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:30:49,873 INFO misc.py line 117 726] Train: [12/20][476/510] Data 2.960 (3.783) Batch 26.845 (27.997) Remain 31:59:39 loss: 0.2150 loss_seg: 0.1250 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:31:19,705 INFO misc.py line 117 726] Train: [12/20][477/510] Data 8.493 (3.793) Batch 29.832 (28.001) Remain 31:59:27 loss: 0.2266 loss_seg: 0.1358 loss_superpoint_edge: 0.0121 loss_superpoint_contrast: 0.0483 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:31:37,270 INFO misc.py line 117 726] Train: [12/20][478/510] Data 1.802 (3.789) Batch 17.564 (27.979) Remain 31:57:29 loss: 0.2632 loss_seg: 0.1601 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:31:58,872 INFO misc.py line 117 726] Train: [12/20][479/510] Data 2.110 (3.785) Batch 21.602 (27.966) Remain 31:56:06 loss: 0.2090 loss_seg: 0.1209 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:32:18,999 INFO misc.py line 117 726] Train: [12/20][480/510] Data 2.061 (3.782) Batch 20.127 (27.949) Remain 31:54:30 loss: 0.2610 loss_seg: 0.1702 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:32:52,631 INFO misc.py line 117 726] Train: [12/20][481/510] Data 3.668 (3.782) Batch 33.631 (27.961) Remain 31:54:51 loss: 0.2583 loss_seg: 0.1615 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:33:21,645 INFO misc.py line 117 726] Train: [12/20][482/510] Data 3.577 (3.781) Batch 29.014 (27.963) Remain 31:54:32 loss: 0.1853 loss_seg: 0.1017 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:33:51,966 INFO misc.py line 117 726] Train: [12/20][483/510] Data 3.816 (3.781) Batch 30.321 (27.968) Remain 31:54:24 loss: 0.2361 loss_seg: 0.1397 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:34:08,893 INFO misc.py line 117 726] Train: [12/20][484/510] Data 2.160 (3.778) Batch 16.927 (27.945) Remain 31:52:22 loss: 0.3166 loss_seg: 0.2218 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:34:31,608 INFO misc.py line 117 726] Train: [12/20][485/510] Data 2.706 (3.776) Batch 22.715 (27.934) Remain 31:51:10 loss: 0.2311 loss_seg: 0.1387 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:34:57,117 INFO misc.py line 117 726] Train: [12/20][486/510] Data 2.927 (3.774) Batch 25.508 (27.929) Remain 31:50:21 loss: 0.1700 loss_seg: 0.0851 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:35:22,531 INFO misc.py line 117 726] Train: [12/20][487/510] Data 3.266 (3.773) Batch 25.414 (27.924) Remain 31:49:32 loss: 0.2273 loss_seg: 0.1319 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:35:55,423 INFO misc.py line 117 726] Train: [12/20][488/510] Data 3.677 (3.773) Batch 32.892 (27.934) Remain 31:49:46 loss: 0.2500 loss_seg: 0.1551 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:36:27,984 INFO misc.py line 117 726] Train: [12/20][489/510] Data 3.192 (3.771) Batch 32.560 (27.944) Remain 31:49:57 loss: 0.1914 loss_seg: 0.1091 loss_superpoint_edge: 0.0140 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:36:49,198 INFO misc.py line 117 726] Train: [12/20][490/510] Data 2.346 (3.769) Batch 21.215 (27.930) Remain 31:48:33 loss: 0.2010 loss_seg: 0.1167 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:37:17,726 INFO misc.py line 117 726] Train: [12/20][491/510] Data 4.413 (3.770) Batch 28.528 (27.931) Remain 31:48:10 loss: 0.2427 loss_seg: 0.1479 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:37:44,450 INFO misc.py line 117 726] Train: [12/20][492/510] Data 2.367 (3.767) Batch 26.723 (27.929) Remain 31:47:32 loss: 0.2367 loss_seg: 0.1422 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:38:05,737 INFO misc.py line 117 726] Train: [12/20][493/510] Data 2.076 (3.764) Batch 21.287 (27.915) Remain 31:46:08 loss: 0.3811 loss_seg: 0.2711 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:38:29,593 INFO misc.py line 117 726] Train: [12/20][494/510] Data 2.287 (3.761) Batch 23.856 (27.907) Remain 31:45:06 loss: 0.2567 loss_seg: 0.1633 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:38:58,287 INFO misc.py line 117 726] Train: [12/20][495/510] Data 4.666 (3.762) Batch 28.693 (27.909) Remain 31:44:45 loss: 0.2736 loss_seg: 0.1805 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:39:24,667 INFO misc.py line 117 726] Train: [12/20][496/510] Data 4.180 (3.763) Batch 26.381 (27.905) Remain 31:44:04 loss: 0.1877 loss_seg: 0.1011 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:39:49,121 INFO misc.py line 117 726] Train: [12/20][497/510] Data 2.815 (3.761) Batch 24.454 (27.898) Remain 31:43:08 loss: 0.2347 loss_seg: 0.1406 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:40:28,737 INFO misc.py line 117 726] Train: [12/20][498/510] Data 6.418 (3.767) Batch 39.617 (27.922) Remain 31:44:17 loss: 0.2212 loss_seg: 0.1285 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:41:07,012 INFO misc.py line 117 726] Train: [12/20][499/510] Data 10.349 (3.780) Batch 38.275 (27.943) Remain 31:45:14 loss: 0.2121 loss_seg: 0.1201 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:41:34,965 INFO misc.py line 117 726] Train: [12/20][500/510] Data 3.825 (3.780) Batch 27.953 (27.943) Remain 31:44:46 loss: 0.2277 loss_seg: 0.1372 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:41:34,966 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 16:42:07,202 INFO misc.py line 117 726] Train: [12/20][501/510] Data 5.350 (3.783) Batch 32.237 (27.952) Remain 31:44:54 loss: 0.3282 loss_seg: 0.2336 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:42:28,670 INFO misc.py line 117 726] Train: [12/20][502/510] Data 3.116 (3.782) Batch 21.468 (27.939) Remain 31:43:33 loss: 0.3413 loss_seg: 0.2367 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:42:51,091 INFO misc.py line 117 726] Train: [12/20][503/510] Data 3.269 (3.781) Batch 22.421 (27.928) Remain 31:42:20 loss: 0.2702 loss_seg: 0.1708 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:43:19,667 INFO misc.py line 117 726] Train: [12/20][504/510] Data 3.536 (3.780) Batch 28.576 (27.929) Remain 31:41:57 loss: 0.2370 loss_seg: 0.1404 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:43:56,217 INFO misc.py line 117 726] Train: [12/20][505/510] Data 5.579 (3.784) Batch 36.550 (27.946) Remain 31:42:39 loss: 0.2490 loss_seg: 0.1490 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:44:17,994 INFO misc.py line 117 726] Train: [12/20][506/510] Data 2.343 (3.781) Batch 21.778 (27.934) Remain 31:41:21 loss: 0.2796 loss_seg: 0.1773 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:44:47,443 INFO misc.py line 117 726] Train: [12/20][507/510] Data 3.175 (3.780) Batch 29.449 (27.937) Remain 31:41:06 loss: 0.2040 loss_seg: 0.1206 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:45:22,170 INFO misc.py line 117 726] Train: [12/20][508/510] Data 4.617 (3.781) Batch 34.727 (27.950) Remain 31:41:33 loss: 0.2536 loss_seg: 0.1589 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:45:48,888 INFO misc.py line 117 726] Train: [12/20][509/510] Data 2.975 (3.780) Batch 26.718 (27.948) Remain 31:40:55 loss: 0.3063 loss_seg: 0.1975 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:46:17,592 INFO misc.py line 117 726] Train: [12/20][510/510] Data 3.847 (3.780) Batch 28.704 (27.949) Remain 31:40:33 loss: 0.2712 loss_seg: 0.1756 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 16:46:17,593 INFO misc.py line 147 726] Train result: loss: 0.2488 loss_seg: 0.1540 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-11 16:46:17,593 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-11 16:46:32,955 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6508 [2026-06-11 16:46:48,815 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6746 [2026-06-11 16:48:03,465 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9580 [2026-06-11 16:48:43,669 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0053 [2026-06-11 16:49:02,977 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0276 [2026-06-11 16:49:38,869 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2114 [2026-06-11 16:50:24,979 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1600 [2026-06-11 16:50:40,214 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.1857 [2026-06-11 16:50:58,001 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.0127 [2026-06-11 16:51:16,551 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4436 [2026-06-11 16:51:32,414 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4888 [2026-06-11 16:51:53,724 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7792 [2026-06-11 16:52:19,677 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9100 [2026-06-11 16:52:30,895 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7326 [2026-06-11 16:53:02,233 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0353 [2026-06-11 16:53:28,144 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.5017 [2026-06-11 16:53:54,758 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.5025 [2026-06-11 16:54:37,502 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1586 [2026-06-11 16:54:58,460 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4535 [2026-06-11 16:55:14,855 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.9491 [2026-06-11 16:55:46,054 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 2.0202 [2026-06-11 16:56:02,559 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.5011 [2026-06-11 16:56:24,629 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3500 [2026-06-11 16:56:46,221 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8685 [2026-06-11 16:56:59,668 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6586 [2026-06-11 16:57:27,717 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.6039 [2026-06-11 16:58:09,344 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0795 [2026-06-11 16:58:26,654 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5270 [2026-06-11 16:58:45,343 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.5243 [2026-06-11 16:59:02,212 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3175 [2026-06-11 16:59:27,168 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.3096 [2026-06-11 16:59:45,289 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.7214 [2026-06-11 17:00:02,718 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1875 [2026-06-11 17:00:27,079 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6894 [2026-06-11 17:00:27,095 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6661/0.7381/0.8958. [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9264/0.9580 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9753/0.9880 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8381/0.9706 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0016/0.0113 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3022/0.3531 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6103/0.6398 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5775/0.6640 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7924/0.8926 [2026-06-11 17:00:27,095 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9113/0.9556 [2026-06-11 17:00:27,096 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6657/0.7407 [2026-06-11 17:00:27,096 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7603/0.8450 [2026-06-11 17:00:27,096 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6971/0.8594 [2026-06-11 17:00:27,096 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.6013/0.7171 [2026-06-11 17:00:27,096 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-11 17:00:27,097 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-11 17:00:27,097 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 17:00:54,789 INFO misc.py line 117 726] Train: [13/20][1/510] Data 2.258 (2.258) Batch 26.157 (26.157) Remain 29:38:15 loss: 0.2383 loss_seg: 0.1422 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:01:18,992 INFO misc.py line 117 726] Train: [13/20][2/510] Data 2.729 (2.729) Batch 24.203 (24.203) Remain 27:24:59 loss: 0.1976 loss_seg: 0.1118 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:01:53,619 INFO misc.py line 117 726] Train: [13/20][3/510] Data 5.398 (5.398) Batch 34.628 (34.628) Remain 39:12:56 loss: 0.2315 loss_seg: 0.1390 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:02:26,992 INFO misc.py line 117 726] Train: [13/20][4/510] Data 3.099 (3.099) Batch 33.372 (33.372) Remain 37:47:05 loss: 0.2556 loss_seg: 0.1564 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:02:50,251 INFO misc.py line 117 726] Train: [13/20][5/510] Data 4.694 (3.897) Batch 23.260 (28.316) Remain 32:03:07 loss: 0.4828 loss_seg: 0.3727 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:03:24,816 INFO misc.py line 117 726] Train: [13/20][6/510] Data 3.183 (3.659) Batch 34.565 (30.399) Remain 34:24:05 loss: 0.2486 loss_seg: 0.1602 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:03:52,443 INFO misc.py line 117 726] Train: [13/20][7/510] Data 3.705 (3.670) Batch 27.627 (29.706) Remain 33:36:32 loss: 0.2114 loss_seg: 0.1198 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:04:26,296 INFO misc.py line 117 726] Train: [13/20][8/510] Data 10.331 (5.002) Batch 33.852 (30.535) Remain 34:32:19 loss: 0.3109 loss_seg: 0.2060 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:04:51,863 INFO misc.py line 117 726] Train: [13/20][9/510] Data 2.665 (4.613) Batch 25.568 (29.707) Remain 33:35:38 loss: 0.1974 loss_seg: 0.1070 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:05:26,924 INFO misc.py line 117 726] Train: [13/20][10/510] Data 4.812 (4.641) Batch 35.061 (30.472) Remain 34:27:01 loss: 0.1925 loss_seg: 0.1062 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:06:01,376 INFO misc.py line 117 726] Train: [13/20][11/510] Data 3.930 (4.552) Batch 34.453 (30.970) Remain 35:00:15 loss: 0.2951 loss_seg: 0.1909 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:06:33,362 INFO misc.py line 117 726] Train: [13/20][12/510] Data 6.179 (4.733) Batch 31.985 (31.082) Remain 35:07:23 loss: 0.2212 loss_seg: 0.1316 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:06:57,422 INFO misc.py line 117 726] Train: [13/20][13/510] Data 2.917 (4.552) Batch 24.060 (30.380) Remain 34:19:16 loss: 0.2653 loss_seg: 0.1619 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:07:24,254 INFO misc.py line 117 726] Train: [13/20][14/510] Data 3.589 (4.464) Batch 26.833 (30.058) Remain 33:56:54 loss: 0.2954 loss_seg: 0.2051 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:07:45,669 INFO misc.py line 117 726] Train: [13/20][15/510] Data 2.728 (4.319) Batch 21.414 (29.337) Remain 33:07:36 loss: 0.2098 loss_seg: 0.1202 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:08:15,845 INFO misc.py line 117 726] Train: [13/20][16/510] Data 6.237 (4.467) Batch 30.176 (29.402) Remain 33:11:29 loss: 0.2929 loss_seg: 0.1889 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:08:40,849 INFO misc.py line 117 726] Train: [13/20][17/510] Data 2.405 (4.320) Batch 25.004 (29.088) Remain 32:49:43 loss: 0.2073 loss_seg: 0.1209 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:09:03,756 INFO misc.py line 117 726] Train: [13/20][18/510] Data 2.350 (4.188) Batch 22.907 (28.676) Remain 32:21:21 loss: 0.2880 loss_seg: 0.1957 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:09:33,584 INFO misc.py line 117 726] Train: [13/20][19/510] Data 5.462 (4.268) Batch 29.828 (28.748) Remain 32:25:44 loss: 0.2349 loss_seg: 0.1465 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:09:57,127 INFO misc.py line 117 726] Train: [13/20][20/510] Data 2.349 (4.155) Batch 23.543 (28.442) Remain 32:04:33 loss: 0.2369 loss_seg: 0.1456 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:10:27,703 INFO misc.py line 117 726] Train: [13/20][21/510] Data 3.866 (4.139) Batch 30.576 (28.560) Remain 32:12:05 loss: 0.2881 loss_seg: 0.1874 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:10:57,315 INFO misc.py line 117 726] Train: [13/20][22/510] Data 3.498 (4.105) Batch 29.612 (28.616) Remain 32:15:21 loss: 0.2633 loss_seg: 0.1612 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:11:32,066 INFO misc.py line 117 726] Train: [13/20][23/510] Data 5.488 (4.174) Batch 34.751 (28.922) Remain 32:35:37 loss: 0.2036 loss_seg: 0.1112 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:11:59,456 INFO misc.py line 117 726] Train: [13/20][24/510] Data 4.902 (4.209) Batch 27.389 (28.849) Remain 32:30:12 loss: 0.2259 loss_seg: 0.1345 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:12:25,737 INFO misc.py line 117 726] Train: [13/20][25/510] Data 2.240 (4.119) Batch 26.281 (28.733) Remain 32:21:50 loss: 0.2235 loss_seg: 0.1304 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:12:48,912 INFO misc.py line 117 726] Train: [13/20][26/510] Data 2.106 (4.032) Batch 23.175 (28.491) Remain 32:05:02 loss: 0.1905 loss_seg: 0.1028 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:13:21,275 INFO misc.py line 117 726] Train: [13/20][27/510] Data 3.582 (4.013) Batch 32.363 (28.652) Remain 32:15:27 loss: 0.3040 loss_seg: 0.2008 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:13:48,778 INFO misc.py line 117 726] Train: [13/20][28/510] Data 3.635 (3.998) Batch 27.503 (28.606) Remain 32:11:52 loss: 0.2248 loss_seg: 0.1370 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:14:06,928 INFO misc.py line 117 726] Train: [13/20][29/510] Data 2.158 (3.927) Batch 18.150 (28.204) Remain 31:44:15 loss: 0.2507 loss_seg: 0.1510 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:14:25,646 INFO misc.py line 117 726] Train: [13/20][30/510] Data 2.518 (3.875) Batch 18.717 (27.853) Remain 31:20:03 loss: 0.2541 loss_seg: 0.1605 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:14:55,801 INFO misc.py line 117 726] Train: [13/20][31/510] Data 2.450 (3.824) Batch 30.155 (27.935) Remain 31:25:09 loss: 0.2519 loss_seg: 0.1543 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:15:19,147 INFO misc.py line 117 726] Train: [13/20][32/510] Data 2.587 (3.782) Batch 23.346 (27.777) Remain 31:14:00 loss: 0.3517 loss_seg: 0.2498 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:15:57,758 INFO misc.py line 117 726] Train: [13/20][33/510] Data 8.481 (3.938) Batch 38.611 (28.138) Remain 31:37:54 loss: 0.2571 loss_seg: 0.1620 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:16:20,499 INFO misc.py line 117 726] Train: [13/20][34/510] Data 4.754 (3.964) Batch 22.741 (27.964) Remain 31:25:41 loss: 0.2803 loss_seg: 0.1818 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:16:42,281 INFO misc.py line 117 726] Train: [13/20][35/510] Data 2.685 (3.925) Batch 21.783 (27.771) Remain 31:12:12 loss: 0.2177 loss_seg: 0.1299 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:17:16,225 INFO misc.py line 117 726] Train: [13/20][36/510] Data 3.507 (3.912) Batch 33.944 (27.958) Remain 31:24:21 loss: 0.2554 loss_seg: 0.1556 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:17:37,579 INFO misc.py line 117 726] Train: [13/20][37/510] Data 2.737 (3.877) Batch 21.354 (27.764) Remain 31:10:47 loss: 0.2299 loss_seg: 0.1342 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:18:08,513 INFO misc.py line 117 726] Train: [13/20][38/510] Data 7.109 (3.970) Batch 30.934 (27.854) Remain 31:16:26 loss: 0.1924 loss_seg: 0.1061 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:18:41,245 INFO misc.py line 117 726] Train: [13/20][39/510] Data 3.090 (3.945) Batch 32.732 (27.990) Remain 31:25:05 loss: 0.3587 loss_seg: 0.2584 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:19:09,419 INFO misc.py line 117 726] Train: [13/20][40/510] Data 3.080 (3.922) Batch 28.173 (27.995) Remain 31:24:58 loss: 0.2196 loss_seg: 0.1267 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:19:48,835 INFO misc.py line 117 726] Train: [13/20][41/510] Data 9.296 (4.063) Batch 39.417 (28.295) Remain 31:44:44 loss: 0.2162 loss_seg: 0.1284 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:20:13,201 INFO misc.py line 117 726] Train: [13/20][42/510] Data 2.759 (4.030) Batch 24.366 (28.194) Remain 31:37:29 loss: 0.2238 loss_seg: 0.1286 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:20:41,907 INFO misc.py line 117 726] Train: [13/20][43/510] Data 3.440 (4.015) Batch 28.706 (28.207) Remain 31:37:52 loss: 0.2222 loss_seg: 0.1301 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:21:12,403 INFO misc.py line 117 726] Train: [13/20][44/510] Data 3.646 (4.006) Batch 30.496 (28.263) Remain 31:41:09 loss: 0.2398 loss_seg: 0.1460 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:21:33,537 INFO misc.py line 117 726] Train: [13/20][45/510] Data 2.603 (3.973) Batch 21.134 (28.093) Remain 31:29:16 loss: 0.2616 loss_seg: 0.1654 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:22:02,618 INFO misc.py line 117 726] Train: [13/20][46/510] Data 2.932 (3.948) Batch 29.081 (28.116) Remain 31:30:20 loss: 0.2299 loss_seg: 0.1362 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:22:25,147 INFO misc.py line 117 726] Train: [13/20][47/510] Data 2.866 (3.924) Batch 22.529 (27.989) Remain 31:21:20 loss: 0.2723 loss_seg: 0.1733 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:22:55,384 INFO misc.py line 117 726] Train: [13/20][48/510] Data 3.097 (3.905) Batch 30.237 (28.039) Remain 31:24:14 loss: 0.2217 loss_seg: 0.1326 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:23:25,118 INFO misc.py line 117 726] Train: [13/20][49/510] Data 2.509 (3.875) Batch 29.734 (28.076) Remain 31:26:14 loss: 0.2306 loss_seg: 0.1409 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:23:56,699 INFO misc.py line 117 726] Train: [13/20][50/510] Data 4.462 (3.888) Batch 31.581 (28.151) Remain 31:30:47 loss: 0.2680 loss_seg: 0.1673 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:23:56,699 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 17:24:24,615 INFO misc.py line 117 726] Train: [13/20][51/510] Data 3.519 (3.880) Batch 27.917 (28.146) Remain 31:29:59 loss: 0.2443 loss_seg: 0.1483 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:24:55,514 INFO misc.py line 117 726] Train: [13/20][52/510] Data 3.698 (3.876) Batch 30.899 (28.202) Remain 31:33:17 loss: 0.2202 loss_seg: 0.1306 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:25:29,384 INFO misc.py line 117 726] Train: [13/20][53/510] Data 8.114 (3.961) Batch 33.870 (28.315) Remain 31:40:25 loss: 0.2325 loss_seg: 0.1386 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:25:59,417 INFO misc.py line 117 726] Train: [13/20][54/510] Data 5.246 (3.986) Batch 30.033 (28.349) Remain 31:42:12 loss: 0.2298 loss_seg: 0.1348 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:26:33,134 INFO misc.py line 117 726] Train: [13/20][55/510] Data 4.602 (3.998) Batch 33.717 (28.452) Remain 31:48:40 loss: 0.2996 loss_seg: 0.1902 loss_superpoint_edge: 0.0438 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:26:56,593 INFO misc.py line 117 726] Train: [13/20][56/510] Data 3.079 (3.981) Batch 23.459 (28.358) Remain 31:41:52 loss: 0.2498 loss_seg: 0.1543 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:27:31,068 INFO misc.py line 117 726] Train: [13/20][57/510] Data 4.635 (3.993) Batch 34.475 (28.471) Remain 31:48:59 loss: 0.2440 loss_seg: 0.1515 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:28:04,627 INFO misc.py line 117 726] Train: [13/20][58/510] Data 4.160 (3.996) Batch 33.559 (28.564) Remain 31:54:43 loss: 0.1611 loss_seg: 0.0769 loss_superpoint_edge: 0.0137 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:28:40,205 INFO misc.py line 117 726] Train: [13/20][59/510] Data 6.629 (4.043) Batch 35.578 (28.689) Remain 32:02:38 loss: 0.3006 loss_seg: 0.1999 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:29:11,624 INFO misc.py line 117 726] Train: [13/20][60/510] Data 6.681 (4.089) Batch 31.419 (28.737) Remain 32:05:22 loss: 0.3346 loss_seg: 0.2260 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:29:30,697 INFO misc.py line 117 726] Train: [13/20][61/510] Data 1.735 (4.049) Batch 19.074 (28.570) Remain 31:53:44 loss: 0.2571 loss_seg: 0.1568 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:29:55,812 INFO misc.py line 117 726] Train: [13/20][62/510] Data 2.490 (4.022) Batch 25.115 (28.512) Remain 31:49:20 loss: 0.3445 loss_seg: 0.2416 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:30:31,269 INFO misc.py line 117 726] Train: [13/20][63/510] Data 9.086 (4.106) Batch 35.457 (28.627) Remain 31:56:36 loss: 0.4815 loss_seg: 0.3435 loss_superpoint_edge: 0.0716 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:30:52,594 INFO misc.py line 117 726] Train: [13/20][64/510] Data 1.969 (4.071) Batch 21.325 (28.508) Remain 31:48:07 loss: 0.2329 loss_seg: 0.1399 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:31:29,075 INFO misc.py line 117 726] Train: [13/20][65/510] Data 6.050 (4.103) Batch 36.481 (28.636) Remain 31:56:15 loss: 0.2536 loss_seg: 0.1591 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:31:59,367 INFO misc.py line 117 726] Train: [13/20][66/510] Data 5.257 (4.122) Batch 30.293 (28.663) Remain 31:57:31 loss: 0.2066 loss_seg: 0.1223 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:32:22,973 INFO misc.py line 117 726] Train: [13/20][67/510] Data 3.626 (4.114) Batch 23.605 (28.584) Remain 31:51:46 loss: 0.2991 loss_seg: 0.1961 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:32:51,575 INFO misc.py line 117 726] Train: [13/20][68/510] Data 4.588 (4.121) Batch 28.603 (28.584) Remain 31:51:18 loss: 0.1994 loss_seg: 0.1051 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0440 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:33:25,908 INFO misc.py line 117 726] Train: [13/20][69/510] Data 6.310 (4.154) Batch 34.333 (28.671) Remain 31:56:39 loss: 0.2280 loss_seg: 0.1346 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:33:57,890 INFO misc.py line 117 726] Train: [13/20][70/510] Data 5.872 (4.180) Batch 31.982 (28.720) Remain 31:59:29 loss: 0.2084 loss_seg: 0.1215 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:34:20,306 INFO misc.py line 117 726] Train: [13/20][71/510] Data 2.501 (4.155) Batch 22.416 (28.628) Remain 31:52:48 loss: 0.2265 loss_seg: 0.1297 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:34:48,151 INFO misc.py line 117 726] Train: [13/20][72/510] Data 4.119 (4.155) Batch 27.845 (28.616) Remain 31:51:34 loss: 0.2183 loss_seg: 0.1275 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0425 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:35:10,610 INFO misc.py line 117 726] Train: [13/20][73/510] Data 2.253 (4.128) Batch 22.458 (28.528) Remain 31:45:13 loss: 0.2072 loss_seg: 0.1178 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:35:31,461 INFO misc.py line 117 726] Train: [13/20][74/510] Data 2.810 (4.109) Batch 20.852 (28.420) Remain 31:37:31 loss: 0.2702 loss_seg: 0.1745 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:35:52,002 INFO misc.py line 117 726] Train: [13/20][75/510] Data 1.926 (4.079) Batch 20.541 (28.311) Remain 31:29:45 loss: 0.2722 loss_seg: 0.1717 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:36:12,200 INFO misc.py line 117 726] Train: [13/20][76/510] Data 2.157 (4.052) Batch 20.197 (28.200) Remain 31:21:51 loss: 0.2542 loss_seg: 0.1549 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:36:31,475 INFO misc.py line 117 726] Train: [13/20][77/510] Data 2.431 (4.031) Batch 19.275 (28.079) Remain 31:13:20 loss: 0.2453 loss_seg: 0.1465 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:36:55,841 INFO misc.py line 117 726] Train: [13/20][78/510] Data 2.395 (4.009) Batch 24.367 (28.030) Remain 31:09:34 loss: 0.1960 loss_seg: 0.1066 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:37:18,536 INFO misc.py line 117 726] Train: [13/20][79/510] Data 2.285 (3.986) Batch 22.694 (27.959) Remain 31:04:25 loss: 0.2061 loss_seg: 0.1136 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:37:50,059 INFO misc.py line 117 726] Train: [13/20][80/510] Data 4.360 (3.991) Batch 31.523 (28.006) Remain 31:07:02 loss: 0.2072 loss_seg: 0.1201 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:38:15,453 INFO misc.py line 117 726] Train: [13/20][81/510] Data 2.931 (3.977) Batch 25.394 (27.972) Remain 31:04:20 loss: 0.2540 loss_seg: 0.1526 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:38:43,612 INFO misc.py line 117 726] Train: [13/20][82/510] Data 3.360 (3.969) Batch 28.159 (27.975) Remain 31:04:02 loss: 0.2410 loss_seg: 0.1507 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:39:06,770 INFO misc.py line 117 726] Train: [13/20][83/510] Data 2.578 (3.952) Batch 23.157 (27.914) Remain 30:59:33 loss: 0.3319 loss_seg: 0.2321 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:39:33,485 INFO misc.py line 117 726] Train: [13/20][84/510] Data 3.067 (3.941) Batch 26.716 (27.900) Remain 30:58:06 loss: 0.1882 loss_seg: 0.1032 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:39:53,660 INFO misc.py line 117 726] Train: [13/20][85/510] Data 2.707 (3.926) Batch 20.175 (27.805) Remain 30:51:22 loss: 0.3143 loss_seg: 0.2176 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:40:25,064 INFO misc.py line 117 726] Train: [13/20][86/510] Data 3.570 (3.922) Batch 31.403 (27.849) Remain 30:53:47 loss: 0.1984 loss_seg: 0.1142 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:40:58,404 INFO misc.py line 117 726] Train: [13/20][87/510] Data 3.435 (3.916) Batch 33.341 (27.914) Remain 30:57:41 loss: 0.2320 loss_seg: 0.1401 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:41:28,217 INFO misc.py line 117 726] Train: [13/20][88/510] Data 5.293 (3.932) Batch 29.812 (27.936) Remain 30:58:42 loss: 0.2242 loss_seg: 0.1331 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:41:43,867 INFO misc.py line 117 726] Train: [13/20][89/510] Data 1.681 (3.906) Batch 15.651 (27.794) Remain 30:48:44 loss: 0.2404 loss_seg: 0.1518 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:42:11,981 INFO misc.py line 117 726] Train: [13/20][90/510] Data 2.663 (3.892) Batch 28.114 (27.797) Remain 30:48:31 loss: 0.2383 loss_seg: 0.1410 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:42:38,462 INFO misc.py line 117 726] Train: [13/20][91/510] Data 2.833 (3.880) Batch 26.480 (27.782) Remain 30:47:03 loss: 0.2230 loss_seg: 0.1302 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:43:01,925 INFO misc.py line 117 726] Train: [13/20][92/510] Data 2.676 (3.866) Batch 23.463 (27.734) Remain 30:43:22 loss: 0.2806 loss_seg: 0.1832 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:43:31,839 INFO misc.py line 117 726] Train: [13/20][93/510] Data 3.014 (3.857) Batch 29.915 (27.758) Remain 30:44:31 loss: 0.2553 loss_seg: 0.1592 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:44:00,240 INFO misc.py line 117 726] Train: [13/20][94/510] Data 4.073 (3.859) Batch 28.400 (27.765) Remain 30:44:31 loss: 0.2294 loss_seg: 0.1384 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:44:19,539 INFO misc.py line 117 726] Train: [13/20][95/510] Data 2.213 (3.841) Batch 19.299 (27.673) Remain 30:37:57 loss: 0.2300 loss_seg: 0.1379 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:44:47,334 INFO misc.py line 117 726] Train: [13/20][96/510] Data 3.204 (3.834) Batch 27.795 (27.674) Remain 30:37:34 loss: 0.4620 loss_seg: 0.3478 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:45:06,191 INFO misc.py line 117 726] Train: [13/20][97/510] Data 2.089 (3.816) Batch 18.856 (27.581) Remain 30:30:53 loss: 0.2572 loss_seg: 0.1617 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:45:33,982 INFO misc.py line 117 726] Train: [13/20][98/510] Data 2.872 (3.806) Batch 27.791 (27.583) Remain 30:30:34 loss: 0.2484 loss_seg: 0.1497 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:46:06,165 INFO misc.py line 117 726] Train: [13/20][99/510] Data 4.834 (3.817) Batch 32.183 (27.631) Remain 30:33:17 loss: 0.2428 loss_seg: 0.1492 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:46:39,586 INFO misc.py line 117 726] Train: [13/20][100/510] Data 3.902 (3.817) Batch 33.421 (27.690) Remain 30:36:47 loss: 0.1840 loss_seg: 0.0989 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:46:39,587 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 17:47:16,577 INFO misc.py line 117 726] Train: [13/20][101/510] Data 6.321 (3.843) Batch 36.990 (27.785) Remain 30:42:37 loss: 0.3163 loss_seg: 0.2151 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:47:40,097 INFO misc.py line 117 726] Train: [13/20][102/510] Data 2.951 (3.834) Batch 23.520 (27.742) Remain 30:39:18 loss: 0.2676 loss_seg: 0.1713 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:48:08,526 INFO misc.py line 117 726] Train: [13/20][103/510] Data 5.454 (3.850) Batch 28.429 (27.749) Remain 30:39:18 loss: 0.4061 loss_seg: 0.3030 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:48:30,974 INFO misc.py line 117 726] Train: [13/20][104/510] Data 2.662 (3.838) Batch 22.448 (27.697) Remain 30:35:21 loss: 0.2347 loss_seg: 0.1405 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:48:54,494 INFO misc.py line 117 726] Train: [13/20][105/510] Data 3.014 (3.830) Batch 23.520 (27.656) Remain 30:32:11 loss: 0.2355 loss_seg: 0.1457 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:49:21,585 INFO misc.py line 117 726] Train: [13/20][106/510] Data 2.389 (3.816) Batch 27.090 (27.650) Remain 30:31:21 loss: 0.2836 loss_seg: 0.1809 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:49:53,512 INFO misc.py line 117 726] Train: [13/20][107/510] Data 6.775 (3.845) Batch 31.927 (27.691) Remain 30:33:37 loss: 0.2453 loss_seg: 0.1501 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:50:14,060 INFO misc.py line 117 726] Train: [13/20][108/510] Data 3.051 (3.837) Batch 20.548 (27.623) Remain 30:28:39 loss: 0.1609 loss_seg: 0.0775 loss_superpoint_edge: 0.0122 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:50:41,180 INFO misc.py line 117 726] Train: [13/20][109/510] Data 2.525 (3.825) Batch 27.121 (27.618) Remain 30:27:53 loss: 0.2292 loss_seg: 0.1329 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:51:16,044 INFO misc.py line 117 726] Train: [13/20][110/510] Data 3.543 (3.822) Batch 34.863 (27.686) Remain 30:31:54 loss: 0.2090 loss_seg: 0.1217 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:51:38,438 INFO misc.py line 117 726] Train: [13/20][111/510] Data 3.129 (3.816) Batch 22.394 (27.637) Remain 30:28:12 loss: 0.2360 loss_seg: 0.1449 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:52:03,080 INFO misc.py line 117 726] Train: [13/20][112/510] Data 2.950 (3.808) Batch 24.642 (27.610) Remain 30:25:55 loss: 0.2708 loss_seg: 0.1717 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:52:32,945 INFO misc.py line 117 726] Train: [13/20][113/510] Data 3.197 (3.802) Batch 29.865 (27.630) Remain 30:26:49 loss: 0.2027 loss_seg: 0.1139 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0322 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:52:59,830 INFO misc.py line 117 726] Train: [13/20][114/510] Data 3.887 (3.803) Batch 26.886 (27.624) Remain 30:25:54 loss: 0.2179 loss_seg: 0.1302 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:53:25,192 INFO misc.py line 117 726] Train: [13/20][115/510] Data 2.403 (3.791) Batch 25.362 (27.603) Remain 30:24:07 loss: 0.1974 loss_seg: 0.1075 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:53:58,888 INFO misc.py line 117 726] Train: [13/20][116/510] Data 4.045 (3.793) Batch 33.696 (27.657) Remain 30:27:13 loss: 0.2729 loss_seg: 0.1738 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:54:28,432 INFO misc.py line 117 726] Train: [13/20][117/510] Data 3.770 (3.793) Batch 29.544 (27.674) Remain 30:27:51 loss: 0.2250 loss_seg: 0.1298 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:55:06,318 INFO misc.py line 117 726] Train: [13/20][118/510] Data 3.842 (3.793) Batch 37.886 (27.763) Remain 30:33:15 loss: 0.2627 loss_seg: 0.1644 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:55:38,235 INFO misc.py line 117 726] Train: [13/20][119/510] Data 3.768 (3.793) Batch 31.917 (27.798) Remain 30:35:09 loss: 0.2921 loss_seg: 0.1877 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:56:09,997 INFO misc.py line 117 726] Train: [13/20][120/510] Data 4.419 (3.798) Batch 31.762 (27.832) Remain 30:36:55 loss: 0.2468 loss_seg: 0.1521 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:56:31,572 INFO misc.py line 117 726] Train: [13/20][121/510] Data 2.544 (3.788) Batch 21.575 (27.779) Remain 30:32:58 loss: 0.2378 loss_seg: 0.1418 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:56:53,176 INFO misc.py line 117 726] Train: [13/20][122/510] Data 2.652 (3.778) Batch 21.605 (27.727) Remain 30:29:04 loss: 0.2382 loss_seg: 0.1413 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:57:28,861 INFO misc.py line 117 726] Train: [13/20][123/510] Data 5.128 (3.789) Batch 35.685 (27.794) Remain 30:32:59 loss: 0.2124 loss_seg: 0.1225 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:57:52,056 INFO misc.py line 117 726] Train: [13/20][124/510] Data 2.739 (3.781) Batch 23.195 (27.756) Remain 30:30:01 loss: 0.1782 loss_seg: 0.0926 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:58:10,678 INFO misc.py line 117 726] Train: [13/20][125/510] Data 2.176 (3.767) Batch 18.622 (27.681) Remain 30:24:37 loss: 0.2869 loss_seg: 0.1856 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:58:49,419 INFO misc.py line 117 726] Train: [13/20][126/510] Data 5.965 (3.785) Batch 38.741 (27.771) Remain 30:30:05 loss: 0.2528 loss_seg: 0.1539 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:59:20,461 INFO misc.py line 117 726] Train: [13/20][127/510] Data 3.295 (3.781) Batch 31.042 (27.797) Remain 30:31:21 loss: 0.2192 loss_seg: 0.1272 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 17:59:47,691 INFO misc.py line 117 726] Train: [13/20][128/510] Data 2.929 (3.775) Batch 27.229 (27.793) Remain 30:30:36 loss: 0.2037 loss_seg: 0.1158 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:00:07,525 INFO misc.py line 117 726] Train: [13/20][129/510] Data 2.013 (3.761) Batch 19.834 (27.729) Remain 30:25:58 loss: 0.2454 loss_seg: 0.1456 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:00:35,326 INFO misc.py line 117 726] Train: [13/20][130/510] Data 3.373 (3.757) Batch 27.801 (27.730) Remain 30:25:33 loss: 0.2468 loss_seg: 0.1498 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:01:07,545 INFO misc.py line 117 726] Train: [13/20][131/510] Data 3.670 (3.757) Batch 32.220 (27.765) Remain 30:27:24 loss: 0.2291 loss_seg: 0.1351 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:01:39,400 INFO misc.py line 117 726] Train: [13/20][132/510] Data 3.713 (3.756) Batch 31.855 (27.797) Remain 30:29:01 loss: 0.2489 loss_seg: 0.1555 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:02:13,452 INFO misc.py line 117 726] Train: [13/20][133/510] Data 4.203 (3.760) Batch 34.052 (27.845) Remain 30:31:43 loss: 0.2072 loss_seg: 0.1170 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:02:49,639 INFO misc.py line 117 726] Train: [13/20][134/510] Data 4.397 (3.765) Batch 36.187 (27.909) Remain 30:35:27 loss: 0.2383 loss_seg: 0.1380 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:03:14,260 INFO misc.py line 117 726] Train: [13/20][135/510] Data 4.090 (3.767) Batch 24.621 (27.884) Remain 30:33:20 loss: 0.2756 loss_seg: 0.1799 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:03:41,865 INFO misc.py line 117 726] Train: [13/20][136/510] Data 4.939 (3.776) Batch 27.605 (27.882) Remain 30:32:44 loss: 0.2168 loss_seg: 0.1282 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:04:08,955 INFO misc.py line 117 726] Train: [13/20][137/510] Data 2.466 (3.766) Batch 27.089 (27.876) Remain 30:31:53 loss: 0.2433 loss_seg: 0.1518 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:04:37,910 INFO misc.py line 117 726] Train: [13/20][138/510] Data 4.513 (3.772) Batch 28.955 (27.884) Remain 30:31:57 loss: 0.2022 loss_seg: 0.1140 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:05:06,865 INFO misc.py line 117 726] Train: [13/20][139/510] Data 2.748 (3.764) Batch 28.955 (27.892) Remain 30:32:00 loss: 0.2266 loss_seg: 0.1333 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:05:37,632 INFO misc.py line 117 726] Train: [13/20][140/510] Data 2.892 (3.758) Batch 30.767 (27.912) Remain 30:32:55 loss: 0.2691 loss_seg: 0.1669 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:06:02,124 INFO misc.py line 117 726] Train: [13/20][141/510] Data 2.746 (3.751) Batch 24.492 (27.888) Remain 30:30:49 loss: 0.2435 loss_seg: 0.1517 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:06:22,719 INFO misc.py line 117 726] Train: [13/20][142/510] Data 1.770 (3.736) Batch 20.595 (27.835) Remain 30:26:55 loss: 0.2045 loss_seg: 0.1155 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:06:56,172 INFO misc.py line 117 726] Train: [13/20][143/510] Data 5.264 (3.747) Batch 33.454 (27.875) Remain 30:29:05 loss: 0.2640 loss_seg: 0.1686 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:07:30,587 INFO misc.py line 117 726] Train: [13/20][144/510] Data 4.327 (3.751) Batch 34.415 (27.922) Remain 30:31:40 loss: 0.2157 loss_seg: 0.1251 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:07:48,637 INFO misc.py line 117 726] Train: [13/20][145/510] Data 1.998 (3.739) Batch 18.050 (27.852) Remain 30:26:38 loss: 0.2356 loss_seg: 0.1403 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:08:21,769 INFO misc.py line 117 726] Train: [13/20][146/510] Data 3.498 (3.737) Batch 33.132 (27.889) Remain 30:28:35 loss: 0.2662 loss_seg: 0.1731 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:08:54,344 INFO misc.py line 117 726] Train: [13/20][147/510] Data 5.445 (3.749) Batch 32.575 (27.922) Remain 30:30:16 loss: 0.2601 loss_seg: 0.1563 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:09:26,826 INFO misc.py line 117 726] Train: [13/20][148/510] Data 2.842 (3.743) Batch 32.481 (27.953) Remain 30:31:51 loss: 0.2223 loss_seg: 0.1308 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:09:56,225 INFO misc.py line 117 726] Train: [13/20][149/510] Data 3.663 (3.742) Batch 29.400 (27.963) Remain 30:32:02 loss: 0.3348 loss_seg: 0.2352 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:10:29,420 INFO misc.py line 117 726] Train: [13/20][150/510] Data 3.288 (3.739) Batch 33.195 (27.999) Remain 30:33:54 loss: 0.3790 loss_seg: 0.2809 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:10:29,420 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 18:10:53,178 INFO misc.py line 117 726] Train: [13/20][151/510] Data 3.880 (3.740) Batch 23.758 (27.970) Remain 30:31:34 loss: 0.4132 loss_seg: 0.3134 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:11:20,093 INFO misc.py line 117 726] Train: [13/20][152/510] Data 3.232 (3.737) Batch 26.916 (27.963) Remain 30:30:38 loss: 0.2097 loss_seg: 0.1191 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:11:49,092 INFO misc.py line 117 726] Train: [13/20][153/510] Data 6.287 (3.754) Batch 28.998 (27.970) Remain 30:30:37 loss: 0.2919 loss_seg: 0.1888 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0427 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:12:28,758 INFO misc.py line 117 726] Train: [13/20][154/510] Data 8.319 (3.784) Batch 39.667 (28.047) Remain 30:35:13 loss: 0.2787 loss_seg: 0.1797 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:12:46,366 INFO misc.py line 117 726] Train: [13/20][155/510] Data 1.749 (3.771) Batch 17.608 (27.979) Remain 30:30:15 loss: 0.2626 loss_seg: 0.1664 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:13:22,476 INFO misc.py line 117 726] Train: [13/20][156/510] Data 3.451 (3.769) Batch 36.111 (28.032) Remain 30:33:16 loss: 0.2697 loss_seg: 0.1690 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:13:51,183 INFO misc.py line 117 726] Train: [13/20][157/510] Data 3.019 (3.764) Batch 28.706 (28.036) Remain 30:33:05 loss: 0.2779 loss_seg: 0.1756 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:14:30,405 INFO misc.py line 117 726] Train: [13/20][158/510] Data 6.415 (3.781) Batch 39.222 (28.108) Remain 30:37:20 loss: 0.2541 loss_seg: 0.1512 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:15:02,815 INFO misc.py line 117 726] Train: [13/20][159/510] Data 3.642 (3.780) Batch 32.410 (28.136) Remain 30:38:40 loss: 0.3101 loss_seg: 0.2133 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:15:32,555 INFO misc.py line 117 726] Train: [13/20][160/510] Data 3.319 (3.777) Batch 29.740 (28.146) Remain 30:38:52 loss: 0.2074 loss_seg: 0.1185 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:16:05,726 INFO misc.py line 117 726] Train: [13/20][161/510] Data 4.000 (3.778) Batch 33.171 (28.178) Remain 30:40:29 loss: 0.2307 loss_seg: 0.1440 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:16:28,648 INFO misc.py line 117 726] Train: [13/20][162/510] Data 2.240 (3.769) Batch 22.923 (28.145) Remain 30:37:51 loss: 0.2515 loss_seg: 0.1620 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:16:47,256 INFO misc.py line 117 726] Train: [13/20][163/510] Data 1.955 (3.757) Batch 18.608 (28.085) Remain 30:33:29 loss: 0.2617 loss_seg: 0.1624 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:17:13,012 INFO misc.py line 117 726] Train: [13/20][164/510] Data 2.470 (3.749) Batch 25.756 (28.071) Remain 30:32:05 loss: 0.2383 loss_seg: 0.1482 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:17:45,141 INFO misc.py line 117 726] Train: [13/20][165/510] Data 5.645 (3.761) Batch 32.129 (28.096) Remain 30:33:15 loss: 0.2573 loss_seg: 0.1584 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:18:04,683 INFO misc.py line 117 726] Train: [13/20][166/510] Data 2.008 (3.750) Batch 19.542 (28.043) Remain 30:29:21 loss: 0.2244 loss_seg: 0.1303 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:18:28,928 INFO misc.py line 117 726] Train: [13/20][167/510] Data 3.878 (3.751) Batch 24.246 (28.020) Remain 30:27:22 loss: 0.2892 loss_seg: 0.1967 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:18:56,166 INFO misc.py line 117 726] Train: [13/20][168/510] Data 2.762 (3.745) Batch 27.237 (28.015) Remain 30:26:36 loss: 0.2779 loss_seg: 0.1781 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:19:26,097 INFO misc.py line 117 726] Train: [13/20][169/510] Data 3.821 (3.746) Batch 29.932 (28.027) Remain 30:26:53 loss: 0.3655 loss_seg: 0.2604 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:19:52,404 INFO misc.py line 117 726] Train: [13/20][170/510] Data 3.626 (3.745) Batch 26.306 (28.017) Remain 30:25:45 loss: 0.2496 loss_seg: 0.1532 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:20:33,158 INFO misc.py line 117 726] Train: [13/20][171/510] Data 10.524 (3.785) Batch 40.755 (28.092) Remain 30:30:13 loss: 0.4027 loss_seg: 0.2908 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:20:54,233 INFO misc.py line 117 726] Train: [13/20][172/510] Data 2.466 (3.777) Batch 21.075 (28.051) Remain 30:27:03 loss: 0.2723 loss_seg: 0.1842 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:21:20,316 INFO misc.py line 117 726] Train: [13/20][173/510] Data 4.969 (3.784) Batch 26.083 (28.039) Remain 30:25:49 loss: 0.2742 loss_seg: 0.1775 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:21:42,744 INFO misc.py line 117 726] Train: [13/20][174/510] Data 2.305 (3.776) Batch 22.428 (28.007) Remain 30:23:13 loss: 0.1982 loss_seg: 0.1072 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:22:05,375 INFO misc.py line 117 726] Train: [13/20][175/510] Data 2.767 (3.770) Batch 22.632 (27.975) Remain 30:20:43 loss: 0.3041 loss_seg: 0.2123 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:22:25,158 INFO misc.py line 117 726] Train: [13/20][176/510] Data 2.016 (3.760) Batch 19.783 (27.928) Remain 30:17:10 loss: 0.3094 loss_seg: 0.2139 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:22:52,043 INFO misc.py line 117 726] Train: [13/20][177/510] Data 6.348 (3.775) Batch 26.885 (27.922) Remain 30:16:19 loss: 0.3722 loss_seg: 0.2603 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:23:24,383 INFO misc.py line 117 726] Train: [13/20][178/510] Data 3.731 (3.774) Batch 32.340 (27.947) Remain 30:17:30 loss: 0.2314 loss_seg: 0.1368 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:23:45,382 INFO misc.py line 117 726] Train: [13/20][179/510] Data 2.282 (3.766) Batch 20.999 (27.908) Remain 30:14:28 loss: 0.2833 loss_seg: 0.1846 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:24:09,619 INFO misc.py line 117 726] Train: [13/20][180/510] Data 2.789 (3.760) Batch 24.236 (27.887) Remain 30:12:39 loss: 0.2691 loss_seg: 0.1677 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:24:40,363 INFO misc.py line 117 726] Train: [13/20][181/510] Data 3.729 (3.760) Batch 30.745 (27.903) Remain 30:13:14 loss: 0.2968 loss_seg: 0.2029 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:25:03,954 INFO misc.py line 117 726] Train: [13/20][182/510] Data 2.520 (3.753) Batch 23.591 (27.879) Remain 30:11:12 loss: 0.2751 loss_seg: 0.1736 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:25:32,704 INFO misc.py line 117 726] Train: [13/20][183/510] Data 3.579 (3.752) Batch 28.750 (27.884) Remain 30:11:03 loss: 0.2841 loss_seg: 0.1827 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:25:55,361 INFO misc.py line 117 726] Train: [13/20][184/510] Data 2.172 (3.744) Batch 22.657 (27.855) Remain 30:08:42 loss: 0.2066 loss_seg: 0.1168 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:26:19,832 INFO misc.py line 117 726] Train: [13/20][185/510] Data 5.027 (3.751) Batch 24.471 (27.836) Remain 30:07:02 loss: 0.2069 loss_seg: 0.1134 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:26:49,706 INFO misc.py line 117 726] Train: [13/20][186/510] Data 3.910 (3.752) Batch 29.874 (27.847) Remain 30:07:18 loss: 0.2144 loss_seg: 0.1232 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:27:21,538 INFO misc.py line 117 726] Train: [13/20][187/510] Data 6.781 (3.768) Batch 31.831 (27.869) Remain 30:08:14 loss: 0.3519 loss_seg: 0.2462 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:27:49,210 INFO misc.py line 117 726] Train: [13/20][188/510] Data 10.252 (3.803) Batch 27.673 (27.868) Remain 30:07:42 loss: 0.2467 loss_seg: 0.1414 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0429 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:28:14,892 INFO misc.py line 117 726] Train: [13/20][189/510] Data 2.756 (3.797) Batch 25.682 (27.856) Remain 30:06:28 loss: 0.1938 loss_seg: 0.1076 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:28:47,614 INFO misc.py line 117 726] Train: [13/20][190/510] Data 5.375 (3.806) Batch 32.722 (27.882) Remain 30:07:42 loss: 0.2594 loss_seg: 0.1619 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:29:20,500 INFO misc.py line 117 726] Train: [13/20][191/510] Data 8.384 (3.830) Batch 32.886 (27.909) Remain 30:08:57 loss: 0.1825 loss_seg: 0.0926 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:29:37,474 INFO misc.py line 117 726] Train: [13/20][192/510] Data 3.002 (3.826) Batch 16.974 (27.851) Remain 30:04:44 loss: 0.4100 loss_seg: 0.3017 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:30:07,844 INFO misc.py line 117 726] Train: [13/20][193/510] Data 3.573 (3.824) Batch 30.371 (27.864) Remain 30:05:08 loss: 0.2822 loss_seg: 0.1790 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:30:30,075 INFO misc.py line 117 726] Train: [13/20][194/510] Data 2.448 (3.817) Batch 22.230 (27.835) Remain 30:02:46 loss: 0.2181 loss_seg: 0.1273 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:30:54,817 INFO misc.py line 117 726] Train: [13/20][195/510] Data 2.592 (3.811) Batch 24.743 (27.819) Remain 30:01:15 loss: 0.2276 loss_seg: 0.1310 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:31:21,969 INFO misc.py line 117 726] Train: [13/20][196/510] Data 2.309 (3.803) Batch 27.152 (27.815) Remain 30:00:34 loss: 0.2576 loss_seg: 0.1558 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:31:53,261 INFO misc.py line 117 726] Train: [13/20][197/510] Data 3.986 (3.804) Batch 31.292 (27.833) Remain 30:01:16 loss: 0.2836 loss_seg: 0.1789 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:32:11,815 INFO misc.py line 117 726] Train: [13/20][198/510] Data 2.070 (3.795) Batch 18.554 (27.786) Remain 29:57:43 loss: 0.2491 loss_seg: 0.1527 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:32:33,481 INFO misc.py line 117 726] Train: [13/20][199/510] Data 2.187 (3.787) Batch 21.666 (27.754) Remain 29:55:14 loss: 0.2079 loss_seg: 0.1197 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:33:00,754 INFO misc.py line 117 726] Train: [13/20][200/510] Data 2.737 (3.782) Batch 27.273 (27.752) Remain 29:54:37 loss: 0.2186 loss_seg: 0.1302 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:33:00,755 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 18:33:27,197 INFO misc.py line 117 726] Train: [13/20][201/510] Data 3.177 (3.779) Batch 26.443 (27.745) Remain 29:53:44 loss: 0.2340 loss_seg: 0.1411 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:34:00,068 INFO misc.py line 117 726] Train: [13/20][202/510] Data 3.371 (3.777) Batch 32.872 (27.771) Remain 29:54:56 loss: 0.1850 loss_seg: 0.1035 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:34:30,244 INFO misc.py line 117 726] Train: [13/20][203/510] Data 4.245 (3.779) Batch 30.175 (27.783) Remain 29:55:15 loss: 0.2262 loss_seg: 0.1325 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:34:53,925 INFO misc.py line 117 726] Train: [13/20][204/510] Data 2.538 (3.773) Batch 23.681 (27.763) Remain 29:53:28 loss: 0.3178 loss_seg: 0.2081 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:35:18,741 INFO misc.py line 117 726] Train: [13/20][205/510] Data 2.768 (3.768) Batch 24.816 (27.748) Remain 29:52:03 loss: 0.2173 loss_seg: 0.1230 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:35:56,908 INFO misc.py line 117 726] Train: [13/20][206/510] Data 5.627 (3.777) Batch 38.167 (27.799) Remain 29:54:55 loss: 0.2393 loss_seg: 0.1476 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:36:30,621 INFO misc.py line 117 726] Train: [13/20][207/510] Data 4.746 (3.782) Batch 33.713 (27.828) Remain 29:56:19 loss: 0.1880 loss_seg: 0.1040 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:37:04,862 INFO misc.py line 117 726] Train: [13/20][208/510] Data 4.551 (3.785) Batch 34.241 (27.860) Remain 29:57:52 loss: 0.2234 loss_seg: 0.1337 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0320 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:37:28,130 INFO misc.py line 117 726] Train: [13/20][209/510] Data 3.936 (3.786) Batch 23.268 (27.837) Remain 29:55:58 loss: 0.2291 loss_seg: 0.1357 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:37:57,474 INFO misc.py line 117 726] Train: [13/20][210/510] Data 3.187 (3.783) Batch 29.345 (27.845) Remain 29:55:59 loss: 0.2761 loss_seg: 0.1774 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:38:23,122 INFO misc.py line 117 726] Train: [13/20][211/510] Data 3.167 (3.780) Batch 25.648 (27.834) Remain 29:54:50 loss: 0.2226 loss_seg: 0.1280 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:38:47,683 INFO misc.py line 117 726] Train: [13/20][212/510] Data 2.604 (3.775) Batch 24.561 (27.818) Remain 29:53:21 loss: 0.1857 loss_seg: 0.1015 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:39:12,432 INFO misc.py line 117 726] Train: [13/20][213/510] Data 3.241 (3.772) Batch 24.748 (27.804) Remain 29:51:57 loss: 0.2690 loss_seg: 0.1651 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:39:39,956 INFO misc.py line 117 726] Train: [13/20][214/510] Data 3.718 (3.772) Batch 27.524 (27.803) Remain 29:51:24 loss: 0.2075 loss_seg: 0.1174 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:40:02,072 INFO misc.py line 117 726] Train: [13/20][215/510] Data 2.678 (3.767) Batch 22.117 (27.776) Remain 29:49:13 loss: 0.2182 loss_seg: 0.1302 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:40:24,912 INFO misc.py line 117 726] Train: [13/20][216/510] Data 3.021 (3.763) Batch 22.840 (27.753) Remain 29:47:15 loss: 0.2133 loss_seg: 0.1222 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:41:03,598 INFO misc.py line 117 726] Train: [13/20][217/510] Data 4.835 (3.768) Batch 38.685 (27.804) Remain 29:50:05 loss: 0.2349 loss_seg: 0.1435 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:41:25,925 INFO misc.py line 117 726] Train: [13/20][218/510] Data 1.938 (3.760) Batch 22.327 (27.778) Remain 29:47:59 loss: 0.2309 loss_seg: 0.1334 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:41:41,823 INFO misc.py line 117 726] Train: [13/20][219/510] Data 2.049 (3.752) Batch 15.898 (27.723) Remain 29:43:59 loss: 0.2189 loss_seg: 0.1290 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:42:04,945 INFO misc.py line 117 726] Train: [13/20][220/510] Data 2.744 (3.747) Batch 23.122 (27.702) Remain 29:42:09 loss: 0.1956 loss_seg: 0.1087 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:42:18,739 INFO misc.py line 117 726] Train: [13/20][221/510] Data 1.987 (3.739) Batch 13.795 (27.638) Remain 29:37:35 loss: 0.2531 loss_seg: 0.1497 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:42:48,325 INFO misc.py line 117 726] Train: [13/20][222/510] Data 4.150 (3.741) Batch 29.586 (27.647) Remain 29:37:42 loss: 0.4164 loss_seg: 0.3007 loss_superpoint_edge: 0.0474 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0336 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:43:11,012 INFO misc.py line 117 726] Train: [13/20][223/510] Data 2.076 (3.733) Batch 22.686 (27.625) Remain 29:35:47 loss: 0.2168 loss_seg: 0.1261 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:43:48,190 INFO misc.py line 117 726] Train: [13/20][224/510] Data 8.919 (3.757) Batch 37.178 (27.668) Remain 29:38:06 loss: 0.1880 loss_seg: 0.1023 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:44:09,421 INFO misc.py line 117 726] Train: [13/20][225/510] Data 2.435 (3.751) Batch 21.231 (27.639) Remain 29:35:47 loss: 0.2179 loss_seg: 0.1238 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:44:34,046 INFO misc.py line 117 726] Train: [13/20][226/510] Data 2.968 (3.747) Batch 24.625 (27.625) Remain 29:34:27 loss: 0.2202 loss_seg: 0.1275 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:44:55,679 INFO misc.py line 117 726] Train: [13/20][227/510] Data 1.892 (3.739) Batch 21.633 (27.598) Remain 29:32:16 loss: 0.1921 loss_seg: 0.1010 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:45:24,335 INFO misc.py line 117 726] Train: [13/20][228/510] Data 3.310 (3.737) Batch 28.656 (27.603) Remain 29:32:07 loss: 0.2744 loss_seg: 0.1688 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:45:51,882 INFO misc.py line 117 726] Train: [13/20][229/510] Data 2.809 (3.733) Batch 27.547 (27.603) Remain 29:31:38 loss: 0.1882 loss_seg: 0.1026 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:46:11,487 INFO misc.py line 117 726] Train: [13/20][230/510] Data 1.699 (3.724) Batch 19.604 (27.568) Remain 29:28:55 loss: 0.2503 loss_seg: 0.1516 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:46:39,207 INFO misc.py line 117 726] Train: [13/20][231/510] Data 3.320 (3.722) Batch 27.720 (27.568) Remain 29:28:30 loss: 0.2775 loss_seg: 0.1857 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:47:04,460 INFO misc.py line 117 726] Train: [13/20][232/510] Data 3.256 (3.720) Batch 25.253 (27.558) Remain 29:27:24 loss: 0.2065 loss_seg: 0.1167 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:47:27,520 INFO misc.py line 117 726] Train: [13/20][233/510] Data 2.482 (3.715) Batch 23.061 (27.539) Remain 29:25:41 loss: 0.2281 loss_seg: 0.1375 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:47:56,003 INFO misc.py line 117 726] Train: [13/20][234/510] Data 3.946 (3.716) Batch 28.483 (27.543) Remain 29:25:29 loss: 0.2424 loss_seg: 0.1487 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:48:24,209 INFO misc.py line 117 726] Train: [13/20][235/510] Data 3.199 (3.714) Batch 28.206 (27.546) Remain 29:25:13 loss: 0.3191 loss_seg: 0.2101 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:48:47,532 INFO misc.py line 117 726] Train: [13/20][236/510] Data 2.529 (3.709) Batch 23.323 (27.528) Remain 29:23:35 loss: 0.3266 loss_seg: 0.2212 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:49:16,269 INFO misc.py line 117 726] Train: [13/20][237/510] Data 3.162 (3.706) Batch 28.736 (27.533) Remain 29:23:28 loss: 0.2392 loss_seg: 0.1447 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:49:46,203 INFO misc.py line 117 726] Train: [13/20][238/510] Data 3.515 (3.705) Batch 29.934 (27.543) Remain 29:23:39 loss: 0.2816 loss_seg: 0.1785 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:50:18,354 INFO misc.py line 117 726] Train: [13/20][239/510] Data 4.682 (3.710) Batch 32.150 (27.562) Remain 29:24:27 loss: 0.2861 loss_seg: 0.1797 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:50:37,619 INFO misc.py line 117 726] Train: [13/20][240/510] Data 1.789 (3.701) Batch 19.266 (27.527) Remain 29:21:45 loss: 0.1933 loss_seg: 0.1019 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:51:13,179 INFO misc.py line 117 726] Train: [13/20][241/510] Data 4.139 (3.703) Batch 35.560 (27.561) Remain 29:23:27 loss: 0.2440 loss_seg: 0.1495 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:51:37,600 INFO misc.py line 117 726] Train: [13/20][242/510] Data 2.291 (3.697) Batch 24.421 (27.548) Remain 29:22:09 loss: 0.2863 loss_seg: 0.1842 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:52:03,439 INFO misc.py line 117 726] Train: [13/20][243/510] Data 2.829 (3.694) Batch 25.839 (27.541) Remain 29:21:14 loss: 0.3278 loss_seg: 0.2137 loss_superpoint_edge: 0.0447 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:52:34,179 INFO misc.py line 117 726] Train: [13/20][244/510] Data 3.653 (3.694) Batch 30.740 (27.554) Remain 29:21:37 loss: 0.2038 loss_seg: 0.1127 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:52:53,792 INFO misc.py line 117 726] Train: [13/20][245/510] Data 2.138 (3.687) Batch 19.613 (27.521) Remain 29:19:04 loss: 0.1996 loss_seg: 0.1144 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:53:15,064 INFO misc.py line 117 726] Train: [13/20][246/510] Data 2.028 (3.680) Batch 21.272 (27.496) Remain 29:16:58 loss: 0.3027 loss_seg: 0.2064 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:53:48,149 INFO misc.py line 117 726] Train: [13/20][247/510] Data 3.457 (3.679) Batch 33.085 (27.519) Remain 29:17:58 loss: 0.1873 loss_seg: 0.1026 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:54:17,832 INFO misc.py line 117 726] Train: [13/20][248/510] Data 7.582 (3.695) Batch 29.682 (27.527) Remain 29:18:04 loss: 0.2185 loss_seg: 0.1267 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:54:45,650 INFO misc.py line 117 726] Train: [13/20][249/510] Data 2.835 (3.692) Batch 27.819 (27.529) Remain 29:17:41 loss: 0.2955 loss_seg: 0.1940 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:55:18,424 INFO misc.py line 117 726] Train: [13/20][250/510] Data 3.693 (3.692) Batch 32.773 (27.550) Remain 29:18:35 loss: 0.1974 loss_seg: 0.1152 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:55:18,424 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 18:55:54,152 INFO misc.py line 117 726] Train: [13/20][251/510] Data 11.884 (3.725) Batch 35.728 (27.583) Remain 29:20:14 loss: 0.2306 loss_seg: 0.1318 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:56:23,348 INFO misc.py line 117 726] Train: [13/20][252/510] Data 4.065 (3.726) Batch 29.196 (27.589) Remain 29:20:11 loss: 0.2412 loss_seg: 0.1428 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:56:52,321 INFO misc.py line 117 726] Train: [13/20][253/510] Data 3.739 (3.726) Batch 28.973 (27.595) Remain 29:20:05 loss: 0.1898 loss_seg: 0.1042 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:57:22,203 INFO misc.py line 117 726] Train: [13/20][254/510] Data 3.603 (3.726) Batch 29.882 (27.604) Remain 29:20:12 loss: 0.2297 loss_seg: 0.1391 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:57:52,263 INFO misc.py line 117 726] Train: [13/20][255/510] Data 3.280 (3.724) Batch 30.060 (27.614) Remain 29:20:22 loss: 0.2098 loss_seg: 0.1214 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:58:26,742 INFO misc.py line 117 726] Train: [13/20][256/510] Data 6.305 (3.734) Batch 34.479 (27.641) Remain 29:21:38 loss: 0.2673 loss_seg: 0.1769 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:59:02,366 INFO misc.py line 117 726] Train: [13/20][257/510] Data 4.100 (3.736) Batch 35.624 (27.672) Remain 29:23:10 loss: 0.2779 loss_seg: 0.1783 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:59:30,740 INFO misc.py line 117 726] Train: [13/20][258/510] Data 3.590 (3.735) Batch 28.373 (27.675) Remain 29:22:53 loss: 0.2311 loss_seg: 0.1376 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 18:59:59,974 INFO misc.py line 117 726] Train: [13/20][259/510] Data 4.467 (3.738) Batch 29.234 (27.681) Remain 29:22:49 loss: 0.3104 loss_seg: 0.2181 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:00:23,674 INFO misc.py line 117 726] Train: [13/20][260/510] Data 2.481 (3.733) Batch 23.700 (27.666) Remain 29:21:22 loss: 0.3581 loss_seg: 0.2466 loss_superpoint_edge: 0.0447 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:00:46,856 INFO misc.py line 117 726] Train: [13/20][261/510] Data 1.912 (3.726) Batch 23.181 (27.648) Remain 29:19:48 loss: 0.2038 loss_seg: 0.1128 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:01:14,896 INFO misc.py line 117 726] Train: [13/20][262/510] Data 4.137 (3.728) Batch 28.040 (27.650) Remain 29:19:26 loss: 0.2229 loss_seg: 0.1289 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:01:45,805 INFO misc.py line 117 726] Train: [13/20][263/510] Data 3.291 (3.726) Batch 30.910 (27.662) Remain 29:19:46 loss: 0.2090 loss_seg: 0.1195 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:02:07,680 INFO misc.py line 117 726] Train: [13/20][264/510] Data 2.039 (3.719) Batch 21.875 (27.640) Remain 29:17:54 loss: 0.2962 loss_seg: 0.2015 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:02:31,252 INFO misc.py line 117 726] Train: [13/20][265/510] Data 2.495 (3.715) Batch 23.572 (27.625) Remain 29:16:27 loss: 0.4153 loss_seg: 0.3068 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:02:51,193 INFO misc.py line 117 726] Train: [13/20][266/510] Data 2.347 (3.710) Batch 19.941 (27.595) Remain 29:14:08 loss: 0.4182 loss_seg: 0.3160 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:03:15,648 INFO misc.py line 117 726] Train: [13/20][267/510] Data 3.010 (3.707) Batch 24.455 (27.583) Remain 29:12:55 loss: 0.2013 loss_seg: 0.1134 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:03:50,109 INFO misc.py line 117 726] Train: [13/20][268/510] Data 4.850 (3.711) Batch 34.461 (27.609) Remain 29:14:07 loss: 0.2298 loss_seg: 0.1391 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:04:15,929 INFO misc.py line 117 726] Train: [13/20][269/510] Data 3.277 (3.710) Batch 25.820 (27.603) Remain 29:13:13 loss: 0.2721 loss_seg: 0.1721 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:04:33,196 INFO misc.py line 117 726] Train: [13/20][270/510] Data 2.020 (3.703) Batch 17.267 (27.564) Remain 29:10:18 loss: 0.1740 loss_seg: 0.0880 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:04:57,020 INFO misc.py line 117 726] Train: [13/20][271/510] Data 4.011 (3.704) Batch 23.824 (27.550) Remain 29:08:57 loss: 0.1775 loss_seg: 0.0913 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:05:31,204 INFO misc.py line 117 726] Train: [13/20][272/510] Data 3.993 (3.706) Batch 34.184 (27.575) Remain 29:10:04 loss: 0.2089 loss_seg: 0.1175 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:06:06,488 INFO misc.py line 117 726] Train: [13/20][273/510] Data 5.207 (3.711) Batch 35.283 (27.603) Remain 29:11:25 loss: 0.2942 loss_seg: 0.1972 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:06:37,394 INFO misc.py line 117 726] Train: [13/20][274/510] Data 4.662 (3.715) Batch 30.906 (27.615) Remain 29:11:44 loss: 0.2698 loss_seg: 0.1743 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:07:00,473 INFO misc.py line 117 726] Train: [13/20][275/510] Data 2.843 (3.711) Batch 23.079 (27.599) Remain 29:10:13 loss: 0.2486 loss_seg: 0.1523 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:07:26,627 INFO misc.py line 117 726] Train: [13/20][276/510] Data 2.286 (3.706) Batch 26.154 (27.593) Remain 29:09:25 loss: 0.2764 loss_seg: 0.1726 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:07:45,739 INFO misc.py line 117 726] Train: [13/20][277/510] Data 1.965 (3.700) Batch 19.112 (27.562) Remain 29:07:00 loss: 0.2156 loss_seg: 0.1253 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:08:17,272 INFO misc.py line 117 726] Train: [13/20][278/510] Data 4.836 (3.704) Batch 31.533 (27.577) Remain 29:07:27 loss: 0.3722 loss_seg: 0.2627 loss_superpoint_edge: 0.0438 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:08:59,295 INFO misc.py line 117 726] Train: [13/20][279/510] Data 10.349 (3.728) Batch 42.023 (27.629) Remain 29:10:18 loss: 0.3500 loss_seg: 0.2404 loss_superpoint_edge: 0.0428 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:09:30,741 INFO misc.py line 117 726] Train: [13/20][280/510] Data 4.158 (3.730) Batch 31.446 (27.643) Remain 29:10:43 loss: 0.2543 loss_seg: 0.1558 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:09:53,690 INFO misc.py line 117 726] Train: [13/20][281/510] Data 4.825 (3.734) Batch 22.949 (27.626) Remain 29:09:11 loss: 0.2129 loss_seg: 0.1201 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:10:19,680 INFO misc.py line 117 726] Train: [13/20][282/510] Data 3.161 (3.731) Batch 25.990 (27.620) Remain 29:08:21 loss: 0.2227 loss_seg: 0.1307 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:10:48,391 INFO misc.py line 117 726] Train: [13/20][283/510] Data 2.876 (3.728) Batch 28.711 (27.624) Remain 29:08:09 loss: 0.2102 loss_seg: 0.1208 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:11:16,509 INFO misc.py line 117 726] Train: [13/20][284/510] Data 3.042 (3.726) Batch 28.118 (27.626) Remain 29:07:48 loss: 0.2194 loss_seg: 0.1279 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:11:49,356 INFO misc.py line 117 726] Train: [13/20][285/510] Data 3.453 (3.725) Batch 32.847 (27.644) Remain 29:08:30 loss: 0.2522 loss_seg: 0.1560 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:12:12,893 INFO misc.py line 117 726] Train: [13/20][286/510] Data 2.882 (3.722) Batch 23.537 (27.630) Remain 29:07:07 loss: 0.2639 loss_seg: 0.1645 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:12:43,676 INFO misc.py line 117 726] Train: [13/20][287/510] Data 5.683 (3.729) Batch 30.782 (27.641) Remain 29:07:22 loss: 0.2208 loss_seg: 0.1323 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:13:18,229 INFO misc.py line 117 726] Train: [13/20][288/510] Data 3.978 (3.730) Batch 34.554 (27.665) Remain 29:08:26 loss: 0.2139 loss_seg: 0.1229 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:13:42,766 INFO misc.py line 117 726] Train: [13/20][289/510] Data 2.971 (3.727) Batch 24.536 (27.654) Remain 29:07:17 loss: 0.2194 loss_seg: 0.1337 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:13:59,460 INFO misc.py line 117 726] Train: [13/20][290/510] Data 1.670 (3.720) Batch 16.694 (27.616) Remain 29:04:25 loss: 0.3671 loss_seg: 0.2686 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:14:21,105 INFO misc.py line 117 726] Train: [13/20][291/510] Data 3.916 (3.721) Batch 21.645 (27.595) Remain 29:02:39 loss: 0.2487 loss_seg: 0.1546 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:14:53,699 INFO misc.py line 117 726] Train: [13/20][292/510] Data 2.883 (3.718) Batch 32.594 (27.613) Remain 29:03:17 loss: 0.2474 loss_seg: 0.1544 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:15:23,395 INFO misc.py line 117 726] Train: [13/20][293/510] Data 3.436 (3.717) Batch 29.696 (27.620) Remain 29:03:16 loss: 0.2141 loss_seg: 0.1201 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:16:00,571 INFO misc.py line 117 726] Train: [13/20][294/510] Data 6.202 (3.725) Batch 37.176 (27.653) Remain 29:04:53 loss: 0.2242 loss_seg: 0.1282 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:16:38,204 INFO misc.py line 117 726] Train: [13/20][295/510] Data 4.393 (3.728) Batch 37.633 (27.687) Remain 29:06:35 loss: 0.3042 loss_seg: 0.2052 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:17:20,454 INFO misc.py line 117 726] Train: [13/20][296/510] Data 7.044 (3.739) Batch 42.249 (27.737) Remain 29:09:15 loss: 0.1710 loss_seg: 0.0832 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:17:47,248 INFO misc.py line 117 726] Train: [13/20][297/510] Data 4.755 (3.742) Batch 26.794 (27.733) Remain 29:08:35 loss: 0.2517 loss_seg: 0.1582 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:18:19,304 INFO misc.py line 117 726] Train: [13/20][298/510] Data 4.215 (3.744) Batch 32.057 (27.748) Remain 29:09:03 loss: 0.2687 loss_seg: 0.1708 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:18:32,826 INFO misc.py line 117 726] Train: [13/20][299/510] Data 1.323 (3.736) Batch 13.522 (27.700) Remain 29:05:33 loss: 0.2026 loss_seg: 0.1173 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:18:47,713 INFO misc.py line 117 726] Train: [13/20][300/510] Data 1.680 (3.729) Batch 14.887 (27.657) Remain 29:02:22 loss: 0.2947 loss_seg: 0.1797 loss_superpoint_edge: 0.0451 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:18:47,713 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 19:19:09,098 INFO misc.py line 117 726] Train: [13/20][301/510] Data 2.736 (3.726) Batch 21.385 (27.636) Remain 29:00:35 loss: 0.2853 loss_seg: 0.1887 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:19:39,328 INFO misc.py line 117 726] Train: [13/20][302/510] Data 3.500 (3.725) Batch 30.230 (27.645) Remain 29:00:40 loss: 0.2087 loss_seg: 0.1224 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:20:03,775 INFO misc.py line 117 726] Train: [13/20][303/510] Data 2.523 (3.721) Batch 24.447 (27.634) Remain 28:59:33 loss: 0.3835 loss_seg: 0.2782 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:20:33,944 INFO misc.py line 117 726] Train: [13/20][304/510] Data 2.704 (3.717) Batch 30.169 (27.642) Remain 28:59:37 loss: 0.1777 loss_seg: 0.0922 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:21:05,554 INFO misc.py line 117 726] Train: [13/20][305/510] Data 3.542 (3.717) Batch 31.610 (27.655) Remain 28:59:59 loss: 0.2312 loss_seg: 0.1367 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:21:34,148 INFO misc.py line 117 726] Train: [13/20][306/510] Data 3.391 (3.716) Batch 28.593 (27.659) Remain 28:59:43 loss: 0.2270 loss_seg: 0.1394 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:21:59,804 INFO misc.py line 117 726] Train: [13/20][307/510] Data 5.280 (3.721) Batch 25.656 (27.652) Remain 28:58:50 loss: 0.3385 loss_seg: 0.2320 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:22:32,727 INFO misc.py line 117 726] Train: [13/20][308/510] Data 5.647 (3.727) Batch 32.923 (27.669) Remain 28:59:28 loss: 0.2950 loss_seg: 0.1959 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:22:54,018 INFO misc.py line 117 726] Train: [13/20][309/510] Data 1.698 (3.721) Batch 21.291 (27.648) Remain 28:57:41 loss: 0.2421 loss_seg: 0.1447 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:23:18,861 INFO misc.py line 117 726] Train: [13/20][310/510] Data 2.688 (3.717) Batch 24.842 (27.639) Remain 28:56:39 loss: 0.2476 loss_seg: 0.1474 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:23:36,522 INFO misc.py line 117 726] Train: [13/20][311/510] Data 1.980 (3.712) Batch 17.662 (27.607) Remain 28:54:10 loss: 0.2300 loss_seg: 0.1343 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:24:03,183 INFO misc.py line 117 726] Train: [13/20][312/510] Data 3.956 (3.712) Batch 26.660 (27.604) Remain 28:53:30 loss: 0.2254 loss_seg: 0.1345 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:24:32,474 INFO misc.py line 117 726] Train: [13/20][313/510] Data 3.783 (3.713) Batch 29.291 (27.609) Remain 28:53:23 loss: 0.2267 loss_seg: 0.1362 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:24:59,129 INFO misc.py line 117 726] Train: [13/20][314/510] Data 3.004 (3.710) Batch 26.654 (27.606) Remain 28:52:44 loss: 0.1886 loss_seg: 0.1047 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:25:26,592 INFO misc.py line 117 726] Train: [13/20][315/510] Data 2.883 (3.708) Batch 27.464 (27.606) Remain 28:52:15 loss: 0.2505 loss_seg: 0.1523 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:25:53,647 INFO misc.py line 117 726] Train: [13/20][316/510] Data 2.650 (3.704) Batch 27.055 (27.604) Remain 28:51:41 loss: 0.2114 loss_seg: 0.1209 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:26:23,420 INFO misc.py line 117 726] Train: [13/20][317/510] Data 2.849 (3.702) Batch 29.773 (27.611) Remain 28:51:39 loss: 0.1960 loss_seg: 0.1091 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:26:56,507 INFO misc.py line 117 726] Train: [13/20][318/510] Data 5.186 (3.706) Batch 33.086 (27.628) Remain 28:52:17 loss: 0.2580 loss_seg: 0.1667 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:27:26,237 INFO misc.py line 117 726] Train: [13/20][319/510] Data 3.125 (3.704) Batch 29.730 (27.635) Remain 28:52:14 loss: 0.2422 loss_seg: 0.1438 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:28:05,604 INFO misc.py line 117 726] Train: [13/20][320/510] Data 5.454 (3.710) Batch 39.367 (27.672) Remain 28:54:06 loss: 0.2148 loss_seg: 0.1252 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:28:37,176 INFO misc.py line 117 726] Train: [13/20][321/510] Data 4.227 (3.712) Batch 31.572 (27.684) Remain 28:54:24 loss: 0.2460 loss_seg: 0.1464 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:28:54,986 INFO misc.py line 117 726] Train: [13/20][322/510] Data 1.580 (3.705) Batch 17.810 (27.653) Remain 28:52:00 loss: 0.2414 loss_seg: 0.1414 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0448 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:29:27,380 INFO misc.py line 117 726] Train: [13/20][323/510] Data 6.735 (3.714) Batch 32.394 (27.668) Remain 28:52:28 loss: 0.2679 loss_seg: 0.1715 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:29:55,758 INFO misc.py line 117 726] Train: [13/20][324/510] Data 4.040 (3.715) Batch 28.378 (27.670) Remain 28:52:09 loss: 0.2197 loss_seg: 0.1253 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:30:14,524 INFO misc.py line 117 726] Train: [13/20][325/510] Data 2.270 (3.711) Batch 18.766 (27.643) Remain 28:49:57 loss: 0.2908 loss_seg: 0.1842 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:30:36,138 INFO misc.py line 117 726] Train: [13/20][326/510] Data 2.630 (3.708) Batch 21.613 (27.624) Remain 28:48:20 loss: 0.2029 loss_seg: 0.1116 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:31:08,573 INFO misc.py line 117 726] Train: [13/20][327/510] Data 7.522 (3.719) Batch 32.435 (27.639) Remain 28:48:48 loss: 0.3183 loss_seg: 0.2147 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:31:34,807 INFO misc.py line 117 726] Train: [13/20][328/510] Data 2.757 (3.716) Batch 26.235 (27.634) Remain 28:48:04 loss: 0.2128 loss_seg: 0.1243 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:32:04,226 INFO misc.py line 117 726] Train: [13/20][329/510] Data 3.178 (3.715) Batch 29.419 (27.640) Remain 28:47:57 loss: 0.2555 loss_seg: 0.1579 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:32:32,239 INFO misc.py line 117 726] Train: [13/20][330/510] Data 2.954 (3.712) Batch 28.012 (27.641) Remain 28:47:33 loss: 0.2505 loss_seg: 0.1611 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:32:57,855 INFO misc.py line 117 726] Train: [13/20][331/510] Data 2.499 (3.709) Batch 25.617 (27.635) Remain 28:46:43 loss: 0.2403 loss_seg: 0.1453 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:33:24,669 INFO misc.py line 117 726] Train: [13/20][332/510] Data 3.553 (3.708) Batch 26.814 (27.632) Remain 28:46:06 loss: 0.2355 loss_seg: 0.1437 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:33:52,094 INFO misc.py line 117 726] Train: [13/20][333/510] Data 2.932 (3.706) Batch 27.425 (27.632) Remain 28:45:36 loss: 0.2791 loss_seg: 0.1788 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:34:17,681 INFO misc.py line 117 726] Train: [13/20][334/510] Data 2.230 (3.701) Batch 25.587 (27.626) Remain 28:44:45 loss: 0.1983 loss_seg: 0.1116 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:34:42,493 INFO misc.py line 117 726] Train: [13/20][335/510] Data 3.216 (3.700) Batch 24.812 (27.617) Remain 28:43:45 loss: 0.3738 loss_seg: 0.2698 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:35:09,164 INFO misc.py line 117 726] Train: [13/20][336/510] Data 3.561 (3.700) Batch 26.671 (27.614) Remain 28:43:07 loss: 0.1687 loss_seg: 0.0846 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:35:31,908 INFO misc.py line 117 726] Train: [13/20][337/510] Data 2.341 (3.695) Batch 22.744 (27.600) Remain 28:41:45 loss: 0.3355 loss_seg: 0.2369 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:36:01,659 INFO misc.py line 117 726] Train: [13/20][338/510] Data 5.690 (3.701) Batch 29.751 (27.606) Remain 28:41:41 loss: 0.5321 loss_seg: 0.4331 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:36:41,690 INFO misc.py line 117 726] Train: [13/20][339/510] Data 12.068 (3.726) Batch 40.030 (27.643) Remain 28:43:32 loss: 0.3038 loss_seg: 0.2040 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:37:07,252 INFO misc.py line 117 726] Train: [13/20][340/510] Data 2.657 (3.723) Batch 25.562 (27.637) Remain 28:42:41 loss: 0.2387 loss_seg: 0.1403 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:37:33,872 INFO misc.py line 117 726] Train: [13/20][341/510] Data 2.356 (3.719) Batch 26.621 (27.634) Remain 28:42:03 loss: 0.2928 loss_seg: 0.1877 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:38:02,425 INFO misc.py line 117 726] Train: [13/20][342/510] Data 3.206 (3.718) Batch 28.552 (27.637) Remain 28:41:45 loss: 0.3044 loss_seg: 0.1911 loss_superpoint_edge: 0.0457 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:38:27,351 INFO misc.py line 117 726] Train: [13/20][343/510] Data 3.745 (3.718) Batch 24.927 (27.629) Remain 28:40:48 loss: 0.2888 loss_seg: 0.1877 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:38:53,962 INFO misc.py line 117 726] Train: [13/20][344/510] Data 2.779 (3.715) Batch 26.610 (27.626) Remain 28:40:09 loss: 0.1742 loss_seg: 0.0905 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:39:21,211 INFO misc.py line 117 726] Train: [13/20][345/510] Data 3.821 (3.715) Batch 27.250 (27.625) Remain 28:39:37 loss: 0.2503 loss_seg: 0.1524 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:39:51,034 INFO misc.py line 117 726] Train: [13/20][346/510] Data 2.624 (3.712) Batch 29.822 (27.631) Remain 28:39:33 loss: 0.2387 loss_seg: 0.1391 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:40:19,411 INFO misc.py line 117 726] Train: [13/20][347/510] Data 4.386 (3.714) Batch 28.377 (27.633) Remain 28:39:14 loss: 0.2407 loss_seg: 0.1502 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:40:42,811 INFO misc.py line 117 726] Train: [13/20][348/510] Data 3.837 (3.714) Batch 23.400 (27.621) Remain 28:38:00 loss: 0.2356 loss_seg: 0.1392 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:41:13,822 INFO misc.py line 117 726] Train: [13/20][349/510] Data 3.348 (3.713) Batch 31.011 (27.631) Remain 28:38:09 loss: 0.2374 loss_seg: 0.1419 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:41:44,744 INFO misc.py line 117 726] Train: [13/20][350/510] Data 4.669 (3.716) Batch 30.922 (27.640) Remain 28:38:17 loss: 0.3425 loss_seg: 0.2336 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:41:44,744 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 19:42:10,435 INFO misc.py line 117 726] Train: [13/20][351/510] Data 3.602 (3.716) Batch 25.691 (27.635) Remain 28:37:29 loss: 0.2171 loss_seg: 0.1276 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:42:43,066 INFO misc.py line 117 726] Train: [13/20][352/510] Data 2.816 (3.713) Batch 32.631 (27.649) Remain 28:37:54 loss: 0.2096 loss_seg: 0.1182 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:43:15,900 INFO misc.py line 117 726] Train: [13/20][353/510] Data 3.808 (3.713) Batch 32.834 (27.664) Remain 28:38:22 loss: 0.2442 loss_seg: 0.1445 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:43:38,629 INFO misc.py line 117 726] Train: [13/20][354/510] Data 3.059 (3.712) Batch 22.730 (27.650) Remain 28:37:02 loss: 0.2553 loss_seg: 0.1561 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:44:03,541 INFO misc.py line 117 726] Train: [13/20][355/510] Data 2.653 (3.709) Batch 24.912 (27.642) Remain 28:36:05 loss: 0.2566 loss_seg: 0.1581 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:44:34,338 INFO misc.py line 117 726] Train: [13/20][356/510] Data 3.833 (3.709) Batch 30.798 (27.651) Remain 28:36:11 loss: 0.2508 loss_seg: 0.1540 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:45:07,761 INFO misc.py line 117 726] Train: [13/20][357/510] Data 4.761 (3.712) Batch 33.423 (27.667) Remain 28:36:44 loss: 0.3327 loss_seg: 0.2308 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:45:33,363 INFO misc.py line 117 726] Train: [13/20][358/510] Data 3.180 (3.710) Batch 25.601 (27.661) Remain 28:35:55 loss: 0.2398 loss_seg: 0.1474 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:46:01,871 INFO misc.py line 117 726] Train: [13/20][359/510] Data 3.583 (3.710) Batch 28.508 (27.664) Remain 28:35:36 loss: 0.1716 loss_seg: 0.0844 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:46:23,889 INFO misc.py line 117 726] Train: [13/20][360/510] Data 2.289 (3.706) Batch 22.018 (27.648) Remain 28:34:09 loss: 0.2192 loss_seg: 0.1318 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:46:51,617 INFO misc.py line 117 726] Train: [13/20][361/510] Data 2.484 (3.703) Batch 27.727 (27.648) Remain 28:33:43 loss: 0.2061 loss_seg: 0.1151 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:47:34,903 INFO misc.py line 117 726] Train: [13/20][362/510] Data 9.968 (3.720) Batch 43.286 (27.692) Remain 28:35:57 loss: 0.3410 loss_seg: 0.2290 loss_superpoint_edge: 0.0442 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:48:12,863 INFO misc.py line 117 726] Train: [13/20][363/510] Data 3.627 (3.720) Batch 37.960 (27.720) Remain 28:37:15 loss: 0.1881 loss_seg: 0.1042 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:48:35,561 INFO misc.py line 117 726] Train: [13/20][364/510] Data 3.226 (3.718) Batch 22.699 (27.706) Remain 28:35:56 loss: 0.3708 loss_seg: 0.2656 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:49:04,079 INFO misc.py line 117 726] Train: [13/20][365/510] Data 4.761 (3.721) Batch 28.518 (27.708) Remain 28:35:36 loss: 0.2301 loss_seg: 0.1389 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:49:32,786 INFO misc.py line 117 726] Train: [13/20][366/510] Data 3.143 (3.720) Batch 28.707 (27.711) Remain 28:35:19 loss: 0.2585 loss_seg: 0.1588 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:50:03,602 INFO misc.py line 117 726] Train: [13/20][367/510] Data 3.247 (3.718) Batch 30.816 (27.720) Remain 28:35:23 loss: 0.2733 loss_seg: 0.1702 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:50:34,694 INFO misc.py line 117 726] Train: [13/20][368/510] Data 2.552 (3.715) Batch 31.091 (27.729) Remain 28:35:29 loss: 0.2275 loss_seg: 0.1298 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:51:00,426 INFO misc.py line 117 726] Train: [13/20][369/510] Data 2.728 (3.713) Batch 25.732 (27.724) Remain 28:34:41 loss: 0.2575 loss_seg: 0.1616 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:51:27,136 INFO misc.py line 117 726] Train: [13/20][370/510] Data 2.382 (3.709) Batch 26.711 (27.721) Remain 28:34:03 loss: 0.1737 loss_seg: 0.0900 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:51:55,564 INFO misc.py line 117 726] Train: [13/20][371/510] Data 2.987 (3.707) Batch 28.429 (27.723) Remain 28:33:43 loss: 0.2402 loss_seg: 0.1474 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:52:24,729 INFO misc.py line 117 726] Train: [13/20][372/510] Data 3.140 (3.705) Batch 29.164 (27.727) Remain 28:33:30 loss: 0.2225 loss_seg: 0.1341 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:52:50,425 INFO misc.py line 117 726] Train: [13/20][373/510] Data 9.644 (3.721) Batch 25.695 (27.721) Remain 28:32:42 loss: 0.1901 loss_seg: 0.0965 loss_superpoint_edge: 0.0146 loss_superpoint_contrast: 0.0481 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:53:22,355 INFO misc.py line 117 726] Train: [13/20][374/510] Data 4.195 (3.723) Batch 31.931 (27.732) Remain 28:32:56 loss: 0.2471 loss_seg: 0.1526 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:53:44,853 INFO misc.py line 117 726] Train: [13/20][375/510] Data 2.964 (3.721) Batch 22.498 (27.718) Remain 28:31:36 loss: 0.1925 loss_seg: 0.1041 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:54:20,603 INFO misc.py line 117 726] Train: [13/20][376/510] Data 6.211 (3.727) Batch 35.750 (27.740) Remain 28:32:28 loss: 0.3287 loss_seg: 0.2224 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:54:52,067 INFO misc.py line 117 726] Train: [13/20][377/510] Data 4.231 (3.729) Batch 31.464 (27.750) Remain 28:32:37 loss: 0.2653 loss_seg: 0.1616 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:55:24,089 INFO misc.py line 117 726] Train: [13/20][378/510] Data 3.389 (3.728) Batch 32.022 (27.761) Remain 28:32:52 loss: 0.2885 loss_seg: 0.1907 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:55:37,590 INFO misc.py line 117 726] Train: [13/20][379/510] Data 1.698 (3.722) Batch 13.501 (27.723) Remain 28:30:04 loss: 0.1965 loss_seg: 0.1022 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0442 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:56:09,197 INFO misc.py line 117 726] Train: [13/20][380/510] Data 5.842 (3.728) Batch 31.607 (27.734) Remain 28:30:14 loss: 0.2232 loss_seg: 0.1323 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:56:40,704 INFO misc.py line 117 726] Train: [13/20][381/510] Data 3.700 (3.728) Batch 31.507 (27.744) Remain 28:30:23 loss: 0.2423 loss_seg: 0.1515 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:57:15,110 INFO misc.py line 117 726] Train: [13/20][382/510] Data 4.860 (3.731) Batch 34.405 (27.761) Remain 28:31:00 loss: 0.2549 loss_seg: 0.1621 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:57:47,030 INFO misc.py line 117 726] Train: [13/20][383/510] Data 3.506 (3.730) Batch 31.920 (27.772) Remain 28:31:13 loss: 0.2427 loss_seg: 0.1446 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:58:14,793 INFO misc.py line 117 726] Train: [13/20][384/510] Data 4.680 (3.733) Batch 27.763 (27.772) Remain 28:30:45 loss: 0.1890 loss_seg: 0.1027 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:58:29,874 INFO misc.py line 117 726] Train: [13/20][385/510] Data 2.129 (3.729) Batch 15.081 (27.739) Remain 28:28:15 loss: 0.2766 loss_seg: 0.1736 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:58:55,343 INFO misc.py line 117 726] Train: [13/20][386/510] Data 3.121 (3.727) Batch 25.468 (27.733) Remain 28:27:25 loss: 0.2308 loss_seg: 0.1323 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:59:27,034 INFO misc.py line 117 726] Train: [13/20][387/510] Data 3.859 (3.727) Batch 31.691 (27.743) Remain 28:27:35 loss: 0.2316 loss_seg: 0.1376 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 19:59:56,523 INFO misc.py line 117 726] Train: [13/20][388/510] Data 3.155 (3.726) Batch 29.490 (27.748) Remain 28:27:24 loss: 0.2416 loss_seg: 0.1473 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:00:23,760 INFO misc.py line 117 726] Train: [13/20][389/510] Data 2.580 (3.723) Batch 27.237 (27.746) Remain 28:26:52 loss: 0.2485 loss_seg: 0.1514 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:00:55,743 INFO misc.py line 117 726] Train: [13/20][390/510] Data 3.199 (3.722) Batch 31.983 (27.757) Remain 28:27:04 loss: 0.2190 loss_seg: 0.1284 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:01:17,828 INFO misc.py line 117 726] Train: [13/20][391/510] Data 2.261 (3.718) Batch 22.084 (27.743) Remain 28:25:43 loss: 0.2397 loss_seg: 0.1448 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:01:45,399 INFO misc.py line 117 726] Train: [13/20][392/510] Data 3.322 (3.717) Batch 27.571 (27.742) Remain 28:25:13 loss: 0.2348 loss_seg: 0.1373 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:02:13,716 INFO misc.py line 117 726] Train: [13/20][393/510] Data 3.447 (3.716) Batch 28.317 (27.744) Remain 28:24:51 loss: 0.2429 loss_seg: 0.1488 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:02:42,355 INFO misc.py line 117 726] Train: [13/20][394/510] Data 4.383 (3.718) Batch 28.639 (27.746) Remain 28:24:32 loss: 0.2319 loss_seg: 0.1413 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:03:11,679 INFO misc.py line 117 726] Train: [13/20][395/510] Data 5.900 (3.723) Batch 29.324 (27.750) Remain 28:24:19 loss: 0.2297 loss_seg: 0.1399 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:03:40,417 INFO misc.py line 117 726] Train: [13/20][396/510] Data 2.762 (3.721) Batch 28.738 (27.753) Remain 28:24:00 loss: 0.1989 loss_seg: 0.1112 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:04:03,066 INFO misc.py line 117 726] Train: [13/20][397/510] Data 2.193 (3.717) Batch 22.649 (27.740) Remain 28:22:45 loss: 0.2041 loss_seg: 0.1134 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:04:42,190 INFO misc.py line 117 726] Train: [13/20][398/510] Data 10.982 (3.735) Batch 39.124 (27.769) Remain 28:24:03 loss: 0.2482 loss_seg: 0.1516 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:05:07,720 INFO misc.py line 117 726] Train: [13/20][399/510] Data 3.104 (3.734) Batch 25.530 (27.763) Remain 28:23:15 loss: 0.1617 loss_seg: 0.0801 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:05:43,088 INFO misc.py line 117 726] Train: [13/20][400/510] Data 9.883 (3.749) Batch 35.368 (27.782) Remain 28:23:57 loss: 0.1994 loss_seg: 0.1069 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0430 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:05:43,089 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 20:06:13,684 INFO misc.py line 117 726] Train: [13/20][401/510] Data 5.222 (3.753) Batch 30.595 (27.789) Remain 28:23:56 loss: 0.2195 loss_seg: 0.1286 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:06:50,595 INFO misc.py line 117 726] Train: [13/20][402/510] Data 5.195 (3.757) Batch 36.912 (27.812) Remain 28:24:52 loss: 0.2873 loss_seg: 0.1958 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:07:14,786 INFO misc.py line 117 726] Train: [13/20][403/510] Data 2.204 (3.753) Batch 24.190 (27.803) Remain 28:23:51 loss: 0.2043 loss_seg: 0.1131 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:07:48,825 INFO misc.py line 117 726] Train: [13/20][404/510] Data 4.586 (3.755) Batch 34.039 (27.818) Remain 28:24:20 loss: 0.2177 loss_seg: 0.1277 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:08:27,682 INFO misc.py line 117 726] Train: [13/20][405/510] Data 5.812 (3.760) Batch 38.857 (27.846) Remain 28:25:33 loss: 0.3494 loss_seg: 0.2451 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:08:58,226 INFO misc.py line 117 726] Train: [13/20][406/510] Data 3.494 (3.759) Batch 30.544 (27.853) Remain 28:25:30 loss: 0.2348 loss_seg: 0.1431 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:09:30,936 INFO misc.py line 117 726] Train: [13/20][407/510] Data 4.834 (3.762) Batch 32.710 (27.865) Remain 28:25:46 loss: 0.2335 loss_seg: 0.1395 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:09:55,905 INFO misc.py line 117 726] Train: [13/20][408/510] Data 3.015 (3.760) Batch 24.969 (27.857) Remain 28:24:52 loss: 0.2048 loss_seg: 0.1153 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:10:24,859 INFO misc.py line 117 726] Train: [13/20][409/510] Data 4.956 (3.763) Batch 28.954 (27.860) Remain 28:24:34 loss: 0.2231 loss_seg: 0.1316 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:10:46,555 INFO misc.py line 117 726] Train: [13/20][410/510] Data 1.792 (3.758) Batch 21.696 (27.845) Remain 28:23:11 loss: 0.2104 loss_seg: 0.1206 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:11:20,882 INFO misc.py line 117 726] Train: [13/20][411/510] Data 3.819 (3.758) Batch 34.326 (27.861) Remain 28:23:41 loss: 0.2247 loss_seg: 0.1311 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:11:50,880 INFO misc.py line 117 726] Train: [13/20][412/510] Data 4.246 (3.760) Batch 29.998 (27.866) Remain 28:23:33 loss: 0.2511 loss_seg: 0.1535 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:12:24,204 INFO misc.py line 117 726] Train: [13/20][413/510] Data 8.791 (3.772) Batch 33.324 (27.879) Remain 28:23:54 loss: 0.1780 loss_seg: 0.0914 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:12:45,967 INFO misc.py line 117 726] Train: [13/20][414/510] Data 2.146 (3.768) Batch 21.763 (27.865) Remain 28:22:31 loss: 0.2116 loss_seg: 0.1192 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:13:14,664 INFO misc.py line 117 726] Train: [13/20][415/510] Data 3.898 (3.768) Batch 28.697 (27.867) Remain 28:22:11 loss: 0.2768 loss_seg: 0.1798 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:13:49,036 INFO misc.py line 117 726] Train: [13/20][416/510] Data 7.840 (3.778) Batch 34.372 (27.882) Remain 28:22:40 loss: 0.3330 loss_seg: 0.2277 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:14:16,836 INFO misc.py line 117 726] Train: [13/20][417/510] Data 2.790 (3.776) Batch 27.800 (27.882) Remain 28:22:12 loss: 0.2266 loss_seg: 0.1346 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:14:47,385 INFO misc.py line 117 726] Train: [13/20][418/510] Data 3.909 (3.776) Batch 30.549 (27.889) Remain 28:22:08 loss: 0.3349 loss_seg: 0.2269 loss_superpoint_edge: 0.0416 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:15:14,548 INFO misc.py line 117 726] Train: [13/20][419/510] Data 2.527 (3.773) Batch 27.163 (27.887) Remain 28:21:33 loss: 0.2860 loss_seg: 0.1853 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:15:40,891 INFO misc.py line 117 726] Train: [13/20][420/510] Data 3.315 (3.772) Batch 26.343 (27.883) Remain 28:20:52 loss: 0.2199 loss_seg: 0.1300 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:16:01,421 INFO misc.py line 117 726] Train: [13/20][421/510] Data 2.713 (3.769) Batch 20.530 (27.866) Remain 28:19:20 loss: 0.2304 loss_seg: 0.1381 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:16:26,535 INFO misc.py line 117 726] Train: [13/20][422/510] Data 3.678 (3.769) Batch 25.114 (27.859) Remain 28:18:28 loss: 0.2034 loss_seg: 0.1152 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:16:56,238 INFO misc.py line 117 726] Train: [13/20][423/510] Data 2.962 (3.767) Batch 29.703 (27.863) Remain 28:18:16 loss: 0.2386 loss_seg: 0.1439 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:17:31,935 INFO misc.py line 117 726] Train: [13/20][424/510] Data 4.701 (3.769) Batch 35.697 (27.882) Remain 28:18:56 loss: 0.2536 loss_seg: 0.1601 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:17:55,763 INFO misc.py line 117 726] Train: [13/20][425/510] Data 2.581 (3.767) Batch 23.829 (27.872) Remain 28:17:53 loss: 0.2555 loss_seg: 0.1556 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:18:27,686 INFO misc.py line 117 726] Train: [13/20][426/510] Data 5.027 (3.770) Batch 31.922 (27.882) Remain 28:18:00 loss: 0.3198 loss_seg: 0.2249 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:19:05,365 INFO misc.py line 117 726] Train: [13/20][427/510] Data 5.973 (3.775) Batch 37.680 (27.905) Remain 28:18:57 loss: 0.2883 loss_seg: 0.1926 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:19:29,673 INFO misc.py line 117 726] Train: [13/20][428/510] Data 2.399 (3.772) Batch 24.308 (27.897) Remain 28:17:58 loss: 0.2413 loss_seg: 0.1458 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:20:01,437 INFO misc.py line 117 726] Train: [13/20][429/510] Data 4.618 (3.774) Batch 31.763 (27.906) Remain 28:18:03 loss: 0.2802 loss_seg: 0.1836 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:20:29,148 INFO misc.py line 117 726] Train: [13/20][430/510] Data 2.975 (3.772) Batch 27.711 (27.905) Remain 28:17:34 loss: 0.1815 loss_seg: 0.0993 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:20:56,050 INFO misc.py line 117 726] Train: [13/20][431/510] Data 3.558 (3.771) Batch 26.902 (27.903) Remain 28:16:57 loss: 0.1876 loss_seg: 0.1034 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:21:26,865 INFO misc.py line 117 726] Train: [13/20][432/510] Data 3.339 (3.770) Batch 30.815 (27.910) Remain 28:16:54 loss: 0.2195 loss_seg: 0.1277 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:21:51,571 INFO misc.py line 117 726] Train: [13/20][433/510] Data 2.865 (3.768) Batch 24.706 (27.902) Remain 28:15:59 loss: 0.2338 loss_seg: 0.1428 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:22:04,350 INFO misc.py line 117 726] Train: [13/20][434/510] Data 2.013 (3.764) Batch 12.779 (27.867) Remain 28:13:23 loss: 0.2676 loss_seg: 0.1621 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:22:41,892 INFO misc.py line 117 726] Train: [13/20][435/510] Data 6.128 (3.769) Batch 37.541 (27.890) Remain 28:14:17 loss: 0.2835 loss_seg: 0.1830 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:23:16,252 INFO misc.py line 117 726] Train: [13/20][436/510] Data 6.075 (3.775) Batch 34.360 (27.904) Remain 28:14:43 loss: 0.2935 loss_seg: 0.1977 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:23:44,343 INFO misc.py line 117 726] Train: [13/20][437/510] Data 4.210 (3.776) Batch 28.091 (27.905) Remain 28:14:17 loss: 0.2395 loss_seg: 0.1448 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:24:13,262 INFO misc.py line 117 726] Train: [13/20][438/510] Data 4.209 (3.777) Batch 28.919 (27.907) Remain 28:13:58 loss: 0.2042 loss_seg: 0.1144 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:24:38,445 INFO misc.py line 117 726] Train: [13/20][439/510] Data 3.909 (3.777) Batch 25.183 (27.901) Remain 28:13:07 loss: 0.2514 loss_seg: 0.1613 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:25:07,282 INFO misc.py line 117 726] Train: [13/20][440/510] Data 4.211 (3.778) Batch 28.837 (27.903) Remain 28:12:47 loss: 0.2383 loss_seg: 0.1520 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:25:42,300 INFO misc.py line 117 726] Train: [13/20][441/510] Data 3.510 (3.777) Batch 35.018 (27.919) Remain 28:13:18 loss: 0.1972 loss_seg: 0.1102 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:26:01,915 INFO misc.py line 117 726] Train: [13/20][442/510] Data 2.383 (3.774) Batch 19.615 (27.900) Remain 28:11:41 loss: 0.2826 loss_seg: 0.1905 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:26:31,602 INFO misc.py line 117 726] Train: [13/20][443/510] Data 6.347 (3.780) Batch 29.687 (27.905) Remain 28:11:28 loss: 0.3912 loss_seg: 0.2885 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:27:02,051 INFO misc.py line 117 726] Train: [13/20][444/510] Data 3.629 (3.780) Batch 30.449 (27.910) Remain 28:11:21 loss: 0.2626 loss_seg: 0.1607 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:27:26,232 INFO misc.py line 117 726] Train: [13/20][445/510] Data 2.605 (3.777) Batch 24.181 (27.902) Remain 28:10:23 loss: 0.2016 loss_seg: 0.1111 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:27:58,153 INFO misc.py line 117 726] Train: [13/20][446/510] Data 3.248 (3.776) Batch 31.921 (27.911) Remain 28:10:28 loss: 0.2144 loss_seg: 0.1229 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:28:31,204 INFO misc.py line 117 726] Train: [13/20][447/510] Data 3.809 (3.776) Batch 33.052 (27.922) Remain 28:10:42 loss: 0.2148 loss_seg: 0.1287 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:28:51,188 INFO misc.py line 117 726] Train: [13/20][448/510] Data 2.240 (3.773) Batch 19.983 (27.905) Remain 28:09:09 loss: 0.2785 loss_seg: 0.1773 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:29:22,480 INFO misc.py line 117 726] Train: [13/20][449/510] Data 5.217 (3.776) Batch 31.293 (27.912) Remain 28:09:09 loss: 0.4645 loss_seg: 0.3744 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:29:49,133 INFO misc.py line 117 726] Train: [13/20][450/510] Data 3.171 (3.774) Batch 26.652 (27.909) Remain 28:08:31 loss: 0.2351 loss_seg: 0.1410 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:29:49,133 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 20:30:11,709 INFO misc.py line 117 726] Train: [13/20][451/510] Data 3.056 (3.773) Batch 22.576 (27.898) Remain 28:07:20 loss: 0.2274 loss_seg: 0.1372 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:30:38,741 INFO misc.py line 117 726] Train: [13/20][452/510] Data 5.163 (3.776) Batch 27.032 (27.896) Remain 28:06:45 loss: 0.2431 loss_seg: 0.1501 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:31:02,269 INFO misc.py line 117 726] Train: [13/20][453/510] Data 2.586 (3.773) Batch 23.528 (27.886) Remain 28:05:42 loss: 0.2296 loss_seg: 0.1443 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:31:31,510 INFO misc.py line 117 726] Train: [13/20][454/510] Data 3.521 (3.773) Batch 29.241 (27.889) Remain 28:05:25 loss: 0.2260 loss_seg: 0.1365 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:32:04,644 INFO misc.py line 117 726] Train: [13/20][455/510] Data 4.575 (3.775) Batch 33.134 (27.900) Remain 28:05:39 loss: 0.1845 loss_seg: 0.1004 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:32:28,725 INFO misc.py line 117 726] Train: [13/20][456/510] Data 2.925 (3.773) Batch 24.081 (27.892) Remain 28:04:40 loss: 0.2443 loss_seg: 0.1453 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:33:04,032 INFO misc.py line 117 726] Train: [13/20][457/510] Data 8.963 (3.784) Batch 35.307 (27.908) Remain 28:05:12 loss: 0.1821 loss_seg: 0.0951 loss_superpoint_edge: 0.0115 loss_superpoint_contrast: 0.0442 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:33:28,173 INFO misc.py line 117 726] Train: [13/20][458/510] Data 3.808 (3.784) Batch 24.141 (27.900) Remain 28:04:14 loss: 0.2207 loss_seg: 0.1277 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:33:46,174 INFO misc.py line 117 726] Train: [13/20][459/510] Data 1.673 (3.780) Batch 18.002 (27.878) Remain 28:02:27 loss: 0.2539 loss_seg: 0.1577 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:34:16,335 INFO misc.py line 117 726] Train: [13/20][460/510] Data 4.581 (3.781) Batch 30.160 (27.883) Remain 28:02:17 loss: 0.2607 loss_seg: 0.1622 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:34:45,243 INFO misc.py line 117 726] Train: [13/20][461/510] Data 4.327 (3.782) Batch 28.909 (27.886) Remain 28:01:58 loss: 0.2361 loss_seg: 0.1451 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:35:10,774 INFO misc.py line 117 726] Train: [13/20][462/510] Data 2.675 (3.780) Batch 25.531 (27.881) Remain 28:01:11 loss: 0.2535 loss_seg: 0.1512 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:35:35,643 INFO misc.py line 117 726] Train: [13/20][463/510] Data 4.338 (3.781) Batch 24.869 (27.874) Remain 28:00:20 loss: 0.2089 loss_seg: 0.1165 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:36:11,263 INFO misc.py line 117 726] Train: [13/20][464/510] Data 3.810 (3.781) Batch 35.620 (27.891) Remain 28:00:53 loss: 0.1797 loss_seg: 0.0993 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:36:34,963 INFO misc.py line 117 726] Train: [13/20][465/510] Data 2.736 (3.779) Batch 23.700 (27.882) Remain 27:59:52 loss: 0.3907 loss_seg: 0.2970 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:37:05,719 INFO misc.py line 117 726] Train: [13/20][466/510] Data 3.180 (3.778) Batch 30.756 (27.888) Remain 27:59:46 loss: 0.1922 loss_seg: 0.1064 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:37:32,212 INFO misc.py line 117 726] Train: [13/20][467/510] Data 3.147 (3.776) Batch 26.493 (27.885) Remain 27:59:08 loss: 0.2163 loss_seg: 0.1252 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:37:59,449 INFO misc.py line 117 726] Train: [13/20][468/510] Data 2.887 (3.774) Batch 27.237 (27.884) Remain 27:58:35 loss: 0.1824 loss_seg: 0.0974 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:38:36,484 INFO misc.py line 117 726] Train: [13/20][469/510] Data 5.438 (3.778) Batch 37.035 (27.903) Remain 27:59:18 loss: 0.2596 loss_seg: 0.1624 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:39:05,386 INFO misc.py line 117 726] Train: [13/20][470/510] Data 3.274 (3.777) Batch 28.902 (27.905) Remain 27:58:58 loss: 0.2574 loss_seg: 0.1582 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:39:37,641 INFO misc.py line 117 726] Train: [13/20][471/510] Data 3.419 (3.776) Batch 32.255 (27.915) Remain 27:59:03 loss: 0.2034 loss_seg: 0.1147 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:40:02,914 INFO misc.py line 117 726] Train: [13/20][472/510] Data 3.018 (3.775) Batch 25.273 (27.909) Remain 27:58:15 loss: 0.1945 loss_seg: 0.1053 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:40:36,509 INFO misc.py line 117 726] Train: [13/20][473/510] Data 3.881 (3.775) Batch 33.595 (27.921) Remain 27:58:31 loss: 0.3913 loss_seg: 0.2653 loss_superpoint_edge: 0.0579 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:41:11,835 INFO misc.py line 117 726] Train: [13/20][474/510] Data 6.525 (3.781) Batch 35.326 (27.937) Remain 27:58:59 loss: 0.4276 loss_seg: 0.3229 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:41:42,766 INFO misc.py line 117 726] Train: [13/20][475/510] Data 3.015 (3.779) Batch 30.931 (27.943) Remain 27:58:54 loss: 0.1999 loss_seg: 0.1090 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:42:15,014 INFO misc.py line 117 726] Train: [13/20][476/510] Data 3.737 (3.779) Batch 32.247 (27.952) Remain 27:58:59 loss: 0.2825 loss_seg: 0.1817 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:42:35,547 INFO misc.py line 117 726] Train: [13/20][477/510] Data 1.808 (3.775) Batch 20.534 (27.937) Remain 27:57:35 loss: 0.3014 loss_seg: 0.2017 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:43:02,956 INFO misc.py line 117 726] Train: [13/20][478/510] Data 3.766 (3.775) Batch 27.409 (27.935) Remain 27:57:03 loss: 0.2481 loss_seg: 0.1507 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:43:40,262 INFO misc.py line 117 726] Train: [13/20][479/510] Data 6.099 (3.780) Batch 37.306 (27.955) Remain 27:57:46 loss: 0.2397 loss_seg: 0.1457 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:44:04,719 INFO misc.py line 117 726] Train: [13/20][480/510] Data 3.035 (3.778) Batch 24.457 (27.948) Remain 27:56:52 loss: 0.2490 loss_seg: 0.1542 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:44:41,884 INFO misc.py line 117 726] Train: [13/20][481/510] Data 10.901 (3.793) Batch 37.165 (27.967) Remain 27:57:33 loss: 0.2180 loss_seg: 0.1223 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:45:07,543 INFO misc.py line 117 726] Train: [13/20][482/510] Data 2.683 (3.791) Batch 25.659 (27.962) Remain 27:56:48 loss: 0.2202 loss_seg: 0.1306 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:45:35,084 INFO misc.py line 117 726] Train: [13/20][483/510] Data 3.027 (3.789) Batch 27.541 (27.961) Remain 27:56:17 loss: 0.2344 loss_seg: 0.1389 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:46:07,337 INFO misc.py line 117 726] Train: [13/20][484/510] Data 4.185 (3.790) Batch 32.253 (27.970) Remain 27:56:21 loss: 0.2833 loss_seg: 0.1786 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:46:39,942 INFO misc.py line 117 726] Train: [13/20][485/510] Data 5.000 (3.792) Batch 32.605 (27.980) Remain 27:56:27 loss: 0.4007 loss_seg: 0.2991 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:47:09,140 INFO misc.py line 117 726] Train: [13/20][486/510] Data 3.589 (3.792) Batch 29.199 (27.982) Remain 27:56:08 loss: 0.2286 loss_seg: 0.1365 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:47:38,920 INFO misc.py line 117 726] Train: [13/20][487/510] Data 3.084 (3.791) Batch 29.780 (27.986) Remain 27:55:54 loss: 0.2049 loss_seg: 0.1183 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:48:06,808 INFO misc.py line 117 726] Train: [13/20][488/510] Data 3.219 (3.789) Batch 27.888 (27.986) Remain 27:55:25 loss: 0.2026 loss_seg: 0.1101 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:48:25,396 INFO misc.py line 117 726] Train: [13/20][489/510] Data 1.691 (3.785) Batch 18.588 (27.967) Remain 27:53:48 loss: 0.2104 loss_seg: 0.1186 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:48:46,450 INFO misc.py line 117 726] Train: [13/20][490/510] Data 2.427 (3.782) Batch 21.054 (27.952) Remain 27:52:29 loss: 0.1808 loss_seg: 0.0970 loss_superpoint_edge: 0.0137 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:49:20,807 INFO misc.py line 117 726] Train: [13/20][491/510] Data 4.861 (3.784) Batch 34.357 (27.966) Remain 27:52:48 loss: 0.2368 loss_seg: 0.1482 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:49:47,989 INFO misc.py line 117 726] Train: [13/20][492/510] Data 3.258 (3.783) Batch 27.183 (27.964) Remain 27:52:14 loss: 0.2473 loss_seg: 0.1548 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:50:25,630 INFO misc.py line 117 726] Train: [13/20][493/510] Data 5.590 (3.787) Batch 37.641 (27.984) Remain 27:52:57 loss: 0.2014 loss_seg: 0.1084 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:50:52,667 INFO misc.py line 117 726] Train: [13/20][494/510] Data 4.330 (3.788) Batch 27.037 (27.982) Remain 27:52:22 loss: 0.2337 loss_seg: 0.1376 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:51:16,568 INFO misc.py line 117 726] Train: [13/20][495/510] Data 3.016 (3.787) Batch 23.901 (27.973) Remain 27:51:24 loss: 0.3167 loss_seg: 0.2136 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:51:50,329 INFO misc.py line 117 726] Train: [13/20][496/510] Data 5.314 (3.790) Batch 33.761 (27.985) Remain 27:51:38 loss: 0.2410 loss_seg: 0.1470 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:52:17,652 INFO misc.py line 117 726] Train: [13/20][497/510] Data 2.444 (3.787) Batch 27.323 (27.984) Remain 27:51:06 loss: 0.2011 loss_seg: 0.1130 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:52:40,916 INFO misc.py line 117 726] Train: [13/20][498/510] Data 2.486 (3.784) Batch 23.264 (27.974) Remain 27:50:04 loss: 0.2854 loss_seg: 0.1854 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:53:10,191 INFO misc.py line 117 726] Train: [13/20][499/510] Data 4.708 (3.786) Batch 29.275 (27.977) Remain 27:49:45 loss: 0.2577 loss_seg: 0.1609 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:53:30,249 INFO misc.py line 117 726] Train: [13/20][500/510] Data 2.090 (3.783) Batch 20.058 (27.961) Remain 27:48:20 loss: 0.3616 loss_seg: 0.2637 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:53:30,249 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 20:54:07,073 INFO misc.py line 117 726] Train: [13/20][501/510] Data 4.601 (3.784) Batch 36.824 (27.979) Remain 27:48:56 loss: 0.2521 loss_seg: 0.1536 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:54:33,794 INFO misc.py line 117 726] Train: [13/20][502/510] Data 5.580 (3.788) Batch 26.721 (27.976) Remain 27:48:19 loss: 0.2576 loss_seg: 0.1571 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:54:59,697 INFO misc.py line 117 726] Train: [13/20][503/510] Data 3.300 (3.787) Batch 25.904 (27.972) Remain 27:47:36 loss: 0.2961 loss_seg: 0.1904 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:55:26,336 INFO misc.py line 117 726] Train: [13/20][504/510] Data 3.331 (3.786) Batch 26.637 (27.969) Remain 27:46:58 loss: 0.2423 loss_seg: 0.1415 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:56:02,333 INFO misc.py line 117 726] Train: [13/20][505/510] Data 4.866 (3.788) Batch 35.998 (27.985) Remain 27:47:28 loss: 0.2457 loss_seg: 0.1472 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:56:27,820 INFO misc.py line 117 726] Train: [13/20][506/510] Data 3.249 (3.787) Batch 25.487 (27.981) Remain 27:46:42 loss: 0.1644 loss_seg: 0.0813 loss_superpoint_edge: 0.0146 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:56:52,208 INFO misc.py line 117 726] Train: [13/20][507/510] Data 2.847 (3.785) Batch 24.388 (27.973) Remain 27:45:48 loss: 0.1500 loss_seg: 0.0678 loss_superpoint_edge: 0.0128 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0294 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:57:08,920 INFO misc.py line 117 726] Train: [13/20][508/510] Data 2.296 (3.782) Batch 16.712 (27.951) Remain 27:44:01 loss: 0.2762 loss_seg: 0.1740 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:57:40,986 INFO misc.py line 117 726] Train: [13/20][509/510] Data 3.124 (3.781) Batch 32.066 (27.959) Remain 27:44:02 loss: 0.2655 loss_seg: 0.1633 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:58:14,642 INFO misc.py line 117 726] Train: [13/20][510/510] Data 5.406 (3.784) Batch 33.656 (27.970) Remain 27:44:14 loss: 0.2405 loss_seg: 0.1454 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 20:58:14,643 INFO misc.py line 147 726] Train result: loss: 0.2504 loss_seg: 0.1554 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-11 20:58:14,644 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-11 20:58:30,087 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6894 [2026-06-11 20:58:45,824 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7080 [2026-06-11 21:00:00,040 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.9500 [2026-06-11 21:00:40,177 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0357 [2026-06-11 21:00:59,337 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.1168 [2026-06-11 21:01:35,152 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2108 [2026-06-11 21:02:21,286 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1257 [2026-06-11 21:02:36,624 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3583 [2026-06-11 21:02:54,202 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.1165 [2026-06-11 21:03:12,724 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3793 [2026-06-11 21:03:28,357 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4900 [2026-06-11 21:03:49,921 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.8468 [2026-06-11 21:04:15,701 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9631 [2026-06-11 21:04:26,879 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.8147 [2026-06-11 21:04:58,115 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0641 [2026-06-11 21:05:23,820 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.4166 [2026-06-11 21:05:50,277 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.4265 [2026-06-11 21:06:32,756 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1832 [2026-06-11 21:06:53,519 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4468 [2026-06-11 21:07:09,830 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8480 [2026-06-11 21:07:40,738 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9431 [2026-06-11 21:07:56,832 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.5818 [2026-06-11 21:08:18,613 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3485 [2026-06-11 21:08:39,824 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8784 [2026-06-11 21:08:53,225 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6630 [2026-06-11 21:09:21,113 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5204 [2026-06-11 21:10:02,249 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.2366 [2026-06-11 21:10:19,326 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5045 [2026-06-11 21:10:37,970 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4096 [2026-06-11 21:10:54,712 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4088 [2026-06-11 21:11:19,621 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2594 [2026-06-11 21:11:37,716 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5921 [2026-06-11 21:11:54,993 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1562 [2026-06-11 21:12:19,381 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6876 [2026-06-11 21:12:19,406 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6686/0.7426/0.8962. [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9268/0.9597 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9758/0.9879 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8388/0.9703 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0043/0.0331 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3138/0.3772 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6083/0.6376 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.5741/0.6537 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7981/0.8950 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9154/0.9570 [2026-06-11 21:12:19,406 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6737/0.7662 [2026-06-11 21:12:19,407 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7609/0.8488 [2026-06-11 21:12:19,407 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7000/0.8551 [2026-06-11 21:12:19,407 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.6017/0.7125 [2026-06-11 21:12:19,407 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-11 21:12:19,408 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-11 21:12:19,408 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 21:12:51,998 INFO misc.py line 117 726] Train: [14/20][1/510] Data 8.245 (8.245) Batch 30.981 (30.981) Remain 30:42:50 loss: 0.1958 loss_seg: 0.1090 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:13:28,526 INFO misc.py line 117 726] Train: [14/20][2/510] Data 6.599 (6.599) Batch 36.528 (36.528) Remain 36:12:12 loss: 0.2650 loss_seg: 0.1612 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:13:57,390 INFO misc.py line 117 726] Train: [14/20][3/510] Data 3.960 (3.960) Batch 28.864 (28.864) Remain 28:35:56 loss: 0.2161 loss_seg: 0.1287 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:14:26,695 INFO misc.py line 117 726] Train: [14/20][4/510] Data 2.793 (2.793) Batch 29.305 (29.305) Remain 29:01:41 loss: 0.2102 loss_seg: 0.1150 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:14:51,121 INFO misc.py line 117 726] Train: [14/20][5/510] Data 3.668 (3.231) Batch 24.426 (26.866) Remain 26:36:15 loss: 0.2977 loss_seg: 0.2098 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:15:15,889 INFO misc.py line 117 726] Train: [14/20][6/510] Data 2.247 (2.903) Batch 24.768 (26.166) Remain 25:54:16 loss: 0.2025 loss_seg: 0.1131 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:15:40,083 INFO misc.py line 117 726] Train: [14/20][7/510] Data 1.981 (2.672) Batch 24.193 (25.673) Remain 25:24:33 loss: 0.2569 loss_seg: 0.1574 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:16:15,853 INFO misc.py line 117 726] Train: [14/20][8/510] Data 5.751 (3.288) Batch 35.771 (27.693) Remain 27:24:00 loss: 0.1989 loss_seg: 0.1114 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:16:46,404 INFO misc.py line 117 726] Train: [14/20][9/510] Data 3.577 (3.336) Batch 30.551 (28.169) Remain 27:51:49 loss: 0.2062 loss_seg: 0.1205 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:17:13,020 INFO misc.py line 117 726] Train: [14/20][10/510] Data 4.225 (3.463) Batch 26.615 (27.947) Remain 27:38:11 loss: 0.1933 loss_seg: 0.1093 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:17:37,478 INFO misc.py line 117 726] Train: [14/20][11/510] Data 2.278 (3.315) Batch 24.459 (27.511) Remain 27:11:51 loss: 0.2164 loss_seg: 0.1236 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:17:54,980 INFO misc.py line 117 726] Train: [14/20][12/510] Data 2.131 (3.183) Batch 17.502 (26.399) Remain 26:05:27 loss: 0.2693 loss_seg: 0.1687 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:18:24,257 INFO misc.py line 117 726] Train: [14/20][13/510] Data 3.316 (3.197) Batch 29.277 (26.687) Remain 26:22:04 loss: 0.2114 loss_seg: 0.1205 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:18:58,743 INFO misc.py line 117 726] Train: [14/20][14/510] Data 3.970 (3.267) Batch 34.486 (27.396) Remain 27:03:39 loss: 0.2273 loss_seg: 0.1356 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:19:20,106 INFO misc.py line 117 726] Train: [14/20][15/510] Data 2.511 (3.204) Batch 21.363 (26.893) Remain 26:33:24 loss: 0.2017 loss_seg: 0.1122 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:19:46,134 INFO misc.py line 117 726] Train: [14/20][16/510] Data 3.126 (3.198) Batch 26.028 (26.826) Remain 26:29:01 loss: 0.2811 loss_seg: 0.1768 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:20:07,680 INFO misc.py line 117 726] Train: [14/20][17/510] Data 2.559 (3.152) Batch 21.546 (26.449) Remain 26:06:14 loss: 0.3567 loss_seg: 0.2592 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:20:35,731 INFO misc.py line 117 726] Train: [14/20][18/510] Data 3.276 (3.161) Batch 28.051 (26.556) Remain 26:12:07 loss: 0.2670 loss_seg: 0.1715 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:21:03,159 INFO misc.py line 117 726] Train: [14/20][19/510] Data 4.435 (3.240) Batch 27.428 (26.611) Remain 26:14:54 loss: 0.2615 loss_seg: 0.1627 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:21:35,482 INFO misc.py line 117 726] Train: [14/20][20/510] Data 4.317 (3.304) Batch 32.323 (26.947) Remain 26:34:20 loss: 0.2050 loss_seg: 0.1168 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:22:01,013 INFO misc.py line 117 726] Train: [14/20][21/510] Data 3.163 (3.296) Batch 25.530 (26.868) Remain 26:29:14 loss: 0.2305 loss_seg: 0.1324 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:22:24,268 INFO misc.py line 117 726] Train: [14/20][22/510] Data 2.661 (3.262) Batch 23.255 (26.678) Remain 26:17:32 loss: 0.1961 loss_seg: 0.1096 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:22:56,991 INFO misc.py line 117 726] Train: [14/20][23/510] Data 3.582 (3.278) Batch 32.723 (26.980) Remain 26:34:58 loss: 0.1960 loss_seg: 0.1086 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:23:28,208 INFO misc.py line 117 726] Train: [14/20][24/510] Data 4.846 (3.353) Batch 31.217 (27.182) Remain 26:46:26 loss: 0.1874 loss_seg: 0.0984 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:23:55,169 INFO misc.py line 117 726] Train: [14/20][25/510] Data 2.761 (3.326) Batch 26.961 (27.172) Remain 26:45:23 loss: 0.2824 loss_seg: 0.1862 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:24:22,134 INFO misc.py line 117 726] Train: [14/20][26/510] Data 2.970 (3.311) Batch 26.965 (27.163) Remain 26:44:24 loss: 0.2370 loss_seg: 0.1426 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:24:49,865 INFO misc.py line 117 726] Train: [14/20][27/510] Data 2.987 (3.297) Batch 27.731 (27.186) Remain 26:45:21 loss: 0.2533 loss_seg: 0.1504 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:25:16,987 INFO misc.py line 117 726] Train: [14/20][28/510] Data 2.274 (3.256) Batch 27.122 (27.184) Remain 26:44:45 loss: 0.2034 loss_seg: 0.1114 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:25:45,926 INFO misc.py line 117 726] Train: [14/20][29/510] Data 4.600 (3.308) Batch 28.939 (27.251) Remain 26:48:17 loss: 0.1687 loss_seg: 0.0836 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:26:05,316 INFO misc.py line 117 726] Train: [14/20][30/510] Data 2.012 (3.260) Batch 19.391 (26.960) Remain 26:30:39 loss: 0.2265 loss_seg: 0.1326 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:26:38,656 INFO misc.py line 117 726] Train: [14/20][31/510] Data 3.827 (3.280) Batch 33.339 (27.188) Remain 26:43:38 loss: 0.2954 loss_seg: 0.1832 loss_superpoint_edge: 0.0476 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:27:03,330 INFO misc.py line 117 726] Train: [14/20][32/510] Data 3.564 (3.290) Batch 24.674 (27.101) Remain 26:38:04 loss: 0.2345 loss_seg: 0.1405 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:27:31,157 INFO misc.py line 117 726] Train: [14/20][33/510] Data 3.397 (3.294) Batch 27.826 (27.126) Remain 26:39:03 loss: 0.4127 loss_seg: 0.3085 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:28:05,164 INFO misc.py line 117 726] Train: [14/20][34/510] Data 3.671 (3.306) Batch 34.007 (27.348) Remain 26:51:40 loss: 0.3056 loss_seg: 0.2091 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:28:33,782 INFO misc.py line 117 726] Train: [14/20][35/510] Data 3.433 (3.310) Batch 28.618 (27.387) Remain 26:53:33 loss: 0.1733 loss_seg: 0.0885 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:29:04,683 INFO misc.py line 117 726] Train: [14/20][36/510] Data 2.958 (3.299) Batch 30.901 (27.494) Remain 26:59:22 loss: 0.1648 loss_seg: 0.0834 loss_superpoint_edge: 0.0146 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:29:30,360 INFO misc.py line 117 726] Train: [14/20][37/510] Data 2.325 (3.270) Batch 25.677 (27.440) Remain 26:55:46 loss: 0.2350 loss_seg: 0.1387 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:29:52,390 INFO misc.py line 117 726] Train: [14/20][38/510] Data 2.555 (3.250) Batch 22.030 (27.286) Remain 26:46:13 loss: 0.4268 loss_seg: 0.3216 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:30:14,647 INFO misc.py line 117 726] Train: [14/20][39/510] Data 2.251 (3.222) Batch 22.257 (27.146) Remain 26:37:32 loss: 0.2213 loss_seg: 0.1297 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:30:34,937 INFO misc.py line 117 726] Train: [14/20][40/510] Data 2.102 (3.192) Batch 20.291 (26.961) Remain 26:26:11 loss: 0.3183 loss_seg: 0.2224 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:31:07,050 INFO misc.py line 117 726] Train: [14/20][41/510] Data 3.742 (3.206) Batch 32.113 (27.096) Remain 26:33:42 loss: 0.2160 loss_seg: 0.1241 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:31:39,006 INFO misc.py line 117 726] Train: [14/20][42/510] Data 4.339 (3.235) Batch 31.956 (27.221) Remain 26:40:35 loss: 0.2458 loss_seg: 0.1512 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:32:13,651 INFO misc.py line 117 726] Train: [14/20][43/510] Data 3.675 (3.246) Batch 34.645 (27.407) Remain 26:51:02 loss: 0.2289 loss_seg: 0.1365 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:32:41,929 INFO misc.py line 117 726] Train: [14/20][44/510] Data 2.850 (3.237) Batch 28.278 (27.428) Remain 26:51:50 loss: 0.2540 loss_seg: 0.1559 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:33:09,198 INFO misc.py line 117 726] Train: [14/20][45/510] Data 4.086 (3.257) Batch 27.268 (27.424) Remain 26:51:09 loss: 0.2009 loss_seg: 0.1123 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:33:44,582 INFO misc.py line 117 726] Train: [14/20][46/510] Data 3.491 (3.262) Batch 35.385 (27.609) Remain 27:01:34 loss: 0.1559 loss_seg: 0.0755 loss_superpoint_edge: 0.0148 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:34:16,216 INFO misc.py line 117 726] Train: [14/20][47/510] Data 3.567 (3.269) Batch 31.634 (27.701) Remain 27:06:29 loss: 0.2011 loss_seg: 0.1134 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:34:48,372 INFO misc.py line 117 726] Train: [14/20][48/510] Data 3.336 (3.271) Batch 32.156 (27.800) Remain 27:11:50 loss: 0.2717 loss_seg: 0.1696 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:35:13,928 INFO misc.py line 117 726] Train: [14/20][49/510] Data 2.132 (3.246) Batch 25.555 (27.751) Remain 27:08:30 loss: 0.2458 loss_seg: 0.1474 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:35:34,929 INFO misc.py line 117 726] Train: [14/20][50/510] Data 2.659 (3.234) Batch 21.001 (27.607) Remain 26:59:37 loss: 0.2624 loss_seg: 0.1620 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:35:34,929 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 21:36:01,432 INFO misc.py line 117 726] Train: [14/20][51/510] Data 4.061 (3.251) Batch 26.503 (27.584) Remain 26:57:48 loss: 0.2491 loss_seg: 0.1482 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:36:27,477 INFO misc.py line 117 726] Train: [14/20][52/510] Data 2.662 (3.239) Batch 26.045 (27.553) Remain 26:55:30 loss: 0.2623 loss_seg: 0.1612 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:36:49,213 INFO misc.py line 117 726] Train: [14/20][53/510] Data 2.410 (3.222) Batch 21.736 (27.436) Remain 26:48:14 loss: 0.2486 loss_seg: 0.1502 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:37:11,212 INFO misc.py line 117 726] Train: [14/20][54/510] Data 1.811 (3.195) Batch 21.999 (27.330) Remain 26:41:31 loss: 0.2291 loss_seg: 0.1363 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:37:48,271 INFO misc.py line 117 726] Train: [14/20][55/510] Data 4.496 (3.220) Batch 37.060 (27.517) Remain 26:52:02 loss: 0.1870 loss_seg: 0.0983 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:38:08,241 INFO misc.py line 117 726] Train: [14/20][56/510] Data 2.043 (3.197) Batch 19.970 (27.375) Remain 26:43:14 loss: 0.3394 loss_seg: 0.2253 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:38:47,320 INFO misc.py line 117 726] Train: [14/20][57/510] Data 5.760 (3.245) Batch 39.078 (27.591) Remain 26:55:28 loss: 0.2444 loss_seg: 0.1503 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:39:16,962 INFO misc.py line 117 726] Train: [14/20][58/510] Data 4.376 (3.265) Batch 29.642 (27.629) Remain 26:57:11 loss: 0.3178 loss_seg: 0.2140 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:39:53,493 INFO misc.py line 117 726] Train: [14/20][59/510] Data 5.803 (3.311) Batch 36.531 (27.788) Remain 27:06:02 loss: 0.3605 loss_seg: 0.2483 loss_superpoint_edge: 0.0461 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:40:34,839 INFO misc.py line 117 726] Train: [14/20][60/510] Data 11.492 (3.454) Batch 41.346 (28.025) Remain 27:19:29 loss: 0.2120 loss_seg: 0.1210 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:41:01,880 INFO misc.py line 117 726] Train: [14/20][61/510] Data 2.737 (3.442) Batch 27.042 (28.008) Remain 27:18:01 loss: 0.3115 loss_seg: 0.2123 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:41:19,905 INFO misc.py line 117 726] Train: [14/20][62/510] Data 1.946 (3.417) Batch 18.024 (27.839) Remain 27:07:40 loss: 0.2704 loss_seg: 0.1672 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:41:46,541 INFO misc.py line 117 726] Train: [14/20][63/510] Data 3.022 (3.410) Batch 26.637 (27.819) Remain 27:06:01 loss: 0.3068 loss_seg: 0.2071 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:42:13,558 INFO misc.py line 117 726] Train: [14/20][64/510] Data 2.555 (3.396) Batch 27.016 (27.806) Remain 27:04:47 loss: 0.2369 loss_seg: 0.1428 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:42:31,155 INFO misc.py line 117 726] Train: [14/20][65/510] Data 1.486 (3.365) Batch 17.597 (27.641) Remain 26:54:43 loss: 0.2383 loss_seg: 0.1484 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:43:08,501 INFO misc.py line 117 726] Train: [14/20][66/510] Data 5.036 (3.392) Batch 37.346 (27.795) Remain 27:03:15 loss: 0.2337 loss_seg: 0.1407 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:43:33,078 INFO misc.py line 117 726] Train: [14/20][67/510] Data 3.177 (3.388) Batch 24.577 (27.745) Remain 26:59:51 loss: 0.3212 loss_seg: 0.2211 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:44:01,746 INFO misc.py line 117 726] Train: [14/20][68/510] Data 3.670 (3.393) Batch 28.668 (27.759) Remain 27:00:13 loss: 0.2204 loss_seg: 0.1307 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:44:37,986 INFO misc.py line 117 726] Train: [14/20][69/510] Data 5.947 (3.431) Batch 36.240 (27.888) Remain 27:07:15 loss: 0.3657 loss_seg: 0.2607 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:45:10,088 INFO misc.py line 117 726] Train: [14/20][70/510] Data 2.608 (3.419) Batch 32.102 (27.951) Remain 27:10:27 loss: 0.2686 loss_seg: 0.1730 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:45:40,832 INFO misc.py line 117 726] Train: [14/20][71/510] Data 8.874 (3.499) Batch 30.744 (27.992) Remain 27:12:23 loss: 0.3798 loss_seg: 0.2591 loss_superpoint_edge: 0.0508 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:46:06,104 INFO misc.py line 117 726] Train: [14/20][72/510] Data 3.245 (3.496) Batch 25.272 (27.952) Remain 27:09:37 loss: 0.2494 loss_seg: 0.1537 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:46:36,562 INFO misc.py line 117 726] Train: [14/20][73/510] Data 3.779 (3.500) Batch 30.458 (27.988) Remain 27:11:14 loss: 0.2169 loss_seg: 0.1241 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:47:01,616 INFO misc.py line 117 726] Train: [14/20][74/510] Data 3.221 (3.496) Batch 25.054 (27.947) Remain 27:08:22 loss: 0.2315 loss_seg: 0.1376 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:47:29,453 INFO misc.py line 117 726] Train: [14/20][75/510] Data 2.629 (3.484) Batch 27.837 (27.945) Remain 27:07:48 loss: 0.2070 loss_seg: 0.1169 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:47:52,334 INFO misc.py line 117 726] Train: [14/20][76/510] Data 3.671 (3.486) Batch 22.881 (27.876) Remain 27:03:18 loss: 0.2549 loss_seg: 0.1605 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:48:24,122 INFO misc.py line 117 726] Train: [14/20][77/510] Data 3.217 (3.483) Batch 31.789 (27.929) Remain 27:05:55 loss: 0.2646 loss_seg: 0.1641 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:48:56,173 INFO misc.py line 117 726] Train: [14/20][78/510] Data 2.601 (3.471) Batch 32.051 (27.984) Remain 27:08:39 loss: 0.2515 loss_seg: 0.1501 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:49:35,285 INFO misc.py line 117 726] Train: [14/20][79/510] Data 9.112 (3.545) Batch 39.112 (28.130) Remain 27:16:42 loss: 0.2119 loss_seg: 0.1218 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:50:00,917 INFO misc.py line 117 726] Train: [14/20][80/510] Data 2.530 (3.532) Batch 25.632 (28.098) Remain 27:14:21 loss: 0.2549 loss_seg: 0.1595 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:50:27,236 INFO misc.py line 117 726] Train: [14/20][81/510] Data 5.765 (3.560) Batch 26.319 (28.075) Remain 27:12:33 loss: 0.2324 loss_seg: 0.1417 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:50:59,327 INFO misc.py line 117 726] Train: [14/20][82/510] Data 7.196 (3.607) Batch 32.091 (28.126) Remain 27:15:02 loss: 0.2717 loss_seg: 0.1805 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:51:23,171 INFO misc.py line 117 726] Train: [14/20][83/510] Data 3.231 (3.602) Batch 23.844 (28.072) Remain 27:11:27 loss: 0.2213 loss_seg: 0.1241 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:51:56,814 INFO misc.py line 117 726] Train: [14/20][84/510] Data 5.045 (3.620) Batch 33.643 (28.141) Remain 27:14:59 loss: 0.2176 loss_seg: 0.1275 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:52:19,612 INFO misc.py line 117 726] Train: [14/20][85/510] Data 2.676 (3.608) Batch 22.798 (28.076) Remain 27:10:44 loss: 0.2477 loss_seg: 0.1503 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:52:47,148 INFO misc.py line 117 726] Train: [14/20][86/510] Data 2.571 (3.596) Batch 27.536 (28.069) Remain 27:09:53 loss: 0.2314 loss_seg: 0.1362 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:53:13,729 INFO misc.py line 117 726] Train: [14/20][87/510] Data 3.143 (3.590) Batch 26.581 (28.052) Remain 27:08:23 loss: 0.3575 loss_seg: 0.2394 loss_superpoint_edge: 0.0500 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:53:33,695 INFO misc.py line 117 726] Train: [14/20][88/510] Data 2.562 (3.578) Batch 19.966 (27.957) Remain 27:02:24 loss: 0.2603 loss_seg: 0.1645 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:54:08,810 INFO misc.py line 117 726] Train: [14/20][89/510] Data 6.119 (3.608) Batch 35.115 (28.040) Remain 27:06:46 loss: 0.1911 loss_seg: 0.1053 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:54:39,177 INFO misc.py line 117 726] Train: [14/20][90/510] Data 4.345 (3.616) Batch 30.367 (28.067) Remain 27:07:51 loss: 0.2563 loss_seg: 0.1587 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:55:10,852 INFO misc.py line 117 726] Train: [14/20][91/510] Data 4.155 (3.622) Batch 31.675 (28.108) Remain 27:09:46 loss: 0.2163 loss_seg: 0.1292 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:55:43,421 INFO misc.py line 117 726] Train: [14/20][92/510] Data 3.377 (3.620) Batch 32.569 (28.158) Remain 27:12:12 loss: 0.2402 loss_seg: 0.1428 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:56:08,064 INFO misc.py line 117 726] Train: [14/20][93/510] Data 3.808 (3.622) Batch 24.643 (28.119) Remain 27:09:28 loss: 0.2518 loss_seg: 0.1521 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:56:22,874 INFO misc.py line 117 726] Train: [14/20][94/510] Data 1.891 (3.603) Batch 14.810 (27.972) Remain 27:00:31 loss: 0.2105 loss_seg: 0.1177 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:56:57,387 INFO misc.py line 117 726] Train: [14/20][95/510] Data 5.785 (3.626) Batch 34.513 (28.043) Remain 27:04:10 loss: 0.2710 loss_seg: 0.1840 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:57:26,239 INFO misc.py line 117 726] Train: [14/20][96/510] Data 4.127 (3.632) Batch 28.853 (28.052) Remain 27:04:13 loss: 0.2227 loss_seg: 0.1307 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:58:05,591 INFO misc.py line 117 726] Train: [14/20][97/510] Data 6.256 (3.660) Batch 39.351 (28.172) Remain 27:10:42 loss: 0.2002 loss_seg: 0.1094 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:58:27,983 INFO misc.py line 117 726] Train: [14/20][98/510] Data 2.723 (3.650) Batch 22.392 (28.112) Remain 27:06:43 loss: 0.2357 loss_seg: 0.1388 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:58:57,892 INFO misc.py line 117 726] Train: [14/20][99/510] Data 5.052 (3.664) Batch 29.908 (28.130) Remain 27:07:20 loss: 0.3454 loss_seg: 0.2491 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:59:29,009 INFO misc.py line 117 726] Train: [14/20][100/510] Data 3.746 (3.665) Batch 31.117 (28.161) Remain 27:08:38 loss: 0.2776 loss_seg: 0.1769 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 21:59:29,009 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 21:59:56,347 INFO misc.py line 117 726] Train: [14/20][101/510] Data 3.000 (3.658) Batch 27.339 (28.153) Remain 27:07:41 loss: 0.2672 loss_seg: 0.1681 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:00:22,945 INFO misc.py line 117 726] Train: [14/20][102/510] Data 3.271 (3.655) Batch 26.598 (28.137) Remain 27:06:18 loss: 0.2361 loss_seg: 0.1448 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:00:56,575 INFO misc.py line 117 726] Train: [14/20][103/510] Data 5.796 (3.676) Batch 33.630 (28.192) Remain 27:09:01 loss: 0.1961 loss_seg: 0.1106 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:01:24,832 INFO misc.py line 117 726] Train: [14/20][104/510] Data 4.708 (3.686) Batch 28.257 (28.192) Remain 27:08:35 loss: 0.2772 loss_seg: 0.1739 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:01:45,452 INFO misc.py line 117 726] Train: [14/20][105/510] Data 2.121 (3.671) Batch 20.620 (28.118) Remain 27:03:49 loss: 0.2768 loss_seg: 0.1710 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:02:19,769 INFO misc.py line 117 726] Train: [14/20][106/510] Data 3.664 (3.671) Batch 34.317 (28.178) Remain 27:06:50 loss: 0.2255 loss_seg: 0.1339 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:02:46,580 INFO misc.py line 117 726] Train: [14/20][107/510] Data 3.114 (3.665) Batch 26.811 (28.165) Remain 27:05:36 loss: 0.3352 loss_seg: 0.2349 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:03:13,755 INFO misc.py line 117 726] Train: [14/20][108/510] Data 2.390 (3.653) Batch 27.175 (28.156) Remain 27:04:35 loss: 0.2203 loss_seg: 0.1282 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:03:38,901 INFO misc.py line 117 726] Train: [14/20][109/510] Data 2.867 (3.646) Batch 25.146 (28.127) Remain 27:02:29 loss: 0.2990 loss_seg: 0.1920 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:04:03,190 INFO misc.py line 117 726] Train: [14/20][110/510] Data 3.460 (3.644) Batch 24.289 (28.092) Remain 26:59:56 loss: 0.3111 loss_seg: 0.2088 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:04:19,531 INFO misc.py line 117 726] Train: [14/20][111/510] Data 2.284 (3.632) Batch 16.341 (27.983) Remain 26:53:12 loss: 0.1735 loss_seg: 0.0865 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:04:43,895 INFO misc.py line 117 726] Train: [14/20][112/510] Data 2.543 (3.622) Batch 24.364 (27.950) Remain 26:50:49 loss: 0.2247 loss_seg: 0.1332 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:05:14,603 INFO misc.py line 117 726] Train: [14/20][113/510] Data 3.036 (3.616) Batch 30.708 (27.975) Remain 26:51:48 loss: 0.1851 loss_seg: 0.0986 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:05:44,473 INFO misc.py line 117 726] Train: [14/20][114/510] Data 3.432 (3.615) Batch 29.870 (27.992) Remain 26:52:19 loss: 0.2415 loss_seg: 0.1444 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:06:05,262 INFO misc.py line 117 726] Train: [14/20][115/510] Data 2.323 (3.603) Batch 20.789 (27.927) Remain 26:48:09 loss: 0.2351 loss_seg: 0.1410 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:06:30,712 INFO misc.py line 117 726] Train: [14/20][116/510] Data 2.867 (3.597) Batch 25.451 (27.906) Remain 26:46:25 loss: 0.2446 loss_seg: 0.1531 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:07:01,525 INFO misc.py line 117 726] Train: [14/20][117/510] Data 4.224 (3.602) Batch 30.813 (27.931) Remain 26:47:25 loss: 0.1896 loss_seg: 0.1087 loss_superpoint_edge: 0.0139 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:07:24,234 INFO misc.py line 117 726] Train: [14/20][118/510] Data 3.240 (3.599) Batch 22.708 (27.886) Remain 26:44:21 loss: 0.2450 loss_seg: 0.1490 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:07:41,656 INFO misc.py line 117 726] Train: [14/20][119/510] Data 2.049 (3.586) Batch 17.423 (27.795) Remain 26:38:41 loss: 0.2282 loss_seg: 0.1335 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:08:05,804 INFO misc.py line 117 726] Train: [14/20][120/510] Data 5.280 (3.600) Batch 24.148 (27.764) Remain 26:36:26 loss: 0.2247 loss_seg: 0.1347 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:08:36,691 INFO misc.py line 117 726] Train: [14/20][121/510] Data 3.496 (3.599) Batch 30.887 (27.791) Remain 26:37:30 loss: 0.2685 loss_seg: 0.1663 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:09:02,289 INFO misc.py line 117 726] Train: [14/20][122/510] Data 3.137 (3.595) Batch 25.597 (27.772) Remain 26:35:58 loss: 0.2521 loss_seg: 0.1556 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:09:35,404 INFO misc.py line 117 726] Train: [14/20][123/510] Data 4.342 (3.601) Batch 33.115 (27.817) Remain 26:38:04 loss: 0.2483 loss_seg: 0.1541 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:10:07,115 INFO misc.py line 117 726] Train: [14/20][124/510] Data 3.880 (3.604) Batch 31.712 (27.849) Remain 26:39:27 loss: 0.2142 loss_seg: 0.1275 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:10:35,146 INFO misc.py line 117 726] Train: [14/20][125/510] Data 1.959 (3.590) Batch 28.031 (27.850) Remain 26:39:04 loss: 0.2462 loss_seg: 0.1533 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:11:08,071 INFO misc.py line 117 726] Train: [14/20][126/510] Data 4.285 (3.596) Batch 32.924 (27.892) Remain 26:40:59 loss: 0.2384 loss_seg: 0.1431 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:11:35,865 INFO misc.py line 117 726] Train: [14/20][127/510] Data 3.917 (3.599) Batch 27.795 (27.891) Remain 26:40:28 loss: 0.2808 loss_seg: 0.1848 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:12:07,468 INFO misc.py line 117 726] Train: [14/20][128/510] Data 4.132 (3.603) Batch 31.603 (27.921) Remain 26:41:42 loss: 0.2913 loss_seg: 0.1850 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:12:39,036 INFO misc.py line 117 726] Train: [14/20][129/510] Data 3.489 (3.602) Batch 31.568 (27.950) Remain 26:42:54 loss: 0.2490 loss_seg: 0.1605 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:13:11,632 INFO misc.py line 117 726] Train: [14/20][130/510] Data 3.451 (3.601) Batch 32.596 (27.986) Remain 26:44:32 loss: 0.2158 loss_seg: 0.1234 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:13:33,962 INFO misc.py line 117 726] Train: [14/20][131/510] Data 2.947 (3.596) Batch 22.330 (27.942) Remain 26:41:32 loss: 0.2423 loss_seg: 0.1482 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:13:56,543 INFO misc.py line 117 726] Train: [14/20][132/510] Data 2.755 (3.589) Batch 22.580 (27.900) Remain 26:38:41 loss: 0.2101 loss_seg: 0.1163 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:14:31,239 INFO misc.py line 117 726] Train: [14/20][133/510] Data 4.344 (3.595) Batch 34.696 (27.953) Remain 26:41:13 loss: 0.3030 loss_seg: 0.1957 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:14:56,382 INFO misc.py line 117 726] Train: [14/20][134/510] Data 4.860 (3.605) Batch 25.143 (27.931) Remain 26:39:31 loss: 0.2006 loss_seg: 0.1113 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:15:25,346 INFO misc.py line 117 726] Train: [14/20][135/510] Data 3.481 (3.604) Batch 28.964 (27.939) Remain 26:39:30 loss: 0.2161 loss_seg: 0.1270 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:15:52,099 INFO misc.py line 117 726] Train: [14/20][136/510] Data 2.922 (3.598) Batch 26.752 (27.930) Remain 26:38:32 loss: 0.2084 loss_seg: 0.1176 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:16:18,915 INFO misc.py line 117 726] Train: [14/20][137/510] Data 3.582 (3.598) Batch 26.816 (27.922) Remain 26:37:35 loss: 0.2563 loss_seg: 0.1564 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:16:45,332 INFO misc.py line 117 726] Train: [14/20][138/510] Data 2.914 (3.593) Batch 26.417 (27.911) Remain 26:36:29 loss: 0.1884 loss_seg: 0.1042 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:17:18,352 INFO misc.py line 117 726] Train: [14/20][139/510] Data 3.324 (3.591) Batch 33.020 (27.948) Remain 26:38:10 loss: 0.2557 loss_seg: 0.1591 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:17:41,987 INFO misc.py line 117 726] Train: [14/20][140/510] Data 2.680 (3.585) Batch 23.635 (27.917) Remain 26:35:54 loss: 0.3212 loss_seg: 0.2247 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:18:18,425 INFO misc.py line 117 726] Train: [14/20][141/510] Data 4.359 (3.590) Batch 36.438 (27.979) Remain 26:38:58 loss: 0.1903 loss_seg: 0.1029 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:18:43,157 INFO misc.py line 117 726] Train: [14/20][142/510] Data 2.875 (3.585) Batch 24.732 (27.955) Remain 26:37:10 loss: 0.2744 loss_seg: 0.1703 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:19:19,204 INFO misc.py line 117 726] Train: [14/20][143/510] Data 5.185 (3.597) Batch 36.047 (28.013) Remain 26:40:00 loss: 0.3289 loss_seg: 0.2235 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:19:46,419 INFO misc.py line 117 726] Train: [14/20][144/510] Data 3.411 (3.595) Batch 27.214 (28.007) Remain 26:39:12 loss: 0.2979 loss_seg: 0.1923 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:20:23,741 INFO misc.py line 117 726] Train: [14/20][145/510] Data 4.059 (3.598) Batch 37.322 (28.073) Remain 26:42:29 loss: 0.3195 loss_seg: 0.2156 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:20:55,834 INFO misc.py line 117 726] Train: [14/20][146/510] Data 3.488 (3.598) Batch 32.093 (28.101) Remain 26:43:37 loss: 0.2695 loss_seg: 0.1682 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:21:09,992 INFO misc.py line 117 726] Train: [14/20][147/510] Data 1.897 (3.586) Batch 14.157 (28.004) Remain 26:37:38 loss: 0.2859 loss_seg: 0.1817 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:21:40,482 INFO misc.py line 117 726] Train: [14/20][148/510] Data 3.524 (3.585) Batch 30.491 (28.021) Remain 26:38:08 loss: 0.2889 loss_seg: 0.1796 loss_superpoint_edge: 0.0438 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:22:06,944 INFO misc.py line 117 726] Train: [14/20][149/510] Data 3.047 (3.582) Batch 26.461 (28.011) Remain 26:37:04 loss: 0.2697 loss_seg: 0.1695 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:22:38,163 INFO misc.py line 117 726] Train: [14/20][150/510] Data 7.339 (3.607) Batch 31.219 (28.032) Remain 26:37:51 loss: 0.3106 loss_seg: 0.2063 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:22:38,163 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 22:23:01,500 INFO misc.py line 117 726] Train: [14/20][151/510] Data 2.885 (3.602) Batch 23.337 (28.001) Remain 26:35:34 loss: 0.2143 loss_seg: 0.1201 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:23:33,249 INFO misc.py line 117 726] Train: [14/20][152/510] Data 4.218 (3.607) Batch 31.749 (28.026) Remain 26:36:32 loss: 0.1932 loss_seg: 0.1070 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:23:51,553 INFO misc.py line 117 726] Train: [14/20][153/510] Data 2.048 (3.596) Batch 18.304 (27.961) Remain 26:32:23 loss: 0.2201 loss_seg: 0.1258 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:24:15,863 INFO misc.py line 117 726] Train: [14/20][154/510] Data 3.169 (3.593) Batch 24.310 (27.937) Remain 26:30:32 loss: 0.1884 loss_seg: 0.1024 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:24:42,731 INFO misc.py line 117 726] Train: [14/20][155/510] Data 3.859 (3.595) Batch 26.868 (27.930) Remain 26:29:40 loss: 0.2336 loss_seg: 0.1422 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:25:02,411 INFO misc.py line 117 726] Train: [14/20][156/510] Data 2.342 (3.587) Batch 19.679 (27.876) Remain 26:26:08 loss: 0.2501 loss_seg: 0.1478 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:25:27,191 INFO misc.py line 117 726] Train: [14/20][157/510] Data 2.436 (3.579) Batch 24.781 (27.856) Remain 26:24:32 loss: 0.2503 loss_seg: 0.1606 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:25:51,060 INFO misc.py line 117 726] Train: [14/20][158/510] Data 2.691 (3.574) Batch 23.869 (27.830) Remain 26:22:36 loss: 0.2624 loss_seg: 0.1639 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:26:22,936 INFO misc.py line 117 726] Train: [14/20][159/510] Data 4.014 (3.577) Batch 31.875 (27.856) Remain 26:23:37 loss: 0.2532 loss_seg: 0.1562 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:26:47,165 INFO misc.py line 117 726] Train: [14/20][160/510] Data 3.769 (3.578) Batch 24.230 (27.833) Remain 26:21:50 loss: 0.2570 loss_seg: 0.1607 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:27:15,526 INFO misc.py line 117 726] Train: [14/20][161/510] Data 2.751 (3.573) Batch 28.361 (27.836) Remain 26:21:33 loss: 0.1834 loss_seg: 0.0992 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:27:40,420 INFO misc.py line 117 726] Train: [14/20][162/510] Data 2.211 (3.564) Batch 24.894 (27.818) Remain 26:20:03 loss: 0.1862 loss_seg: 0.0993 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:28:02,286 INFO misc.py line 117 726] Train: [14/20][163/510] Data 2.159 (3.555) Batch 21.866 (27.781) Remain 26:17:28 loss: 0.2846 loss_seg: 0.1872 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:28:18,060 INFO misc.py line 117 726] Train: [14/20][164/510] Data 1.901 (3.545) Batch 15.774 (27.706) Remain 26:12:46 loss: 0.3017 loss_seg: 0.1977 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:28:48,955 INFO misc.py line 117 726] Train: [14/20][165/510] Data 2.731 (3.540) Batch 30.895 (27.726) Remain 26:13:26 loss: 0.3064 loss_seg: 0.2124 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:29:17,031 INFO misc.py line 117 726] Train: [14/20][166/510] Data 2.634 (3.534) Batch 28.076 (27.728) Remain 26:13:05 loss: 0.2220 loss_seg: 0.1288 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:29:39,638 INFO misc.py line 117 726] Train: [14/20][167/510] Data 3.141 (3.532) Batch 22.607 (27.697) Remain 26:10:51 loss: 0.3075 loss_seg: 0.2002 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:30:01,834 INFO misc.py line 117 726] Train: [14/20][168/510] Data 2.084 (3.523) Batch 22.196 (27.663) Remain 26:08:30 loss: 0.2410 loss_seg: 0.1452 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:30:25,334 INFO misc.py line 117 726] Train: [14/20][169/510] Data 2.755 (3.519) Batch 23.501 (27.638) Remain 26:06:37 loss: 0.2306 loss_seg: 0.1315 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:30:48,519 INFO misc.py line 117 726] Train: [14/20][170/510] Data 2.752 (3.514) Batch 23.184 (27.612) Remain 26:04:39 loss: 0.2461 loss_seg: 0.1496 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:31:05,482 INFO misc.py line 117 726] Train: [14/20][171/510] Data 2.483 (3.508) Batch 16.963 (27.548) Remain 26:00:36 loss: 0.2137 loss_seg: 0.1223 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:31:35,533 INFO misc.py line 117 726] Train: [14/20][172/510] Data 4.304 (3.513) Batch 30.052 (27.563) Remain 26:00:58 loss: 0.2695 loss_seg: 0.1648 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:32:07,685 INFO misc.py line 117 726] Train: [14/20][173/510] Data 3.289 (3.511) Batch 32.151 (27.590) Remain 26:02:03 loss: 0.2532 loss_seg: 0.1566 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:32:39,035 INFO misc.py line 117 726] Train: [14/20][174/510] Data 5.073 (3.520) Batch 31.350 (27.612) Remain 26:02:50 loss: 0.2204 loss_seg: 0.1291 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:33:07,899 INFO misc.py line 117 726] Train: [14/20][175/510] Data 2.364 (3.514) Batch 28.864 (27.619) Remain 26:02:47 loss: 0.2159 loss_seg: 0.1253 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:33:35,436 INFO misc.py line 117 726] Train: [14/20][176/510] Data 2.991 (3.511) Batch 27.536 (27.619) Remain 26:02:18 loss: 0.2419 loss_seg: 0.1493 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:33:51,482 INFO misc.py line 117 726] Train: [14/20][177/510] Data 2.264 (3.503) Batch 16.047 (27.552) Remain 25:58:04 loss: 0.2180 loss_seg: 0.1280 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:34:12,519 INFO misc.py line 117 726] Train: [14/20][178/510] Data 2.181 (3.496) Batch 21.036 (27.515) Remain 25:55:30 loss: 0.2204 loss_seg: 0.1291 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:34:42,997 INFO misc.py line 117 726] Train: [14/20][179/510] Data 3.020 (3.493) Batch 30.478 (27.532) Remain 25:56:00 loss: 0.1935 loss_seg: 0.1062 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:35:05,650 INFO misc.py line 117 726] Train: [14/20][180/510] Data 2.430 (3.487) Batch 22.653 (27.504) Remain 25:53:59 loss: 0.2353 loss_seg: 0.1448 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:35:34,292 INFO misc.py line 117 726] Train: [14/20][181/510] Data 2.175 (3.480) Batch 28.641 (27.511) Remain 25:53:53 loss: 0.1994 loss_seg: 0.1107 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:36:00,317 INFO misc.py line 117 726] Train: [14/20][182/510] Data 3.427 (3.480) Batch 26.026 (27.502) Remain 25:52:58 loss: 0.2267 loss_seg: 0.1327 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:36:26,684 INFO misc.py line 117 726] Train: [14/20][183/510] Data 2.914 (3.476) Batch 26.367 (27.496) Remain 25:52:09 loss: 0.2517 loss_seg: 0.1535 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:36:49,276 INFO misc.py line 117 726] Train: [14/20][184/510] Data 2.314 (3.470) Batch 22.592 (27.469) Remain 25:50:09 loss: 0.2034 loss_seg: 0.1143 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:37:17,636 INFO misc.py line 117 726] Train: [14/20][185/510] Data 4.499 (3.476) Batch 28.360 (27.474) Remain 25:49:59 loss: 0.2665 loss_seg: 0.1615 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:37:48,681 INFO misc.py line 117 726] Train: [14/20][186/510] Data 3.368 (3.475) Batch 31.045 (27.493) Remain 25:50:37 loss: 0.2602 loss_seg: 0.1659 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:38:07,013 INFO misc.py line 117 726] Train: [14/20][187/510] Data 2.630 (3.470) Batch 18.333 (27.444) Remain 25:47:21 loss: 0.2591 loss_seg: 0.1646 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:38:27,217 INFO misc.py line 117 726] Train: [14/20][188/510] Data 2.402 (3.465) Batch 20.203 (27.404) Remain 25:44:41 loss: 0.2321 loss_seg: 0.1389 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:38:55,653 INFO misc.py line 117 726] Train: [14/20][189/510] Data 2.868 (3.461) Batch 28.437 (27.410) Remain 25:44:33 loss: 0.2236 loss_seg: 0.1335 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:39:30,649 INFO misc.py line 117 726] Train: [14/20][190/510] Data 5.797 (3.474) Batch 34.995 (27.451) Remain 25:46:22 loss: 0.2422 loss_seg: 0.1411 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:39:57,943 INFO misc.py line 117 726] Train: [14/20][191/510] Data 3.039 (3.472) Batch 27.294 (27.450) Remain 25:45:52 loss: 0.2468 loss_seg: 0.1456 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:40:24,465 INFO misc.py line 117 726] Train: [14/20][192/510] Data 3.615 (3.472) Batch 26.522 (27.445) Remain 25:45:08 loss: 0.1979 loss_seg: 0.1099 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:40:42,343 INFO misc.py line 117 726] Train: [14/20][193/510] Data 2.149 (3.465) Batch 17.877 (27.394) Remain 25:41:51 loss: 0.3058 loss_seg: 0.2035 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:41:10,969 INFO misc.py line 117 726] Train: [14/20][194/510] Data 4.050 (3.468) Batch 28.627 (27.401) Remain 25:41:45 loss: 0.2365 loss_seg: 0.1501 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:41:44,156 INFO misc.py line 117 726] Train: [14/20][195/510] Data 4.451 (3.474) Batch 33.187 (27.431) Remain 25:42:59 loss: 0.2212 loss_seg: 0.1293 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:42:12,674 INFO misc.py line 117 726] Train: [14/20][196/510] Data 2.603 (3.469) Batch 28.518 (27.437) Remain 25:42:51 loss: 0.2672 loss_seg: 0.1760 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:42:46,320 INFO misc.py line 117 726] Train: [14/20][197/510] Data 4.739 (3.476) Batch 33.646 (27.469) Remain 25:44:11 loss: 0.2406 loss_seg: 0.1458 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:43:08,443 INFO misc.py line 117 726] Train: [14/20][198/510] Data 2.582 (3.471) Batch 22.123 (27.441) Remain 25:42:12 loss: 0.2602 loss_seg: 0.1657 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:43:33,045 INFO misc.py line 117 726] Train: [14/20][199/510] Data 3.146 (3.469) Batch 24.601 (27.427) Remain 25:40:55 loss: 0.2136 loss_seg: 0.1262 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:44:02,905 INFO misc.py line 117 726] Train: [14/20][200/510] Data 5.329 (3.479) Batch 29.860 (27.439) Remain 25:41:09 loss: 0.2905 loss_seg: 0.1927 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:44:02,905 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 22:44:44,849 INFO misc.py line 117 726] Train: [14/20][201/510] Data 11.318 (3.518) Batch 41.944 (27.512) Remain 25:44:49 loss: 0.3219 loss_seg: 0.2276 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:45:12,872 INFO misc.py line 117 726] Train: [14/20][202/510] Data 4.631 (3.524) Batch 28.023 (27.515) Remain 25:44:30 loss: 0.2538 loss_seg: 0.1567 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:45:45,331 INFO misc.py line 117 726] Train: [14/20][203/510] Data 3.869 (3.526) Batch 32.460 (27.540) Remain 25:45:26 loss: 0.2171 loss_seg: 0.1286 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:46:08,006 INFO misc.py line 117 726] Train: [14/20][204/510] Data 2.502 (3.521) Batch 22.675 (27.516) Remain 25:43:37 loss: 0.3140 loss_seg: 0.2044 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:46:42,371 INFO misc.py line 117 726] Train: [14/20][205/510] Data 4.494 (3.525) Batch 34.365 (27.549) Remain 25:45:03 loss: 0.2235 loss_seg: 0.1314 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:47:06,854 INFO misc.py line 117 726] Train: [14/20][206/510] Data 3.039 (3.523) Batch 24.484 (27.534) Remain 25:43:45 loss: 0.2559 loss_seg: 0.1536 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:47:37,200 INFO misc.py line 117 726] Train: [14/20][207/510] Data 2.690 (3.519) Batch 30.345 (27.548) Remain 25:44:04 loss: 0.2597 loss_seg: 0.1614 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:48:14,941 INFO misc.py line 117 726] Train: [14/20][208/510] Data 7.427 (3.538) Batch 37.741 (27.598) Remain 25:46:23 loss: 0.1998 loss_seg: 0.1078 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:48:42,869 INFO misc.py line 117 726] Train: [14/20][209/510] Data 3.103 (3.536) Batch 27.928 (27.599) Remain 25:46:01 loss: 0.2436 loss_seg: 0.1469 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:49:03,092 INFO misc.py line 117 726] Train: [14/20][210/510] Data 2.201 (3.529) Batch 20.223 (27.564) Remain 25:43:34 loss: 0.2210 loss_seg: 0.1301 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:49:18,279 INFO misc.py line 117 726] Train: [14/20][211/510] Data 2.277 (3.523) Batch 15.188 (27.504) Remain 25:39:46 loss: 0.2494 loss_seg: 0.1574 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:49:51,889 INFO misc.py line 117 726] Train: [14/20][212/510] Data 5.039 (3.531) Batch 33.610 (27.533) Remain 25:40:57 loss: 0.3076 loss_seg: 0.1986 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:50:21,271 INFO misc.py line 117 726] Train: [14/20][213/510] Data 3.269 (3.529) Batch 29.382 (27.542) Remain 25:40:59 loss: 0.2691 loss_seg: 0.1677 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0322 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:50:47,182 INFO misc.py line 117 726] Train: [14/20][214/510] Data 3.106 (3.527) Batch 25.911 (27.535) Remain 25:40:05 loss: 0.2627 loss_seg: 0.1649 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:51:17,245 INFO misc.py line 117 726] Train: [14/20][215/510] Data 3.510 (3.527) Batch 30.063 (27.546) Remain 25:40:18 loss: 0.1968 loss_seg: 0.1096 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:51:42,938 INFO misc.py line 117 726] Train: [14/20][216/510] Data 2.180 (3.521) Batch 25.693 (27.538) Remain 25:39:21 loss: 0.2056 loss_seg: 0.1180 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:52:04,272 INFO misc.py line 117 726] Train: [14/20][217/510] Data 2.424 (3.516) Batch 21.334 (27.509) Remain 25:37:16 loss: 0.2231 loss_seg: 0.1310 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:52:31,906 INFO misc.py line 117 726] Train: [14/20][218/510] Data 3.171 (3.514) Batch 27.634 (27.509) Remain 25:36:51 loss: 0.1977 loss_seg: 0.1063 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:53:01,508 INFO misc.py line 117 726] Train: [14/20][219/510] Data 2.781 (3.511) Batch 29.603 (27.519) Remain 25:36:56 loss: 0.2289 loss_seg: 0.1379 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:53:25,306 INFO misc.py line 117 726] Train: [14/20][220/510] Data 4.087 (3.514) Batch 23.798 (27.502) Remain 25:35:31 loss: 0.3478 loss_seg: 0.2455 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:53:59,210 INFO misc.py line 117 726] Train: [14/20][221/510] Data 3.251 (3.512) Batch 33.904 (27.531) Remain 25:36:42 loss: 0.2589 loss_seg: 0.1577 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:54:31,239 INFO misc.py line 117 726] Train: [14/20][222/510] Data 3.860 (3.514) Batch 32.029 (27.552) Remain 25:37:23 loss: 0.2579 loss_seg: 0.1574 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:55:01,757 INFO misc.py line 117 726] Train: [14/20][223/510] Data 3.632 (3.514) Batch 30.518 (27.565) Remain 25:37:41 loss: 0.2665 loss_seg: 0.1670 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:55:22,365 INFO misc.py line 117 726] Train: [14/20][224/510] Data 2.469 (3.510) Batch 20.608 (27.534) Remain 25:35:28 loss: 0.2556 loss_seg: 0.1640 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:55:48,446 INFO misc.py line 117 726] Train: [14/20][225/510] Data 3.215 (3.508) Batch 26.081 (27.527) Remain 25:34:38 loss: 0.2082 loss_seg: 0.1173 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:56:07,468 INFO misc.py line 117 726] Train: [14/20][226/510] Data 1.742 (3.501) Batch 19.022 (27.489) Remain 25:32:03 loss: 0.2348 loss_seg: 0.1365 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:56:32,603 INFO misc.py line 117 726] Train: [14/20][227/510] Data 5.122 (3.508) Batch 25.135 (27.479) Remain 25:31:01 loss: 0.1908 loss_seg: 0.1054 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:56:58,062 INFO misc.py line 117 726] Train: [14/20][228/510] Data 4.668 (3.513) Batch 25.459 (27.470) Remain 25:30:03 loss: 0.2050 loss_seg: 0.1133 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:57:34,229 INFO misc.py line 117 726] Train: [14/20][229/510] Data 5.455 (3.522) Batch 36.167 (27.508) Remain 25:31:44 loss: 0.2900 loss_seg: 0.1877 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:58:04,501 INFO misc.py line 117 726] Train: [14/20][230/510] Data 4.211 (3.525) Batch 30.271 (27.520) Remain 25:31:57 loss: 0.1849 loss_seg: 0.0950 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:58:40,336 INFO misc.py line 117 726] Train: [14/20][231/510] Data 6.634 (3.538) Batch 35.836 (27.557) Remain 25:33:32 loss: 0.2731 loss_seg: 0.1755 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:59:09,001 INFO misc.py line 117 726] Train: [14/20][232/510] Data 5.048 (3.545) Batch 28.665 (27.562) Remain 25:33:20 loss: 0.1974 loss_seg: 0.1090 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 22:59:33,035 INFO misc.py line 117 726] Train: [14/20][233/510] Data 2.660 (3.541) Batch 24.034 (27.546) Remain 25:32:01 loss: 0.2099 loss_seg: 0.1186 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:00:03,207 INFO misc.py line 117 726] Train: [14/20][234/510] Data 3.311 (3.540) Batch 30.172 (27.558) Remain 25:32:12 loss: 0.2694 loss_seg: 0.1698 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:00:26,389 INFO misc.py line 117 726] Train: [14/20][235/510] Data 4.225 (3.543) Batch 23.181 (27.539) Remain 25:30:41 loss: 0.2651 loss_seg: 0.1659 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:00:48,127 INFO misc.py line 117 726] Train: [14/20][236/510] Data 2.278 (3.537) Batch 21.738 (27.514) Remain 25:28:51 loss: 0.2497 loss_seg: 0.1504 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:01:26,394 INFO misc.py line 117 726] Train: [14/20][237/510] Data 6.525 (3.550) Batch 38.267 (27.560) Remain 25:30:56 loss: 0.2725 loss_seg: 0.1717 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:01:58,574 INFO misc.py line 117 726] Train: [14/20][238/510] Data 3.810 (3.551) Batch 32.180 (27.580) Remain 25:31:34 loss: 0.3349 loss_seg: 0.2378 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:02:35,389 INFO misc.py line 117 726] Train: [14/20][239/510] Data 4.256 (3.554) Batch 36.815 (27.619) Remain 25:33:17 loss: 0.2731 loss_seg: 0.1740 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:03:04,818 INFO misc.py line 117 726] Train: [14/20][240/510] Data 5.621 (3.563) Batch 29.429 (27.626) Remain 25:33:15 loss: 0.2920 loss_seg: 0.1968 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:03:37,435 INFO misc.py line 117 726] Train: [14/20][241/510] Data 4.915 (3.569) Batch 32.616 (27.647) Remain 25:33:57 loss: 0.2627 loss_seg: 0.1657 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:04:12,551 INFO misc.py line 117 726] Train: [14/20][242/510] Data 5.271 (3.576) Batch 35.116 (27.678) Remain 25:35:14 loss: 0.2354 loss_seg: 0.1446 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:04:40,796 INFO misc.py line 117 726] Train: [14/20][243/510] Data 2.833 (3.573) Batch 28.245 (27.681) Remain 25:34:54 loss: 0.2500 loss_seg: 0.1532 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:05:08,949 INFO misc.py line 117 726] Train: [14/20][244/510] Data 2.691 (3.569) Batch 28.153 (27.683) Remain 25:34:33 loss: 0.2241 loss_seg: 0.1308 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:05:47,168 INFO misc.py line 117 726] Train: [14/20][245/510] Data 9.980 (3.596) Batch 38.219 (27.726) Remain 25:36:30 loss: 0.2702 loss_seg: 0.1727 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:06:21,987 INFO misc.py line 117 726] Train: [14/20][246/510] Data 5.515 (3.603) Batch 34.819 (27.756) Remain 25:37:39 loss: 0.2151 loss_seg: 0.1214 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:06:47,760 INFO misc.py line 117 726] Train: [14/20][247/510] Data 2.618 (3.599) Batch 25.773 (27.747) Remain 25:36:44 loss: 0.2442 loss_seg: 0.1488 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:07:19,981 INFO misc.py line 117 726] Train: [14/20][248/510] Data 3.458 (3.599) Batch 32.221 (27.766) Remain 25:37:17 loss: 0.2056 loss_seg: 0.1165 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:07:33,393 INFO misc.py line 117 726] Train: [14/20][249/510] Data 1.463 (3.590) Batch 13.412 (27.707) Remain 25:33:36 loss: 0.2391 loss_seg: 0.1414 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0461 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:07:55,530 INFO misc.py line 117 726] Train: [14/20][250/510] Data 1.894 (3.583) Batch 22.137 (27.685) Remain 25:31:53 loss: 0.2603 loss_seg: 0.1720 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:07:55,531 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 23:08:25,504 INFO misc.py line 117 726] Train: [14/20][251/510] Data 3.581 (3.583) Batch 29.974 (27.694) Remain 25:31:56 loss: 0.2141 loss_seg: 0.1204 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:08:54,621 INFO misc.py line 117 726] Train: [14/20][252/510] Data 2.952 (3.581) Batch 29.117 (27.700) Remain 25:31:47 loss: 0.1851 loss_seg: 0.1010 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:09:21,872 INFO misc.py line 117 726] Train: [14/20][253/510] Data 3.432 (3.580) Batch 27.251 (27.698) Remain 25:31:14 loss: 0.2694 loss_seg: 0.1717 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:09:49,842 INFO misc.py line 117 726] Train: [14/20][254/510] Data 3.320 (3.579) Batch 27.970 (27.699) Remain 25:30:49 loss: 0.1744 loss_seg: 0.0920 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:10:15,912 INFO misc.py line 117 726] Train: [14/20][255/510] Data 2.549 (3.575) Batch 26.070 (27.693) Remain 25:30:00 loss: 0.2917 loss_seg: 0.1901 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:10:38,246 INFO misc.py line 117 726] Train: [14/20][256/510] Data 2.698 (3.572) Batch 22.334 (27.671) Remain 25:28:22 loss: 0.3022 loss_seg: 0.2008 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:11:13,681 INFO misc.py line 117 726] Train: [14/20][257/510] Data 6.251 (3.582) Batch 35.435 (27.702) Remain 25:29:36 loss: 0.3005 loss_seg: 0.2024 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:11:29,554 INFO misc.py line 117 726] Train: [14/20][258/510] Data 1.546 (3.574) Batch 15.873 (27.656) Remain 25:26:35 loss: 0.2500 loss_seg: 0.1563 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:11:50,888 INFO misc.py line 117 726] Train: [14/20][259/510] Data 2.355 (3.569) Batch 21.334 (27.631) Remain 25:24:45 loss: 0.2437 loss_seg: 0.1436 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:12:25,904 INFO misc.py line 117 726] Train: [14/20][260/510] Data 4.882 (3.574) Batch 35.016 (27.660) Remain 25:25:53 loss: 0.3050 loss_seg: 0.2025 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:12:50,363 INFO misc.py line 117 726] Train: [14/20][261/510] Data 2.908 (3.572) Batch 24.459 (27.647) Remain 25:24:44 loss: 0.3365 loss_seg: 0.2256 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:13:21,329 INFO misc.py line 117 726] Train: [14/20][262/510] Data 5.317 (3.579) Batch 30.966 (27.660) Remain 25:24:59 loss: 0.2155 loss_seg: 0.1241 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:13:51,608 INFO misc.py line 117 726] Train: [14/20][263/510] Data 5.160 (3.585) Batch 30.279 (27.670) Remain 25:25:04 loss: 0.2306 loss_seg: 0.1407 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:14:28,778 INFO misc.py line 117 726] Train: [14/20][264/510] Data 10.544 (3.611) Batch 37.170 (27.706) Remain 25:26:37 loss: 0.2645 loss_seg: 0.1610 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:14:59,013 INFO misc.py line 117 726] Train: [14/20][265/510] Data 3.150 (3.610) Batch 30.235 (27.716) Remain 25:26:41 loss: 0.2414 loss_seg: 0.1481 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:15:35,754 INFO misc.py line 117 726] Train: [14/20][266/510] Data 6.781 (3.622) Batch 36.741 (27.750) Remain 25:28:07 loss: 0.2849 loss_seg: 0.1795 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:16:03,198 INFO misc.py line 117 726] Train: [14/20][267/510] Data 3.093 (3.620) Batch 27.443 (27.749) Remain 25:27:35 loss: 0.2334 loss_seg: 0.1400 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:16:27,939 INFO misc.py line 117 726] Train: [14/20][268/510] Data 2.877 (3.617) Batch 24.741 (27.738) Remain 25:26:30 loss: 0.2397 loss_seg: 0.1405 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:16:46,485 INFO misc.py line 117 726] Train: [14/20][269/510] Data 2.532 (3.613) Batch 18.547 (27.703) Remain 25:24:08 loss: 0.1769 loss_seg: 0.0957 loss_superpoint_edge: 0.0108 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:17:18,533 INFO misc.py line 117 726] Train: [14/20][270/510] Data 9.623 (3.635) Batch 32.048 (27.720) Remain 25:24:34 loss: 0.3497 loss_seg: 0.2464 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0349 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:17:55,197 INFO misc.py line 117 726] Train: [14/20][271/510] Data 5.502 (3.642) Batch 36.664 (27.753) Remain 25:25:57 loss: 0.1960 loss_seg: 0.1079 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:18:20,530 INFO misc.py line 117 726] Train: [14/20][272/510] Data 2.270 (3.637) Batch 25.333 (27.744) Remain 25:24:59 loss: 0.2205 loss_seg: 0.1279 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:18:48,882 INFO misc.py line 117 726] Train: [14/20][273/510] Data 3.713 (3.637) Batch 28.351 (27.746) Remain 25:24:39 loss: 0.2849 loss_seg: 0.1844 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:19:17,419 INFO misc.py line 117 726] Train: [14/20][274/510] Data 3.191 (3.636) Batch 28.538 (27.749) Remain 25:24:21 loss: 0.1905 loss_seg: 0.1038 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:19:55,232 INFO misc.py line 117 726] Train: [14/20][275/510] Data 5.510 (3.643) Batch 37.813 (27.786) Remain 25:25:55 loss: 0.3125 loss_seg: 0.2106 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:20:21,088 INFO misc.py line 117 726] Train: [14/20][276/510] Data 2.557 (3.639) Batch 25.856 (27.779) Remain 25:25:04 loss: 0.2138 loss_seg: 0.1230 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:20:50,719 INFO misc.py line 117 726] Train: [14/20][277/510] Data 3.160 (3.637) Batch 29.631 (27.786) Remain 25:24:58 loss: 0.2853 loss_seg: 0.1800 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:21:21,451 INFO misc.py line 117 726] Train: [14/20][278/510] Data 3.379 (3.636) Batch 30.732 (27.797) Remain 25:25:06 loss: 0.2087 loss_seg: 0.1205 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:21:49,969 INFO misc.py line 117 726] Train: [14/20][279/510] Data 4.425 (3.639) Batch 28.518 (27.799) Remain 25:24:47 loss: 0.2111 loss_seg: 0.1198 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:22:23,523 INFO misc.py line 117 726] Train: [14/20][280/510] Data 5.086 (3.644) Batch 33.554 (27.820) Remain 25:25:27 loss: 0.2002 loss_seg: 0.1147 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:22:43,946 INFO misc.py line 117 726] Train: [14/20][281/510] Data 2.162 (3.639) Batch 20.423 (27.793) Remain 25:23:32 loss: 0.2163 loss_seg: 0.1233 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:23:08,982 INFO misc.py line 117 726] Train: [14/20][282/510] Data 3.381 (3.638) Batch 25.036 (27.783) Remain 25:22:32 loss: 0.2249 loss_seg: 0.1312 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:23:41,037 INFO misc.py line 117 726] Train: [14/20][283/510] Data 3.518 (3.637) Batch 32.054 (27.799) Remain 25:22:54 loss: 0.3116 loss_seg: 0.2089 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:24:15,698 INFO misc.py line 117 726] Train: [14/20][284/510] Data 4.285 (3.640) Batch 34.662 (27.823) Remain 25:23:46 loss: 0.1818 loss_seg: 0.0983 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:24:47,740 INFO misc.py line 117 726] Train: [14/20][285/510] Data 6.212 (3.649) Batch 32.042 (27.838) Remain 25:24:08 loss: 0.2927 loss_seg: 0.2000 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:25:16,103 INFO misc.py line 117 726] Train: [14/20][286/510] Data 3.996 (3.650) Batch 28.363 (27.840) Remain 25:23:46 loss: 0.2384 loss_seg: 0.1425 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:25:42,931 INFO misc.py line 117 726] Train: [14/20][287/510] Data 5.287 (3.656) Batch 26.828 (27.836) Remain 25:23:06 loss: 0.1726 loss_seg: 0.0872 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:26:13,380 INFO misc.py line 117 726] Train: [14/20][288/510] Data 3.818 (3.656) Batch 30.449 (27.846) Remain 25:23:09 loss: 0.2967 loss_seg: 0.1918 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:26:42,483 INFO misc.py line 117 726] Train: [14/20][289/510] Data 2.469 (3.652) Batch 29.104 (27.850) Remain 25:22:55 loss: 0.2338 loss_seg: 0.1382 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:27:03,931 INFO misc.py line 117 726] Train: [14/20][290/510] Data 5.158 (3.658) Batch 21.448 (27.828) Remain 25:21:14 loss: 0.2224 loss_seg: 0.1277 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:27:24,639 INFO misc.py line 117 726] Train: [14/20][291/510] Data 1.827 (3.651) Batch 20.707 (27.803) Remain 25:19:25 loss: 0.2135 loss_seg: 0.1234 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:27:54,753 INFO misc.py line 117 726] Train: [14/20][292/510] Data 4.109 (3.653) Batch 30.115 (27.811) Remain 25:19:24 loss: 0.1770 loss_seg: 0.0931 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:28:12,640 INFO misc.py line 117 726] Train: [14/20][293/510] Data 2.112 (3.647) Batch 17.887 (27.777) Remain 25:17:04 loss: 0.3861 loss_seg: 0.2740 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:28:49,492 INFO misc.py line 117 726] Train: [14/20][294/510] Data 6.429 (3.657) Batch 36.851 (27.808) Remain 25:18:18 loss: 0.2249 loss_seg: 0.1325 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:29:18,882 INFO misc.py line 117 726] Train: [14/20][295/510] Data 3.774 (3.657) Batch 29.390 (27.813) Remain 25:18:08 loss: 0.3015 loss_seg: 0.2090 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:29:54,872 INFO misc.py line 117 726] Train: [14/20][296/510] Data 3.567 (3.657) Batch 35.990 (27.841) Remain 25:19:12 loss: 0.2331 loss_seg: 0.1392 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:30:27,698 INFO misc.py line 117 726] Train: [14/20][297/510] Data 4.025 (3.658) Batch 32.825 (27.858) Remain 25:19:39 loss: 0.1695 loss_seg: 0.0869 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:30:57,503 INFO misc.py line 117 726] Train: [14/20][298/510] Data 5.211 (3.664) Batch 29.805 (27.865) Remain 25:19:33 loss: 0.2671 loss_seg: 0.1726 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:31:22,334 INFO misc.py line 117 726] Train: [14/20][299/510] Data 3.647 (3.664) Batch 24.831 (27.855) Remain 25:18:32 loss: 0.2764 loss_seg: 0.1775 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:31:52,114 INFO misc.py line 117 726] Train: [14/20][300/510] Data 3.138 (3.662) Batch 29.781 (27.861) Remain 25:18:25 loss: 0.1714 loss_seg: 0.0900 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:31:52,115 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 23:32:23,653 INFO misc.py line 117 726] Train: [14/20][301/510] Data 3.418 (3.661) Batch 31.539 (27.873) Remain 25:18:38 loss: 0.2133 loss_seg: 0.1179 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:32:57,135 INFO misc.py line 117 726] Train: [14/20][302/510] Data 5.542 (3.667) Batch 33.482 (27.892) Remain 25:19:11 loss: 0.2709 loss_seg: 0.1701 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:33:24,410 INFO misc.py line 117 726] Train: [14/20][303/510] Data 4.047 (3.669) Batch 27.275 (27.890) Remain 25:18:36 loss: 0.2209 loss_seg: 0.1328 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:33:57,302 INFO misc.py line 117 726] Train: [14/20][304/510] Data 4.156 (3.670) Batch 32.892 (27.907) Remain 25:19:03 loss: 0.2462 loss_seg: 0.1482 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:34:27,658 INFO misc.py line 117 726] Train: [14/20][305/510] Data 4.023 (3.671) Batch 30.356 (27.915) Remain 25:19:01 loss: 0.2780 loss_seg: 0.1814 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:34:56,778 INFO misc.py line 117 726] Train: [14/20][306/510] Data 4.708 (3.675) Batch 29.120 (27.919) Remain 25:18:46 loss: 0.1950 loss_seg: 0.1029 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0427 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:35:25,922 INFO misc.py line 117 726] Train: [14/20][307/510] Data 2.791 (3.672) Batch 29.144 (27.923) Remain 25:18:32 loss: 0.2906 loss_seg: 0.1987 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:35:53,266 INFO misc.py line 117 726] Train: [14/20][308/510] Data 3.111 (3.670) Batch 27.344 (27.921) Remain 25:17:57 loss: 0.1888 loss_seg: 0.1043 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:36:15,577 INFO misc.py line 117 726] Train: [14/20][309/510] Data 2.610 (3.667) Batch 22.311 (27.903) Remain 25:16:30 loss: 0.2982 loss_seg: 0.1969 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:36:44,265 INFO misc.py line 117 726] Train: [14/20][310/510] Data 3.606 (3.666) Batch 28.688 (27.905) Remain 25:16:10 loss: 0.2731 loss_seg: 0.1735 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:37:08,280 INFO misc.py line 117 726] Train: [14/20][311/510] Data 3.071 (3.664) Batch 24.015 (27.892) Remain 25:15:01 loss: 0.1996 loss_seg: 0.1078 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:37:41,216 INFO misc.py line 117 726] Train: [14/20][312/510] Data 4.186 (3.666) Batch 32.937 (27.909) Remain 25:15:26 loss: 0.2324 loss_seg: 0.1418 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:38:23,635 INFO misc.py line 117 726] Train: [14/20][313/510] Data 10.362 (3.688) Batch 42.418 (27.956) Remain 25:17:31 loss: 0.2365 loss_seg: 0.1454 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:38:54,949 INFO misc.py line 117 726] Train: [14/20][314/510] Data 4.494 (3.690) Batch 31.314 (27.966) Remain 25:17:38 loss: 0.2367 loss_seg: 0.1457 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:39:14,969 INFO misc.py line 117 726] Train: [14/20][315/510] Data 3.392 (3.689) Batch 20.020 (27.941) Remain 25:15:47 loss: 0.2024 loss_seg: 0.1109 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:39:39,346 INFO misc.py line 117 726] Train: [14/20][316/510] Data 2.853 (3.687) Batch 24.377 (27.930) Remain 25:14:42 loss: 0.2129 loss_seg: 0.1226 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:40:08,396 INFO misc.py line 117 726] Train: [14/20][317/510] Data 3.387 (3.686) Batch 29.050 (27.933) Remain 25:14:26 loss: 0.3344 loss_seg: 0.2224 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:40:50,539 INFO misc.py line 117 726] Train: [14/20][318/510] Data 12.542 (3.714) Batch 42.143 (27.978) Remain 25:16:25 loss: 0.7043 loss_seg: 0.5070 loss_superpoint_edge: 0.1303 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:41:20,879 INFO misc.py line 117 726] Train: [14/20][319/510] Data 3.636 (3.714) Batch 30.340 (27.986) Remain 25:16:21 loss: 0.1943 loss_seg: 0.1093 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:41:52,878 INFO misc.py line 117 726] Train: [14/20][320/510] Data 3.922 (3.714) Batch 32.000 (27.998) Remain 25:16:34 loss: 0.2059 loss_seg: 0.1153 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:42:28,361 INFO misc.py line 117 726] Train: [14/20][321/510] Data 6.193 (3.722) Batch 35.483 (28.022) Remain 25:17:23 loss: 0.2683 loss_seg: 0.1718 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:42:52,278 INFO misc.py line 117 726] Train: [14/20][322/510] Data 2.389 (3.718) Batch 23.918 (28.009) Remain 25:16:13 loss: 0.2169 loss_seg: 0.1272 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:43:22,685 INFO misc.py line 117 726] Train: [14/20][323/510] Data 3.208 (3.716) Batch 30.406 (28.017) Remain 25:16:09 loss: 0.2197 loss_seg: 0.1277 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:43:45,799 INFO misc.py line 117 726] Train: [14/20][324/510] Data 2.457 (3.712) Batch 23.114 (28.001) Remain 25:14:52 loss: 0.2394 loss_seg: 0.1385 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:44:15,449 INFO misc.py line 117 726] Train: [14/20][325/510] Data 3.274 (3.711) Batch 29.651 (28.006) Remain 25:14:40 loss: 0.2665 loss_seg: 0.1689 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:44:37,091 INFO misc.py line 117 726] Train: [14/20][326/510] Data 2.564 (3.707) Batch 21.642 (27.987) Remain 25:13:08 loss: 0.2487 loss_seg: 0.1490 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:45:07,903 INFO misc.py line 117 726] Train: [14/20][327/510] Data 3.664 (3.707) Batch 30.812 (27.995) Remain 25:13:09 loss: 0.2321 loss_seg: 0.1425 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:45:49,075 INFO misc.py line 117 726] Train: [14/20][328/510] Data 10.705 (3.729) Batch 41.171 (28.036) Remain 25:14:52 loss: 0.2423 loss_seg: 0.1552 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:46:15,067 INFO misc.py line 117 726] Train: [14/20][329/510] Data 2.646 (3.725) Batch 25.993 (28.030) Remain 25:14:04 loss: 0.2855 loss_seg: 0.1826 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:46:37,120 INFO misc.py line 117 726] Train: [14/20][330/510] Data 3.128 (3.724) Batch 22.053 (28.011) Remain 25:12:36 loss: 0.2703 loss_seg: 0.1814 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:47:04,619 INFO misc.py line 117 726] Train: [14/20][331/510] Data 2.311 (3.719) Batch 27.499 (28.010) Remain 25:12:03 loss: 0.2251 loss_seg: 0.1326 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:47:28,477 INFO misc.py line 117 726] Train: [14/20][332/510] Data 3.728 (3.719) Batch 23.858 (27.997) Remain 25:10:55 loss: 0.2702 loss_seg: 0.1799 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:47:48,594 INFO misc.py line 117 726] Train: [14/20][333/510] Data 3.054 (3.717) Batch 20.117 (27.973) Remain 25:09:09 loss: 0.1754 loss_seg: 0.0891 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:48:16,854 INFO misc.py line 117 726] Train: [14/20][334/510] Data 3.279 (3.716) Batch 28.261 (27.974) Remain 25:08:44 loss: 0.2995 loss_seg: 0.1953 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:48:46,147 INFO misc.py line 117 726] Train: [14/20][335/510] Data 3.460 (3.715) Batch 29.292 (27.978) Remain 25:08:29 loss: 0.2228 loss_seg: 0.1340 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:49:20,370 INFO misc.py line 117 726] Train: [14/20][336/510] Data 4.240 (3.717) Batch 34.223 (27.997) Remain 25:09:02 loss: 0.2381 loss_seg: 0.1448 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:49:53,215 INFO misc.py line 117 726] Train: [14/20][337/510] Data 3.913 (3.717) Batch 32.846 (28.011) Remain 25:09:21 loss: 0.2590 loss_seg: 0.1604 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:50:16,780 INFO misc.py line 117 726] Train: [14/20][338/510] Data 1.975 (3.712) Batch 23.565 (27.998) Remain 25:08:10 loss: 0.2948 loss_seg: 0.1854 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:50:50,473 INFO misc.py line 117 726] Train: [14/20][339/510] Data 8.499 (3.726) Batch 33.693 (28.015) Remain 25:08:36 loss: 0.2493 loss_seg: 0.1522 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0449 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:51:24,560 INFO misc.py line 117 726] Train: [14/20][340/510] Data 4.023 (3.727) Batch 34.087 (28.033) Remain 25:09:07 loss: 0.2258 loss_seg: 0.1365 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:51:54,820 INFO misc.py line 117 726] Train: [14/20][341/510] Data 4.423 (3.729) Batch 30.260 (28.040) Remain 25:09:00 loss: 0.1991 loss_seg: 0.1114 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:52:28,407 INFO misc.py line 117 726] Train: [14/20][342/510] Data 4.918 (3.733) Batch 33.587 (28.056) Remain 25:09:25 loss: 0.2304 loss_seg: 0.1348 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00001 [2026-06-11 23:52:57,528 INFO misc.py line 117 726] Train: [14/20][343/510] Data 6.137 (3.740) Batch 29.121 (28.059) Remain 25:09:07 loss: 0.2834 loss_seg: 0.1838 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:53:26,695 INFO misc.py line 117 726] Train: [14/20][344/510] Data 3.392 (3.739) Batch 29.168 (28.062) Remain 25:08:49 loss: 0.2337 loss_seg: 0.1441 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:53:53,617 INFO misc.py line 117 726] Train: [14/20][345/510] Data 2.844 (3.736) Batch 26.922 (28.059) Remain 25:08:10 loss: 0.3392 loss_seg: 0.2388 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:54:20,449 INFO misc.py line 117 726] Train: [14/20][346/510] Data 3.715 (3.736) Batch 26.832 (28.056) Remain 25:07:31 loss: 0.3280 loss_seg: 0.2358 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:54:56,842 INFO misc.py line 117 726] Train: [14/20][347/510] Data 4.399 (3.738) Batch 36.393 (28.080) Remain 25:08:21 loss: 0.3022 loss_seg: 0.1950 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:55:24,708 INFO misc.py line 117 726] Train: [14/20][348/510] Data 4.326 (3.740) Batch 27.867 (28.079) Remain 25:07:51 loss: 0.2458 loss_seg: 0.1488 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:55:55,433 INFO misc.py line 117 726] Train: [14/20][349/510] Data 3.439 (3.739) Batch 30.725 (28.087) Remain 25:07:47 loss: 0.2153 loss_seg: 0.1255 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:56:26,590 INFO misc.py line 117 726] Train: [14/20][350/510] Data 4.801 (3.742) Batch 31.157 (28.096) Remain 25:07:48 loss: 0.2378 loss_seg: 0.1474 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:56:26,593 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-11 23:56:54,808 INFO misc.py line 117 726] Train: [14/20][351/510] Data 5.818 (3.748) Batch 28.218 (28.096) Remain 25:07:21 loss: 0.1717 loss_seg: 0.0872 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:57:19,434 INFO misc.py line 117 726] Train: [14/20][352/510] Data 3.180 (3.746) Batch 24.626 (28.086) Remain 25:06:21 loss: 0.2758 loss_seg: 0.1766 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:57:47,799 INFO misc.py line 117 726] Train: [14/20][353/510] Data 3.364 (3.745) Batch 28.366 (28.087) Remain 25:05:55 loss: 0.2457 loss_seg: 0.1529 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:58:12,745 INFO misc.py line 117 726] Train: [14/20][354/510] Data 2.465 (3.742) Batch 24.946 (28.078) Remain 25:04:58 loss: 0.2665 loss_seg: 0.1667 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:58:41,377 INFO misc.py line 117 726] Train: [14/20][355/510] Data 2.668 (3.739) Batch 28.631 (28.080) Remain 25:04:35 loss: 0.2078 loss_seg: 0.1188 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:59:13,485 INFO misc.py line 117 726] Train: [14/20][356/510] Data 5.884 (3.745) Batch 32.108 (28.091) Remain 25:04:44 loss: 0.2087 loss_seg: 0.1213 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-11 23:59:44,741 INFO misc.py line 117 726] Train: [14/20][357/510] Data 6.110 (3.751) Batch 31.256 (28.100) Remain 25:04:44 loss: 0.2412 loss_seg: 0.1472 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:00:02,621 INFO misc.py line 117 726] Train: [14/20][358/510] Data 2.132 (3.747) Batch 17.881 (28.071) Remain 25:02:44 loss: 0.2263 loss_seg: 0.1310 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:00:37,108 INFO misc.py line 117 726] Train: [14/20][359/510] Data 6.013 (3.753) Batch 34.487 (28.089) Remain 25:03:14 loss: 0.2398 loss_seg: 0.1436 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:01:08,753 INFO misc.py line 117 726] Train: [14/20][360/510] Data 4.055 (3.754) Batch 31.645 (28.099) Remain 25:03:17 loss: 0.2078 loss_seg: 0.1182 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:01:33,463 INFO misc.py line 117 726] Train: [14/20][361/510] Data 2.385 (3.750) Batch 24.710 (28.090) Remain 25:02:19 loss: 0.1817 loss_seg: 0.0952 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:02:04,323 INFO misc.py line 117 726] Train: [14/20][362/510] Data 4.496 (3.752) Batch 30.859 (28.097) Remain 25:02:16 loss: 0.2157 loss_seg: 0.1289 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:02:28,541 INFO misc.py line 117 726] Train: [14/20][363/510] Data 3.629 (3.752) Batch 24.218 (28.087) Remain 25:01:13 loss: 0.3023 loss_seg: 0.1910 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:03:00,001 INFO misc.py line 117 726] Train: [14/20][364/510] Data 4.245 (3.753) Batch 31.460 (28.096) Remain 25:01:15 loss: 0.2496 loss_seg: 0.1570 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:03:21,941 INFO misc.py line 117 726] Train: [14/20][365/510] Data 2.433 (3.750) Batch 21.940 (28.079) Remain 24:59:52 loss: 0.2334 loss_seg: 0.1376 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:03:51,362 INFO misc.py line 117 726] Train: [14/20][366/510] Data 3.504 (3.749) Batch 29.421 (28.083) Remain 24:59:36 loss: 0.2353 loss_seg: 0.1445 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:04:19,544 INFO misc.py line 117 726] Train: [14/20][367/510] Data 3.065 (3.747) Batch 28.182 (28.083) Remain 24:59:09 loss: 0.2441 loss_seg: 0.1475 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:04:45,993 INFO misc.py line 117 726] Train: [14/20][368/510] Data 3.342 (3.746) Batch 26.449 (28.078) Remain 24:58:26 loss: 0.2326 loss_seg: 0.1358 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:05:25,324 INFO misc.py line 117 726] Train: [14/20][369/510] Data 7.404 (3.756) Batch 39.331 (28.109) Remain 24:59:37 loss: 0.3348 loss_seg: 0.2351 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:05:49,049 INFO misc.py line 117 726] Train: [14/20][370/510] Data 2.922 (3.754) Batch 23.725 (28.097) Remain 24:58:30 loss: 0.3043 loss_seg: 0.2070 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:06:20,879 INFO misc.py line 117 726] Train: [14/20][371/510] Data 4.104 (3.755) Batch 31.831 (28.107) Remain 24:58:35 loss: 0.3033 loss_seg: 0.2118 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:06:42,702 INFO misc.py line 117 726] Train: [14/20][372/510] Data 2.310 (3.751) Batch 21.822 (28.090) Remain 24:57:12 loss: 0.2339 loss_seg: 0.1432 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:07:10,828 INFO misc.py line 117 726] Train: [14/20][373/510] Data 2.722 (3.748) Batch 28.127 (28.090) Remain 24:56:44 loss: 0.2888 loss_seg: 0.1848 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:07:45,481 INFO misc.py line 117 726] Train: [14/20][374/510] Data 6.057 (3.754) Batch 34.653 (28.108) Remain 24:57:13 loss: 0.2924 loss_seg: 0.1871 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:08:03,536 INFO misc.py line 117 726] Train: [14/20][375/510] Data 2.247 (3.750) Batch 18.055 (28.081) Remain 24:55:18 loss: 0.2572 loss_seg: 0.1574 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:08:39,614 INFO misc.py line 117 726] Train: [14/20][376/510] Data 3.787 (3.750) Batch 36.079 (28.102) Remain 24:55:59 loss: 0.2521 loss_seg: 0.1510 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:09:14,087 INFO misc.py line 117 726] Train: [14/20][377/510] Data 5.289 (3.754) Batch 34.473 (28.120) Remain 24:56:25 loss: 0.3756 loss_seg: 0.2681 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0342 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:09:36,342 INFO misc.py line 117 726] Train: [14/20][378/510] Data 2.971 (3.752) Batch 22.255 (28.104) Remain 24:55:07 loss: 0.3341 loss_seg: 0.2351 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:10:01,700 INFO misc.py line 117 726] Train: [14/20][379/510] Data 2.714 (3.750) Batch 25.358 (28.097) Remain 24:54:16 loss: 0.2497 loss_seg: 0.1592 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:10:36,296 INFO misc.py line 117 726] Train: [14/20][380/510] Data 3.238 (3.748) Batch 34.597 (28.114) Remain 24:54:43 loss: 0.1983 loss_seg: 0.1130 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:11:05,458 INFO misc.py line 117 726] Train: [14/20][381/510] Data 3.187 (3.747) Batch 29.162 (28.117) Remain 24:54:23 loss: 0.2055 loss_seg: 0.1170 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:11:44,740 INFO misc.py line 117 726] Train: [14/20][382/510] Data 5.115 (3.750) Batch 39.282 (28.146) Remain 24:55:29 loss: 0.2794 loss_seg: 0.1784 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:12:14,920 INFO misc.py line 117 726] Train: [14/20][383/510] Data 2.977 (3.748) Batch 30.179 (28.151) Remain 24:55:18 loss: 0.2264 loss_seg: 0.1355 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:12:52,659 INFO misc.py line 117 726] Train: [14/20][384/510] Data 10.323 (3.766) Batch 37.739 (28.177) Remain 24:56:10 loss: 0.2272 loss_seg: 0.1305 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:13:20,500 INFO misc.py line 117 726] Train: [14/20][385/510] Data 2.448 (3.762) Batch 27.841 (28.176) Remain 24:55:39 loss: 0.2506 loss_seg: 0.1575 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:13:39,652 INFO misc.py line 117 726] Train: [14/20][386/510] Data 2.134 (3.758) Batch 19.152 (28.152) Remain 24:53:56 loss: 0.2923 loss_seg: 0.1851 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:14:08,254 INFO misc.py line 117 726] Train: [14/20][387/510] Data 4.943 (3.761) Batch 28.602 (28.153) Remain 24:53:31 loss: 0.2002 loss_seg: 0.1133 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:14:38,953 INFO misc.py line 117 726] Train: [14/20][388/510] Data 3.136 (3.759) Batch 30.699 (28.160) Remain 24:53:24 loss: 0.2320 loss_seg: 0.1405 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:14:57,032 INFO misc.py line 117 726] Train: [14/20][389/510] Data 2.405 (3.756) Batch 18.079 (28.134) Remain 24:51:33 loss: 0.1987 loss_seg: 0.1092 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:15:17,881 INFO misc.py line 117 726] Train: [14/20][390/510] Data 2.692 (3.753) Batch 20.849 (28.115) Remain 24:50:05 loss: 0.1734 loss_seg: 0.0872 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:15:49,383 INFO misc.py line 117 726] Train: [14/20][391/510] Data 3.505 (3.752) Batch 31.501 (28.124) Remain 24:50:05 loss: 0.2506 loss_seg: 0.1563 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:16:08,740 INFO misc.py line 117 726] Train: [14/20][392/510] Data 2.100 (3.748) Batch 19.357 (28.101) Remain 24:48:25 loss: 0.2160 loss_seg: 0.1230 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:16:30,806 INFO misc.py line 117 726] Train: [14/20][393/510] Data 2.501 (3.745) Batch 22.067 (28.086) Remain 24:47:08 loss: 0.3089 loss_seg: 0.2051 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:16:55,357 INFO misc.py line 117 726] Train: [14/20][394/510] Data 4.439 (3.747) Batch 24.550 (28.077) Remain 24:46:11 loss: 0.2327 loss_seg: 0.1454 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:17:17,469 INFO misc.py line 117 726] Train: [14/20][395/510] Data 2.661 (3.744) Batch 22.113 (28.061) Remain 24:44:55 loss: 0.3110 loss_seg: 0.2043 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:17:47,520 INFO misc.py line 117 726] Train: [14/20][396/510] Data 3.038 (3.742) Batch 30.051 (28.066) Remain 24:44:43 loss: 0.2865 loss_seg: 0.1936 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:18:06,684 INFO misc.py line 117 726] Train: [14/20][397/510] Data 1.881 (3.737) Batch 19.164 (28.044) Remain 24:43:03 loss: 0.2511 loss_seg: 0.1551 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:18:37,258 INFO misc.py line 117 726] Train: [14/20][398/510] Data 5.307 (3.741) Batch 30.574 (28.050) Remain 24:42:55 loss: 0.2215 loss_seg: 0.1343 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:19:02,087 INFO misc.py line 117 726] Train: [14/20][399/510] Data 2.212 (3.738) Batch 24.829 (28.042) Remain 24:42:01 loss: 0.2110 loss_seg: 0.1235 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:19:36,528 INFO misc.py line 117 726] Train: [14/20][400/510] Data 4.092 (3.738) Batch 34.441 (28.058) Remain 24:42:24 loss: 0.2263 loss_seg: 0.1318 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:19:36,528 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 00:20:03,400 INFO misc.py line 117 726] Train: [14/20][401/510] Data 3.744 (3.738) Batch 26.872 (28.055) Remain 24:41:47 loss: 0.1878 loss_seg: 0.1015 loss_superpoint_edge: 0.0142 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:20:30,791 INFO misc.py line 117 726] Train: [14/20][402/510] Data 2.938 (3.736) Batch 27.391 (28.054) Remain 24:41:13 loss: 0.2339 loss_seg: 0.1393 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:20:53,951 INFO misc.py line 117 726] Train: [14/20][403/510] Data 2.561 (3.733) Batch 23.160 (28.041) Remain 24:40:07 loss: 0.2258 loss_seg: 0.1338 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:21:24,558 INFO misc.py line 117 726] Train: [14/20][404/510] Data 3.748 (3.734) Batch 30.607 (28.048) Remain 24:39:59 loss: 0.3559 loss_seg: 0.2622 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:21:55,918 INFO misc.py line 117 726] Train: [14/20][405/510] Data 3.639 (3.733) Batch 31.360 (28.056) Remain 24:39:57 loss: 0.2767 loss_seg: 0.1705 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:22:15,208 INFO misc.py line 117 726] Train: [14/20][406/510] Data 2.260 (3.730) Batch 19.290 (28.034) Remain 24:38:20 loss: 0.2502 loss_seg: 0.1570 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:22:42,146 INFO misc.py line 117 726] Train: [14/20][407/510] Data 2.397 (3.726) Batch 26.938 (28.032) Remain 24:37:43 loss: 0.2261 loss_seg: 0.1384 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:23:05,657 INFO misc.py line 117 726] Train: [14/20][408/510] Data 2.667 (3.724) Batch 23.511 (28.020) Remain 24:36:40 loss: 0.2073 loss_seg: 0.1205 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:23:28,168 INFO misc.py line 117 726] Train: [14/20][409/510] Data 2.557 (3.721) Batch 22.511 (28.007) Remain 24:35:29 loss: 0.2114 loss_seg: 0.1183 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:23:50,931 INFO misc.py line 117 726] Train: [14/20][410/510] Data 2.921 (3.719) Batch 22.763 (27.994) Remain 24:34:20 loss: 0.1943 loss_seg: 0.1061 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:24:23,459 INFO misc.py line 117 726] Train: [14/20][411/510] Data 6.039 (3.725) Batch 32.528 (28.005) Remain 24:34:28 loss: 0.1872 loss_seg: 0.1031 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:24:47,134 INFO misc.py line 117 726] Train: [14/20][412/510] Data 3.125 (3.723) Batch 23.674 (27.994) Remain 24:33:26 loss: 0.2629 loss_seg: 0.1657 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:25:07,571 INFO misc.py line 117 726] Train: [14/20][413/510] Data 2.545 (3.720) Batch 20.438 (27.976) Remain 24:32:00 loss: 0.3309 loss_seg: 0.2337 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:25:32,327 INFO misc.py line 117 726] Train: [14/20][414/510] Data 2.264 (3.717) Batch 24.756 (27.968) Remain 24:31:07 loss: 0.2301 loss_seg: 0.1346 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:26:02,199 INFO misc.py line 117 726] Train: [14/20][415/510] Data 3.073 (3.715) Batch 29.872 (27.973) Remain 24:30:54 loss: 0.2295 loss_seg: 0.1352 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:26:19,751 INFO misc.py line 117 726] Train: [14/20][416/510] Data 2.473 (3.712) Batch 17.552 (27.948) Remain 24:29:06 loss: 0.2951 loss_seg: 0.1940 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:26:46,762 INFO misc.py line 117 726] Train: [14/20][417/510] Data 2.657 (3.710) Batch 27.011 (27.945) Remain 24:28:31 loss: 0.2201 loss_seg: 0.1257 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:27:19,435 INFO misc.py line 117 726] Train: [14/20][418/510] Data 4.260 (3.711) Batch 32.673 (27.957) Remain 24:28:39 loss: 0.2311 loss_seg: 0.1391 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:27:50,538 INFO misc.py line 117 726] Train: [14/20][419/510] Data 3.811 (3.711) Batch 31.103 (27.964) Remain 24:28:35 loss: 0.2240 loss_seg: 0.1338 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:28:23,026 INFO misc.py line 117 726] Train: [14/20][420/510] Data 3.317 (3.710) Batch 32.488 (27.975) Remain 24:28:41 loss: 0.2653 loss_seg: 0.1658 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:28:47,607 INFO misc.py line 117 726] Train: [14/20][421/510] Data 2.766 (3.708) Batch 24.582 (27.967) Remain 24:27:48 loss: 0.2604 loss_seg: 0.1603 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:29:15,945 INFO misc.py line 117 726] Train: [14/20][422/510] Data 3.729 (3.708) Batch 28.338 (27.968) Remain 24:27:22 loss: 0.2223 loss_seg: 0.1345 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:29:50,162 INFO misc.py line 117 726] Train: [14/20][423/510] Data 7.739 (3.718) Batch 34.218 (27.983) Remain 24:27:41 loss: 0.3341 loss_seg: 0.2383 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:30:24,091 INFO misc.py line 117 726] Train: [14/20][424/510] Data 8.609 (3.729) Batch 33.928 (27.997) Remain 24:27:58 loss: 0.3130 loss_seg: 0.2234 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:30:55,560 INFO misc.py line 117 726] Train: [14/20][425/510] Data 3.430 (3.728) Batch 31.469 (28.005) Remain 24:27:56 loss: 0.3107 loss_seg: 0.2052 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:31:17,254 INFO misc.py line 117 726] Train: [14/20][426/510] Data 3.834 (3.729) Batch 21.694 (27.990) Remain 24:26:41 loss: 0.2533 loss_seg: 0.1645 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:31:43,089 INFO misc.py line 117 726] Train: [14/20][427/510] Data 3.337 (3.728) Batch 25.835 (27.985) Remain 24:25:57 loss: 0.3000 loss_seg: 0.1992 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:32:17,700 INFO misc.py line 117 726] Train: [14/20][428/510] Data 6.641 (3.735) Batch 34.611 (28.001) Remain 24:26:18 loss: 0.2273 loss_seg: 0.1352 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:32:49,356 INFO misc.py line 117 726] Train: [14/20][429/510] Data 4.175 (3.736) Batch 31.656 (28.009) Remain 24:26:17 loss: 0.2142 loss_seg: 0.1233 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:33:09,592 INFO misc.py line 117 726] Train: [14/20][430/510] Data 3.417 (3.735) Batch 20.236 (27.991) Remain 24:24:52 loss: 0.2932 loss_seg: 0.1869 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:33:29,906 INFO misc.py line 117 726] Train: [14/20][431/510] Data 2.318 (3.732) Batch 20.313 (27.973) Remain 24:23:27 loss: 0.2004 loss_seg: 0.1136 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:33:48,089 INFO misc.py line 117 726] Train: [14/20][432/510] Data 2.182 (3.728) Batch 18.184 (27.950) Remain 24:21:48 loss: 0.3238 loss_seg: 0.2352 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:34:08,077 INFO misc.py line 117 726] Train: [14/20][433/510] Data 2.479 (3.725) Batch 19.988 (27.932) Remain 24:20:22 loss: 0.2361 loss_seg: 0.1410 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:34:35,303 INFO misc.py line 117 726] Train: [14/20][434/510] Data 3.562 (3.725) Batch 27.226 (27.930) Remain 24:19:49 loss: 0.2203 loss_seg: 0.1284 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:34:56,934 INFO misc.py line 117 726] Train: [14/20][435/510] Data 2.035 (3.721) Batch 21.631 (27.916) Remain 24:18:35 loss: 0.2396 loss_seg: 0.1462 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:35:31,081 INFO misc.py line 117 726] Train: [14/20][436/510] Data 3.966 (3.721) Batch 34.146 (27.930) Remain 24:18:52 loss: 0.2716 loss_seg: 0.1696 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:36:00,589 INFO misc.py line 117 726] Train: [14/20][437/510] Data 5.153 (3.725) Batch 29.509 (27.934) Remain 24:18:36 loss: 0.1935 loss_seg: 0.1058 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:36:23,059 INFO misc.py line 117 726] Train: [14/20][438/510] Data 2.720 (3.722) Batch 22.469 (27.921) Remain 24:17:28 loss: 0.2332 loss_seg: 0.1356 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:36:56,025 INFO misc.py line 117 726] Train: [14/20][439/510] Data 6.108 (3.728) Batch 32.966 (27.933) Remain 24:17:37 loss: 0.2216 loss_seg: 0.1331 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:37:18,916 INFO misc.py line 117 726] Train: [14/20][440/510] Data 2.724 (3.726) Batch 22.891 (27.921) Remain 24:16:33 loss: 0.2220 loss_seg: 0.1314 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:37:54,954 INFO misc.py line 117 726] Train: [14/20][441/510] Data 6.188 (3.731) Batch 36.039 (27.940) Remain 24:17:03 loss: 0.3169 loss_seg: 0.2228 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:38:32,845 INFO misc.py line 117 726] Train: [14/20][442/510] Data 6.733 (3.738) Batch 37.890 (27.962) Remain 24:17:46 loss: 0.2788 loss_seg: 0.1736 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:39:05,455 INFO misc.py line 117 726] Train: [14/20][443/510] Data 3.447 (3.737) Batch 32.610 (27.973) Remain 24:17:51 loss: 0.2682 loss_seg: 0.1801 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:39:31,830 INFO misc.py line 117 726] Train: [14/20][444/510] Data 2.636 (3.735) Batch 26.376 (27.969) Remain 24:17:11 loss: 0.2034 loss_seg: 0.1137 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:39:55,813 INFO misc.py line 117 726] Train: [14/20][445/510] Data 3.205 (3.734) Batch 23.983 (27.960) Remain 24:16:15 loss: 0.3037 loss_seg: 0.2013 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:40:27,388 INFO misc.py line 117 726] Train: [14/20][446/510] Data 2.930 (3.732) Batch 31.575 (27.968) Remain 24:16:13 loss: 0.2457 loss_seg: 0.1469 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:40:55,763 INFO misc.py line 117 726] Train: [14/20][447/510] Data 3.796 (3.732) Batch 28.375 (27.969) Remain 24:15:48 loss: 0.2539 loss_seg: 0.1621 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:41:28,905 INFO misc.py line 117 726] Train: [14/20][448/510] Data 6.101 (3.737) Batch 33.142 (27.981) Remain 24:15:56 loss: 0.2337 loss_seg: 0.1384 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:41:56,404 INFO misc.py line 117 726] Train: [14/20][449/510] Data 3.106 (3.736) Batch 27.499 (27.980) Remain 24:15:25 loss: 0.2092 loss_seg: 0.1204 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:42:38,960 INFO misc.py line 117 726] Train: [14/20][450/510] Data 11.644 (3.754) Batch 42.555 (28.012) Remain 24:16:38 loss: 0.1970 loss_seg: 0.1121 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:42:38,961 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 00:43:06,515 INFO misc.py line 117 726] Train: [14/20][451/510] Data 3.773 (3.754) Batch 27.555 (28.011) Remain 24:16:07 loss: 0.2697 loss_seg: 0.1695 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:43:33,321 INFO misc.py line 117 726] Train: [14/20][452/510] Data 2.897 (3.752) Batch 26.807 (28.009) Remain 24:15:31 loss: 0.2006 loss_seg: 0.1148 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:44:01,753 INFO misc.py line 117 726] Train: [14/20][453/510] Data 3.066 (3.750) Batch 28.432 (28.010) Remain 24:15:06 loss: 0.2237 loss_seg: 0.1329 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:44:32,504 INFO misc.py line 117 726] Train: [14/20][454/510] Data 3.526 (3.750) Batch 30.751 (28.016) Remain 24:14:57 loss: 0.2991 loss_seg: 0.1986 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:45:01,033 INFO misc.py line 117 726] Train: [14/20][455/510] Data 3.384 (3.749) Batch 28.529 (28.017) Remain 24:14:32 loss: 0.2478 loss_seg: 0.1497 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:45:25,623 INFO misc.py line 117 726] Train: [14/20][456/510] Data 4.052 (3.750) Batch 24.589 (28.009) Remain 24:13:41 loss: 0.4466 loss_seg: 0.3420 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:45:52,963 INFO misc.py line 117 726] Train: [14/20][457/510] Data 3.202 (3.748) Batch 27.340 (28.008) Remain 24:13:08 loss: 0.2120 loss_seg: 0.1203 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:46:09,727 INFO misc.py line 117 726] Train: [14/20][458/510] Data 1.646 (3.744) Batch 16.765 (27.983) Remain 24:11:23 loss: 0.2153 loss_seg: 0.1225 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:46:37,721 INFO misc.py line 117 726] Train: [14/20][459/510] Data 8.691 (3.755) Batch 27.994 (27.983) Remain 24:10:55 loss: 0.2546 loss_seg: 0.1573 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:46:57,902 INFO misc.py line 117 726] Train: [14/20][460/510] Data 2.389 (3.752) Batch 20.181 (27.966) Remain 24:09:34 loss: 0.2132 loss_seg: 0.1247 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:47:32,111 INFO misc.py line 117 726] Train: [14/20][461/510] Data 5.080 (3.755) Batch 34.209 (27.980) Remain 24:09:49 loss: 0.2170 loss_seg: 0.1258 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:47:59,388 INFO misc.py line 117 726] Train: [14/20][462/510] Data 2.689 (3.752) Batch 27.277 (27.978) Remain 24:09:16 loss: 0.2302 loss_seg: 0.1363 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:48:24,941 INFO misc.py line 117 726] Train: [14/20][463/510] Data 3.012 (3.751) Batch 25.552 (27.973) Remain 24:08:31 loss: 0.2745 loss_seg: 0.1747 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:49:00,019 INFO misc.py line 117 726] Train: [14/20][464/510] Data 10.867 (3.766) Batch 35.078 (27.988) Remain 24:08:51 loss: 0.1991 loss_seg: 0.1134 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:49:25,695 INFO misc.py line 117 726] Train: [14/20][465/510] Data 2.627 (3.764) Batch 25.677 (27.983) Remain 24:08:08 loss: 0.2136 loss_seg: 0.1267 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:50:04,890 INFO misc.py line 117 726] Train: [14/20][466/510] Data 7.812 (3.772) Batch 39.194 (28.008) Remain 24:08:55 loss: 0.3170 loss_seg: 0.2126 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:50:38,314 INFO misc.py line 117 726] Train: [14/20][467/510] Data 2.738 (3.770) Batch 33.424 (28.019) Remain 24:09:03 loss: 0.2957 loss_seg: 0.1870 loss_superpoint_edge: 0.0427 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:51:03,199 INFO misc.py line 117 726] Train: [14/20][468/510] Data 2.900 (3.768) Batch 24.884 (28.012) Remain 24:08:14 loss: 0.2108 loss_seg: 0.1204 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:51:33,637 INFO misc.py line 117 726] Train: [14/20][469/510] Data 4.677 (3.770) Batch 30.438 (28.018) Remain 24:08:02 loss: 0.2357 loss_seg: 0.1421 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:52:00,957 INFO misc.py line 117 726] Train: [14/20][470/510] Data 3.872 (3.770) Batch 27.320 (28.016) Remain 24:07:30 loss: 0.2761 loss_seg: 0.1780 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:52:24,257 INFO misc.py line 117 726] Train: [14/20][471/510] Data 2.911 (3.769) Batch 23.301 (28.006) Remain 24:06:30 loss: 0.2699 loss_seg: 0.1690 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:53:02,430 INFO misc.py line 117 726] Train: [14/20][472/510] Data 8.514 (3.779) Batch 38.172 (28.028) Remain 24:07:10 loss: 0.2337 loss_seg: 0.1437 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:53:23,232 INFO misc.py line 117 726] Train: [14/20][473/510] Data 2.826 (3.777) Batch 20.802 (28.012) Remain 24:05:54 loss: 0.2504 loss_seg: 0.1594 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:53:51,577 INFO misc.py line 117 726] Train: [14/20][474/510] Data 6.381 (3.782) Batch 28.345 (28.013) Remain 24:05:28 loss: 0.2701 loss_seg: 0.1768 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:54:31,034 INFO misc.py line 117 726] Train: [14/20][475/510] Data 5.013 (3.785) Batch 39.457 (28.037) Remain 24:06:15 loss: 0.2789 loss_seg: 0.1786 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:55:01,585 INFO misc.py line 117 726] Train: [14/20][476/510] Data 3.135 (3.783) Batch 30.551 (28.043) Remain 24:06:04 loss: 0.2324 loss_seg: 0.1429 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:55:19,679 INFO misc.py line 117 726] Train: [14/20][477/510] Data 1.537 (3.779) Batch 18.094 (28.022) Remain 24:04:31 loss: 0.2282 loss_seg: 0.1332 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:55:44,099 INFO misc.py line 117 726] Train: [14/20][478/510] Data 2.591 (3.776) Batch 24.420 (28.014) Remain 24:03:39 loss: 0.1958 loss_seg: 0.1071 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:56:28,435 INFO misc.py line 117 726] Train: [14/20][479/510] Data 10.785 (3.791) Batch 44.336 (28.048) Remain 24:04:57 loss: 0.1748 loss_seg: 0.0894 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:56:56,488 INFO misc.py line 117 726] Train: [14/20][480/510] Data 1.683 (3.786) Batch 28.053 (28.048) Remain 24:04:29 loss: 0.3225 loss_seg: 0.2270 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:57:20,633 INFO misc.py line 117 726] Train: [14/20][481/510] Data 2.663 (3.784) Batch 24.145 (28.040) Remain 24:03:36 loss: 0.2171 loss_seg: 0.1268 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:57:43,539 INFO misc.py line 117 726] Train: [14/20][482/510] Data 2.344 (3.781) Batch 22.906 (28.030) Remain 24:02:35 loss: 0.2194 loss_seg: 0.1293 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:58:05,387 INFO misc.py line 117 726] Train: [14/20][483/510] Data 2.547 (3.779) Batch 21.848 (28.017) Remain 24:01:27 loss: 0.1996 loss_seg: 0.1096 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:58:29,782 INFO misc.py line 117 726] Train: [14/20][484/510] Data 2.424 (3.776) Batch 24.396 (28.009) Remain 24:00:36 loss: 0.5146 loss_seg: 0.4139 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:58:49,005 INFO misc.py line 117 726] Train: [14/20][485/510] Data 2.457 (3.773) Batch 19.223 (27.991) Remain 23:59:11 loss: 0.2367 loss_seg: 0.1403 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:59:17,728 INFO misc.py line 117 726] Train: [14/20][486/510] Data 2.618 (3.771) Batch 28.722 (27.992) Remain 23:58:48 loss: 0.2123 loss_seg: 0.1228 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 00:59:54,423 INFO misc.py line 117 726] Train: [14/20][487/510] Data 11.567 (3.787) Batch 36.695 (28.010) Remain 23:59:16 loss: 0.2511 loss_seg: 0.1525 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0430 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:00:20,480 INFO misc.py line 117 726] Train: [14/20][488/510] Data 2.698 (3.784) Batch 26.057 (28.006) Remain 23:58:35 loss: 0.2265 loss_seg: 0.1346 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:00:52,923 INFO misc.py line 117 726] Train: [14/20][489/510] Data 6.970 (3.791) Batch 32.443 (28.015) Remain 23:58:35 loss: 0.1975 loss_seg: 0.1077 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:01:23,632 INFO misc.py line 117 726] Train: [14/20][490/510] Data 3.621 (3.791) Batch 30.709 (28.021) Remain 23:58:24 loss: 0.2469 loss_seg: 0.1496 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:01:51,589 INFO misc.py line 117 726] Train: [14/20][491/510] Data 4.464 (3.792) Batch 27.957 (28.021) Remain 23:57:56 loss: 0.2613 loss_seg: 0.1687 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:02:09,916 INFO misc.py line 117 726] Train: [14/20][492/510] Data 1.876 (3.788) Batch 18.327 (28.001) Remain 23:56:27 loss: 0.2031 loss_seg: 0.1135 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:02:32,406 INFO misc.py line 117 726] Train: [14/20][493/510] Data 2.849 (3.786) Batch 22.490 (27.990) Remain 23:55:24 loss: 0.2823 loss_seg: 0.1753 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:03:06,537 INFO misc.py line 117 726] Train: [14/20][494/510] Data 5.619 (3.790) Batch 34.131 (28.002) Remain 23:55:35 loss: 0.2215 loss_seg: 0.1291 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:03:33,994 INFO misc.py line 117 726] Train: [14/20][495/510] Data 3.030 (3.788) Batch 27.458 (28.001) Remain 23:55:03 loss: 0.2708 loss_seg: 0.1676 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:04:13,979 INFO misc.py line 117 726] Train: [14/20][496/510] Data 5.994 (3.793) Batch 39.984 (28.026) Remain 23:55:50 loss: 0.2140 loss_seg: 0.1264 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:04:42,849 INFO misc.py line 117 726] Train: [14/20][497/510] Data 2.344 (3.790) Batch 28.870 (28.027) Remain 23:55:27 loss: 0.2610 loss_seg: 0.1638 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:05:16,573 INFO misc.py line 117 726] Train: [14/20][498/510] Data 4.006 (3.790) Batch 33.724 (28.039) Remain 23:55:35 loss: 0.2828 loss_seg: 0.1818 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:05:42,396 INFO misc.py line 117 726] Train: [14/20][499/510] Data 3.448 (3.790) Batch 25.822 (28.034) Remain 23:54:53 loss: 0.3399 loss_seg: 0.2429 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:06:10,900 INFO misc.py line 117 726] Train: [14/20][500/510] Data 3.460 (3.789) Batch 28.504 (28.035) Remain 23:54:28 loss: 0.2175 loss_seg: 0.1251 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:06:10,900 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 01:06:32,234 INFO misc.py line 117 726] Train: [14/20][501/510] Data 2.998 (3.787) Batch 21.335 (28.022) Remain 23:53:18 loss: 0.2415 loss_seg: 0.1451 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:06:59,985 INFO misc.py line 117 726] Train: [14/20][502/510] Data 5.519 (3.791) Batch 27.750 (28.021) Remain 23:52:49 loss: 0.5641 loss_seg: 0.4544 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:07:30,613 INFO misc.py line 117 726] Train: [14/20][503/510] Data 3.918 (3.791) Batch 30.628 (28.026) Remain 23:52:37 loss: 0.2140 loss_seg: 0.1234 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:08:03,488 INFO misc.py line 117 726] Train: [14/20][504/510] Data 2.692 (3.789) Batch 32.875 (28.036) Remain 23:52:38 loss: 0.1752 loss_seg: 0.0918 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:08:37,243 INFO misc.py line 117 726] Train: [14/20][505/510] Data 3.762 (3.789) Batch 33.755 (28.048) Remain 23:52:45 loss: 0.2931 loss_seg: 0.1921 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:08:57,411 INFO misc.py line 117 726] Train: [14/20][506/510] Data 1.771 (3.785) Batch 20.168 (28.032) Remain 23:51:29 loss: 0.2097 loss_seg: 0.1178 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:09:27,542 INFO misc.py line 117 726] Train: [14/20][507/510] Data 3.207 (3.784) Batch 30.131 (28.036) Remain 23:51:14 loss: 0.1964 loss_seg: 0.1118 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:09:46,807 INFO misc.py line 117 726] Train: [14/20][508/510] Data 2.844 (3.782) Batch 19.266 (28.019) Remain 23:49:53 loss: 0.2736 loss_seg: 0.1837 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:10:12,908 INFO misc.py line 117 726] Train: [14/20][509/510] Data 3.540 (3.781) Batch 26.101 (28.015) Remain 23:49:13 loss: 0.2841 loss_seg: 0.1846 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:10:59,342 INFO misc.py line 117 726] Train: [14/20][510/510] Data 11.914 (3.797) Batch 46.434 (28.051) Remain 23:50:36 loss: 0.2009 loss_seg: 0.1054 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:10:59,343 INFO misc.py line 147 726] Train result: loss: 0.2490 loss_seg: 0.1540 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 [2026-06-12 01:10:59,344 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-12 01:11:14,869 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7238 [2026-06-12 01:11:30,728 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7330 [2026-06-12 01:12:44,977 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8853 [2026-06-12 01:13:24,924 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9962 [2026-06-12 01:13:44,274 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0689 [2026-06-12 01:14:20,312 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2112 [2026-06-12 01:15:06,707 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1391 [2026-06-12 01:15:22,244 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.1753 [2026-06-12 01:15:40,007 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.0203 [2026-06-12 01:15:58,509 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4760 [2026-06-12 01:16:14,219 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5117 [2026-06-12 01:16:35,620 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.6615 [2026-06-12 01:17:01,340 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9827 [2026-06-12 01:17:12,570 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6983 [2026-06-12 01:17:43,808 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.1199 [2026-06-12 01:18:09,810 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3676 [2026-06-12 01:18:36,560 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3935 [2026-06-12 01:19:19,367 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1503 [2026-06-12 01:19:40,219 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4062 [2026-06-12 01:19:56,573 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8802 [2026-06-12 01:20:27,547 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.8963 [2026-06-12 01:20:43,738 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4703 [2026-06-12 01:21:05,475 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3487 [2026-06-12 01:21:26,930 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8194 [2026-06-12 01:21:40,369 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6339 [2026-06-12 01:22:07,945 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5285 [2026-06-12 01:22:49,170 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1770 [2026-06-12 01:23:06,399 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5182 [2026-06-12 01:23:25,005 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4326 [2026-06-12 01:23:41,869 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3986 [2026-06-12 01:24:06,845 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1884 [2026-06-12 01:24:24,924 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5274 [2026-06-12 01:24:42,278 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.0432 [2026-06-12 01:25:06,795 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7689 [2026-06-12 01:25:06,887 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6711/0.7424/0.8974. [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9281/0.9604 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9766/0.9878 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8401/0.9706 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0022/0.0162 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3303/0.3887 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6023/0.6248 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6113/0.6995 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7962/0.9043 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9140/0.9572 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6748/0.7304 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7601/0.8445 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6875/0.8538 [2026-06-12 01:25:06,888 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.6016/0.7126 [2026-06-12 01:25:06,888 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-12 01:25:06,889 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-12 01:25:06,889 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 01:25:42,598 INFO misc.py line 117 726] Train: [15/20][1/510] Data 6.487 (6.487) Batch 34.171 (34.171) Remain 29:02:09 loss: 0.2612 loss_seg: 0.1690 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:26:10,707 INFO misc.py line 117 726] Train: [15/20][2/510] Data 3.309 (3.309) Batch 28.109 (28.109) Remain 23:52:37 loss: 0.2398 loss_seg: 0.1469 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:26:38,960 INFO misc.py line 117 726] Train: [15/20][3/510] Data 3.254 (3.254) Batch 28.254 (28.254) Remain 23:59:31 loss: 0.3287 loss_seg: 0.2242 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:27:05,010 INFO misc.py line 117 726] Train: [15/20][4/510] Data 3.003 (3.003) Batch 26.050 (26.050) Remain 22:06:49 loss: 0.1876 loss_seg: 0.1005 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:27:28,720 INFO misc.py line 117 726] Train: [15/20][5/510] Data 2.456 (2.730) Batch 23.709 (24.880) Remain 21:06:47 loss: 0.1685 loss_seg: 0.0830 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:27:58,429 INFO misc.py line 117 726] Train: [15/20][6/510] Data 4.066 (3.175) Batch 29.709 (26.489) Remain 22:28:18 loss: 0.2148 loss_seg: 0.1249 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:28:20,238 INFO misc.py line 117 726] Train: [15/20][7/510] Data 2.067 (2.898) Batch 21.810 (25.320) Remain 21:28:20 loss: 0.1966 loss_seg: 0.1060 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:28:53,133 INFO misc.py line 117 726] Train: [15/20][8/510] Data 3.456 (3.010) Batch 32.894 (26.834) Remain 22:44:58 loss: 0.1999 loss_seg: 0.1152 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:29:17,044 INFO misc.py line 117 726] Train: [15/20][9/510] Data 2.571 (2.936) Batch 23.911 (26.347) Remain 22:19:45 loss: 0.2436 loss_seg: 0.1443 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:29:44,818 INFO misc.py line 117 726] Train: [15/20][10/510] Data 5.132 (3.250) Batch 27.774 (26.551) Remain 22:29:40 loss: 0.2528 loss_seg: 0.1536 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:30:10,251 INFO misc.py line 117 726] Train: [15/20][11/510] Data 2.663 (3.177) Batch 25.433 (26.411) Remain 22:22:08 loss: 0.2463 loss_seg: 0.1546 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:30:48,274 INFO misc.py line 117 726] Train: [15/20][12/510] Data 6.623 (3.560) Batch 38.023 (27.701) Remain 23:27:14 loss: 0.2514 loss_seg: 0.1594 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:31:15,241 INFO misc.py line 117 726] Train: [15/20][13/510] Data 2.464 (3.450) Batch 26.967 (27.628) Remain 23:23:02 loss: 0.2286 loss_seg: 0.1396 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:31:39,076 INFO misc.py line 117 726] Train: [15/20][14/510] Data 2.290 (3.345) Batch 23.835 (27.283) Remain 23:05:04 loss: 0.2823 loss_seg: 0.1786 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:32:03,854 INFO misc.py line 117 726] Train: [15/20][15/510] Data 2.940 (3.311) Batch 24.779 (27.075) Remain 22:54:01 loss: 0.2308 loss_seg: 0.1381 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:32:33,404 INFO misc.py line 117 726] Train: [15/20][16/510] Data 7.139 (3.605) Batch 29.549 (27.265) Remain 23:03:14 loss: 0.2993 loss_seg: 0.1995 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:33:03,810 INFO misc.py line 117 726] Train: [15/20][17/510] Data 4.054 (3.637) Batch 30.407 (27.489) Remain 23:14:09 loss: 0.1991 loss_seg: 0.1138 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:33:30,608 INFO misc.py line 117 726] Train: [15/20][18/510] Data 2.631 (3.570) Batch 26.798 (27.443) Remain 23:11:22 loss: 0.2809 loss_seg: 0.1816 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:33:55,992 INFO misc.py line 117 726] Train: [15/20][19/510] Data 3.530 (3.568) Batch 25.384 (27.314) Remain 23:04:23 loss: 0.2882 loss_seg: 0.1834 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:34:17,655 INFO misc.py line 117 726] Train: [15/20][20/510] Data 2.886 (3.528) Batch 21.663 (26.982) Remain 22:47:05 loss: 0.1970 loss_seg: 0.1102 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:34:40,322 INFO misc.py line 117 726] Train: [15/20][21/510] Data 1.849 (3.434) Batch 22.667 (26.742) Remain 22:34:29 loss: 0.2263 loss_seg: 0.1362 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:35:01,734 INFO misc.py line 117 726] Train: [15/20][22/510] Data 2.554 (3.388) Batch 21.412 (26.462) Remain 22:19:50 loss: 0.2098 loss_seg: 0.1183 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:35:32,948 INFO misc.py line 117 726] Train: [15/20][23/510] Data 3.263 (3.382) Batch 31.215 (26.699) Remain 22:31:26 loss: 0.2342 loss_seg: 0.1367 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:35:56,075 INFO misc.py line 117 726] Train: [15/20][24/510] Data 2.685 (3.349) Batch 23.127 (26.529) Remain 22:22:22 loss: 0.2970 loss_seg: 0.2051 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:36:31,141 INFO misc.py line 117 726] Train: [15/20][25/510] Data 3.947 (3.376) Batch 35.066 (26.917) Remain 22:41:34 loss: 0.2063 loss_seg: 0.1165 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:36:53,638 INFO misc.py line 117 726] Train: [15/20][26/510] Data 2.970 (3.358) Batch 22.497 (26.725) Remain 22:31:24 loss: 0.3327 loss_seg: 0.2252 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:37:15,651 INFO misc.py line 117 726] Train: [15/20][27/510] Data 1.959 (3.300) Batch 22.013 (26.529) Remain 22:21:01 loss: 0.2499 loss_seg: 0.1463 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:37:48,315 INFO misc.py line 117 726] Train: [15/20][28/510] Data 3.505 (3.308) Batch 32.664 (26.774) Remain 22:32:59 loss: 0.2277 loss_seg: 0.1312 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:38:14,225 INFO misc.py line 117 726] Train: [15/20][29/510] Data 2.807 (3.289) Batch 25.911 (26.741) Remain 22:30:51 loss: 0.2868 loss_seg: 0.1917 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:38:50,592 INFO misc.py line 117 726] Train: [15/20][30/510] Data 4.413 (3.331) Batch 36.367 (27.097) Remain 22:48:25 loss: 0.2499 loss_seg: 0.1531 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:39:18,821 INFO misc.py line 117 726] Train: [15/20][31/510] Data 3.971 (3.353) Batch 28.229 (27.138) Remain 22:50:00 loss: 0.2949 loss_seg: 0.1839 loss_superpoint_edge: 0.0434 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:39:48,700 INFO misc.py line 117 726] Train: [15/20][32/510] Data 3.400 (3.355) Batch 29.879 (27.232) Remain 22:54:19 loss: 0.2003 loss_seg: 0.1134 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:40:15,671 INFO misc.py line 117 726] Train: [15/20][33/510] Data 3.388 (3.356) Batch 26.971 (27.224) Remain 22:53:26 loss: 0.2468 loss_seg: 0.1493 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:40:41,676 INFO misc.py line 117 726] Train: [15/20][34/510] Data 2.770 (3.337) Batch 26.006 (27.184) Remain 22:50:59 loss: 0.1915 loss_seg: 0.1067 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:41:05,371 INFO misc.py line 117 726] Train: [15/20][35/510] Data 2.177 (3.301) Batch 23.694 (27.075) Remain 22:45:02 loss: 0.2441 loss_seg: 0.1398 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:41:31,055 INFO misc.py line 117 726] Train: [15/20][36/510] Data 3.401 (3.304) Batch 25.684 (27.033) Remain 22:42:28 loss: 0.1954 loss_seg: 0.1076 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:41:57,758 INFO misc.py line 117 726] Train: [15/20][37/510] Data 2.686 (3.286) Batch 26.703 (27.023) Remain 22:41:31 loss: 0.1962 loss_seg: 0.1104 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:42:26,667 INFO misc.py line 117 726] Train: [15/20][38/510] Data 2.966 (3.277) Batch 28.909 (27.077) Remain 22:43:47 loss: 0.3097 loss_seg: 0.2100 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:42:42,483 INFO misc.py line 117 726] Train: [15/20][39/510] Data 2.088 (3.244) Batch 15.816 (26.765) Remain 22:27:35 loss: 0.2278 loss_seg: 0.1391 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:43:05,141 INFO misc.py line 117 726] Train: [15/20][40/510] Data 2.080 (3.212) Batch 22.658 (26.654) Remain 22:21:33 loss: 0.2604 loss_seg: 0.1687 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:43:30,047 INFO misc.py line 117 726] Train: [15/20][41/510] Data 2.862 (3.203) Batch 24.906 (26.608) Remain 22:18:48 loss: 0.2512 loss_seg: 0.1520 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:43:52,670 INFO misc.py line 117 726] Train: [15/20][42/510] Data 2.992 (3.198) Batch 22.624 (26.505) Remain 22:13:13 loss: 0.2546 loss_seg: 0.1631 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:44:09,611 INFO misc.py line 117 726] Train: [15/20][43/510] Data 2.259 (3.174) Batch 16.940 (26.266) Remain 22:00:45 loss: 0.2350 loss_seg: 0.1404 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:44:35,942 INFO misc.py line 117 726] Train: [15/20][44/510] Data 2.868 (3.167) Batch 26.331 (26.268) Remain 22:00:23 loss: 0.2250 loss_seg: 0.1356 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:45:08,153 INFO misc.py line 117 726] Train: [15/20][45/510] Data 6.821 (3.254) Batch 32.212 (26.409) Remain 22:07:04 loss: 0.2931 loss_seg: 0.1895 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:45:34,358 INFO misc.py line 117 726] Train: [15/20][46/510] Data 2.742 (3.242) Batch 26.205 (26.405) Remain 22:06:23 loss: 0.2521 loss_seg: 0.1531 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:45:56,828 INFO misc.py line 117 726] Train: [15/20][47/510] Data 2.828 (3.232) Batch 22.470 (26.315) Remain 22:01:27 loss: 0.2518 loss_seg: 0.1524 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:46:23,765 INFO misc.py line 117 726] Train: [15/20][48/510] Data 3.261 (3.233) Batch 26.937 (26.329) Remain 22:01:42 loss: 0.2923 loss_seg: 0.1905 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:46:57,869 INFO misc.py line 117 726] Train: [15/20][49/510] Data 3.707 (3.243) Batch 34.103 (26.498) Remain 22:09:45 loss: 0.2318 loss_seg: 0.1393 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:47:22,971 INFO misc.py line 117 726] Train: [15/20][50/510] Data 2.381 (3.225) Batch 25.103 (26.468) Remain 22:07:49 loss: 0.1970 loss_seg: 0.1072 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:47:22,972 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 01:47:52,395 INFO misc.py line 117 726] Train: [15/20][51/510] Data 5.707 (3.277) Batch 29.423 (26.530) Remain 22:10:28 loss: 0.2733 loss_seg: 0.1732 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:48:22,345 INFO misc.py line 117 726] Train: [15/20][52/510] Data 3.560 (3.282) Batch 29.950 (26.600) Remain 22:13:31 loss: 0.2392 loss_seg: 0.1457 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:48:57,801 INFO misc.py line 117 726] Train: [15/20][53/510] Data 4.229 (3.301) Batch 35.456 (26.777) Remain 22:21:57 loss: 0.2597 loss_seg: 0.1669 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:49:28,425 INFO misc.py line 117 726] Train: [15/20][54/510] Data 3.778 (3.311) Batch 30.624 (26.852) Remain 22:25:17 loss: 0.2580 loss_seg: 0.1553 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:49:53,776 INFO misc.py line 117 726] Train: [15/20][55/510] Data 3.032 (3.305) Batch 25.352 (26.823) Remain 22:23:24 loss: 0.2392 loss_seg: 0.1505 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:50:22,670 INFO misc.py line 117 726] Train: [15/20][56/510] Data 3.564 (3.310) Batch 28.894 (26.862) Remain 22:24:54 loss: 0.2317 loss_seg: 0.1398 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:50:48,476 INFO misc.py line 117 726] Train: [15/20][57/510] Data 2.853 (3.302) Batch 25.805 (26.843) Remain 22:23:29 loss: 0.1833 loss_seg: 0.0985 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:51:18,395 INFO misc.py line 117 726] Train: [15/20][58/510] Data 3.564 (3.307) Batch 29.920 (26.899) Remain 22:25:50 loss: 0.2275 loss_seg: 0.1310 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:51:52,962 INFO misc.py line 117 726] Train: [15/20][59/510] Data 4.251 (3.323) Batch 34.567 (27.036) Remain 22:32:14 loss: 0.3531 loss_seg: 0.2565 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:52:16,405 INFO misc.py line 117 726] Train: [15/20][60/510] Data 2.357 (3.306) Batch 23.443 (26.973) Remain 22:28:38 loss: 0.2129 loss_seg: 0.1189 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:52:43,392 INFO misc.py line 117 726] Train: [15/20][61/510] Data 2.988 (3.301) Batch 26.987 (26.973) Remain 22:28:11 loss: 0.2413 loss_seg: 0.1440 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:53:07,020 INFO misc.py line 117 726] Train: [15/20][62/510] Data 2.977 (3.295) Batch 23.628 (26.916) Remain 22:24:54 loss: 0.1974 loss_seg: 0.1110 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:53:37,410 INFO misc.py line 117 726] Train: [15/20][63/510] Data 5.987 (3.340) Batch 30.390 (26.974) Remain 22:27:21 loss: 0.2461 loss_seg: 0.1537 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:54:05,757 INFO misc.py line 117 726] Train: [15/20][64/510] Data 3.143 (3.337) Batch 28.347 (26.997) Remain 22:28:01 loss: 0.2661 loss_seg: 0.1737 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:54:40,937 INFO misc.py line 117 726] Train: [15/20][65/510] Data 6.426 (3.387) Batch 35.180 (27.129) Remain 22:34:10 loss: 0.3222 loss_seg: 0.2180 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:55:11,526 INFO misc.py line 117 726] Train: [15/20][66/510] Data 6.358 (3.434) Batch 30.590 (27.184) Remain 22:36:27 loss: 0.2343 loss_seg: 0.1380 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:55:28,243 INFO misc.py line 117 726] Train: [15/20][67/510] Data 2.126 (3.414) Batch 16.717 (27.020) Remain 22:27:51 loss: 0.2358 loss_seg: 0.1403 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:56:06,447 INFO misc.py line 117 726] Train: [15/20][68/510] Data 8.534 (3.492) Batch 38.204 (27.192) Remain 22:35:58 loss: 0.2676 loss_seg: 0.1677 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:56:35,015 INFO misc.py line 117 726] Train: [15/20][69/510] Data 3.382 (3.491) Batch 28.568 (27.213) Remain 22:36:33 loss: 0.2395 loss_seg: 0.1420 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:57:08,058 INFO misc.py line 117 726] Train: [15/20][70/510] Data 5.777 (3.525) Batch 33.043 (27.300) Remain 22:40:26 loss: 0.2711 loss_seg: 0.1762 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:57:38,626 INFO misc.py line 117 726] Train: [15/20][71/510] Data 3.347 (3.522) Batch 30.568 (27.348) Remain 22:42:23 loss: 0.1719 loss_seg: 0.0869 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:58:08,831 INFO misc.py line 117 726] Train: [15/20][72/510] Data 3.494 (3.522) Batch 30.205 (27.389) Remain 22:43:59 loss: 0.2015 loss_seg: 0.1147 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:58:39,805 INFO misc.py line 117 726] Train: [15/20][73/510] Data 3.270 (3.518) Batch 30.974 (27.441) Remain 22:46:05 loss: 0.2329 loss_seg: 0.1413 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:59:08,730 INFO misc.py line 117 726] Train: [15/20][74/510] Data 4.342 (3.530) Batch 28.925 (27.462) Remain 22:46:40 loss: 0.3229 loss_seg: 0.2184 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 01:59:39,444 INFO misc.py line 117 726] Train: [15/20][75/510] Data 4.927 (3.549) Batch 30.713 (27.507) Remain 22:48:27 loss: 0.2236 loss_seg: 0.1308 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:00:09,092 INFO misc.py line 117 726] Train: [15/20][76/510] Data 2.881 (3.540) Batch 29.648 (27.536) Remain 22:49:27 loss: 0.1988 loss_seg: 0.1104 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:00:49,172 INFO misc.py line 117 726] Train: [15/20][77/510] Data 6.366 (3.578) Batch 40.079 (27.706) Remain 22:57:25 loss: 0.2379 loss_seg: 0.1419 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:01:19,947 INFO misc.py line 117 726] Train: [15/20][78/510] Data 3.335 (3.575) Batch 30.775 (27.746) Remain 22:59:00 loss: 0.2576 loss_seg: 0.1623 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:01:54,901 INFO misc.py line 117 726] Train: [15/20][79/510] Data 5.859 (3.605) Batch 34.954 (27.841) Remain 23:03:14 loss: 0.1950 loss_seg: 0.1112 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:02:22,212 INFO misc.py line 117 726] Train: [15/20][80/510] Data 2.896 (3.596) Batch 27.311 (27.834) Remain 23:02:26 loss: 0.2463 loss_seg: 0.1551 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:02:49,477 INFO misc.py line 117 726] Train: [15/20][81/510] Data 2.474 (3.581) Batch 27.265 (27.827) Remain 23:01:37 loss: 0.2921 loss_seg: 0.1907 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:03:10,873 INFO misc.py line 117 726] Train: [15/20][82/510] Data 1.977 (3.561) Batch 21.396 (27.746) Remain 22:57:06 loss: 0.2496 loss_seg: 0.1518 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:03:35,649 INFO misc.py line 117 726] Train: [15/20][83/510] Data 2.718 (3.551) Batch 24.775 (27.709) Remain 22:54:48 loss: 0.2653 loss_seg: 0.1570 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:04:02,450 INFO misc.py line 117 726] Train: [15/20][84/510] Data 2.612 (3.539) Batch 26.801 (27.697) Remain 22:53:47 loss: 0.2122 loss_seg: 0.1222 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:04:22,456 INFO misc.py line 117 726] Train: [15/20][85/510] Data 2.216 (3.523) Batch 20.006 (27.604) Remain 22:48:40 loss: 0.2039 loss_seg: 0.1141 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:04:48,141 INFO misc.py line 117 726] Train: [15/20][86/510] Data 2.505 (3.511) Batch 25.685 (27.580) Remain 22:47:04 loss: 0.2606 loss_seg: 0.1594 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:05:19,915 INFO misc.py line 117 726] Train: [15/20][87/510] Data 4.075 (3.517) Batch 31.775 (27.630) Remain 22:49:05 loss: 0.1929 loss_seg: 0.1048 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:05:42,007 INFO misc.py line 117 726] Train: [15/20][88/510] Data 2.251 (3.502) Batch 22.091 (27.565) Remain 22:45:23 loss: 0.2144 loss_seg: 0.1229 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:06:01,165 INFO misc.py line 117 726] Train: [15/20][89/510] Data 2.581 (3.492) Batch 19.159 (27.467) Remain 22:40:05 loss: 0.2402 loss_seg: 0.1390 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:06:38,915 INFO misc.py line 117 726] Train: [15/20][90/510] Data 5.387 (3.514) Batch 37.750 (27.586) Remain 22:45:29 loss: 0.2109 loss_seg: 0.1237 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:07:07,612 INFO misc.py line 117 726] Train: [15/20][91/510] Data 2.873 (3.506) Batch 28.697 (27.598) Remain 22:45:39 loss: 0.2187 loss_seg: 0.1224 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:07:36,215 INFO misc.py line 117 726] Train: [15/20][92/510] Data 2.948 (3.500) Batch 28.604 (27.610) Remain 22:45:45 loss: 0.2631 loss_seg: 0.1617 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:08:02,217 INFO misc.py line 117 726] Train: [15/20][93/510] Data 2.585 (3.490) Batch 26.001 (27.592) Remain 22:44:24 loss: 0.2281 loss_seg: 0.1336 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:08:26,668 INFO misc.py line 117 726] Train: [15/20][94/510] Data 2.535 (3.479) Batch 24.452 (27.557) Remain 22:42:14 loss: 0.2080 loss_seg: 0.1161 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:08:48,863 INFO misc.py line 117 726] Train: [15/20][95/510] Data 2.366 (3.467) Batch 22.194 (27.499) Remain 22:38:54 loss: 0.2122 loss_seg: 0.1252 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:09:14,117 INFO misc.py line 117 726] Train: [15/20][96/510] Data 2.790 (3.460) Batch 25.255 (27.475) Remain 22:37:15 loss: 0.3288 loss_seg: 0.2295 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:09:47,295 INFO misc.py line 117 726] Train: [15/20][97/510] Data 3.718 (3.463) Batch 33.178 (27.535) Remain 22:39:47 loss: 0.2411 loss_seg: 0.1418 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:10:15,431 INFO misc.py line 117 726] Train: [15/20][98/510] Data 3.677 (3.465) Batch 28.136 (27.542) Remain 22:39:38 loss: 0.2357 loss_seg: 0.1406 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:10:37,557 INFO misc.py line 117 726] Train: [15/20][99/510] Data 3.172 (3.462) Batch 22.126 (27.485) Remain 22:36:24 loss: 0.2131 loss_seg: 0.1244 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:11:12,122 INFO misc.py line 117 726] Train: [15/20][100/510] Data 4.327 (3.471) Batch 34.565 (27.558) Remain 22:39:32 loss: 0.2591 loss_seg: 0.1646 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:11:12,122 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 02:11:37,456 INFO misc.py line 117 726] Train: [15/20][101/510] Data 3.367 (3.470) Batch 25.334 (27.536) Remain 22:37:58 loss: 0.2842 loss_seg: 0.1727 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:12:09,283 INFO misc.py line 117 726] Train: [15/20][102/510] Data 5.782 (3.493) Batch 31.827 (27.579) Remain 22:39:38 loss: 0.2389 loss_seg: 0.1443 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:12:39,431 INFO misc.py line 117 726] Train: [15/20][103/510] Data 3.798 (3.496) Batch 30.148 (27.605) Remain 22:40:27 loss: 0.2712 loss_seg: 0.1695 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:13:00,402 INFO misc.py line 117 726] Train: [15/20][104/510] Data 2.611 (3.487) Batch 20.971 (27.539) Remain 22:36:45 loss: 0.2816 loss_seg: 0.1857 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:13:18,304 INFO misc.py line 117 726] Train: [15/20][105/510] Data 1.628 (3.469) Batch 17.902 (27.445) Remain 22:31:38 loss: 0.2096 loss_seg: 0.1220 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:13:45,565 INFO misc.py line 117 726] Train: [15/20][106/510] Data 3.149 (3.466) Batch 27.261 (27.443) Remain 22:31:05 loss: 0.2133 loss_seg: 0.1219 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:14:15,847 INFO misc.py line 117 726] Train: [15/20][107/510] Data 5.949 (3.490) Batch 30.282 (27.470) Remain 22:31:59 loss: 0.2740 loss_seg: 0.1746 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:14:49,814 INFO misc.py line 117 726] Train: [15/20][108/510] Data 4.918 (3.504) Batch 33.967 (27.532) Remain 22:34:34 loss: 0.2306 loss_seg: 0.1367 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:15:21,326 INFO misc.py line 117 726] Train: [15/20][109/510] Data 4.620 (3.514) Batch 31.512 (27.569) Remain 22:35:57 loss: 0.2391 loss_seg: 0.1464 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:15:44,824 INFO misc.py line 117 726] Train: [15/20][110/510] Data 2.475 (3.504) Batch 23.498 (27.531) Remain 22:33:37 loss: 0.3088 loss_seg: 0.2112 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:16:14,123 INFO misc.py line 117 726] Train: [15/20][111/510] Data 2.906 (3.499) Batch 29.298 (27.548) Remain 22:33:58 loss: 0.2491 loss_seg: 0.1552 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:16:44,343 INFO misc.py line 117 726] Train: [15/20][112/510] Data 2.313 (3.488) Batch 30.220 (27.572) Remain 22:34:43 loss: 0.2881 loss_seg: 0.1820 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:17:23,643 INFO misc.py line 117 726] Train: [15/20][113/510] Data 6.810 (3.518) Batch 39.301 (27.679) Remain 22:39:29 loss: 0.1928 loss_seg: 0.1065 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:17:56,826 INFO misc.py line 117 726] Train: [15/20][114/510] Data 3.035 (3.514) Batch 33.182 (27.729) Remain 22:41:28 loss: 0.2733 loss_seg: 0.1760 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:18:18,594 INFO misc.py line 117 726] Train: [15/20][115/510] Data 2.721 (3.507) Batch 21.769 (27.675) Remain 22:38:23 loss: 0.3080 loss_seg: 0.2009 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:18:44,401 INFO misc.py line 117 726] Train: [15/20][116/510] Data 3.118 (3.503) Batch 25.807 (27.659) Remain 22:37:07 loss: 0.3688 loss_seg: 0.2680 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:19:02,345 INFO misc.py line 117 726] Train: [15/20][117/510] Data 1.790 (3.488) Batch 17.944 (27.574) Remain 22:32:28 loss: 0.1664 loss_seg: 0.0830 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:19:30,171 INFO misc.py line 117 726] Train: [15/20][118/510] Data 3.568 (3.489) Batch 27.826 (27.576) Remain 22:32:07 loss: 0.1908 loss_seg: 0.1070 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:19:50,245 INFO misc.py line 117 726] Train: [15/20][119/510] Data 2.694 (3.482) Batch 20.074 (27.511) Remain 22:28:30 loss: 0.2232 loss_seg: 0.1300 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:20:17,516 INFO misc.py line 117 726] Train: [15/20][120/510] Data 2.759 (3.476) Batch 27.272 (27.509) Remain 22:27:56 loss: 0.2957 loss_seg: 0.2047 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:20:48,407 INFO misc.py line 117 726] Train: [15/20][121/510] Data 3.950 (3.480) Batch 30.890 (27.538) Remain 22:28:53 loss: 0.3485 loss_seg: 0.2321 loss_superpoint_edge: 0.0503 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:21:27,345 INFO misc.py line 117 726] Train: [15/20][122/510] Data 9.481 (3.530) Batch 38.938 (27.633) Remain 22:33:07 loss: 0.2196 loss_seg: 0.1234 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:21:57,669 INFO misc.py line 117 726] Train: [15/20][123/510] Data 5.339 (3.545) Batch 30.325 (27.656) Remain 22:33:45 loss: 0.2594 loss_seg: 0.1631 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:22:28,189 INFO misc.py line 117 726] Train: [15/20][124/510] Data 3.928 (3.549) Batch 30.520 (27.680) Remain 22:34:27 loss: 0.1932 loss_seg: 0.1031 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:22:54,742 INFO misc.py line 117 726] Train: [15/20][125/510] Data 3.483 (3.548) Batch 26.553 (27.670) Remain 22:33:32 loss: 0.2235 loss_seg: 0.1294 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:23:25,419 INFO misc.py line 117 726] Train: [15/20][126/510] Data 2.663 (3.541) Batch 30.677 (27.695) Remain 22:34:16 loss: 0.2339 loss_seg: 0.1351 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:23:54,110 INFO misc.py line 117 726] Train: [15/20][127/510] Data 4.597 (3.549) Batch 28.691 (27.703) Remain 22:34:12 loss: 0.5565 loss_seg: 0.4363 loss_superpoint_edge: 0.0504 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:24:13,549 INFO misc.py line 117 726] Train: [15/20][128/510] Data 2.223 (3.539) Batch 19.439 (27.637) Remain 22:30:30 loss: 0.3454 loss_seg: 0.2371 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:24:33,567 INFO misc.py line 117 726] Train: [15/20][129/510] Data 2.143 (3.528) Batch 20.018 (27.576) Remain 22:27:05 loss: 0.2589 loss_seg: 0.1587 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:25:00,090 INFO misc.py line 117 726] Train: [15/20][130/510] Data 2.968 (3.523) Batch 26.523 (27.568) Remain 22:26:14 loss: 0.2491 loss_seg: 0.1583 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:25:28,273 INFO misc.py line 117 726] Train: [15/20][131/510] Data 3.232 (3.521) Batch 28.183 (27.573) Remain 22:26:00 loss: 0.2059 loss_seg: 0.1122 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:25:56,023 INFO misc.py line 117 726] Train: [15/20][132/510] Data 3.706 (3.522) Batch 27.749 (27.574) Remain 22:25:37 loss: 0.2262 loss_seg: 0.1313 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:26:32,155 INFO misc.py line 117 726] Train: [15/20][133/510] Data 5.514 (3.538) Batch 36.133 (27.640) Remain 22:28:22 loss: 0.2434 loss_seg: 0.1547 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:26:58,057 INFO misc.py line 117 726] Train: [15/20][134/510] Data 4.210 (3.543) Batch 25.902 (27.627) Remain 22:27:15 loss: 0.3289 loss_seg: 0.2227 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:27:27,526 INFO misc.py line 117 726] Train: [15/20][135/510] Data 4.655 (3.551) Batch 29.469 (27.641) Remain 22:27:28 loss: 0.2565 loss_seg: 0.1591 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:28:03,737 INFO misc.py line 117 726] Train: [15/20][136/510] Data 9.879 (3.599) Batch 36.210 (27.705) Remain 22:30:09 loss: 0.2709 loss_seg: 0.1771 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:28:15,889 INFO misc.py line 117 726] Train: [15/20][137/510] Data 1.823 (3.586) Batch 12.153 (27.589) Remain 22:24:02 loss: 0.2226 loss_seg: 0.1277 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:28:38,219 INFO misc.py line 117 726] Train: [15/20][138/510] Data 2.122 (3.575) Batch 22.330 (27.550) Remain 22:21:41 loss: 0.2242 loss_seg: 0.1320 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:29:01,557 INFO misc.py line 117 726] Train: [15/20][139/510] Data 2.402 (3.566) Batch 23.339 (27.519) Remain 22:19:43 loss: 0.1921 loss_seg: 0.1051 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:29:31,628 INFO misc.py line 117 726] Train: [15/20][140/510] Data 2.990 (3.562) Batch 30.071 (27.538) Remain 22:20:10 loss: 0.1912 loss_seg: 0.1105 loss_superpoint_edge: 0.0145 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:29:58,896 INFO misc.py line 117 726] Train: [15/20][141/510] Data 3.436 (3.561) Batch 27.268 (27.536) Remain 22:19:36 loss: 0.1982 loss_seg: 0.1100 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:30:25,023 INFO misc.py line 117 726] Train: [15/20][142/510] Data 3.026 (3.557) Batch 26.128 (27.526) Remain 22:18:39 loss: 0.2087 loss_seg: 0.1192 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:30:52,479 INFO misc.py line 117 726] Train: [15/20][143/510] Data 2.964 (3.553) Batch 27.456 (27.525) Remain 22:18:10 loss: 0.2510 loss_seg: 0.1490 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:31:13,752 INFO misc.py line 117 726] Train: [15/20][144/510] Data 1.953 (3.542) Batch 21.273 (27.481) Remain 22:15:33 loss: 0.1922 loss_seg: 0.1022 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:31:35,904 INFO misc.py line 117 726] Train: [15/20][145/510] Data 1.730 (3.529) Batch 22.152 (27.443) Remain 22:13:17 loss: 0.2204 loss_seg: 0.1255 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:32:10,783 INFO misc.py line 117 726] Train: [15/20][146/510] Data 4.695 (3.537) Batch 34.879 (27.495) Remain 22:15:21 loss: 0.2233 loss_seg: 0.1303 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:32:46,343 INFO misc.py line 117 726] Train: [15/20][147/510] Data 4.045 (3.541) Batch 35.560 (27.551) Remain 22:17:36 loss: 0.2315 loss_seg: 0.1356 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:33:17,850 INFO misc.py line 117 726] Train: [15/20][148/510] Data 5.814 (3.556) Batch 31.507 (27.579) Remain 22:18:28 loss: 0.2135 loss_seg: 0.1264 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:33:49,512 INFO misc.py line 117 726] Train: [15/20][149/510] Data 5.307 (3.568) Batch 31.662 (27.607) Remain 22:19:22 loss: 0.2180 loss_seg: 0.1296 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:34:31,320 INFO misc.py line 117 726] Train: [15/20][150/510] Data 7.012 (3.592) Batch 41.808 (27.703) Remain 22:23:36 loss: 0.1594 loss_seg: 0.0758 loss_superpoint_edge: 0.0142 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:34:31,320 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 02:35:03,156 INFO misc.py line 117 726] Train: [15/20][151/510] Data 4.019 (3.595) Batch 31.836 (27.731) Remain 22:24:29 loss: 0.2386 loss_seg: 0.1469 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:35:31,558 INFO misc.py line 117 726] Train: [15/20][152/510] Data 2.958 (3.590) Batch 28.402 (27.736) Remain 22:24:14 loss: 0.1863 loss_seg: 0.0968 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:36:04,855 INFO misc.py line 117 726] Train: [15/20][153/510] Data 3.341 (3.589) Batch 33.297 (27.773) Remain 22:25:35 loss: 0.3702 loss_seg: 0.2697 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:36:25,404 INFO misc.py line 117 726] Train: [15/20][154/510] Data 2.309 (3.580) Batch 20.550 (27.725) Remain 22:22:48 loss: 0.2243 loss_seg: 0.1331 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:36:50,754 INFO misc.py line 117 726] Train: [15/20][155/510] Data 2.547 (3.573) Batch 25.349 (27.709) Remain 22:21:35 loss: 0.2510 loss_seg: 0.1538 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:37:22,608 INFO misc.py line 117 726] Train: [15/20][156/510] Data 3.890 (3.575) Batch 31.854 (27.736) Remain 22:22:26 loss: 0.2894 loss_seg: 0.1820 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:37:52,846 INFO misc.py line 117 726] Train: [15/20][157/510] Data 2.894 (3.571) Batch 30.239 (27.753) Remain 22:22:45 loss: 0.2426 loss_seg: 0.1526 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:38:26,079 INFO misc.py line 117 726] Train: [15/20][158/510] Data 4.407 (3.576) Batch 33.232 (27.788) Remain 22:24:00 loss: 0.3075 loss_seg: 0.2109 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:38:57,509 INFO misc.py line 117 726] Train: [15/20][159/510] Data 4.074 (3.580) Batch 31.430 (27.811) Remain 22:24:40 loss: 0.2753 loss_seg: 0.1748 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:39:26,258 INFO misc.py line 117 726] Train: [15/20][160/510] Data 3.792 (3.581) Batch 28.750 (27.817) Remain 22:24:29 loss: 0.2063 loss_seg: 0.1118 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:39:53,153 INFO misc.py line 117 726] Train: [15/20][161/510] Data 2.689 (3.575) Batch 26.895 (27.811) Remain 22:23:45 loss: 0.2436 loss_seg: 0.1463 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:40:23,193 INFO misc.py line 117 726] Train: [15/20][162/510] Data 2.903 (3.571) Batch 30.039 (27.825) Remain 22:23:57 loss: 0.2102 loss_seg: 0.1214 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:40:48,596 INFO misc.py line 117 726] Train: [15/20][163/510] Data 2.810 (3.566) Batch 25.403 (27.810) Remain 22:22:46 loss: 0.1964 loss_seg: 0.1052 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:41:21,671 INFO misc.py line 117 726] Train: [15/20][164/510] Data 3.589 (3.566) Batch 33.076 (27.843) Remain 22:23:53 loss: 0.2505 loss_seg: 0.1524 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:41:55,870 INFO misc.py line 117 726] Train: [15/20][165/510] Data 5.307 (3.577) Batch 34.198 (27.882) Remain 22:25:18 loss: 0.4033 loss_seg: 0.3005 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:42:23,438 INFO misc.py line 117 726] Train: [15/20][166/510] Data 2.905 (3.573) Batch 27.567 (27.880) Remain 22:24:45 loss: 0.2454 loss_seg: 0.1498 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:43:01,635 INFO misc.py line 117 726] Train: [15/20][167/510] Data 6.095 (3.588) Batch 38.197 (27.943) Remain 22:27:19 loss: 0.2068 loss_seg: 0.1208 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:43:32,053 INFO misc.py line 117 726] Train: [15/20][168/510] Data 3.530 (3.588) Batch 30.418 (27.958) Remain 22:27:34 loss: 0.1981 loss_seg: 0.1122 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:43:58,135 INFO misc.py line 117 726] Train: [15/20][169/510] Data 3.345 (3.587) Batch 26.082 (27.947) Remain 22:26:34 loss: 0.1935 loss_seg: 0.1077 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:44:19,189 INFO misc.py line 117 726] Train: [15/20][170/510] Data 2.517 (3.580) Batch 21.054 (27.906) Remain 22:24:07 loss: 0.2896 loss_seg: 0.1963 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:44:53,403 INFO misc.py line 117 726] Train: [15/20][171/510] Data 4.503 (3.586) Batch 34.214 (27.943) Remain 22:25:27 loss: 0.2677 loss_seg: 0.1704 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:45:28,353 INFO misc.py line 117 726] Train: [15/20][172/510] Data 8.580 (3.615) Batch 34.951 (27.985) Remain 22:26:59 loss: 0.2053 loss_seg: 0.1126 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:45:55,824 INFO misc.py line 117 726] Train: [15/20][173/510] Data 3.191 (3.613) Batch 27.471 (27.982) Remain 22:26:22 loss: 0.2288 loss_seg: 0.1353 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:46:18,265 INFO misc.py line 117 726] Train: [15/20][174/510] Data 2.529 (3.606) Batch 22.439 (27.949) Remain 22:24:21 loss: 0.2409 loss_seg: 0.1427 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:46:51,636 INFO misc.py line 117 726] Train: [15/20][175/510] Data 3.793 (3.607) Batch 33.372 (27.981) Remain 22:25:24 loss: 0.2801 loss_seg: 0.1780 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:47:24,769 INFO misc.py line 117 726] Train: [15/20][176/510] Data 7.182 (3.628) Batch 33.133 (28.010) Remain 22:26:22 loss: 0.2437 loss_seg: 0.1468 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:47:59,159 INFO misc.py line 117 726] Train: [15/20][177/510] Data 3.400 (3.627) Batch 34.390 (28.047) Remain 22:27:39 loss: 0.2805 loss_seg: 0.1819 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:48:31,865 INFO misc.py line 117 726] Train: [15/20][178/510] Data 4.527 (3.632) Batch 32.707 (28.074) Remain 22:28:28 loss: 0.2581 loss_seg: 0.1619 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:49:02,542 INFO misc.py line 117 726] Train: [15/20][179/510] Data 3.643 (3.632) Batch 30.677 (28.089) Remain 22:28:43 loss: 0.1837 loss_seg: 0.0951 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0431 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:49:25,732 INFO misc.py line 117 726] Train: [15/20][180/510] Data 2.559 (3.626) Batch 23.189 (28.061) Remain 22:26:55 loss: 0.2342 loss_seg: 0.1369 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:50:10,593 INFO misc.py line 117 726] Train: [15/20][181/510] Data 14.650 (3.688) Batch 44.861 (28.155) Remain 22:30:58 loss: 0.2189 loss_seg: 0.1291 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:50:37,660 INFO misc.py line 117 726] Train: [15/20][182/510] Data 4.301 (3.691) Batch 27.067 (28.149) Remain 22:30:13 loss: 0.2915 loss_seg: 0.1957 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:51:05,383 INFO misc.py line 117 726] Train: [15/20][183/510] Data 3.022 (3.688) Batch 27.723 (28.147) Remain 22:29:38 loss: 0.2216 loss_seg: 0.1287 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:51:42,130 INFO misc.py line 117 726] Train: [15/20][184/510] Data 8.625 (3.715) Batch 36.746 (28.194) Remain 22:31:26 loss: 0.1854 loss_seg: 0.1000 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:52:24,283 INFO misc.py line 117 726] Train: [15/20][185/510] Data 12.412 (3.763) Batch 42.154 (28.271) Remain 22:34:39 loss: 0.1958 loss_seg: 0.1089 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:52:48,511 INFO misc.py line 117 726] Train: [15/20][186/510] Data 2.449 (3.756) Batch 24.228 (28.249) Remain 22:33:07 loss: 0.2158 loss_seg: 0.1276 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:53:10,492 INFO misc.py line 117 726] Train: [15/20][187/510] Data 2.522 (3.749) Batch 21.981 (28.215) Remain 22:31:01 loss: 0.2895 loss_seg: 0.1936 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:53:24,424 INFO misc.py line 117 726] Train: [15/20][188/510] Data 1.866 (3.739) Batch 13.932 (28.138) Remain 22:26:51 loss: 0.1940 loss_seg: 0.1056 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:53:42,042 INFO misc.py line 117 726] Train: [15/20][189/510] Data 3.195 (3.736) Batch 17.618 (28.081) Remain 22:23:40 loss: 0.2670 loss_seg: 0.1684 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:54:02,968 INFO misc.py line 117 726] Train: [15/20][190/510] Data 1.868 (3.726) Batch 20.926 (28.043) Remain 22:21:22 loss: 0.3377 loss_seg: 0.2312 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:54:37,657 INFO misc.py line 117 726] Train: [15/20][191/510] Data 5.185 (3.733) Batch 34.689 (28.078) Remain 22:22:36 loss: 0.2081 loss_seg: 0.1159 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:55:06,411 INFO misc.py line 117 726] Train: [15/20][192/510] Data 3.765 (3.734) Batch 28.753 (28.082) Remain 22:22:18 loss: 0.2880 loss_seg: 0.1832 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:55:29,731 INFO misc.py line 117 726] Train: [15/20][193/510] Data 3.371 (3.732) Batch 23.320 (28.057) Remain 22:20:38 loss: 0.1928 loss_seg: 0.1077 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:55:58,716 INFO misc.py line 117 726] Train: [15/20][194/510] Data 3.638 (3.731) Batch 28.984 (28.062) Remain 22:20:24 loss: 0.2012 loss_seg: 0.1134 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:56:27,304 INFO misc.py line 117 726] Train: [15/20][195/510] Data 4.844 (3.737) Batch 28.589 (28.064) Remain 22:20:04 loss: 0.2033 loss_seg: 0.1117 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:56:58,579 INFO misc.py line 117 726] Train: [15/20][196/510] Data 5.281 (3.745) Batch 31.275 (28.081) Remain 22:20:23 loss: 0.2543 loss_seg: 0.1598 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:57:18,968 INFO misc.py line 117 726] Train: [15/20][197/510] Data 2.200 (3.737) Batch 20.388 (28.041) Remain 22:18:02 loss: 0.2486 loss_seg: 0.1571 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:57:46,052 INFO misc.py line 117 726] Train: [15/20][198/510] Data 2.580 (3.731) Batch 27.084 (28.036) Remain 22:17:20 loss: 0.2444 loss_seg: 0.1522 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:58:13,812 INFO misc.py line 117 726] Train: [15/20][199/510] Data 3.370 (3.729) Batch 27.760 (28.035) Remain 22:16:48 loss: 0.4079 loss_seg: 0.2868 loss_superpoint_edge: 0.0530 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:58:33,454 INFO misc.py line 117 726] Train: [15/20][200/510] Data 2.250 (3.722) Batch 19.642 (27.992) Remain 22:14:18 loss: 0.2684 loss_seg: 0.1673 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:58:33,454 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 02:58:56,417 INFO misc.py line 117 726] Train: [15/20][201/510] Data 2.837 (3.717) Batch 22.963 (27.967) Remain 22:12:37 loss: 0.2475 loss_seg: 0.1492 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:59:28,268 INFO misc.py line 117 726] Train: [15/20][202/510] Data 5.192 (3.725) Batch 31.851 (27.986) Remain 22:13:05 loss: 0.4028 loss_seg: 0.2929 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 02:59:46,657 INFO misc.py line 117 726] Train: [15/20][203/510] Data 2.436 (3.718) Batch 18.389 (27.938) Remain 22:10:20 loss: 0.2270 loss_seg: 0.1291 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:00:25,599 INFO misc.py line 117 726] Train: [15/20][204/510] Data 12.264 (3.761) Batch 38.942 (27.993) Remain 22:12:28 loss: 0.2711 loss_seg: 0.1807 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:01:01,430 INFO misc.py line 117 726] Train: [15/20][205/510] Data 5.211 (3.768) Batch 35.831 (28.032) Remain 22:13:51 loss: 0.2624 loss_seg: 0.1653 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:01:23,826 INFO misc.py line 117 726] Train: [15/20][206/510] Data 3.132 (3.765) Batch 22.396 (28.004) Remain 22:12:04 loss: 0.2498 loss_seg: 0.1567 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:01:53,622 INFO misc.py line 117 726] Train: [15/20][207/510] Data 3.075 (3.761) Batch 29.796 (28.013) Remain 22:12:01 loss: 0.2504 loss_seg: 0.1529 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:02:28,126 INFO misc.py line 117 726] Train: [15/20][208/510] Data 7.261 (3.779) Batch 34.503 (28.045) Remain 22:13:03 loss: 0.2720 loss_seg: 0.1707 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:02:55,474 INFO misc.py line 117 726] Train: [15/20][209/510] Data 2.920 (3.774) Batch 27.349 (28.041) Remain 22:12:25 loss: 0.2756 loss_seg: 0.1792 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:03:27,839 INFO misc.py line 117 726] Train: [15/20][210/510] Data 6.657 (3.788) Batch 32.365 (28.062) Remain 22:12:57 loss: 0.2332 loss_seg: 0.1417 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:03:56,681 INFO misc.py line 117 726] Train: [15/20][211/510] Data 3.276 (3.786) Batch 28.842 (28.066) Remain 22:12:39 loss: 0.2433 loss_seg: 0.1470 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:04:24,284 INFO misc.py line 117 726] Train: [15/20][212/510] Data 2.952 (3.782) Batch 27.603 (28.064) Remain 22:12:05 loss: 0.1989 loss_seg: 0.1087 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:04:51,532 INFO misc.py line 117 726] Train: [15/20][213/510] Data 3.082 (3.779) Batch 27.249 (28.060) Remain 22:11:26 loss: 0.2792 loss_seg: 0.1768 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:05:09,282 INFO misc.py line 117 726] Train: [15/20][214/510] Data 2.059 (3.770) Batch 17.749 (28.011) Remain 22:08:39 loss: 0.1976 loss_seg: 0.1089 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:05:34,851 INFO misc.py line 117 726] Train: [15/20][215/510] Data 2.617 (3.765) Batch 25.569 (27.999) Remain 22:07:38 loss: 0.2275 loss_seg: 0.1313 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:06:07,176 INFO misc.py line 117 726] Train: [15/20][216/510] Data 6.183 (3.776) Batch 32.325 (28.020) Remain 22:08:08 loss: 0.1999 loss_seg: 0.1143 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:06:33,610 INFO misc.py line 117 726] Train: [15/20][217/510] Data 2.637 (3.771) Batch 26.435 (28.012) Remain 22:07:19 loss: 0.4492 loss_seg: 0.3241 loss_superpoint_edge: 0.0556 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:06:58,471 INFO misc.py line 117 726] Train: [15/20][218/510] Data 2.800 (3.766) Batch 24.861 (27.998) Remain 22:06:09 loss: 0.2244 loss_seg: 0.1345 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:07:33,083 INFO misc.py line 117 726] Train: [15/20][219/510] Data 3.416 (3.765) Batch 34.612 (28.028) Remain 22:07:08 loss: 0.2192 loss_seg: 0.1296 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:08:03,192 INFO misc.py line 117 726] Train: [15/20][220/510] Data 4.133 (3.767) Batch 30.109 (28.038) Remain 22:07:07 loss: 0.2947 loss_seg: 0.1933 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:08:23,722 INFO misc.py line 117 726] Train: [15/20][221/510] Data 2.080 (3.759) Batch 20.530 (28.003) Remain 22:05:01 loss: 0.1993 loss_seg: 0.1099 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:08:51,234 INFO misc.py line 117 726] Train: [15/20][222/510] Data 2.622 (3.754) Batch 27.511 (28.001) Remain 22:04:27 loss: 0.2386 loss_seg: 0.1435 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:09:07,622 INFO misc.py line 117 726] Train: [15/20][223/510] Data 1.952 (3.745) Batch 16.388 (27.948) Remain 22:01:29 loss: 0.2619 loss_seg: 0.1630 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:09:29,202 INFO misc.py line 117 726] Train: [15/20][224/510] Data 2.255 (3.739) Batch 21.579 (27.920) Remain 21:59:40 loss: 0.2036 loss_seg: 0.1148 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:10:00,778 INFO misc.py line 117 726] Train: [15/20][225/510] Data 6.616 (3.752) Batch 31.576 (27.936) Remain 21:59:58 loss: 0.2553 loss_seg: 0.1588 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:10:24,838 INFO misc.py line 117 726] Train: [15/20][226/510] Data 2.061 (3.744) Batch 24.060 (27.919) Remain 21:58:41 loss: 0.2702 loss_seg: 0.1691 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:10:58,357 INFO misc.py line 117 726] Train: [15/20][227/510] Data 6.340 (3.756) Batch 33.519 (27.944) Remain 21:59:24 loss: 0.3147 loss_seg: 0.2062 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:11:32,272 INFO misc.py line 117 726] Train: [15/20][228/510] Data 4.419 (3.759) Batch 33.915 (27.970) Remain 22:00:11 loss: 0.2403 loss_seg: 0.1437 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:12:02,438 INFO misc.py line 117 726] Train: [15/20][229/510] Data 5.976 (3.768) Batch 30.166 (27.980) Remain 22:00:11 loss: 0.1997 loss_seg: 0.1088 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:12:27,103 INFO misc.py line 117 726] Train: [15/20][230/510] Data 2.351 (3.762) Batch 24.665 (27.965) Remain 21:59:02 loss: 0.2026 loss_seg: 0.1140 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:12:49,042 INFO misc.py line 117 726] Train: [15/20][231/510] Data 3.372 (3.760) Batch 21.938 (27.939) Remain 21:57:19 loss: 0.2031 loss_seg: 0.1134 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:13:06,186 INFO misc.py line 117 726] Train: [15/20][232/510] Data 1.698 (3.751) Batch 17.144 (27.892) Remain 21:54:38 loss: 0.2242 loss_seg: 0.1298 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:13:34,582 INFO misc.py line 117 726] Train: [15/20][233/510] Data 3.738 (3.751) Batch 28.396 (27.894) Remain 21:54:16 loss: 0.2587 loss_seg: 0.1633 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:14:02,061 INFO misc.py line 117 726] Train: [15/20][234/510] Data 3.142 (3.749) Batch 27.480 (27.892) Remain 21:53:43 loss: 0.2205 loss_seg: 0.1251 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:14:28,270 INFO misc.py line 117 726] Train: [15/20][235/510] Data 3.141 (3.746) Batch 26.209 (27.885) Remain 21:52:54 loss: 0.2655 loss_seg: 0.1622 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:15:03,724 INFO misc.py line 117 726] Train: [15/20][236/510] Data 5.933 (3.755) Batch 35.454 (27.917) Remain 21:53:58 loss: 0.3319 loss_seg: 0.2388 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:15:26,742 INFO misc.py line 117 726] Train: [15/20][237/510] Data 2.511 (3.750) Batch 23.018 (27.897) Remain 21:52:31 loss: 0.2852 loss_seg: 0.1890 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:16:05,653 INFO misc.py line 117 726] Train: [15/20][238/510] Data 5.838 (3.759) Batch 38.910 (27.943) Remain 21:54:16 loss: 0.3866 loss_seg: 0.2840 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:16:37,576 INFO misc.py line 117 726] Train: [15/20][239/510] Data 3.772 (3.759) Batch 31.923 (27.960) Remain 21:54:35 loss: 0.2566 loss_seg: 0.1609 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:17:05,384 INFO misc.py line 117 726] Train: [15/20][240/510] Data 2.584 (3.754) Batch 27.808 (27.960) Remain 21:54:06 loss: 0.2236 loss_seg: 0.1337 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:17:29,175 INFO misc.py line 117 726] Train: [15/20][241/510] Data 2.909 (3.751) Batch 23.792 (27.942) Remain 21:52:48 loss: 0.2475 loss_seg: 0.1517 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:17:59,545 INFO misc.py line 117 726] Train: [15/20][242/510] Data 3.395 (3.749) Batch 30.370 (27.952) Remain 21:52:49 loss: 0.2245 loss_seg: 0.1267 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:18:40,015 INFO misc.py line 117 726] Train: [15/20][243/510] Data 9.575 (3.773) Batch 40.469 (28.004) Remain 21:54:48 loss: 0.2159 loss_seg: 0.1252 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:19:04,912 INFO misc.py line 117 726] Train: [15/20][244/510] Data 2.730 (3.769) Batch 24.897 (27.991) Remain 21:53:44 loss: 0.2724 loss_seg: 0.1807 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:19:33,508 INFO misc.py line 117 726] Train: [15/20][245/510] Data 3.571 (3.768) Batch 28.595 (27.994) Remain 21:53:23 loss: 0.2223 loss_seg: 0.1348 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:20:04,999 INFO misc.py line 117 726] Train: [15/20][246/510] Data 5.711 (3.776) Batch 31.491 (28.008) Remain 21:53:35 loss: 0.2748 loss_seg: 0.1774 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:20:30,769 INFO misc.py line 117 726] Train: [15/20][247/510] Data 2.584 (3.771) Batch 25.770 (27.999) Remain 21:52:41 loss: 0.2164 loss_seg: 0.1228 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:20:50,781 INFO misc.py line 117 726] Train: [15/20][248/510] Data 2.257 (3.765) Batch 20.013 (27.967) Remain 21:50:42 loss: 0.3692 loss_seg: 0.2673 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:21:17,113 INFO misc.py line 117 726] Train: [15/20][249/510] Data 2.783 (3.761) Batch 26.332 (27.960) Remain 21:49:55 loss: 0.2030 loss_seg: 0.1156 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:21:44,970 INFO misc.py line 117 726] Train: [15/20][250/510] Data 2.730 (3.757) Batch 27.857 (27.960) Remain 21:49:26 loss: 0.2266 loss_seg: 0.1351 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:21:44,970 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 03:22:13,507 INFO misc.py line 117 726] Train: [15/20][251/510] Data 4.083 (3.758) Batch 28.537 (27.962) Remain 21:49:04 loss: 0.2753 loss_seg: 0.1740 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:22:30,142 INFO misc.py line 117 726] Train: [15/20][252/510] Data 2.053 (3.751) Batch 16.635 (27.916) Remain 21:46:29 loss: 0.4091 loss_seg: 0.3107 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:22:54,341 INFO misc.py line 117 726] Train: [15/20][253/510] Data 3.169 (3.749) Batch 24.199 (27.902) Remain 21:45:19 loss: 0.2293 loss_seg: 0.1341 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:23:19,635 INFO misc.py line 117 726] Train: [15/20][254/510] Data 2.958 (3.746) Batch 25.293 (27.891) Remain 21:44:22 loss: 0.2292 loss_seg: 0.1372 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:23:48,265 INFO misc.py line 117 726] Train: [15/20][255/510] Data 3.928 (3.747) Batch 28.631 (27.894) Remain 21:44:02 loss: 0.2231 loss_seg: 0.1350 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:24:18,158 INFO misc.py line 117 726] Train: [15/20][256/510] Data 2.458 (3.742) Batch 29.892 (27.902) Remain 21:43:57 loss: 0.3117 loss_seg: 0.2164 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:24:51,877 INFO misc.py line 117 726] Train: [15/20][257/510] Data 3.545 (3.741) Batch 33.720 (27.925) Remain 21:44:33 loss: 0.2996 loss_seg: 0.2105 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:25:11,828 INFO misc.py line 117 726] Train: [15/20][258/510] Data 2.257 (3.735) Batch 19.951 (27.894) Remain 21:42:37 loss: 0.2097 loss_seg: 0.1177 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:25:43,580 INFO misc.py line 117 726] Train: [15/20][259/510] Data 3.266 (3.733) Batch 31.753 (27.909) Remain 21:42:52 loss: 0.2359 loss_seg: 0.1404 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:26:08,518 INFO misc.py line 117 726] Train: [15/20][260/510] Data 2.587 (3.729) Batch 24.938 (27.897) Remain 21:41:51 loss: 0.2725 loss_seg: 0.1678 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:26:27,803 INFO misc.py line 117 726] Train: [15/20][261/510] Data 2.382 (3.723) Batch 19.285 (27.864) Remain 21:39:50 loss: 0.2560 loss_seg: 0.1602 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:26:55,784 INFO misc.py line 117 726] Train: [15/20][262/510] Data 2.686 (3.719) Batch 27.981 (27.864) Remain 21:39:23 loss: 0.2325 loss_seg: 0.1367 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:27:25,388 INFO misc.py line 117 726] Train: [15/20][263/510] Data 4.531 (3.723) Batch 29.603 (27.871) Remain 21:39:14 loss: 0.2353 loss_seg: 0.1433 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:27:53,855 INFO misc.py line 117 726] Train: [15/20][264/510] Data 3.892 (3.723) Batch 28.467 (27.873) Remain 21:38:53 loss: 0.1835 loss_seg: 0.0959 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:28:27,296 INFO misc.py line 117 726] Train: [15/20][265/510] Data 5.267 (3.729) Batch 33.441 (27.894) Remain 21:39:24 loss: 0.1907 loss_seg: 0.1041 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:28:48,683 INFO misc.py line 117 726] Train: [15/20][266/510] Data 2.867 (3.726) Batch 21.386 (27.870) Remain 21:37:47 loss: 0.2510 loss_seg: 0.1544 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:29:17,476 INFO misc.py line 117 726] Train: [15/20][267/510] Data 3.645 (3.726) Batch 28.793 (27.873) Remain 21:37:29 loss: 0.2257 loss_seg: 0.1305 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:29:42,661 INFO misc.py line 117 726] Train: [15/20][268/510] Data 2.618 (3.721) Batch 25.186 (27.863) Remain 21:36:33 loss: 0.2195 loss_seg: 0.1305 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:30:12,328 INFO misc.py line 117 726] Train: [15/20][269/510] Data 3.456 (3.720) Batch 29.667 (27.870) Remain 21:36:24 loss: 0.2347 loss_seg: 0.1406 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:30:31,754 INFO misc.py line 117 726] Train: [15/20][270/510] Data 2.245 (3.715) Batch 19.426 (27.838) Remain 21:34:28 loss: 0.2946 loss_seg: 0.1832 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:30:55,483 INFO misc.py line 117 726] Train: [15/20][271/510] Data 3.034 (3.712) Batch 23.730 (27.823) Remain 21:33:17 loss: 0.2146 loss_seg: 0.1216 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:31:33,876 INFO misc.py line 117 726] Train: [15/20][272/510] Data 5.723 (3.720) Batch 38.392 (27.862) Remain 21:34:39 loss: 0.2014 loss_seg: 0.1147 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:32:00,097 INFO misc.py line 117 726] Train: [15/20][273/510] Data 2.937 (3.717) Batch 26.221 (27.856) Remain 21:33:54 loss: 0.2444 loss_seg: 0.1493 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:32:21,764 INFO misc.py line 117 726] Train: [15/20][274/510] Data 2.527 (3.712) Batch 21.667 (27.833) Remain 21:32:23 loss: 0.2168 loss_seg: 0.1240 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:32:50,410 INFO misc.py line 117 726] Train: [15/20][275/510] Data 3.320 (3.711) Batch 28.645 (27.836) Remain 21:32:03 loss: 0.1938 loss_seg: 0.1042 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:33:17,141 INFO misc.py line 117 726] Train: [15/20][276/510] Data 4.412 (3.714) Batch 26.732 (27.832) Remain 21:31:24 loss: 0.2864 loss_seg: 0.1818 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:33:46,453 INFO misc.py line 117 726] Train: [15/20][277/510] Data 2.958 (3.711) Batch 29.312 (27.838) Remain 21:31:11 loss: 0.3037 loss_seg: 0.1931 loss_superpoint_edge: 0.0447 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:34:11,536 INFO misc.py line 117 726] Train: [15/20][278/510] Data 4.029 (3.712) Batch 25.083 (27.828) Remain 21:30:16 loss: 0.2179 loss_seg: 0.1262 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:34:37,746 INFO misc.py line 117 726] Train: [15/20][279/510] Data 2.686 (3.708) Batch 26.209 (27.822) Remain 21:29:32 loss: 0.2826 loss_seg: 0.1815 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:34:59,557 INFO misc.py line 117 726] Train: [15/20][280/510] Data 3.012 (3.706) Batch 21.811 (27.800) Remain 21:28:03 loss: 0.2147 loss_seg: 0.1226 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:35:16,590 INFO misc.py line 117 726] Train: [15/20][281/510] Data 2.158 (3.700) Batch 17.034 (27.761) Remain 21:25:48 loss: 0.3217 loss_seg: 0.2253 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:35:48,184 INFO misc.py line 117 726] Train: [15/20][282/510] Data 8.092 (3.716) Batch 31.594 (27.775) Remain 21:25:58 loss: 0.2173 loss_seg: 0.1234 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:36:11,377 INFO misc.py line 117 726] Train: [15/20][283/510] Data 3.998 (3.717) Batch 23.194 (27.759) Remain 21:24:45 loss: 0.2562 loss_seg: 0.1615 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:36:34,643 INFO misc.py line 117 726] Train: [15/20][284/510] Data 2.159 (3.711) Batch 23.265 (27.743) Remain 21:23:33 loss: 0.2439 loss_seg: 0.1440 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:37:10,325 INFO misc.py line 117 726] Train: [15/20][285/510] Data 7.912 (3.726) Batch 35.682 (27.771) Remain 21:24:23 loss: 0.2658 loss_seg: 0.1643 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:37:43,661 INFO misc.py line 117 726] Train: [15/20][286/510] Data 6.725 (3.737) Batch 33.337 (27.790) Remain 21:24:50 loss: 0.2844 loss_seg: 0.1900 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:38:16,464 INFO misc.py line 117 726] Train: [15/20][287/510] Data 4.519 (3.740) Batch 32.803 (27.808) Remain 21:25:11 loss: 0.2651 loss_seg: 0.1684 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:38:47,885 INFO misc.py line 117 726] Train: [15/20][288/510] Data 3.362 (3.738) Batch 31.421 (27.821) Remain 21:25:19 loss: 0.2260 loss_seg: 0.1299 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:39:23,191 INFO misc.py line 117 726] Train: [15/20][289/510] Data 5.044 (3.743) Batch 35.305 (27.847) Remain 21:26:03 loss: 0.3669 loss_seg: 0.2625 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:39:57,768 INFO misc.py line 117 726] Train: [15/20][290/510] Data 5.999 (3.751) Batch 34.578 (27.870) Remain 21:26:41 loss: 0.2771 loss_seg: 0.1852 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:40:26,639 INFO misc.py line 117 726] Train: [15/20][291/510] Data 3.755 (3.751) Batch 28.871 (27.874) Remain 21:26:22 loss: 0.2838 loss_seg: 0.1916 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:40:58,551 INFO misc.py line 117 726] Train: [15/20][292/510] Data 5.386 (3.756) Batch 31.912 (27.888) Remain 21:26:33 loss: 0.2672 loss_seg: 0.1678 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:41:32,559 INFO misc.py line 117 726] Train: [15/20][293/510] Data 3.839 (3.757) Batch 34.009 (27.909) Remain 21:27:04 loss: 0.2787 loss_seg: 0.1818 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:42:05,398 INFO misc.py line 117 726] Train: [15/20][294/510] Data 5.006 (3.761) Batch 32.839 (27.926) Remain 21:27:23 loss: 0.3166 loss_seg: 0.2191 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:42:34,849 INFO misc.py line 117 726] Train: [15/20][295/510] Data 2.264 (3.756) Batch 29.451 (27.931) Remain 21:27:09 loss: 0.3000 loss_seg: 0.2004 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:43:07,540 INFO misc.py line 117 726] Train: [15/20][296/510] Data 5.717 (3.763) Batch 32.691 (27.947) Remain 21:27:26 loss: 0.2573 loss_seg: 0.1587 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:43:44,807 INFO misc.py line 117 726] Train: [15/20][297/510] Data 7.616 (3.776) Batch 37.268 (27.979) Remain 21:28:26 loss: 0.2345 loss_seg: 0.1394 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:44:10,694 INFO misc.py line 117 726] Train: [15/20][298/510] Data 3.042 (3.773) Batch 25.887 (27.972) Remain 21:27:38 loss: 0.2833 loss_seg: 0.1929 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:44:39,063 INFO misc.py line 117 726] Train: [15/20][299/510] Data 3.291 (3.772) Batch 28.369 (27.973) Remain 21:27:14 loss: 0.2093 loss_seg: 0.1160 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:45:14,290 INFO misc.py line 117 726] Train: [15/20][300/510] Data 8.978 (3.789) Batch 35.227 (27.998) Remain 21:27:53 loss: 0.2372 loss_seg: 0.1441 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:45:14,291 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 03:45:41,868 INFO misc.py line 117 726] Train: [15/20][301/510] Data 4.053 (3.790) Batch 27.578 (27.996) Remain 21:27:21 loss: 0.3247 loss_seg: 0.2221 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:46:06,562 INFO misc.py line 117 726] Train: [15/20][302/510] Data 4.416 (3.792) Batch 24.694 (27.985) Remain 21:26:23 loss: 0.2920 loss_seg: 0.1995 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:46:39,961 INFO misc.py line 117 726] Train: [15/20][303/510] Data 5.430 (3.798) Batch 33.399 (28.003) Remain 21:26:45 loss: 0.2825 loss_seg: 0.1744 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:46:59,435 INFO misc.py line 117 726] Train: [15/20][304/510] Data 2.200 (3.792) Batch 19.474 (27.975) Remain 21:24:59 loss: 0.1611 loss_seg: 0.0797 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:47:20,203 INFO misc.py line 117 726] Train: [15/20][305/510] Data 3.893 (3.793) Batch 20.768 (27.951) Remain 21:23:25 loss: 0.2818 loss_seg: 0.1827 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:47:48,717 INFO misc.py line 117 726] Train: [15/20][306/510] Data 4.729 (3.796) Batch 28.514 (27.953) Remain 21:23:02 loss: 0.2366 loss_seg: 0.1483 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:48:27,277 INFO misc.py line 117 726] Train: [15/20][307/510] Data 7.425 (3.808) Batch 38.560 (27.988) Remain 21:24:10 loss: 0.2418 loss_seg: 0.1523 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:49:00,575 INFO misc.py line 117 726] Train: [15/20][308/510] Data 4.257 (3.809) Batch 33.299 (28.005) Remain 21:24:30 loss: 0.2871 loss_seg: 0.1828 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:49:33,407 INFO misc.py line 117 726] Train: [15/20][309/510] Data 4.346 (3.811) Batch 32.832 (28.021) Remain 21:24:45 loss: 0.2521 loss_seg: 0.1520 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:50:02,447 INFO misc.py line 117 726] Train: [15/20][310/510] Data 3.291 (3.809) Batch 29.040 (28.024) Remain 21:24:27 loss: 0.3417 loss_seg: 0.2452 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:50:27,064 INFO misc.py line 117 726] Train: [15/20][311/510] Data 2.258 (3.804) Batch 24.618 (28.013) Remain 21:23:28 loss: 0.2344 loss_seg: 0.1406 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:50:52,594 INFO misc.py line 117 726] Train: [15/20][312/510] Data 3.492 (3.803) Batch 25.529 (28.005) Remain 21:22:38 loss: 0.2544 loss_seg: 0.1569 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:51:22,842 INFO misc.py line 117 726] Train: [15/20][313/510] Data 5.816 (3.810) Batch 30.248 (28.013) Remain 21:22:30 loss: 0.3418 loss_seg: 0.2449 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:51:55,223 INFO misc.py line 117 726] Train: [15/20][314/510] Data 2.914 (3.807) Batch 32.381 (28.027) Remain 21:22:40 loss: 0.2943 loss_seg: 0.1908 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:52:29,478 INFO misc.py line 117 726] Train: [15/20][315/510] Data 3.860 (3.807) Batch 34.255 (28.047) Remain 21:23:07 loss: 0.2395 loss_seg: 0.1446 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:52:57,481 INFO misc.py line 117 726] Train: [15/20][316/510] Data 5.534 (3.812) Batch 28.003 (28.046) Remain 21:22:39 loss: 0.1997 loss_seg: 0.1103 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:53:26,354 INFO misc.py line 117 726] Train: [15/20][317/510] Data 2.882 (3.809) Batch 28.873 (28.049) Remain 21:22:18 loss: 0.2635 loss_seg: 0.1694 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:53:48,837 INFO misc.py line 117 726] Train: [15/20][318/510] Data 4.040 (3.810) Batch 22.483 (28.031) Remain 21:21:01 loss: 0.2130 loss_seg: 0.1238 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:54:12,295 INFO misc.py line 117 726] Train: [15/20][319/510] Data 2.664 (3.807) Batch 23.459 (28.017) Remain 21:19:54 loss: 0.2346 loss_seg: 0.1436 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:54:42,338 INFO misc.py line 117 726] Train: [15/20][320/510] Data 5.698 (3.813) Batch 30.043 (28.023) Remain 21:19:43 loss: 0.2079 loss_seg: 0.1180 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:55:12,465 INFO misc.py line 117 726] Train: [15/20][321/510] Data 5.118 (3.817) Batch 30.126 (28.030) Remain 21:19:33 loss: 0.2255 loss_seg: 0.1303 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:55:43,533 INFO misc.py line 117 726] Train: [15/20][322/510] Data 2.585 (3.813) Batch 31.068 (28.039) Remain 21:19:31 loss: 0.1927 loss_seg: 0.1072 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:56:13,958 INFO misc.py line 117 726] Train: [15/20][323/510] Data 3.602 (3.812) Batch 30.425 (28.047) Remain 21:19:24 loss: 0.2340 loss_seg: 0.1415 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:56:43,980 INFO misc.py line 117 726] Train: [15/20][324/510] Data 3.614 (3.811) Batch 30.022 (28.053) Remain 21:19:13 loss: 0.2454 loss_seg: 0.1455 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:57:12,604 INFO misc.py line 117 726] Train: [15/20][325/510] Data 3.096 (3.809) Batch 28.624 (28.055) Remain 21:18:49 loss: 0.2213 loss_seg: 0.1324 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:57:44,840 INFO misc.py line 117 726] Train: [15/20][326/510] Data 3.639 (3.809) Batch 32.236 (28.068) Remain 21:18:57 loss: 0.2089 loss_seg: 0.1182 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:58:04,991 INFO misc.py line 117 726] Train: [15/20][327/510] Data 2.693 (3.805) Batch 20.151 (28.043) Remain 21:17:22 loss: 0.2672 loss_seg: 0.1648 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:58:31,615 INFO misc.py line 117 726] Train: [15/20][328/510] Data 2.823 (3.802) Batch 26.624 (28.039) Remain 21:16:42 loss: 0.2178 loss_seg: 0.1251 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:58:59,122 INFO misc.py line 117 726] Train: [15/20][329/510] Data 2.754 (3.799) Batch 27.507 (28.037) Remain 21:16:09 loss: 0.2304 loss_seg: 0.1353 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 03:59:36,982 INFO misc.py line 117 726] Train: [15/20][330/510] Data 9.224 (3.816) Batch 37.861 (28.067) Remain 21:17:03 loss: 0.3941 loss_seg: 0.2829 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:00:09,695 INFO misc.py line 117 726] Train: [15/20][331/510] Data 5.269 (3.820) Batch 32.713 (28.082) Remain 21:17:14 loss: 0.2114 loss_seg: 0.1237 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:00:38,851 INFO misc.py line 117 726] Train: [15/20][332/510] Data 2.358 (3.816) Batch 29.156 (28.085) Remain 21:16:55 loss: 0.2860 loss_seg: 0.1804 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:01:18,415 INFO misc.py line 117 726] Train: [15/20][333/510] Data 10.608 (3.836) Batch 39.564 (28.120) Remain 21:18:02 loss: 0.2154 loss_seg: 0.1241 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:01:38,986 INFO misc.py line 117 726] Train: [15/20][334/510] Data 2.504 (3.832) Batch 20.571 (28.097) Remain 21:16:31 loss: 0.2652 loss_seg: 0.1618 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:02:11,028 INFO misc.py line 117 726] Train: [15/20][335/510] Data 5.297 (3.837) Batch 32.042 (28.109) Remain 21:16:36 loss: 0.3120 loss_seg: 0.2237 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:02:40,854 INFO misc.py line 117 726] Train: [15/20][336/510] Data 3.360 (3.835) Batch 29.827 (28.114) Remain 21:16:21 loss: 0.2746 loss_seg: 0.1737 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:03:12,345 INFO misc.py line 117 726] Train: [15/20][337/510] Data 4.246 (3.836) Batch 31.491 (28.124) Remain 21:16:21 loss: 0.3219 loss_seg: 0.2298 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:03:41,907 INFO misc.py line 117 726] Train: [15/20][338/510] Data 2.840 (3.833) Batch 29.562 (28.128) Remain 21:16:04 loss: 0.2216 loss_seg: 0.1276 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:04:11,313 INFO misc.py line 117 726] Train: [15/20][339/510] Data 3.281 (3.832) Batch 29.406 (28.132) Remain 21:15:47 loss: 0.1925 loss_seg: 0.1106 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:04:45,619 INFO misc.py line 117 726] Train: [15/20][340/510] Data 4.227 (3.833) Batch 34.306 (28.150) Remain 21:16:08 loss: 0.2503 loss_seg: 0.1521 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:05:12,126 INFO misc.py line 117 726] Train: [15/20][341/510] Data 1.972 (3.827) Batch 26.506 (28.145) Remain 21:15:27 loss: 0.2128 loss_seg: 0.1209 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:05:39,991 INFO misc.py line 117 726] Train: [15/20][342/510] Data 3.622 (3.827) Batch 27.866 (28.145) Remain 21:14:57 loss: 0.2451 loss_seg: 0.1516 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:06:03,541 INFO misc.py line 117 726] Train: [15/20][343/510] Data 3.322 (3.825) Batch 23.550 (28.131) Remain 21:13:52 loss: 0.2525 loss_seg: 0.1607 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:06:33,690 INFO misc.py line 117 726] Train: [15/20][344/510] Data 4.182 (3.826) Batch 30.149 (28.137) Remain 21:13:40 loss: 0.2170 loss_seg: 0.1260 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:06:59,191 INFO misc.py line 117 726] Train: [15/20][345/510] Data 2.708 (3.823) Batch 25.501 (28.129) Remain 21:12:51 loss: 0.2285 loss_seg: 0.1358 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:07:25,296 INFO misc.py line 117 726] Train: [15/20][346/510] Data 2.722 (3.820) Batch 26.105 (28.123) Remain 21:12:06 loss: 0.2428 loss_seg: 0.1456 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:07:49,417 INFO misc.py line 117 726] Train: [15/20][347/510] Data 2.412 (3.816) Batch 24.121 (28.112) Remain 21:11:07 loss: 0.2524 loss_seg: 0.1529 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:08:17,656 INFO misc.py line 117 726] Train: [15/20][348/510] Data 2.976 (3.813) Batch 28.239 (28.112) Remain 21:10:40 loss: 0.2107 loss_seg: 0.1190 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:08:51,171 INFO misc.py line 117 726] Train: [15/20][349/510] Data 5.622 (3.819) Batch 33.515 (28.128) Remain 21:10:54 loss: 0.2158 loss_seg: 0.1247 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:09:18,629 INFO misc.py line 117 726] Train: [15/20][350/510] Data 3.146 (3.817) Batch 27.458 (28.126) Remain 21:10:21 loss: 0.2229 loss_seg: 0.1285 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:09:18,629 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 04:09:47,683 INFO misc.py line 117 726] Train: [15/20][351/510] Data 4.293 (3.818) Batch 29.054 (28.129) Remain 21:10:00 loss: 0.1897 loss_seg: 0.0988 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:10:16,183 INFO misc.py line 117 726] Train: [15/20][352/510] Data 3.358 (3.817) Batch 28.501 (28.130) Remain 21:09:34 loss: 0.2858 loss_seg: 0.1824 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:10:47,240 INFO misc.py line 117 726] Train: [15/20][353/510] Data 3.934 (3.817) Batch 31.057 (28.138) Remain 21:09:29 loss: 0.2077 loss_seg: 0.1187 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:11:08,805 INFO misc.py line 117 726] Train: [15/20][354/510] Data 2.599 (3.814) Batch 21.565 (28.119) Remain 21:08:10 loss: 0.2519 loss_seg: 0.1524 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:11:35,573 INFO misc.py line 117 726] Train: [15/20][355/510] Data 4.299 (3.815) Batch 26.768 (28.115) Remain 21:07:32 loss: 0.3007 loss_seg: 0.2038 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:12:01,470 INFO misc.py line 117 726] Train: [15/20][356/510] Data 3.600 (3.814) Batch 25.897 (28.109) Remain 21:06:46 loss: 0.3249 loss_seg: 0.2182 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:12:36,605 INFO misc.py line 117 726] Train: [15/20][357/510] Data 11.594 (3.836) Batch 35.134 (28.129) Remain 21:07:12 loss: 0.2098 loss_seg: 0.1154 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:12:53,908 INFO misc.py line 117 726] Train: [15/20][358/510] Data 2.196 (3.832) Batch 17.303 (28.098) Remain 21:05:21 loss: 0.1933 loss_seg: 0.1061 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:13:22,832 INFO misc.py line 117 726] Train: [15/20][359/510] Data 3.204 (3.830) Batch 28.925 (28.101) Remain 21:05:00 loss: 0.2588 loss_seg: 0.1666 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:13:48,068 INFO misc.py line 117 726] Train: [15/20][360/510] Data 2.377 (3.826) Batch 25.235 (28.093) Remain 21:04:10 loss: 0.2567 loss_seg: 0.1566 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:14:11,307 INFO misc.py line 117 726] Train: [15/20][361/510] Data 2.803 (3.823) Batch 23.239 (28.079) Remain 21:03:05 loss: 0.2533 loss_seg: 0.1561 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:14:28,473 INFO misc.py line 117 726] Train: [15/20][362/510] Data 2.660 (3.820) Batch 17.166 (28.049) Remain 21:01:15 loss: 0.2446 loss_seg: 0.1435 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:15:02,914 INFO misc.py line 117 726] Train: [15/20][363/510] Data 4.313 (3.821) Batch 34.442 (28.067) Remain 21:01:35 loss: 0.2678 loss_seg: 0.1693 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:15:24,699 INFO misc.py line 117 726] Train: [15/20][364/510] Data 2.628 (3.818) Batch 21.785 (28.049) Remain 21:00:20 loss: 0.2448 loss_seg: 0.1485 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:15:47,595 INFO misc.py line 117 726] Train: [15/20][365/510] Data 2.623 (3.815) Batch 22.896 (28.035) Remain 20:59:14 loss: 0.3191 loss_seg: 0.2223 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:16:14,162 INFO misc.py line 117 726] Train: [15/20][366/510] Data 2.060 (3.810) Batch 26.566 (28.031) Remain 20:58:35 loss: 0.2114 loss_seg: 0.1214 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:16:44,189 INFO misc.py line 117 726] Train: [15/20][367/510] Data 4.121 (3.811) Batch 30.027 (28.036) Remain 20:58:21 loss: 0.2791 loss_seg: 0.1858 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:17:10,201 INFO misc.py line 117 726] Train: [15/20][368/510] Data 3.198 (3.809) Batch 26.013 (28.031) Remain 20:57:38 loss: 0.3530 loss_seg: 0.2392 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:17:35,872 INFO misc.py line 117 726] Train: [15/20][369/510] Data 2.515 (3.805) Batch 25.671 (28.024) Remain 20:56:53 loss: 0.2418 loss_seg: 0.1479 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:18:07,656 INFO misc.py line 117 726] Train: [15/20][370/510] Data 3.111 (3.803) Batch 31.784 (28.035) Remain 20:56:53 loss: 0.2572 loss_seg: 0.1618 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:18:40,461 INFO misc.py line 117 726] Train: [15/20][371/510] Data 4.258 (3.805) Batch 32.805 (28.048) Remain 20:56:59 loss: 0.3216 loss_seg: 0.2308 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:19:08,321 INFO misc.py line 117 726] Train: [15/20][372/510] Data 3.131 (3.803) Batch 27.860 (28.047) Remain 20:56:30 loss: 0.2542 loss_seg: 0.1597 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:19:42,315 INFO misc.py line 117 726] Train: [15/20][373/510] Data 6.204 (3.809) Batch 33.994 (28.063) Remain 20:56:45 loss: 0.1797 loss_seg: 0.0981 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:20:06,709 INFO misc.py line 117 726] Train: [15/20][374/510] Data 5.116 (3.813) Batch 24.393 (28.053) Remain 20:55:50 loss: 0.2514 loss_seg: 0.1588 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:20:32,712 INFO misc.py line 117 726] Train: [15/20][375/510] Data 2.856 (3.810) Batch 26.003 (28.048) Remain 20:55:08 loss: 0.2242 loss_seg: 0.1363 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:21:03,907 INFO misc.py line 117 726] Train: [15/20][376/510] Data 3.385 (3.809) Batch 31.195 (28.056) Remain 20:55:02 loss: 0.2136 loss_seg: 0.1279 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:21:25,619 INFO misc.py line 117 726] Train: [15/20][377/510] Data 3.366 (3.808) Batch 21.712 (28.039) Remain 20:53:49 loss: 0.2044 loss_seg: 0.1174 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:22:00,999 INFO misc.py line 117 726] Train: [15/20][378/510] Data 4.353 (3.809) Batch 35.379 (28.059) Remain 20:54:13 loss: 0.2224 loss_seg: 0.1347 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:22:31,168 INFO misc.py line 117 726] Train: [15/20][379/510] Data 3.184 (3.808) Batch 30.170 (28.064) Remain 20:54:00 loss: 0.2124 loss_seg: 0.1180 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:23:06,195 INFO misc.py line 117 726] Train: [15/20][380/510] Data 9.950 (3.824) Batch 35.026 (28.083) Remain 20:54:22 loss: 0.2432 loss_seg: 0.1532 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:23:33,735 INFO misc.py line 117 726] Train: [15/20][381/510] Data 3.239 (3.823) Batch 27.540 (28.081) Remain 20:53:50 loss: 0.2529 loss_seg: 0.1559 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:23:59,294 INFO misc.py line 117 726] Train: [15/20][382/510] Data 2.616 (3.819) Batch 25.559 (28.075) Remain 20:53:04 loss: 0.2012 loss_seg: 0.1101 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:24:24,343 INFO misc.py line 117 726] Train: [15/20][383/510] Data 4.422 (3.821) Batch 25.049 (28.067) Remain 20:52:14 loss: 0.1897 loss_seg: 0.1040 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:24:42,862 INFO misc.py line 117 726] Train: [15/20][384/510] Data 1.485 (3.815) Batch 18.519 (28.042) Remain 20:50:39 loss: 0.2348 loss_seg: 0.1445 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:25:13,012 INFO misc.py line 117 726] Train: [15/20][385/510] Data 3.607 (3.814) Batch 30.151 (28.047) Remain 20:50:26 loss: 0.2130 loss_seg: 0.1226 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:25:45,596 INFO misc.py line 117 726] Train: [15/20][386/510] Data 5.367 (3.818) Batch 32.584 (28.059) Remain 20:50:30 loss: 0.3083 loss_seg: 0.2194 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:26:16,274 INFO misc.py line 117 726] Train: [15/20][387/510] Data 3.002 (3.816) Batch 30.678 (28.066) Remain 20:50:20 loss: 0.2053 loss_seg: 0.1155 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:26:47,922 INFO misc.py line 117 726] Train: [15/20][388/510] Data 5.362 (3.820) Batch 31.647 (28.075) Remain 20:50:16 loss: 0.2700 loss_seg: 0.1697 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:27:11,350 INFO misc.py line 117 726] Train: [15/20][389/510] Data 2.376 (3.816) Batch 23.429 (28.063) Remain 20:49:16 loss: 0.2281 loss_seg: 0.1396 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:27:37,999 INFO misc.py line 117 726] Train: [15/20][390/510] Data 2.415 (3.813) Batch 26.649 (28.060) Remain 20:48:38 loss: 0.3062 loss_seg: 0.1994 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:28:07,116 INFO misc.py line 117 726] Train: [15/20][391/510] Data 3.621 (3.812) Batch 29.117 (28.062) Remain 20:48:18 loss: 0.2599 loss_seg: 0.1619 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:28:29,854 INFO misc.py line 117 726] Train: [15/20][392/510] Data 2.911 (3.810) Batch 22.738 (28.049) Remain 20:47:13 loss: 0.2352 loss_seg: 0.1446 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:28:56,567 INFO misc.py line 117 726] Train: [15/20][393/510] Data 2.908 (3.808) Batch 26.712 (28.045) Remain 20:46:36 loss: 0.2658 loss_seg: 0.1648 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:29:18,129 INFO misc.py line 117 726] Train: [15/20][394/510] Data 2.183 (3.804) Batch 21.562 (28.029) Remain 20:45:24 loss: 0.2505 loss_seg: 0.1543 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:29:47,629 INFO misc.py line 117 726] Train: [15/20][395/510] Data 3.510 (3.803) Batch 29.499 (28.032) Remain 20:45:06 loss: 0.2975 loss_seg: 0.2065 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:30:18,356 INFO misc.py line 117 726] Train: [15/20][396/510] Data 3.453 (3.802) Batch 30.727 (28.039) Remain 20:44:56 loss: 0.2321 loss_seg: 0.1367 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:30:55,696 INFO misc.py line 117 726] Train: [15/20][397/510] Data 4.927 (3.805) Batch 37.341 (28.063) Remain 20:45:31 loss: 0.2601 loss_seg: 0.1643 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:31:22,303 INFO misc.py line 117 726] Train: [15/20][398/510] Data 2.885 (3.802) Batch 26.607 (28.059) Remain 20:44:53 loss: 0.1560 loss_seg: 0.0758 loss_superpoint_edge: 0.0137 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:31:47,502 INFO misc.py line 117 726] Train: [15/20][399/510] Data 3.235 (3.801) Batch 25.199 (28.052) Remain 20:44:06 loss: 0.1830 loss_seg: 0.0984 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:32:14,252 INFO misc.py line 117 726] Train: [15/20][400/510] Data 4.920 (3.804) Batch 26.750 (28.049) Remain 20:43:29 loss: 0.2139 loss_seg: 0.1266 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:32:14,253 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 04:32:39,711 INFO misc.py line 117 726] Train: [15/20][401/510] Data 3.043 (3.802) Batch 25.459 (28.042) Remain 20:42:43 loss: 0.2010 loss_seg: 0.1151 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:33:02,150 INFO misc.py line 117 726] Train: [15/20][402/510] Data 2.332 (3.798) Batch 22.439 (28.028) Remain 20:41:38 loss: 0.2288 loss_seg: 0.1360 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:33:30,721 INFO misc.py line 117 726] Train: [15/20][403/510] Data 3.860 (3.798) Batch 28.571 (28.029) Remain 20:41:14 loss: 0.3556 loss_seg: 0.2544 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:33:57,552 INFO misc.py line 117 726] Train: [15/20][404/510] Data 3.083 (3.797) Batch 26.831 (28.026) Remain 20:40:38 loss: 0.1419 loss_seg: 0.0622 loss_superpoint_edge: 0.0108 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:34:23,854 INFO misc.py line 117 726] Train: [15/20][405/510] Data 3.219 (3.795) Batch 26.302 (28.022) Remain 20:39:58 loss: 0.2410 loss_seg: 0.1480 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:34:52,731 INFO misc.py line 117 726] Train: [15/20][406/510] Data 4.477 (3.797) Batch 28.877 (28.024) Remain 20:39:36 loss: 0.2356 loss_seg: 0.1439 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:35:23,203 INFO misc.py line 117 726] Train: [15/20][407/510] Data 3.369 (3.796) Batch 30.472 (28.030) Remain 20:39:24 loss: 0.2008 loss_seg: 0.1105 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:35:49,913 INFO misc.py line 117 726] Train: [15/20][408/510] Data 3.127 (3.794) Batch 26.710 (28.027) Remain 20:38:47 loss: 0.2428 loss_seg: 0.1462 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:36:16,750 INFO misc.py line 117 726] Train: [15/20][409/510] Data 2.697 (3.791) Batch 26.837 (28.024) Remain 20:38:11 loss: 0.2503 loss_seg: 0.1546 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:36:41,151 INFO misc.py line 117 726] Train: [15/20][410/510] Data 3.080 (3.790) Batch 24.402 (28.015) Remain 20:37:20 loss: 0.3079 loss_seg: 0.2022 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:37:10,447 INFO misc.py line 117 726] Train: [15/20][411/510] Data 6.014 (3.795) Batch 29.296 (28.018) Remain 20:37:00 loss: 0.3801 loss_seg: 0.2863 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:37:30,223 INFO misc.py line 117 726] Train: [15/20][412/510] Data 3.004 (3.793) Batch 19.776 (27.998) Remain 20:35:39 loss: 0.2348 loss_seg: 0.1444 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:37:57,674 INFO misc.py line 117 726] Train: [15/20][413/510] Data 3.398 (3.792) Batch 27.451 (27.997) Remain 20:35:07 loss: 0.2447 loss_seg: 0.1495 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:38:24,901 INFO misc.py line 117 726] Train: [15/20][414/510] Data 3.322 (3.791) Batch 27.227 (27.995) Remain 20:34:34 loss: 0.1845 loss_seg: 0.0976 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:38:51,949 INFO misc.py line 117 726] Train: [15/20][415/510] Data 2.181 (3.787) Batch 27.048 (27.993) Remain 20:34:00 loss: 0.2756 loss_seg: 0.1698 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:39:30,281 INFO misc.py line 117 726] Train: [15/20][416/510] Data 8.179 (3.798) Batch 38.332 (28.018) Remain 20:34:38 loss: 0.2443 loss_seg: 0.1466 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:39:56,581 INFO misc.py line 117 726] Train: [15/20][417/510] Data 3.785 (3.798) Batch 26.300 (28.014) Remain 20:33:59 loss: 0.2373 loss_seg: 0.1443 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:40:25,481 INFO misc.py line 117 726] Train: [15/20][418/510] Data 3.337 (3.797) Batch 28.900 (28.016) Remain 20:33:37 loss: 0.2995 loss_seg: 0.2057 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:41:00,733 INFO misc.py line 117 726] Train: [15/20][419/510] Data 4.136 (3.798) Batch 35.253 (28.033) Remain 20:33:55 loss: 0.2755 loss_seg: 0.1759 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:41:37,394 INFO misc.py line 117 726] Train: [15/20][420/510] Data 5.640 (3.802) Batch 36.660 (28.054) Remain 20:34:22 loss: 0.2450 loss_seg: 0.1502 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:42:07,106 INFO misc.py line 117 726] Train: [15/20][421/510] Data 3.759 (3.802) Batch 29.712 (28.058) Remain 20:34:04 loss: 0.1997 loss_seg: 0.1118 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:42:35,955 INFO misc.py line 117 726] Train: [15/20][422/510] Data 2.497 (3.799) Batch 28.849 (28.060) Remain 20:33:41 loss: 0.2006 loss_seg: 0.1142 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:43:09,454 INFO misc.py line 117 726] Train: [15/20][423/510] Data 6.123 (3.804) Batch 33.500 (28.073) Remain 20:33:47 loss: 0.2108 loss_seg: 0.1275 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:43:38,521 INFO misc.py line 117 726] Train: [15/20][424/510] Data 2.936 (3.802) Batch 29.066 (28.075) Remain 20:33:25 loss: 0.2303 loss_seg: 0.1403 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:43:57,845 INFO misc.py line 117 726] Train: [15/20][425/510] Data 2.996 (3.800) Batch 19.325 (28.054) Remain 20:32:02 loss: 0.3190 loss_seg: 0.2239 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:44:23,059 INFO misc.py line 117 726] Train: [15/20][426/510] Data 2.829 (3.798) Batch 25.214 (28.048) Remain 20:31:17 loss: 0.2252 loss_seg: 0.1324 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:44:58,725 INFO misc.py line 117 726] Train: [15/20][427/510] Data 5.389 (3.802) Batch 35.666 (28.065) Remain 20:31:36 loss: 0.2273 loss_seg: 0.1276 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:45:21,358 INFO misc.py line 117 726] Train: [15/20][428/510] Data 2.428 (3.798) Batch 22.633 (28.053) Remain 20:30:34 loss: 0.2639 loss_seg: 0.1614 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:45:44,108 INFO misc.py line 117 726] Train: [15/20][429/510] Data 2.357 (3.795) Batch 22.751 (28.040) Remain 20:29:33 loss: 0.2033 loss_seg: 0.1122 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:46:13,763 INFO misc.py line 117 726] Train: [15/20][430/510] Data 6.292 (3.801) Batch 29.654 (28.044) Remain 20:29:15 loss: 0.2052 loss_seg: 0.1149 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:46:35,996 INFO misc.py line 117 726] Train: [15/20][431/510] Data 2.325 (3.798) Batch 22.233 (28.030) Remain 20:28:12 loss: 0.2158 loss_seg: 0.1232 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:47:18,515 INFO misc.py line 117 726] Train: [15/20][432/510] Data 12.193 (3.817) Batch 42.519 (28.064) Remain 20:29:12 loss: 0.2304 loss_seg: 0.1331 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:47:37,949 INFO misc.py line 117 726] Train: [15/20][433/510] Data 2.002 (3.813) Batch 19.434 (28.044) Remain 20:27:51 loss: 0.2528 loss_seg: 0.1610 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:48:01,804 INFO misc.py line 117 726] Train: [15/20][434/510] Data 3.180 (3.811) Batch 23.855 (28.034) Remain 20:26:58 loss: 0.2492 loss_seg: 0.1574 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:48:32,626 INFO misc.py line 117 726] Train: [15/20][435/510] Data 4.484 (3.813) Batch 30.822 (28.041) Remain 20:26:47 loss: 0.2828 loss_seg: 0.1815 loss_superpoint_edge: 0.0354 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:48:58,816 INFO misc.py line 117 726] Train: [15/20][436/510] Data 2.861 (3.811) Batch 26.191 (28.037) Remain 20:26:08 loss: 0.2288 loss_seg: 0.1327 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:49:29,077 INFO misc.py line 117 726] Train: [15/20][437/510] Data 5.648 (3.815) Batch 30.260 (28.042) Remain 20:25:53 loss: 0.2840 loss_seg: 0.1867 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:49:50,722 INFO misc.py line 117 726] Train: [15/20][438/510] Data 2.945 (3.813) Batch 21.645 (28.027) Remain 20:24:46 loss: 0.2465 loss_seg: 0.1487 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:50:11,603 INFO misc.py line 117 726] Train: [15/20][439/510] Data 2.422 (3.810) Batch 20.881 (28.011) Remain 20:23:35 loss: 0.2866 loss_seg: 0.1819 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:50:51,875 INFO misc.py line 117 726] Train: [15/20][440/510] Data 7.092 (3.817) Batch 40.272 (28.039) Remain 20:24:21 loss: 0.3140 loss_seg: 0.2247 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:51:16,915 INFO misc.py line 117 726] Train: [15/20][441/510] Data 2.342 (3.814) Batch 25.040 (28.032) Remain 20:23:35 loss: 0.2106 loss_seg: 0.1220 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:51:45,870 INFO misc.py line 117 726] Train: [15/20][442/510] Data 3.073 (3.812) Batch 28.955 (28.034) Remain 20:23:12 loss: 0.2239 loss_seg: 0.1293 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:52:09,520 INFO misc.py line 117 726] Train: [15/20][443/510] Data 2.519 (3.809) Batch 23.650 (28.024) Remain 20:22:18 loss: 0.3389 loss_seg: 0.2257 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:52:29,818 INFO misc.py line 117 726] Train: [15/20][444/510] Data 2.206 (3.806) Batch 20.299 (28.006) Remain 20:21:04 loss: 0.2668 loss_seg: 0.1685 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:52:56,867 INFO misc.py line 117 726] Train: [15/20][445/510] Data 2.808 (3.803) Batch 27.048 (28.004) Remain 20:20:31 loss: 0.2161 loss_seg: 0.1238 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:53:22,606 INFO misc.py line 117 726] Train: [15/20][446/510] Data 2.918 (3.801) Batch 25.740 (27.999) Remain 20:19:49 loss: 0.2266 loss_seg: 0.1366 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:53:42,592 INFO misc.py line 117 726] Train: [15/20][447/510] Data 1.855 (3.797) Batch 19.986 (27.981) Remain 20:18:34 loss: 0.2109 loss_seg: 0.1187 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:54:04,340 INFO misc.py line 117 726] Train: [15/20][448/510] Data 3.796 (3.797) Batch 21.748 (27.967) Remain 20:17:30 loss: 0.2372 loss_seg: 0.1445 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:54:28,744 INFO misc.py line 117 726] Train: [15/20][449/510] Data 2.737 (3.795) Batch 24.405 (27.959) Remain 20:16:41 loss: 0.1936 loss_seg: 0.1042 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:55:00,565 INFO misc.py line 117 726] Train: [15/20][450/510] Data 3.785 (3.795) Batch 31.821 (27.968) Remain 20:16:35 loss: 0.2193 loss_seg: 0.1275 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:55:00,566 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 04:55:24,564 INFO misc.py line 117 726] Train: [15/20][451/510] Data 2.903 (3.793) Batch 23.998 (27.959) Remain 20:15:44 loss: 0.2482 loss_seg: 0.1494 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:55:39,845 INFO misc.py line 117 726] Train: [15/20][452/510] Data 2.070 (3.789) Batch 15.281 (27.931) Remain 20:14:03 loss: 0.2176 loss_seg: 0.1249 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:56:04,520 INFO misc.py line 117 726] Train: [15/20][453/510] Data 3.124 (3.787) Batch 24.675 (27.923) Remain 20:13:16 loss: 0.1730 loss_seg: 0.0860 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:56:36,279 INFO misc.py line 117 726] Train: [15/20][454/510] Data 4.437 (3.789) Batch 31.759 (27.932) Remain 20:13:10 loss: 0.2416 loss_seg: 0.1490 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:57:09,167 INFO misc.py line 117 726] Train: [15/20][455/510] Data 2.886 (3.787) Batch 32.888 (27.943) Remain 20:13:11 loss: 0.2141 loss_seg: 0.1240 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:57:44,635 INFO misc.py line 117 726] Train: [15/20][456/510] Data 4.650 (3.789) Batch 35.468 (27.960) Remain 20:13:26 loss: 0.2332 loss_seg: 0.1381 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:58:18,265 INFO misc.py line 117 726] Train: [15/20][457/510] Data 4.569 (3.790) Batch 33.630 (27.972) Remain 20:13:31 loss: 0.2136 loss_seg: 0.1264 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:58:56,691 INFO misc.py line 117 726] Train: [15/20][458/510] Data 5.416 (3.794) Batch 38.426 (27.995) Remain 20:14:03 loss: 0.3286 loss_seg: 0.2234 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:59:27,282 INFO misc.py line 117 726] Train: [15/20][459/510] Data 3.258 (3.793) Batch 30.591 (28.001) Remain 20:13:49 loss: 0.2112 loss_seg: 0.1185 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 04:59:49,688 INFO misc.py line 117 726] Train: [15/20][460/510] Data 3.512 (3.792) Batch 22.406 (27.988) Remain 20:12:49 loss: 0.2613 loss_seg: 0.1652 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:00:07,068 INFO misc.py line 117 726] Train: [15/20][461/510] Data 1.881 (3.788) Batch 17.380 (27.965) Remain 20:11:21 loss: 0.3477 loss_seg: 0.2493 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:00:37,769 INFO misc.py line 117 726] Train: [15/20][462/510] Data 3.942 (3.788) Batch 30.700 (27.971) Remain 20:11:09 loss: 0.2202 loss_seg: 0.1299 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:01:07,033 INFO misc.py line 117 726] Train: [15/20][463/510] Data 4.475 (3.790) Batch 29.264 (27.974) Remain 20:10:48 loss: 0.2435 loss_seg: 0.1489 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:01:43,393 INFO misc.py line 117 726] Train: [15/20][464/510] Data 5.569 (3.794) Batch 36.360 (27.992) Remain 20:11:07 loss: 0.2488 loss_seg: 0.1549 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:02:09,743 INFO misc.py line 117 726] Train: [15/20][465/510] Data 3.026 (3.792) Batch 26.347 (27.989) Remain 20:10:30 loss: 0.2527 loss_seg: 0.1549 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:02:27,298 INFO misc.py line 117 726] Train: [15/20][466/510] Data 2.274 (3.789) Batch 17.558 (27.966) Remain 20:09:04 loss: 0.2125 loss_seg: 0.1191 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:02:46,193 INFO misc.py line 117 726] Train: [15/20][467/510] Data 2.246 (3.785) Batch 18.895 (27.947) Remain 20:07:45 loss: 0.2107 loss_seg: 0.1143 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:03:14,409 INFO misc.py line 117 726] Train: [15/20][468/510] Data 2.642 (3.783) Batch 28.217 (27.947) Remain 20:07:19 loss: 0.1943 loss_seg: 0.1055 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:03:48,938 INFO misc.py line 117 726] Train: [15/20][469/510] Data 3.195 (3.782) Batch 34.528 (27.961) Remain 20:07:27 loss: 0.3032 loss_seg: 0.2101 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:04:23,669 INFO misc.py line 117 726] Train: [15/20][470/510] Data 4.361 (3.783) Batch 34.732 (27.976) Remain 20:07:37 loss: 0.2853 loss_seg: 0.1877 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:04:49,532 INFO misc.py line 117 726] Train: [15/20][471/510] Data 2.907 (3.781) Batch 25.863 (27.971) Remain 20:06:57 loss: 0.2088 loss_seg: 0.1174 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:05:21,854 INFO misc.py line 117 726] Train: [15/20][472/510] Data 3.348 (3.780) Batch 32.322 (27.981) Remain 20:06:53 loss: 0.2561 loss_seg: 0.1604 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:05:49,545 INFO misc.py line 117 726] Train: [15/20][473/510] Data 4.783 (3.782) Batch 27.691 (27.980) Remain 20:06:24 loss: 0.1819 loss_seg: 0.0986 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:06:24,974 INFO misc.py line 117 726] Train: [15/20][474/510] Data 5.181 (3.785) Batch 35.429 (27.996) Remain 20:06:37 loss: 0.1826 loss_seg: 0.0954 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0294 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:06:54,302 INFO misc.py line 117 726] Train: [15/20][475/510] Data 3.224 (3.784) Batch 29.328 (27.999) Remain 20:06:16 loss: 0.2038 loss_seg: 0.1144 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:07:21,142 INFO misc.py line 117 726] Train: [15/20][476/510] Data 2.906 (3.782) Batch 26.840 (27.996) Remain 20:05:42 loss: 0.2275 loss_seg: 0.1356 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:07:38,104 INFO misc.py line 117 726] Train: [15/20][477/510] Data 1.783 (3.778) Batch 16.962 (27.973) Remain 20:04:13 loss: 0.2117 loss_seg: 0.1216 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:08:04,342 INFO misc.py line 117 726] Train: [15/20][478/510] Data 2.787 (3.776) Batch 26.238 (27.969) Remain 20:03:36 loss: 0.2119 loss_seg: 0.1178 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:08:30,902 INFO misc.py line 117 726] Train: [15/20][479/510] Data 6.028 (3.781) Batch 26.560 (27.966) Remain 20:03:00 loss: 0.1822 loss_seg: 0.0976 loss_superpoint_edge: 0.0143 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:09:03,719 INFO misc.py line 117 726] Train: [15/20][480/510] Data 6.078 (3.785) Batch 32.817 (27.976) Remain 20:02:59 loss: 0.1975 loss_seg: 0.1043 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:09:34,852 INFO misc.py line 117 726] Train: [15/20][481/510] Data 7.824 (3.794) Batch 31.133 (27.983) Remain 20:02:48 loss: 0.2523 loss_seg: 0.1517 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:10:05,260 INFO misc.py line 117 726] Train: [15/20][482/510] Data 3.878 (3.794) Batch 30.408 (27.988) Remain 20:02:33 loss: 0.3100 loss_seg: 0.2003 loss_superpoint_edge: 0.0405 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:10:41,946 INFO misc.py line 117 726] Train: [15/20][483/510] Data 3.990 (3.794) Batch 36.686 (28.006) Remain 20:02:52 loss: 0.2235 loss_seg: 0.1312 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:11:21,322 INFO misc.py line 117 726] Train: [15/20][484/510] Data 6.879 (3.801) Batch 39.376 (28.030) Remain 20:03:24 loss: 0.2764 loss_seg: 0.1780 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:11:53,206 INFO misc.py line 117 726] Train: [15/20][485/510] Data 4.226 (3.802) Batch 31.884 (28.038) Remain 20:03:17 loss: 0.2317 loss_seg: 0.1388 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:12:23,309 INFO misc.py line 117 726] Train: [15/20][486/510] Data 3.513 (3.801) Batch 30.103 (28.042) Remain 20:03:00 loss: 0.2452 loss_seg: 0.1514 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:12:42,674 INFO misc.py line 117 726] Train: [15/20][487/510] Data 2.274 (3.798) Batch 19.365 (28.024) Remain 20:01:46 loss: 0.2312 loss_seg: 0.1357 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:13:03,340 INFO misc.py line 117 726] Train: [15/20][488/510] Data 3.762 (3.798) Batch 20.665 (28.009) Remain 20:00:39 loss: 0.1956 loss_seg: 0.1015 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:13:42,982 INFO misc.py line 117 726] Train: [15/20][489/510] Data 11.188 (3.813) Batch 39.643 (28.033) Remain 20:01:12 loss: 0.1936 loss_seg: 0.1100 loss_superpoint_edge: 0.0139 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:14:09,612 INFO misc.py line 117 726] Train: [15/20][490/510] Data 3.695 (3.813) Batch 26.630 (28.030) Remain 20:00:37 loss: 0.3820 loss_seg: 0.2626 loss_superpoint_edge: 0.0512 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:14:44,479 INFO misc.py line 117 726] Train: [15/20][491/510] Data 5.601 (3.817) Batch 34.867 (28.044) Remain 20:00:45 loss: 0.2967 loss_seg: 0.1908 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:15:06,993 INFO misc.py line 117 726] Train: [15/20][492/510] Data 3.095 (3.815) Batch 22.514 (28.033) Remain 19:59:48 loss: 0.3169 loss_seg: 0.2212 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:15:31,010 INFO misc.py line 117 726] Train: [15/20][493/510] Data 3.244 (3.814) Batch 24.016 (28.025) Remain 19:58:59 loss: 0.2674 loss_seg: 0.1675 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:15:53,312 INFO misc.py line 117 726] Train: [15/20][494/510] Data 3.508 (3.813) Batch 22.302 (28.013) Remain 19:58:01 loss: 0.1981 loss_seg: 0.1076 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:16:21,656 INFO misc.py line 117 726] Train: [15/20][495/510] Data 3.436 (3.813) Batch 28.344 (28.014) Remain 19:57:34 loss: 0.2132 loss_seg: 0.1203 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:16:48,128 INFO misc.py line 117 726] Train: [15/20][496/510] Data 3.925 (3.813) Batch 26.472 (28.010) Remain 19:56:58 loss: 0.2477 loss_seg: 0.1610 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:17:12,962 INFO misc.py line 117 726] Train: [15/20][497/510] Data 2.810 (3.811) Batch 24.835 (28.004) Remain 19:56:14 loss: 0.2268 loss_seg: 0.1365 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:17:33,407 INFO misc.py line 117 726] Train: [15/20][498/510] Data 2.029 (3.807) Batch 20.444 (27.989) Remain 19:55:07 loss: 0.2731 loss_seg: 0.1719 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:18:01,485 INFO misc.py line 117 726] Train: [15/20][499/510] Data 2.794 (3.805) Batch 28.078 (27.989) Remain 19:54:39 loss: 0.2414 loss_seg: 0.1449 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:18:31,453 INFO misc.py line 117 726] Train: [15/20][500/510] Data 4.181 (3.806) Batch 29.968 (27.993) Remain 19:54:21 loss: 0.1820 loss_seg: 0.0960 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:18:31,453 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 05:19:02,032 INFO misc.py line 117 726] Train: [15/20][501/510] Data 3.749 (3.806) Batch 30.579 (27.998) Remain 19:54:07 loss: 0.2212 loss_seg: 0.1310 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:19:31,206 INFO misc.py line 117 726] Train: [15/20][502/510] Data 5.480 (3.809) Batch 29.174 (28.000) Remain 19:53:45 loss: 0.2299 loss_seg: 0.1355 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:20:03,829 INFO misc.py line 117 726] Train: [15/20][503/510] Data 3.648 (3.809) Batch 32.623 (28.010) Remain 19:53:40 loss: 0.2649 loss_seg: 0.1685 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:20:30,565 INFO misc.py line 117 726] Train: [15/20][504/510] Data 4.320 (3.810) Batch 26.736 (28.007) Remain 19:53:06 loss: 0.2516 loss_seg: 0.1513 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:20:55,160 INFO misc.py line 117 726] Train: [15/20][505/510] Data 3.245 (3.809) Batch 24.595 (28.000) Remain 19:52:21 loss: 0.2414 loss_seg: 0.1444 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:21:20,835 INFO misc.py line 117 726] Train: [15/20][506/510] Data 2.630 (3.806) Batch 25.674 (27.996) Remain 19:51:41 loss: 0.2986 loss_seg: 0.2104 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:21:53,051 INFO misc.py line 117 726] Train: [15/20][507/510] Data 3.449 (3.806) Batch 32.217 (28.004) Remain 19:51:34 loss: 0.2608 loss_seg: 0.1639 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:22:14,897 INFO misc.py line 117 726] Train: [15/20][508/510] Data 2.565 (3.803) Batch 21.846 (27.992) Remain 19:50:35 loss: 0.3512 loss_seg: 0.2446 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:22:50,484 INFO misc.py line 117 726] Train: [15/20][509/510] Data 4.567 (3.805) Batch 35.587 (28.007) Remain 19:50:45 loss: 0.2130 loss_seg: 0.1232 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:23:18,348 INFO misc.py line 117 726] Train: [15/20][510/510] Data 3.564 (3.804) Batch 27.863 (28.007) Remain 19:50:17 loss: 0.2237 loss_seg: 0.1314 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:23:18,349 INFO misc.py line 147 726] Train result: loss: 0.2471 loss_seg: 0.1525 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 [2026-06-12 05:23:18,350 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-12 05:23:33,955 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.7330 [2026-06-12 05:23:50,956 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7220 [2026-06-12 05:25:05,085 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8882 [2026-06-12 05:25:45,183 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9899 [2026-06-12 05:26:04,263 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0097 [2026-06-12 05:26:40,144 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2175 [2026-06-12 05:27:26,846 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.0927 [2026-06-12 05:27:42,405 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3254 [2026-06-12 05:27:59,970 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.8754 [2026-06-12 05:28:18,501 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3110 [2026-06-12 05:28:34,651 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5198 [2026-06-12 05:28:56,242 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.8082 [2026-06-12 05:29:22,344 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9498 [2026-06-12 05:29:33,802 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7051 [2026-06-12 05:30:05,080 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0559 [2026-06-12 05:30:30,953 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3727 [2026-06-12 05:30:57,650 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3172 [2026-06-12 05:31:40,400 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1313 [2026-06-12 05:32:01,408 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3913 [2026-06-12 05:32:17,836 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8225 [2026-06-12 05:32:48,895 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9125 [2026-06-12 05:33:05,077 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4100 [2026-06-12 05:33:26,852 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2721 [2026-06-12 05:33:48,417 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8404 [2026-06-12 05:34:01,852 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6329 [2026-06-12 05:34:30,005 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5243 [2026-06-12 05:35:11,358 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0782 [2026-06-12 05:35:28,589 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5109 [2026-06-12 05:35:47,008 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4957 [2026-06-12 05:36:03,806 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4604 [2026-06-12 05:36:29,060 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2134 [2026-06-12 05:36:47,282 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5843 [2026-06-12 05:37:05,053 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9911 [2026-06-12 05:37:29,844 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7237 [2026-06-12 05:37:29,857 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6696/0.7415/0.8962. [2026-06-12 05:37:29,857 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9253/0.9595 [2026-06-12 05:37:29,857 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9764/0.9881 [2026-06-12 05:37:29,857 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8399/0.9691 [2026-06-12 05:37:29,857 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0017/0.0128 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3267/0.3919 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6050/0.6299 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6039/0.6904 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7907/0.8937 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9106/0.9503 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6684/0.7407 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7606/0.8513 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7020/0.8585 [2026-06-12 05:37:29,858 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5931/0.7036 [2026-06-12 05:37:29,858 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-12 05:37:29,859 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-12 05:37:29,859 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 05:37:59,450 INFO misc.py line 117 726] Train: [16/20][1/510] Data 2.583 (2.583) Batch 28.057 (28.057) Remain 19:51:56 loss: 0.2367 loss_seg: 0.1418 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:38:22,849 INFO misc.py line 117 726] Train: [16/20][2/510] Data 2.543 (2.543) Batch 23.399 (23.399) Remain 16:33:40 loss: 0.2255 loss_seg: 0.1321 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:38:50,921 INFO misc.py line 117 726] Train: [16/20][3/510] Data 3.916 (3.916) Batch 28.072 (28.072) Remain 19:51:38 loss: 0.2948 loss_seg: 0.2013 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:39:20,600 INFO misc.py line 117 726] Train: [16/20][4/510] Data 3.220 (3.220) Batch 29.679 (29.679) Remain 20:59:23 loss: 0.2588 loss_seg: 0.1627 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:39:49,744 INFO misc.py line 117 726] Train: [16/20][5/510] Data 3.693 (3.456) Batch 29.144 (29.412) Remain 20:47:32 loss: 0.1896 loss_seg: 0.1007 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:40:10,246 INFO misc.py line 117 726] Train: [16/20][6/510] Data 2.389 (3.101) Batch 20.502 (26.442) Remain 18:41:07 loss: 0.1784 loss_seg: 0.0936 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:40:28,273 INFO misc.py line 117 726] Train: [16/20][7/510] Data 2.856 (3.040) Batch 18.027 (24.338) Remain 17:11:31 loss: 0.1733 loss_seg: 0.0850 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:40:47,253 INFO misc.py line 117 726] Train: [16/20][8/510] Data 1.935 (2.819) Batch 18.980 (23.266) Remain 16:25:43 loss: 0.2792 loss_seg: 0.1806 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:41:10,256 INFO misc.py line 117 726] Train: [16/20][9/510] Data 2.478 (2.762) Batch 23.003 (23.222) Remain 16:23:28 loss: 0.2032 loss_seg: 0.1133 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:41:41,259 INFO misc.py line 117 726] Train: [16/20][10/510] Data 4.027 (2.943) Batch 31.004 (24.334) Remain 17:10:08 loss: 0.2457 loss_seg: 0.1504 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:42:06,469 INFO misc.py line 117 726] Train: [16/20][11/510] Data 2.224 (2.853) Batch 25.210 (24.444) Remain 17:14:22 loss: 0.2488 loss_seg: 0.1538 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:42:30,707 INFO misc.py line 117 726] Train: [16/20][12/510] Data 4.016 (2.982) Batch 24.237 (24.421) Remain 17:12:59 loss: 0.3216 loss_seg: 0.2276 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:42:55,499 INFO misc.py line 117 726] Train: [16/20][13/510] Data 4.263 (3.110) Batch 24.793 (24.458) Remain 17:14:09 loss: 0.2592 loss_seg: 0.1644 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:43:24,374 INFO misc.py line 117 726] Train: [16/20][14/510] Data 2.913 (3.092) Batch 28.875 (24.859) Remain 17:30:43 loss: 0.2119 loss_seg: 0.1223 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:43:53,249 INFO misc.py line 117 726] Train: [16/20][15/510] Data 3.555 (3.131) Batch 28.875 (25.194) Remain 17:44:26 loss: 0.2538 loss_seg: 0.1567 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:44:21,644 INFO misc.py line 117 726] Train: [16/20][16/510] Data 4.555 (3.240) Batch 28.395 (25.440) Remain 17:54:25 loss: 0.2696 loss_seg: 0.1717 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:44:51,529 INFO misc.py line 117 726] Train: [16/20][17/510] Data 3.715 (3.274) Batch 29.885 (25.758) Remain 18:07:24 loss: 0.2818 loss_seg: 0.1860 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:45:17,249 INFO misc.py line 117 726] Train: [16/20][18/510] Data 2.905 (3.250) Batch 25.720 (25.755) Remain 18:06:52 loss: 0.2375 loss_seg: 0.1405 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:45:51,537 INFO misc.py line 117 726] Train: [16/20][19/510] Data 5.685 (3.402) Batch 34.288 (26.288) Remain 18:28:56 loss: 0.1970 loss_seg: 0.1081 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:46:09,782 INFO misc.py line 117 726] Train: [16/20][20/510] Data 2.452 (3.346) Batch 18.245 (25.815) Remain 18:08:32 loss: 0.2435 loss_seg: 0.1489 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:46:42,891 INFO misc.py line 117 726] Train: [16/20][21/510] Data 3.651 (3.363) Batch 33.109 (26.221) Remain 18:25:11 loss: 0.2354 loss_seg: 0.1424 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:47:09,847 INFO misc.py line 117 726] Train: [16/20][22/510] Data 3.844 (3.388) Batch 26.956 (26.259) Remain 18:26:23 loss: 0.1961 loss_seg: 0.1075 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:47:39,982 INFO misc.py line 117 726] Train: [16/20][23/510] Data 3.711 (3.404) Batch 30.135 (26.453) Remain 18:34:06 loss: 0.2264 loss_seg: 0.1342 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:48:02,306 INFO misc.py line 117 726] Train: [16/20][24/510] Data 2.515 (3.362) Batch 22.324 (26.256) Remain 18:25:23 loss: 0.2670 loss_seg: 0.1665 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:48:34,736 INFO misc.py line 117 726] Train: [16/20][25/510] Data 4.271 (3.403) Batch 32.431 (26.537) Remain 18:36:46 loss: 0.2817 loss_seg: 0.1799 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:49:10,667 INFO misc.py line 117 726] Train: [16/20][26/510] Data 4.557 (3.454) Batch 35.930 (26.945) Remain 18:53:30 loss: 0.2602 loss_seg: 0.1641 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:49:34,390 INFO misc.py line 117 726] Train: [16/20][27/510] Data 2.645 (3.420) Batch 23.723 (26.811) Remain 18:47:24 loss: 0.2194 loss_seg: 0.1296 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:50:04,590 INFO misc.py line 117 726] Train: [16/20][28/510] Data 3.857 (3.437) Batch 30.200 (26.947) Remain 18:52:39 loss: 0.2671 loss_seg: 0.1704 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:50:36,374 INFO misc.py line 117 726] Train: [16/20][29/510] Data 4.018 (3.460) Batch 31.784 (27.133) Remain 19:00:01 loss: 0.1897 loss_seg: 0.1018 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:51:04,081 INFO misc.py line 117 726] Train: [16/20][30/510] Data 2.881 (3.438) Batch 27.707 (27.154) Remain 19:00:28 loss: 0.2295 loss_seg: 0.1338 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:51:30,722 INFO misc.py line 117 726] Train: [16/20][31/510] Data 3.082 (3.426) Batch 26.641 (27.136) Remain 18:59:14 loss: 0.2838 loss_seg: 0.1760 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:51:51,457 INFO misc.py line 117 726] Train: [16/20][32/510] Data 2.476 (3.393) Batch 20.735 (26.915) Remain 18:49:32 loss: 0.3406 loss_seg: 0.2320 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:52:19,580 INFO misc.py line 117 726] Train: [16/20][33/510] Data 4.081 (3.416) Batch 28.123 (26.955) Remain 18:50:46 loss: 0.2219 loss_seg: 0.1314 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:52:52,688 INFO misc.py line 117 726] Train: [16/20][34/510] Data 5.513 (3.483) Batch 33.108 (27.154) Remain 18:58:38 loss: 0.2262 loss_seg: 0.1352 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:53:15,095 INFO misc.py line 117 726] Train: [16/20][35/510] Data 2.384 (3.449) Batch 22.408 (27.005) Remain 18:51:58 loss: 0.1927 loss_seg: 0.1042 loss_superpoint_edge: 0.0149 loss_superpoint_contrast: 0.0429 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:53:49,897 INFO misc.py line 117 726] Train: [16/20][36/510] Data 6.406 (3.539) Batch 34.802 (27.242) Remain 19:01:25 loss: 0.1729 loss_seg: 0.0881 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:54:12,989 INFO misc.py line 117 726] Train: [16/20][37/510] Data 2.235 (3.500) Batch 23.092 (27.120) Remain 18:55:51 loss: 0.2645 loss_seg: 0.1697 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:54:44,898 INFO misc.py line 117 726] Train: [16/20][38/510] Data 3.815 (3.509) Batch 31.909 (27.256) Remain 19:01:08 loss: 0.2281 loss_seg: 0.1378 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:55:16,958 INFO misc.py line 117 726] Train: [16/20][39/510] Data 3.644 (3.513) Batch 32.060 (27.390) Remain 19:06:16 loss: 0.2557 loss_seg: 0.1637 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:55:42,340 INFO misc.py line 117 726] Train: [16/20][40/510] Data 2.089 (3.475) Batch 25.382 (27.336) Remain 19:03:32 loss: 0.2514 loss_seg: 0.1500 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:56:11,652 INFO misc.py line 117 726] Train: [16/20][41/510] Data 3.664 (3.480) Batch 29.312 (27.388) Remain 19:05:15 loss: 0.2689 loss_seg: 0.1752 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:56:41,186 INFO misc.py line 117 726] Train: [16/20][42/510] Data 3.619 (3.483) Batch 29.534 (27.443) Remain 19:07:06 loss: 0.1910 loss_seg: 0.1052 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:57:07,341 INFO misc.py line 117 726] Train: [16/20][43/510] Data 2.894 (3.468) Batch 26.155 (27.410) Remain 19:05:18 loss: 0.2598 loss_seg: 0.1638 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:57:40,714 INFO misc.py line 117 726] Train: [16/20][44/510] Data 3.219 (3.462) Batch 33.373 (27.556) Remain 19:10:55 loss: 0.3067 loss_seg: 0.2142 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:58:02,478 INFO misc.py line 117 726] Train: [16/20][45/510] Data 2.622 (3.442) Batch 21.764 (27.418) Remain 19:04:42 loss: 0.2041 loss_seg: 0.1151 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:58:22,751 INFO misc.py line 117 726] Train: [16/20][46/510] Data 2.070 (3.410) Batch 20.273 (27.252) Remain 18:57:18 loss: 0.1987 loss_seg: 0.1119 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:58:51,424 INFO misc.py line 117 726] Train: [16/20][47/510] Data 2.797 (3.396) Batch 28.673 (27.284) Remain 18:58:12 loss: 0.2473 loss_seg: 0.1497 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:59:18,231 INFO misc.py line 117 726] Train: [16/20][48/510] Data 2.464 (3.376) Batch 26.806 (27.274) Remain 18:57:18 loss: 0.2905 loss_seg: 0.1850 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 05:59:38,420 INFO misc.py line 117 726] Train: [16/20][49/510] Data 1.842 (3.342) Batch 20.190 (27.120) Remain 18:50:25 loss: 0.2911 loss_seg: 0.1854 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:00:07,186 INFO misc.py line 117 726] Train: [16/20][50/510] Data 3.143 (3.338) Batch 28.765 (27.155) Remain 18:51:26 loss: 0.2244 loss_seg: 0.1308 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:00:07,186 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 06:00:38,830 INFO misc.py line 117 726] Train: [16/20][51/510] Data 4.178 (3.356) Batch 31.645 (27.248) Remain 18:54:53 loss: 0.2702 loss_seg: 0.1704 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:01:00,786 INFO misc.py line 117 726] Train: [16/20][52/510] Data 2.357 (3.335) Batch 21.955 (27.140) Remain 18:49:55 loss: 0.2016 loss_seg: 0.1128 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:01:31,840 INFO misc.py line 117 726] Train: [16/20][53/510] Data 3.244 (3.333) Batch 31.055 (27.218) Remain 18:52:44 loss: 0.2002 loss_seg: 0.1107 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:02:02,274 INFO misc.py line 117 726] Train: [16/20][54/510] Data 4.120 (3.349) Batch 30.434 (27.281) Remain 18:54:54 loss: 0.2583 loss_seg: 0.1656 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:02:34,716 INFO misc.py line 117 726] Train: [16/20][55/510] Data 5.558 (3.391) Batch 32.442 (27.381) Remain 18:58:34 loss: 0.2740 loss_seg: 0.1774 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:03:00,607 INFO misc.py line 117 726] Train: [16/20][56/510] Data 4.023 (3.403) Batch 25.890 (27.353) Remain 18:56:57 loss: 0.2554 loss_seg: 0.1632 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:03:24,885 INFO misc.py line 117 726] Train: [16/20][57/510] Data 2.310 (3.383) Batch 24.278 (27.296) Remain 18:54:07 loss: 0.3300 loss_seg: 0.2319 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:03:53,368 INFO misc.py line 117 726] Train: [16/20][58/510] Data 2.680 (3.370) Batch 28.484 (27.317) Remain 18:54:34 loss: 0.1971 loss_seg: 0.1078 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:04:19,257 INFO misc.py line 117 726] Train: [16/20][59/510] Data 2.930 (3.362) Batch 25.888 (27.292) Remain 18:53:03 loss: 0.1936 loss_seg: 0.1060 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:04:50,060 INFO misc.py line 117 726] Train: [16/20][60/510] Data 3.350 (3.362) Batch 30.803 (27.353) Remain 18:55:09 loss: 0.2476 loss_seg: 0.1546 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:05:13,560 INFO misc.py line 117 726] Train: [16/20][61/510] Data 2.627 (3.350) Batch 23.500 (27.287) Remain 18:51:57 loss: 0.2480 loss_seg: 0.1523 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:05:32,878 INFO misc.py line 117 726] Train: [16/20][62/510] Data 1.954 (3.326) Batch 19.318 (27.152) Remain 18:45:53 loss: 0.2305 loss_seg: 0.1416 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:05:59,357 INFO misc.py line 117 726] Train: [16/20][63/510] Data 3.179 (3.323) Batch 26.480 (27.141) Remain 18:44:58 loss: 0.2934 loss_seg: 0.2000 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:06:34,471 INFO misc.py line 117 726] Train: [16/20][64/510] Data 4.353 (3.340) Batch 35.113 (27.271) Remain 18:49:56 loss: 0.2168 loss_seg: 0.1243 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:07:11,894 INFO misc.py line 117 726] Train: [16/20][65/510] Data 5.332 (3.372) Batch 37.423 (27.435) Remain 18:56:16 loss: 0.2149 loss_seg: 0.1275 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:07:47,581 INFO misc.py line 117 726] Train: [16/20][66/510] Data 5.845 (3.412) Batch 35.688 (27.566) Remain 19:01:14 loss: 0.2803 loss_seg: 0.1869 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:08:16,813 INFO misc.py line 117 726] Train: [16/20][67/510] Data 2.417 (3.396) Batch 29.230 (27.592) Remain 19:01:51 loss: 0.2302 loss_seg: 0.1370 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:08:51,609 INFO misc.py line 117 726] Train: [16/20][68/510] Data 3.480 (3.397) Batch 34.797 (27.703) Remain 19:05:58 loss: 0.2499 loss_seg: 0.1556 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:09:23,431 INFO misc.py line 117 726] Train: [16/20][69/510] Data 4.527 (3.415) Batch 31.821 (27.765) Remain 19:08:05 loss: 0.2926 loss_seg: 0.1863 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:10:01,051 INFO misc.py line 117 726] Train: [16/20][70/510] Data 8.028 (3.483) Batch 37.621 (27.912) Remain 19:13:42 loss: 0.2390 loss_seg: 0.1448 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:10:23,458 INFO misc.py line 117 726] Train: [16/20][71/510] Data 2.829 (3.474) Batch 22.407 (27.831) Remain 19:09:54 loss: 0.2011 loss_seg: 0.1145 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:10:47,315 INFO misc.py line 117 726] Train: [16/20][72/510] Data 3.376 (3.472) Batch 23.857 (27.774) Remain 19:07:03 loss: 0.2758 loss_seg: 0.1703 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:11:17,839 INFO misc.py line 117 726] Train: [16/20][73/510] Data 4.890 (3.493) Batch 30.524 (27.813) Remain 19:08:13 loss: 0.2227 loss_seg: 0.1271 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:11:50,587 INFO misc.py line 117 726] Train: [16/20][74/510] Data 3.644 (3.495) Batch 32.748 (27.883) Remain 19:10:37 loss: 0.2745 loss_seg: 0.1773 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:12:09,718 INFO misc.py line 117 726] Train: [16/20][75/510] Data 1.630 (3.469) Batch 19.131 (27.761) Remain 19:05:08 loss: 0.1840 loss_seg: 0.0939 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:12:40,964 INFO misc.py line 117 726] Train: [16/20][76/510] Data 5.225 (3.493) Batch 31.246 (27.809) Remain 19:06:38 loss: 0.2787 loss_seg: 0.1796 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:13:09,049 INFO misc.py line 117 726] Train: [16/20][77/510] Data 3.488 (3.493) Batch 28.085 (27.813) Remain 19:06:20 loss: 0.2987 loss_seg: 0.1924 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:13:37,209 INFO misc.py line 117 726] Train: [16/20][78/510] Data 2.659 (3.482) Batch 28.160 (27.817) Remain 19:06:04 loss: 0.2579 loss_seg: 0.1550 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:14:05,341 INFO misc.py line 117 726] Train: [16/20][79/510] Data 2.600 (3.470) Batch 28.133 (27.821) Remain 19:05:46 loss: 0.2760 loss_seg: 0.1783 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:14:35,449 INFO misc.py line 117 726] Train: [16/20][80/510] Data 2.924 (3.463) Batch 30.107 (27.851) Remain 19:06:31 loss: 0.3439 loss_seg: 0.2370 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:15:03,659 INFO misc.py line 117 726] Train: [16/20][81/510] Data 3.099 (3.458) Batch 28.211 (27.856) Remain 19:06:15 loss: 0.2454 loss_seg: 0.1487 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:15:26,812 INFO misc.py line 117 726] Train: [16/20][82/510] Data 2.446 (3.446) Batch 23.153 (27.796) Remain 19:03:20 loss: 0.2051 loss_seg: 0.1166 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:16:02,564 INFO misc.py line 117 726] Train: [16/20][83/510] Data 5.936 (3.477) Batch 35.752 (27.896) Remain 19:06:58 loss: 0.2401 loss_seg: 0.1472 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:16:29,709 INFO misc.py line 117 726] Train: [16/20][84/510] Data 3.365 (3.475) Batch 27.145 (27.886) Remain 19:06:07 loss: 0.2862 loss_seg: 0.1801 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:17:07,918 INFO misc.py line 117 726] Train: [16/20][85/510] Data 10.349 (3.559) Batch 38.208 (28.012) Remain 19:10:49 loss: 0.2570 loss_seg: 0.1640 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:17:33,038 INFO misc.py line 117 726] Train: [16/20][86/510] Data 3.007 (3.552) Batch 25.120 (27.977) Remain 19:08:56 loss: 0.1844 loss_seg: 0.0976 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:18:00,191 INFO misc.py line 117 726] Train: [16/20][87/510] Data 5.691 (3.578) Batch 27.153 (27.968) Remain 19:08:03 loss: 0.3081 loss_seg: 0.2083 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:18:26,202 INFO misc.py line 117 726] Train: [16/20][88/510] Data 2.762 (3.568) Batch 26.011 (27.944) Remain 19:06:39 loss: 0.2614 loss_seg: 0.1613 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:18:51,886 INFO misc.py line 117 726] Train: [16/20][89/510] Data 2.364 (3.554) Batch 25.685 (27.918) Remain 19:05:06 loss: 0.2202 loss_seg: 0.1277 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:19:16,954 INFO misc.py line 117 726] Train: [16/20][90/510] Data 5.149 (3.573) Batch 25.068 (27.885) Remain 19:03:18 loss: 0.2453 loss_seg: 0.1543 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:19:46,603 INFO misc.py line 117 726] Train: [16/20][91/510] Data 3.370 (3.570) Batch 29.648 (27.905) Remain 19:03:39 loss: 0.3315 loss_seg: 0.2350 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:20:23,423 INFO misc.py line 117 726] Train: [16/20][92/510] Data 7.409 (3.613) Batch 36.820 (28.006) Remain 19:07:17 loss: 0.2220 loss_seg: 0.1307 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:20:56,164 INFO misc.py line 117 726] Train: [16/20][93/510] Data 3.582 (3.613) Batch 32.742 (28.058) Remain 19:08:59 loss: 0.2084 loss_seg: 0.1202 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:21:29,647 INFO misc.py line 117 726] Train: [16/20][94/510] Data 3.919 (3.616) Batch 33.482 (28.118) Remain 19:10:57 loss: 0.3057 loss_seg: 0.1990 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:21:56,795 INFO misc.py line 117 726] Train: [16/20][95/510] Data 3.289 (3.613) Batch 27.148 (28.107) Remain 19:10:03 loss: 0.2661 loss_seg: 0.1711 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:22:31,586 INFO misc.py line 117 726] Train: [16/20][96/510] Data 5.428 (3.632) Batch 34.790 (28.179) Remain 19:12:31 loss: 0.2078 loss_seg: 0.1205 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:23:01,876 INFO misc.py line 117 726] Train: [16/20][97/510] Data 4.215 (3.639) Batch 30.291 (28.202) Remain 19:12:58 loss: 0.2600 loss_seg: 0.1599 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:23:26,826 INFO misc.py line 117 726] Train: [16/20][98/510] Data 4.071 (3.643) Batch 24.950 (28.167) Remain 19:11:06 loss: 0.2501 loss_seg: 0.1558 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:23:44,988 INFO misc.py line 117 726] Train: [16/20][99/510] Data 1.917 (3.625) Batch 18.162 (28.063) Remain 19:06:22 loss: 0.2753 loss_seg: 0.1768 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:24:17,808 INFO misc.py line 117 726] Train: [16/20][100/510] Data 4.228 (3.631) Batch 32.819 (28.112) Remain 19:07:54 loss: 0.3214 loss_seg: 0.2263 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:24:17,808 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 06:24:50,084 INFO misc.py line 117 726] Train: [16/20][101/510] Data 4.265 (3.638) Batch 32.277 (28.155) Remain 19:09:10 loss: 0.3282 loss_seg: 0.2123 loss_superpoint_edge: 0.0446 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:25:23,371 INFO misc.py line 117 726] Train: [16/20][102/510] Data 9.390 (3.696) Batch 33.287 (28.207) Remain 19:10:49 loss: 0.2719 loss_seg: 0.1719 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:26:03,796 INFO misc.py line 117 726] Train: [16/20][103/510] Data 6.827 (3.727) Batch 40.425 (28.329) Remain 19:15:20 loss: 0.2298 loss_seg: 0.1351 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:26:33,569 INFO misc.py line 117 726] Train: [16/20][104/510] Data 7.379 (3.763) Batch 29.773 (28.343) Remain 19:15:27 loss: 0.3558 loss_seg: 0.2452 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:26:56,894 INFO misc.py line 117 726] Train: [16/20][105/510] Data 2.952 (3.755) Batch 23.325 (28.294) Remain 19:12:58 loss: 0.2501 loss_seg: 0.1526 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:27:34,401 INFO misc.py line 117 726] Train: [16/20][106/510] Data 8.536 (3.802) Batch 37.507 (28.383) Remain 19:16:08 loss: 0.2889 loss_seg: 0.1875 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:28:00,342 INFO misc.py line 117 726] Train: [16/20][107/510] Data 2.409 (3.789) Batch 25.941 (28.360) Remain 19:14:43 loss: 0.2384 loss_seg: 0.1444 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:28:28,470 INFO misc.py line 117 726] Train: [16/20][108/510] Data 3.394 (3.785) Batch 28.128 (28.358) Remain 19:14:09 loss: 0.2376 loss_seg: 0.1486 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:28:59,909 INFO misc.py line 117 726] Train: [16/20][109/510] Data 3.887 (3.786) Batch 31.439 (28.387) Remain 19:14:51 loss: 0.2320 loss_seg: 0.1367 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:29:26,358 INFO misc.py line 117 726] Train: [16/20][110/510] Data 4.798 (3.795) Batch 26.449 (28.369) Remain 19:13:39 loss: 0.2036 loss_seg: 0.1135 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:29:57,502 INFO misc.py line 117 726] Train: [16/20][111/510] Data 3.602 (3.793) Batch 31.144 (28.394) Remain 19:14:13 loss: 0.2458 loss_seg: 0.1507 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:30:23,468 INFO misc.py line 117 726] Train: [16/20][112/510] Data 3.453 (3.790) Batch 25.966 (28.372) Remain 19:12:50 loss: 0.2535 loss_seg: 0.1560 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:30:46,102 INFO misc.py line 117 726] Train: [16/20][113/510] Data 2.637 (3.780) Batch 22.634 (28.320) Remain 19:10:15 loss: 0.2173 loss_seg: 0.1242 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:31:16,405 INFO misc.py line 117 726] Train: [16/20][114/510] Data 4.158 (3.783) Batch 30.304 (28.338) Remain 19:10:30 loss: 0.2317 loss_seg: 0.1347 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:31:53,255 INFO misc.py line 117 726] Train: [16/20][115/510] Data 8.570 (3.826) Batch 36.850 (28.414) Remain 19:13:07 loss: 0.1975 loss_seg: 0.1123 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:32:23,559 INFO misc.py line 117 726] Train: [16/20][116/510] Data 3.056 (3.819) Batch 30.304 (28.430) Remain 19:13:19 loss: 0.2389 loss_seg: 0.1404 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:32:56,506 INFO misc.py line 117 726] Train: [16/20][117/510] Data 3.723 (3.818) Batch 32.947 (28.470) Remain 19:14:27 loss: 0.2487 loss_seg: 0.1531 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:33:25,633 INFO misc.py line 117 726] Train: [16/20][118/510] Data 3.596 (3.816) Batch 29.128 (28.476) Remain 19:14:13 loss: 0.2711 loss_seg: 0.1816 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:33:47,329 INFO misc.py line 117 726] Train: [16/20][119/510] Data 4.551 (3.823) Batch 21.695 (28.417) Remain 19:11:22 loss: 0.2460 loss_seg: 0.1514 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:34:15,241 INFO misc.py line 117 726] Train: [16/20][120/510] Data 3.562 (3.820) Batch 27.913 (28.413) Remain 19:10:43 loss: 0.2773 loss_seg: 0.1742 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:34:39,729 INFO misc.py line 117 726] Train: [16/20][121/510] Data 3.005 (3.814) Batch 24.487 (28.380) Remain 19:08:54 loss: 0.3561 loss_seg: 0.2431 loss_superpoint_edge: 0.0448 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:35:17,610 INFO misc.py line 117 726] Train: [16/20][122/510] Data 3.965 (3.815) Batch 37.881 (28.460) Remain 19:11:39 loss: 0.2775 loss_seg: 0.1724 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:35:49,798 INFO misc.py line 117 726] Train: [16/20][123/510] Data 6.309 (3.836) Batch 32.188 (28.491) Remain 19:12:26 loss: 0.2091 loss_seg: 0.1165 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:36:06,993 INFO misc.py line 117 726] Train: [16/20][124/510] Data 2.511 (3.825) Batch 17.195 (28.397) Remain 19:08:11 loss: 0.2708 loss_seg: 0.1728 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:36:39,087 INFO misc.py line 117 726] Train: [16/20][125/510] Data 4.322 (3.829) Batch 32.093 (28.428) Remain 19:08:56 loss: 0.2387 loss_seg: 0.1409 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:37:07,805 INFO misc.py line 117 726] Train: [16/20][126/510] Data 2.814 (3.820) Batch 28.719 (28.430) Remain 19:08:34 loss: 0.1816 loss_seg: 0.0977 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:37:28,972 INFO misc.py line 117 726] Train: [16/20][127/510] Data 2.759 (3.812) Batch 21.166 (28.371) Remain 19:05:43 loss: 0.1773 loss_seg: 0.0886 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:37:53,371 INFO misc.py line 117 726] Train: [16/20][128/510] Data 3.213 (3.807) Batch 24.399 (28.340) Remain 19:03:58 loss: 0.2203 loss_seg: 0.1266 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:38:18,816 INFO misc.py line 117 726] Train: [16/20][129/510] Data 3.012 (3.801) Batch 25.445 (28.317) Remain 19:02:34 loss: 0.2141 loss_seg: 0.1212 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:38:52,356 INFO misc.py line 117 726] Train: [16/20][130/510] Data 4.102 (3.803) Batch 33.540 (28.358) Remain 19:03:45 loss: 0.2513 loss_seg: 0.1549 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:39:18,980 INFO misc.py line 117 726] Train: [16/20][131/510] Data 2.501 (3.793) Batch 26.624 (28.344) Remain 19:02:44 loss: 0.1828 loss_seg: 0.0969 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:39:49,469 INFO misc.py line 117 726] Train: [16/20][132/510] Data 3.816 (3.793) Batch 30.490 (28.361) Remain 19:02:56 loss: 0.2344 loss_seg: 0.1404 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:40:08,722 INFO misc.py line 117 726] Train: [16/20][133/510] Data 2.979 (3.787) Batch 19.253 (28.291) Remain 18:59:38 loss: 0.2187 loss_seg: 0.1249 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:40:44,007 INFO misc.py line 117 726] Train: [16/20][134/510] Data 4.572 (3.793) Batch 35.285 (28.344) Remain 19:01:19 loss: 0.2725 loss_seg: 0.1753 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:41:06,498 INFO misc.py line 117 726] Train: [16/20][135/510] Data 2.430 (3.783) Batch 22.491 (28.300) Remain 18:59:04 loss: 0.1863 loss_seg: 0.1019 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:41:38,203 INFO misc.py line 117 726] Train: [16/20][136/510] Data 3.667 (3.782) Batch 31.704 (28.325) Remain 18:59:37 loss: 0.1661 loss_seg: 0.0826 loss_superpoint_edge: 0.0130 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:42:14,597 INFO misc.py line 117 726] Train: [16/20][137/510] Data 5.419 (3.794) Batch 36.394 (28.386) Remain 19:01:34 loss: 0.1846 loss_seg: 0.0999 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:42:40,685 INFO misc.py line 117 726] Train: [16/20][138/510] Data 3.758 (3.794) Batch 26.089 (28.369) Remain 19:00:25 loss: 0.2299 loss_seg: 0.1346 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:43:09,819 INFO misc.py line 117 726] Train: [16/20][139/510] Data 4.564 (3.799) Batch 29.134 (28.374) Remain 19:00:10 loss: 0.2092 loss_seg: 0.1180 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:43:41,201 INFO misc.py line 117 726] Train: [16/20][140/510] Data 4.052 (3.801) Batch 31.382 (28.396) Remain 19:00:34 loss: 0.2463 loss_seg: 0.1519 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:44:11,035 INFO misc.py line 117 726] Train: [16/20][141/510] Data 2.827 (3.794) Batch 29.835 (28.407) Remain 19:00:31 loss: 0.2477 loss_seg: 0.1497 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:44:33,125 INFO misc.py line 117 726] Train: [16/20][142/510] Data 2.371 (3.784) Batch 22.089 (28.361) Remain 18:58:13 loss: 0.1765 loss_seg: 0.0879 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:45:07,271 INFO misc.py line 117 726] Train: [16/20][143/510] Data 6.912 (3.806) Batch 34.147 (28.403) Remain 18:59:24 loss: 0.3200 loss_seg: 0.2208 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:45:37,690 INFO misc.py line 117 726] Train: [16/20][144/510] Data 4.131 (3.809) Batch 30.419 (28.417) Remain 18:59:30 loss: 0.2089 loss_seg: 0.1188 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:45:56,305 INFO misc.py line 117 726] Train: [16/20][145/510] Data 2.385 (3.799) Batch 18.614 (28.348) Remain 18:56:16 loss: 0.2469 loss_seg: 0.1519 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:46:22,804 INFO misc.py line 117 726] Train: [16/20][146/510] Data 3.528 (3.797) Batch 26.499 (28.335) Remain 18:55:16 loss: 0.3671 loss_seg: 0.2613 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:46:56,618 INFO misc.py line 117 726] Train: [16/20][147/510] Data 4.067 (3.799) Batch 33.814 (28.373) Remain 18:56:20 loss: 0.2735 loss_seg: 0.1730 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:47:23,005 INFO misc.py line 117 726] Train: [16/20][148/510] Data 3.192 (3.794) Batch 26.387 (28.359) Remain 18:55:18 loss: 0.2567 loss_seg: 0.1580 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:47:53,700 INFO misc.py line 117 726] Train: [16/20][149/510] Data 3.904 (3.795) Batch 30.695 (28.375) Remain 18:55:28 loss: 0.2455 loss_seg: 0.1519 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:48:18,346 INFO misc.py line 117 726] Train: [16/20][150/510] Data 5.085 (3.804) Batch 24.647 (28.350) Remain 18:53:59 loss: 0.5063 loss_seg: 0.4120 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:48:18,347 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 06:48:36,615 INFO misc.py line 117 726] Train: [16/20][151/510] Data 2.868 (3.798) Batch 18.269 (28.282) Remain 18:50:47 loss: 0.2939 loss_seg: 0.1956 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:49:03,019 INFO misc.py line 117 726] Train: [16/20][152/510] Data 2.873 (3.791) Batch 26.404 (28.269) Remain 18:49:49 loss: 0.2107 loss_seg: 0.1259 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:49:32,939 INFO misc.py line 117 726] Train: [16/20][153/510] Data 3.352 (3.788) Batch 29.920 (28.280) Remain 18:49:47 loss: 0.2320 loss_seg: 0.1413 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:49:52,690 INFO misc.py line 117 726] Train: [16/20][154/510] Data 3.502 (3.787) Batch 19.751 (28.224) Remain 18:47:03 loss: 0.2539 loss_seg: 0.1590 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:50:26,914 INFO misc.py line 117 726] Train: [16/20][155/510] Data 5.772 (3.800) Batch 34.224 (28.263) Remain 18:48:10 loss: 0.1753 loss_seg: 0.0952 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:50:54,080 INFO misc.py line 117 726] Train: [16/20][156/510] Data 2.718 (3.793) Batch 27.166 (28.256) Remain 18:47:24 loss: 0.2448 loss_seg: 0.1452 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:51:18,294 INFO misc.py line 117 726] Train: [16/20][157/510] Data 2.884 (3.787) Batch 24.213 (28.230) Remain 18:45:53 loss: 0.1908 loss_seg: 0.1047 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:51:47,506 INFO misc.py line 117 726] Train: [16/20][158/510] Data 3.435 (3.784) Batch 29.213 (28.236) Remain 18:45:40 loss: 0.2107 loss_seg: 0.1226 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:52:16,703 INFO misc.py line 117 726] Train: [16/20][159/510] Data 4.202 (3.787) Batch 29.197 (28.242) Remain 18:45:27 loss: 0.2475 loss_seg: 0.1490 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:52:47,103 INFO misc.py line 117 726] Train: [16/20][160/510] Data 2.766 (3.781) Batch 30.400 (28.256) Remain 18:45:31 loss: 0.3127 loss_seg: 0.2014 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:53:10,134 INFO misc.py line 117 726] Train: [16/20][161/510] Data 2.788 (3.774) Batch 23.031 (28.223) Remain 18:43:44 loss: 0.2052 loss_seg: 0.1169 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:53:30,873 INFO misc.py line 117 726] Train: [16/20][162/510] Data 2.783 (3.768) Batch 20.739 (28.176) Remain 18:41:23 loss: 0.2489 loss_seg: 0.1556 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:53:58,858 INFO misc.py line 117 726] Train: [16/20][163/510] Data 3.101 (3.764) Batch 27.984 (28.175) Remain 18:40:52 loss: 0.2416 loss_seg: 0.1544 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:54:29,461 INFO misc.py line 117 726] Train: [16/20][164/510] Data 3.673 (3.763) Batch 30.603 (28.190) Remain 18:41:00 loss: 0.2181 loss_seg: 0.1257 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:54:59,439 INFO misc.py line 117 726] Train: [16/20][165/510] Data 4.078 (3.765) Batch 29.979 (28.201) Remain 18:40:58 loss: 0.2229 loss_seg: 0.1343 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:55:17,569 INFO misc.py line 117 726] Train: [16/20][166/510] Data 2.117 (3.755) Batch 18.129 (28.139) Remain 18:38:03 loss: 0.2749 loss_seg: 0.1764 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:55:44,189 INFO misc.py line 117 726] Train: [16/20][167/510] Data 3.966 (3.756) Batch 26.620 (28.130) Remain 18:37:13 loss: 0.2466 loss_seg: 0.1515 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:56:07,481 INFO misc.py line 117 726] Train: [16/20][168/510] Data 2.101 (3.746) Batch 23.292 (28.100) Remain 18:35:35 loss: 0.2125 loss_seg: 0.1224 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:56:30,493 INFO misc.py line 117 726] Train: [16/20][169/510] Data 2.709 (3.740) Batch 23.012 (28.070) Remain 18:33:53 loss: 0.2671 loss_seg: 0.1702 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:56:59,884 INFO misc.py line 117 726] Train: [16/20][170/510] Data 5.591 (3.751) Batch 29.391 (28.078) Remain 18:33:44 loss: 0.2669 loss_seg: 0.1722 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:57:25,819 INFO misc.py line 117 726] Train: [16/20][171/510] Data 3.687 (3.751) Batch 25.936 (28.065) Remain 18:32:46 loss: 0.2620 loss_seg: 0.1636 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:57:55,087 INFO misc.py line 117 726] Train: [16/20][172/510] Data 3.121 (3.747) Batch 29.268 (28.072) Remain 18:32:35 loss: 0.2808 loss_seg: 0.1750 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:58:24,140 INFO misc.py line 117 726] Train: [16/20][173/510] Data 2.299 (3.739) Batch 29.053 (28.078) Remain 18:32:20 loss: 0.2707 loss_seg: 0.1722 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:58:46,662 INFO misc.py line 117 726] Train: [16/20][174/510] Data 2.124 (3.729) Batch 22.521 (28.045) Remain 18:30:35 loss: 0.2700 loss_seg: 0.1685 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:59:21,886 INFO misc.py line 117 726] Train: [16/20][175/510] Data 4.193 (3.732) Batch 35.224 (28.087) Remain 18:31:46 loss: 0.2681 loss_seg: 0.1688 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 06:59:57,865 INFO misc.py line 117 726] Train: [16/20][176/510] Data 4.599 (3.737) Batch 35.980 (28.133) Remain 18:33:06 loss: 0.2553 loss_seg: 0.1627 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:00:28,993 INFO misc.py line 117 726] Train: [16/20][177/510] Data 3.957 (3.738) Batch 31.128 (28.150) Remain 18:33:19 loss: 0.2538 loss_seg: 0.1583 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:00:48,791 INFO misc.py line 117 726] Train: [16/20][178/510] Data 2.398 (3.730) Batch 19.798 (28.102) Remain 18:30:58 loss: 0.2144 loss_seg: 0.1223 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:01:10,992 INFO misc.py line 117 726] Train: [16/20][179/510] Data 2.575 (3.724) Batch 22.201 (28.069) Remain 18:29:10 loss: 0.3566 loss_seg: 0.2585 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:01:36,415 INFO misc.py line 117 726] Train: [16/20][180/510] Data 2.643 (3.718) Batch 25.423 (28.054) Remain 18:28:07 loss: 0.2525 loss_seg: 0.1536 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:02:08,122 INFO misc.py line 117 726] Train: [16/20][181/510] Data 4.254 (3.721) Batch 31.707 (28.074) Remain 18:28:27 loss: 0.2520 loss_seg: 0.1579 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:02:36,053 INFO misc.py line 117 726] Train: [16/20][182/510] Data 3.293 (3.718) Batch 27.931 (28.073) Remain 18:27:57 loss: 0.1837 loss_seg: 0.0974 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:02:59,333 INFO misc.py line 117 726] Train: [16/20][183/510] Data 2.410 (3.711) Batch 23.280 (28.047) Remain 18:26:26 loss: 0.2443 loss_seg: 0.1489 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:03:32,083 INFO misc.py line 117 726] Train: [16/20][184/510] Data 3.346 (3.709) Batch 32.750 (28.073) Remain 18:27:00 loss: 0.2616 loss_seg: 0.1623 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:03:55,613 INFO misc.py line 117 726] Train: [16/20][185/510] Data 5.207 (3.717) Batch 23.530 (28.048) Remain 18:25:32 loss: 0.3398 loss_seg: 0.2297 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0343 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:04:22,113 INFO misc.py line 117 726] Train: [16/20][186/510] Data 2.187 (3.709) Batch 26.500 (28.039) Remain 18:24:44 loss: 0.2786 loss_seg: 0.1791 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:04:52,344 INFO misc.py line 117 726] Train: [16/20][187/510] Data 2.848 (3.704) Batch 30.230 (28.051) Remain 18:24:45 loss: 0.2268 loss_seg: 0.1365 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:05:20,981 INFO misc.py line 117 726] Train: [16/20][188/510] Data 3.342 (3.702) Batch 28.637 (28.054) Remain 18:24:24 loss: 0.2440 loss_seg: 0.1472 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:05:54,419 INFO misc.py line 117 726] Train: [16/20][189/510] Data 3.208 (3.700) Batch 33.438 (28.083) Remain 18:25:04 loss: 0.2618 loss_seg: 0.1667 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:06:12,240 INFO misc.py line 117 726] Train: [16/20][190/510] Data 2.389 (3.693) Batch 17.821 (28.028) Remain 18:22:27 loss: 0.2173 loss_seg: 0.1286 loss_superpoint_edge: 0.0153 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:06:44,189 INFO misc.py line 117 726] Train: [16/20][191/510] Data 7.664 (3.714) Batch 31.949 (28.049) Remain 18:22:48 loss: 0.2325 loss_seg: 0.1394 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:07:18,978 INFO misc.py line 117 726] Train: [16/20][192/510] Data 5.532 (3.723) Batch 34.789 (28.085) Remain 18:23:44 loss: 0.2134 loss_seg: 0.1240 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:07:52,264 INFO misc.py line 117 726] Train: [16/20][193/510] Data 4.864 (3.729) Batch 33.286 (28.112) Remain 18:24:20 loss: 0.3189 loss_seg: 0.2132 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:08:27,652 INFO misc.py line 117 726] Train: [16/20][194/510] Data 6.196 (3.742) Batch 35.388 (28.150) Remain 18:25:22 loss: 0.4749 loss_seg: 0.3644 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:08:47,757 INFO misc.py line 117 726] Train: [16/20][195/510] Data 2.386 (3.735) Batch 20.105 (28.109) Remain 18:23:15 loss: 0.2031 loss_seg: 0.1166 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:09:19,851 INFO misc.py line 117 726] Train: [16/20][196/510] Data 5.285 (3.743) Batch 32.094 (28.129) Remain 18:23:36 loss: 0.2016 loss_seg: 0.1108 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:09:39,981 INFO misc.py line 117 726] Train: [16/20][197/510] Data 2.048 (3.735) Batch 20.130 (28.088) Remain 18:21:30 loss: 0.4333 loss_seg: 0.3095 loss_superpoint_edge: 0.0539 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:10:06,521 INFO misc.py line 117 726] Train: [16/20][198/510] Data 2.824 (3.730) Batch 26.540 (28.080) Remain 18:20:44 loss: 0.2795 loss_seg: 0.1775 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:10:32,332 INFO misc.py line 117 726] Train: [16/20][199/510] Data 2.885 (3.726) Batch 25.812 (28.068) Remain 18:19:48 loss: 0.2211 loss_seg: 0.1274 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:10:53,712 INFO misc.py line 117 726] Train: [16/20][200/510] Data 2.558 (3.720) Batch 21.379 (28.034) Remain 18:18:00 loss: 0.2122 loss_seg: 0.1228 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:10:53,712 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 07:11:14,773 INFO misc.py line 117 726] Train: [16/20][201/510] Data 2.732 (3.715) Batch 21.062 (27.999) Remain 18:16:10 loss: 0.2195 loss_seg: 0.1286 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:11:53,052 INFO misc.py line 117 726] Train: [16/20][202/510] Data 5.148 (3.722) Batch 38.278 (28.051) Remain 18:17:43 loss: 0.2430 loss_seg: 0.1475 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:12:21,781 INFO misc.py line 117 726] Train: [16/20][203/510] Data 3.151 (3.719) Batch 28.729 (28.054) Remain 18:17:23 loss: 0.2838 loss_seg: 0.1818 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:12:53,628 INFO misc.py line 117 726] Train: [16/20][204/510] Data 5.431 (3.728) Batch 31.847 (28.073) Remain 18:17:39 loss: 0.3418 loss_seg: 0.2378 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:13:12,660 INFO misc.py line 117 726] Train: [16/20][205/510] Data 2.280 (3.720) Batch 19.031 (28.028) Remain 18:15:26 loss: 0.2822 loss_seg: 0.1802 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:13:40,099 INFO misc.py line 117 726] Train: [16/20][206/510] Data 4.634 (3.725) Batch 27.439 (28.026) Remain 18:14:51 loss: 0.3199 loss_seg: 0.2193 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:14:08,134 INFO misc.py line 117 726] Train: [16/20][207/510] Data 4.188 (3.727) Batch 28.035 (28.026) Remain 18:14:23 loss: 0.2561 loss_seg: 0.1586 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:14:34,862 INFO misc.py line 117 726] Train: [16/20][208/510] Data 4.759 (3.732) Batch 26.728 (28.019) Remain 18:13:41 loss: 0.2248 loss_seg: 0.1306 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:15:07,290 INFO misc.py line 117 726] Train: [16/20][209/510] Data 3.639 (3.732) Batch 32.428 (28.041) Remain 18:14:03 loss: 0.2144 loss_seg: 0.1255 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:15:41,924 INFO misc.py line 117 726] Train: [16/20][210/510] Data 7.207 (3.749) Batch 34.634 (28.072) Remain 18:14:49 loss: 0.2253 loss_seg: 0.1341 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:16:03,679 INFO misc.py line 117 726] Train: [16/20][211/510] Data 2.558 (3.743) Batch 21.755 (28.042) Remain 18:13:10 loss: 0.2158 loss_seg: 0.1231 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:16:28,738 INFO misc.py line 117 726] Train: [16/20][212/510] Data 3.605 (3.742) Batch 25.060 (28.028) Remain 18:12:09 loss: 0.2389 loss_seg: 0.1459 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:16:47,627 INFO misc.py line 117 726] Train: [16/20][213/510] Data 1.886 (3.733) Batch 18.888 (27.984) Remain 18:09:59 loss: 0.2088 loss_seg: 0.1152 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:17:23,959 INFO misc.py line 117 726] Train: [16/20][214/510] Data 6.197 (3.745) Batch 36.332 (28.024) Remain 18:11:03 loss: 0.2037 loss_seg: 0.1132 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:17:37,050 INFO misc.py line 117 726] Train: [16/20][215/510] Data 2.360 (3.738) Batch 13.091 (27.953) Remain 18:07:51 loss: 0.2118 loss_seg: 0.1211 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:18:08,848 INFO misc.py line 117 726] Train: [16/20][216/510] Data 3.551 (3.738) Batch 31.798 (27.971) Remain 18:08:05 loss: 0.2841 loss_seg: 0.1843 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:18:42,083 INFO misc.py line 117 726] Train: [16/20][217/510] Data 2.654 (3.732) Batch 33.235 (27.996) Remain 18:08:34 loss: 0.3677 loss_seg: 0.2763 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:19:11,379 INFO misc.py line 117 726] Train: [16/20][218/510] Data 3.229 (3.730) Batch 29.295 (28.002) Remain 18:08:20 loss: 0.1939 loss_seg: 0.1111 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:19:49,088 INFO misc.py line 117 726] Train: [16/20][219/510] Data 6.529 (3.743) Batch 37.709 (28.047) Remain 18:09:37 loss: 0.3269 loss_seg: 0.2270 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:20:16,799 INFO misc.py line 117 726] Train: [16/20][220/510] Data 3.200 (3.741) Batch 27.711 (28.046) Remain 18:09:06 loss: 0.2554 loss_seg: 0.1579 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:20:51,878 INFO misc.py line 117 726] Train: [16/20][221/510] Data 6.067 (3.751) Batch 35.079 (28.078) Remain 18:09:53 loss: 0.2925 loss_seg: 0.1903 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:21:15,137 INFO misc.py line 117 726] Train: [16/20][222/510] Data 2.318 (3.745) Batch 23.260 (28.056) Remain 18:08:33 loss: 0.3012 loss_seg: 0.1986 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:21:47,392 INFO misc.py line 117 726] Train: [16/20][223/510] Data 3.101 (3.742) Batch 32.255 (28.075) Remain 18:08:50 loss: 0.2316 loss_seg: 0.1357 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:22:14,951 INFO misc.py line 117 726] Train: [16/20][224/510] Data 3.936 (3.743) Batch 27.558 (28.073) Remain 18:08:16 loss: 0.2113 loss_seg: 0.1224 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:22:49,674 INFO misc.py line 117 726] Train: [16/20][225/510] Data 3.559 (3.742) Batch 34.723 (28.102) Remain 18:08:58 loss: 0.2009 loss_seg: 0.1160 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:23:22,199 INFO misc.py line 117 726] Train: [16/20][226/510] Data 4.271 (3.744) Batch 32.526 (28.122) Remain 18:09:16 loss: 0.2806 loss_seg: 0.1762 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:23:42,713 INFO misc.py line 117 726] Train: [16/20][227/510] Data 3.308 (3.742) Batch 20.514 (28.088) Remain 18:07:29 loss: 0.2694 loss_seg: 0.1693 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:24:11,494 INFO misc.py line 117 726] Train: [16/20][228/510] Data 3.487 (3.741) Batch 28.781 (28.091) Remain 18:07:08 loss: 0.2296 loss_seg: 0.1368 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:24:43,169 INFO misc.py line 117 726] Train: [16/20][229/510] Data 4.552 (3.745) Batch 31.675 (28.107) Remain 18:07:17 loss: 0.2347 loss_seg: 0.1381 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:25:11,437 INFO misc.py line 117 726] Train: [16/20][230/510] Data 3.656 (3.744) Batch 28.267 (28.108) Remain 18:06:50 loss: 0.2247 loss_seg: 0.1302 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:25:38,178 INFO misc.py line 117 726] Train: [16/20][231/510] Data 2.327 (3.738) Batch 26.741 (28.102) Remain 18:06:08 loss: 0.2313 loss_seg: 0.1367 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:26:00,186 INFO misc.py line 117 726] Train: [16/20][232/510] Data 2.476 (3.733) Batch 22.008 (28.075) Remain 18:04:38 loss: 0.1807 loss_seg: 0.0952 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:26:34,095 INFO misc.py line 117 726] Train: [16/20][233/510] Data 4.749 (3.737) Batch 33.909 (28.101) Remain 18:05:09 loss: 0.2236 loss_seg: 0.1279 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:26:50,808 INFO misc.py line 117 726] Train: [16/20][234/510] Data 1.851 (3.729) Batch 16.713 (28.051) Remain 18:02:47 loss: 0.2533 loss_seg: 0.1552 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:27:21,070 INFO misc.py line 117 726] Train: [16/20][235/510] Data 3.181 (3.727) Batch 30.262 (28.061) Remain 18:02:41 loss: 0.2264 loss_seg: 0.1348 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:27:45,023 INFO misc.py line 117 726] Train: [16/20][236/510] Data 2.727 (3.722) Batch 23.953 (28.043) Remain 18:01:32 loss: 0.1874 loss_seg: 0.0993 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:28:14,030 INFO misc.py line 117 726] Train: [16/20][237/510] Data 3.565 (3.722) Batch 29.006 (28.047) Remain 18:01:13 loss: 0.2654 loss_seg: 0.1675 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:28:45,373 INFO misc.py line 117 726] Train: [16/20][238/510] Data 2.673 (3.717) Batch 31.343 (28.061) Remain 18:01:18 loss: 0.2342 loss_seg: 0.1399 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:29:17,447 INFO misc.py line 117 726] Train: [16/20][239/510] Data 3.986 (3.718) Batch 32.074 (28.078) Remain 18:01:29 loss: 0.3361 loss_seg: 0.2351 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:29:39,102 INFO misc.py line 117 726] Train: [16/20][240/510] Data 2.683 (3.714) Batch 21.655 (28.051) Remain 17:59:58 loss: 0.3013 loss_seg: 0.2053 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:30:08,281 INFO misc.py line 117 726] Train: [16/20][241/510] Data 3.608 (3.713) Batch 29.179 (28.056) Remain 17:59:41 loss: 0.1979 loss_seg: 0.1158 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:30:40,655 INFO misc.py line 117 726] Train: [16/20][242/510] Data 4.609 (3.717) Batch 32.374 (28.074) Remain 17:59:55 loss: 0.2915 loss_seg: 0.1891 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:31:10,099 INFO misc.py line 117 726] Train: [16/20][243/510] Data 3.328 (3.716) Batch 29.445 (28.080) Remain 17:59:40 loss: 0.2027 loss_seg: 0.1147 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:31:41,999 INFO misc.py line 117 726] Train: [16/20][244/510] Data 4.186 (3.717) Batch 31.900 (28.096) Remain 17:59:48 loss: 0.2731 loss_seg: 0.1757 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:32:19,831 INFO misc.py line 117 726] Train: [16/20][245/510] Data 4.763 (3.722) Batch 37.832 (28.136) Remain 18:00:53 loss: 0.2990 loss_seg: 0.2078 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:32:47,611 INFO misc.py line 117 726] Train: [16/20][246/510] Data 3.782 (3.722) Batch 27.780 (28.135) Remain 18:00:21 loss: 0.2666 loss_seg: 0.1664 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:33:18,352 INFO misc.py line 117 726] Train: [16/20][247/510] Data 4.983 (3.727) Batch 30.741 (28.145) Remain 18:00:18 loss: 0.2046 loss_seg: 0.1138 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:33:39,835 INFO misc.py line 117 726] Train: [16/20][248/510] Data 2.544 (3.722) Batch 21.483 (28.118) Remain 17:58:47 loss: 0.1922 loss_seg: 0.1059 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:34:15,048 INFO misc.py line 117 726] Train: [16/20][249/510] Data 4.036 (3.724) Batch 35.213 (28.147) Remain 17:59:25 loss: 0.2430 loss_seg: 0.1505 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:34:40,840 INFO misc.py line 117 726] Train: [16/20][250/510] Data 2.308 (3.718) Batch 25.792 (28.137) Remain 17:58:35 loss: 0.2578 loss_seg: 0.1546 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:34:40,841 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 07:35:11,440 INFO misc.py line 117 726] Train: [16/20][251/510] Data 3.415 (3.717) Batch 30.600 (28.147) Remain 17:58:30 loss: 0.2933 loss_seg: 0.1949 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:35:52,854 INFO misc.py line 117 726] Train: [16/20][252/510] Data 11.083 (3.746) Batch 41.414 (28.201) Remain 18:00:04 loss: 0.2185 loss_seg: 0.1286 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:36:28,067 INFO misc.py line 117 726] Train: [16/20][253/510] Data 5.051 (3.752) Batch 35.213 (28.229) Remain 18:00:41 loss: 0.2279 loss_seg: 0.1309 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:36:56,472 INFO misc.py line 117 726] Train: [16/20][254/510] Data 3.296 (3.750) Batch 28.405 (28.229) Remain 18:00:14 loss: 0.2001 loss_seg: 0.1103 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:37:36,613 INFO misc.py line 117 726] Train: [16/20][255/510] Data 10.885 (3.778) Batch 40.141 (28.277) Remain 18:01:34 loss: 0.3040 loss_seg: 0.2006 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:38:02,887 INFO misc.py line 117 726] Train: [16/20][256/510] Data 3.160 (3.776) Batch 26.273 (28.269) Remain 18:00:48 loss: 0.2457 loss_seg: 0.1535 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:38:30,302 INFO misc.py line 117 726] Train: [16/20][257/510] Data 3.451 (3.774) Batch 27.416 (28.265) Remain 18:00:12 loss: 0.2747 loss_seg: 0.1746 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:38:56,407 INFO misc.py line 117 726] Train: [16/20][258/510] Data 2.594 (3.770) Batch 26.105 (28.257) Remain 17:59:24 loss: 0.2127 loss_seg: 0.1210 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:39:21,739 INFO misc.py line 117 726] Train: [16/20][259/510] Data 3.214 (3.768) Batch 25.332 (28.245) Remain 17:58:30 loss: 0.2120 loss_seg: 0.1221 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:39:50,770 INFO misc.py line 117 726] Train: [16/20][260/510] Data 4.278 (3.769) Batch 29.031 (28.248) Remain 17:58:08 loss: 0.2260 loss_seg: 0.1356 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:40:07,117 INFO misc.py line 117 726] Train: [16/20][261/510] Data 2.253 (3.764) Batch 16.347 (28.202) Remain 17:55:55 loss: 0.2115 loss_seg: 0.1176 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0439 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:40:40,428 INFO misc.py line 117 726] Train: [16/20][262/510] Data 3.371 (3.762) Batch 33.311 (28.222) Remain 17:56:12 loss: 0.2042 loss_seg: 0.1165 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:40:59,422 INFO misc.py line 117 726] Train: [16/20][263/510] Data 2.089 (3.756) Batch 18.995 (28.187) Remain 17:54:22 loss: 0.2612 loss_seg: 0.1573 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:41:25,483 INFO misc.py line 117 726] Train: [16/20][264/510] Data 3.185 (3.753) Batch 26.061 (28.178) Remain 17:53:35 loss: 0.2243 loss_seg: 0.1341 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:41:50,510 INFO misc.py line 117 726] Train: [16/20][265/510] Data 2.792 (3.750) Batch 25.027 (28.166) Remain 17:52:40 loss: 0.2139 loss_seg: 0.1197 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:42:19,597 INFO misc.py line 117 726] Train: [16/20][266/510] Data 2.675 (3.746) Batch 29.088 (28.170) Remain 17:52:19 loss: 0.2810 loss_seg: 0.1732 loss_superpoint_edge: 0.0405 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:42:41,403 INFO misc.py line 117 726] Train: [16/20][267/510] Data 2.386 (3.741) Batch 21.805 (28.146) Remain 17:50:56 loss: 0.2880 loss_seg: 0.1846 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:43:09,104 INFO misc.py line 117 726] Train: [16/20][268/510] Data 2.576 (3.736) Batch 27.701 (28.144) Remain 17:50:24 loss: 0.2114 loss_seg: 0.1184 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:43:45,049 INFO misc.py line 117 726] Train: [16/20][269/510] Data 5.948 (3.744) Batch 35.945 (28.173) Remain 17:51:03 loss: 0.2328 loss_seg: 0.1429 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:44:08,401 INFO misc.py line 117 726] Train: [16/20][270/510] Data 3.688 (3.744) Batch 23.352 (28.155) Remain 17:49:54 loss: 0.2508 loss_seg: 0.1511 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:44:38,204 INFO misc.py line 117 726] Train: [16/20][271/510] Data 2.987 (3.741) Batch 29.803 (28.162) Remain 17:49:40 loss: 0.2490 loss_seg: 0.1499 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:45:08,360 INFO misc.py line 117 726] Train: [16/20][272/510] Data 4.963 (3.746) Batch 30.156 (28.169) Remain 17:49:28 loss: 0.2103 loss_seg: 0.1226 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:45:42,782 INFO misc.py line 117 726] Train: [16/20][273/510] Data 3.988 (3.747) Batch 34.422 (28.192) Remain 17:49:53 loss: 0.1887 loss_seg: 0.1047 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:46:09,160 INFO misc.py line 117 726] Train: [16/20][274/510] Data 2.359 (3.742) Batch 26.378 (28.185) Remain 17:49:09 loss: 0.2544 loss_seg: 0.1565 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:46:36,498 INFO misc.py line 117 726] Train: [16/20][275/510] Data 2.873 (3.739) Batch 27.337 (28.182) Remain 17:48:34 loss: 0.2098 loss_seg: 0.1198 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:47:02,590 INFO misc.py line 117 726] Train: [16/20][276/510] Data 2.590 (3.734) Batch 26.092 (28.175) Remain 17:47:49 loss: 0.2612 loss_seg: 0.1651 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:47:22,621 INFO misc.py line 117 726] Train: [16/20][277/510] Data 2.699 (3.731) Batch 20.032 (28.145) Remain 17:46:13 loss: 0.2840 loss_seg: 0.1757 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:47:49,124 INFO misc.py line 117 726] Train: [16/20][278/510] Data 2.448 (3.726) Batch 26.503 (28.139) Remain 17:45:31 loss: 0.2309 loss_seg: 0.1389 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:48:22,243 INFO misc.py line 117 726] Train: [16/20][279/510] Data 4.202 (3.728) Batch 33.119 (28.157) Remain 17:45:44 loss: 0.2559 loss_seg: 0.1579 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:48:51,510 INFO misc.py line 117 726] Train: [16/20][280/510] Data 3.595 (3.727) Batch 29.267 (28.161) Remain 17:45:25 loss: 0.2452 loss_seg: 0.1477 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:49:23,835 INFO misc.py line 117 726] Train: [16/20][281/510] Data 3.207 (3.725) Batch 32.325 (28.176) Remain 17:45:31 loss: 0.1661 loss_seg: 0.0777 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:49:48,392 INFO misc.py line 117 726] Train: [16/20][282/510] Data 2.945 (3.722) Batch 24.557 (28.163) Remain 17:44:33 loss: 0.2054 loss_seg: 0.1196 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:50:19,198 INFO misc.py line 117 726] Train: [16/20][283/510] Data 3.629 (3.722) Batch 30.806 (28.172) Remain 17:44:26 loss: 0.2147 loss_seg: 0.1228 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:50:56,047 INFO misc.py line 117 726] Train: [16/20][284/510] Data 4.546 (3.725) Batch 36.848 (28.203) Remain 17:45:08 loss: 0.2561 loss_seg: 0.1536 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:51:33,962 INFO misc.py line 117 726] Train: [16/20][285/510] Data 4.970 (3.730) Batch 37.915 (28.238) Remain 17:45:58 loss: 0.2307 loss_seg: 0.1424 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:52:08,536 INFO misc.py line 117 726] Train: [16/20][286/510] Data 4.054 (3.731) Batch 34.574 (28.260) Remain 17:46:20 loss: 0.2379 loss_seg: 0.1462 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:52:41,801 INFO misc.py line 117 726] Train: [16/20][287/510] Data 8.046 (3.746) Batch 33.265 (28.278) Remain 17:46:32 loss: 0.2518 loss_seg: 0.1538 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:53:06,160 INFO misc.py line 117 726] Train: [16/20][288/510] Data 3.194 (3.744) Batch 24.359 (28.264) Remain 17:45:33 loss: 0.1912 loss_seg: 0.1004 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:53:40,462 INFO misc.py line 117 726] Train: [16/20][289/510] Data 5.075 (3.749) Batch 34.302 (28.285) Remain 17:45:52 loss: 0.3042 loss_seg: 0.1986 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:54:09,265 INFO misc.py line 117 726] Train: [16/20][290/510] Data 5.005 (3.753) Batch 28.803 (28.287) Remain 17:45:28 loss: 0.2160 loss_seg: 0.1239 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:54:30,069 INFO misc.py line 117 726] Train: [16/20][291/510] Data 2.612 (3.749) Batch 20.804 (28.261) Remain 17:44:01 loss: 0.2472 loss_seg: 0.1543 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:54:57,271 INFO misc.py line 117 726] Train: [16/20][292/510] Data 4.852 (3.753) Batch 27.202 (28.257) Remain 17:43:24 loss: 0.1749 loss_seg: 0.0920 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:55:16,674 INFO misc.py line 117 726] Train: [16/20][293/510] Data 2.400 (3.748) Batch 19.403 (28.227) Remain 17:41:47 loss: 0.2589 loss_seg: 0.1616 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:55:44,075 INFO misc.py line 117 726] Train: [16/20][294/510] Data 3.187 (3.746) Batch 27.401 (28.224) Remain 17:41:13 loss: 0.2590 loss_seg: 0.1591 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:56:13,646 INFO misc.py line 117 726] Train: [16/20][295/510] Data 4.148 (3.748) Batch 29.571 (28.229) Remain 17:40:55 loss: 0.2973 loss_seg: 0.2030 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:56:39,627 INFO misc.py line 117 726] Train: [16/20][296/510] Data 2.577 (3.744) Batch 25.981 (28.221) Remain 17:40:09 loss: 0.2743 loss_seg: 0.1721 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:57:12,697 INFO misc.py line 117 726] Train: [16/20][297/510] Data 5.312 (3.749) Batch 33.070 (28.237) Remain 17:40:18 loss: 0.2965 loss_seg: 0.1885 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:57:45,572 INFO misc.py line 117 726] Train: [16/20][298/510] Data 4.991 (3.753) Batch 32.875 (28.253) Remain 17:40:25 loss: 0.2845 loss_seg: 0.1863 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:58:15,706 INFO misc.py line 117 726] Train: [16/20][299/510] Data 4.412 (3.755) Batch 30.134 (28.259) Remain 17:40:11 loss: 0.3199 loss_seg: 0.2119 loss_superpoint_edge: 0.0409 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:58:56,696 INFO misc.py line 117 726] Train: [16/20][300/510] Data 9.660 (3.775) Batch 40.990 (28.302) Remain 17:41:20 loss: 0.2328 loss_seg: 0.1384 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:58:56,696 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 07:59:25,028 INFO misc.py line 117 726] Train: [16/20][301/510] Data 4.393 (3.777) Batch 28.333 (28.302) Remain 17:40:52 loss: 0.2916 loss_seg: 0.1893 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 07:59:53,591 INFO misc.py line 117 726] Train: [16/20][302/510] Data 2.779 (3.774) Batch 28.562 (28.303) Remain 17:40:25 loss: 0.2564 loss_seg: 0.1563 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:00:20,576 INFO misc.py line 117 726] Train: [16/20][303/510] Data 2.950 (3.771) Batch 26.985 (28.299) Remain 17:39:47 loss: 0.2258 loss_seg: 0.1329 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:00:56,538 INFO misc.py line 117 726] Train: [16/20][304/510] Data 5.615 (3.777) Batch 35.963 (28.324) Remain 17:40:16 loss: 0.1886 loss_seg: 0.1029 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:01:27,450 INFO misc.py line 117 726] Train: [16/20][305/510] Data 4.157 (3.779) Batch 30.911 (28.333) Remain 17:40:07 loss: 0.2407 loss_seg: 0.1419 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:01:56,170 INFO misc.py line 117 726] Train: [16/20][306/510] Data 3.103 (3.776) Batch 28.720 (28.334) Remain 17:39:41 loss: 0.2131 loss_seg: 0.1215 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:02:26,682 INFO misc.py line 117 726] Train: [16/20][307/510] Data 3.566 (3.776) Batch 30.512 (28.341) Remain 17:39:29 loss: 0.2101 loss_seg: 0.1222 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:02:59,403 INFO misc.py line 117 726] Train: [16/20][308/510] Data 3.224 (3.774) Batch 32.721 (28.356) Remain 17:39:33 loss: 0.1949 loss_seg: 0.1086 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:03:26,810 INFO misc.py line 117 726] Train: [16/20][309/510] Data 2.767 (3.771) Batch 27.408 (28.353) Remain 17:38:58 loss: 0.2722 loss_seg: 0.1760 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:03:54,408 INFO misc.py line 117 726] Train: [16/20][310/510] Data 2.772 (3.767) Batch 27.598 (28.350) Remain 17:38:24 loss: 0.2173 loss_seg: 0.1265 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:04:16,228 INFO misc.py line 117 726] Train: [16/20][311/510] Data 2.005 (3.762) Batch 21.820 (28.329) Remain 17:37:08 loss: 0.2759 loss_seg: 0.1774 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:04:38,340 INFO misc.py line 117 726] Train: [16/20][312/510] Data 2.558 (3.758) Batch 22.112 (28.309) Remain 17:35:55 loss: 0.2402 loss_seg: 0.1427 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:05:10,510 INFO misc.py line 117 726] Train: [16/20][313/510] Data 3.664 (3.757) Batch 32.170 (28.321) Remain 17:35:54 loss: 0.3181 loss_seg: 0.2058 loss_superpoint_edge: 0.0439 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0339 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:05:35,052 INFO misc.py line 117 726] Train: [16/20][314/510] Data 3.649 (3.757) Batch 24.542 (28.309) Remain 17:34:59 loss: 0.2230 loss_seg: 0.1336 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:06:02,310 INFO misc.py line 117 726] Train: [16/20][315/510] Data 3.270 (3.756) Batch 27.258 (28.306) Remain 17:34:23 loss: 0.1689 loss_seg: 0.0854 loss_superpoint_edge: 0.0129 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:06:30,623 INFO misc.py line 117 726] Train: [16/20][316/510] Data 2.663 (3.752) Batch 28.313 (28.306) Remain 17:33:55 loss: 0.1975 loss_seg: 0.1071 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:06:55,752 INFO misc.py line 117 726] Train: [16/20][317/510] Data 3.459 (3.751) Batch 25.129 (28.296) Remain 17:33:04 loss: 0.2566 loss_seg: 0.1608 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:07:23,183 INFO misc.py line 117 726] Train: [16/20][318/510] Data 2.496 (3.747) Batch 27.430 (28.293) Remain 17:32:29 loss: 0.2301 loss_seg: 0.1350 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:07:54,903 INFO misc.py line 117 726] Train: [16/20][319/510] Data 5.734 (3.753) Batch 31.720 (28.304) Remain 17:32:25 loss: 0.2041 loss_seg: 0.1161 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:08:17,538 INFO misc.py line 117 726] Train: [16/20][320/510] Data 2.357 (3.749) Batch 22.634 (28.286) Remain 17:31:17 loss: 0.2843 loss_seg: 0.1970 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:08:47,812 INFO misc.py line 117 726] Train: [16/20][321/510] Data 2.611 (3.745) Batch 30.274 (28.292) Remain 17:31:03 loss: 0.2978 loss_seg: 0.1902 loss_superpoint_edge: 0.0415 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:09:17,087 INFO misc.py line 117 726] Train: [16/20][322/510] Data 5.847 (3.752) Batch 29.275 (28.295) Remain 17:30:41 loss: 0.2245 loss_seg: 0.1295 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:09:54,978 INFO misc.py line 117 726] Train: [16/20][323/510] Data 8.503 (3.767) Batch 37.892 (28.325) Remain 17:31:20 loss: 0.2078 loss_seg: 0.1191 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:10:16,220 INFO misc.py line 117 726] Train: [16/20][324/510] Data 2.530 (3.763) Batch 21.241 (28.303) Remain 17:30:02 loss: 0.2197 loss_seg: 0.1301 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:10:37,367 INFO misc.py line 117 726] Train: [16/20][325/510] Data 2.300 (3.758) Batch 21.147 (28.281) Remain 17:28:44 loss: 0.1994 loss_seg: 0.1096 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:10:55,663 INFO misc.py line 117 726] Train: [16/20][326/510] Data 2.715 (3.755) Batch 18.296 (28.250) Remain 17:27:07 loss: 0.3039 loss_seg: 0.1958 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:11:25,203 INFO misc.py line 117 726] Train: [16/20][327/510] Data 3.601 (3.755) Batch 29.541 (28.254) Remain 17:26:48 loss: 0.2720 loss_seg: 0.1704 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:11:44,662 INFO misc.py line 117 726] Train: [16/20][328/510] Data 1.638 (3.748) Batch 19.459 (28.227) Remain 17:25:20 loss: 0.2109 loss_seg: 0.1153 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:12:14,035 INFO misc.py line 117 726] Train: [16/20][329/510] Data 4.181 (3.750) Batch 29.373 (28.230) Remain 17:24:59 loss: 0.3005 loss_seg: 0.1892 loss_superpoint_edge: 0.0443 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:12:48,451 INFO misc.py line 117 726] Train: [16/20][330/510] Data 6.033 (3.757) Batch 34.416 (28.249) Remain 17:25:13 loss: 0.2188 loss_seg: 0.1287 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:13:16,975 INFO misc.py line 117 726] Train: [16/20][331/510] Data 2.417 (3.752) Batch 28.524 (28.250) Remain 17:24:47 loss: 0.2599 loss_seg: 0.1553 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:13:45,185 INFO misc.py line 117 726] Train: [16/20][332/510] Data 5.848 (3.759) Batch 28.210 (28.250) Remain 17:24:18 loss: 0.4209 loss_seg: 0.2834 loss_superpoint_edge: 0.0677 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:14:11,740 INFO misc.py line 117 726] Train: [16/20][333/510] Data 3.145 (3.757) Batch 26.556 (28.245) Remain 17:23:38 loss: 0.2173 loss_seg: 0.1237 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:14:40,255 INFO misc.py line 117 726] Train: [16/20][334/510] Data 3.269 (3.755) Batch 28.515 (28.246) Remain 17:23:12 loss: 0.2502 loss_seg: 0.1514 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:15:19,414 INFO misc.py line 117 726] Train: [16/20][335/510] Data 11.536 (3.779) Batch 39.158 (28.279) Remain 17:23:57 loss: 0.2113 loss_seg: 0.1204 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0436 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:15:48,734 INFO misc.py line 117 726] Train: [16/20][336/510] Data 3.401 (3.778) Batch 29.320 (28.282) Remain 17:23:35 loss: 0.2089 loss_seg: 0.1192 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:16:23,098 INFO misc.py line 117 726] Train: [16/20][337/510] Data 3.394 (3.777) Batch 34.364 (28.300) Remain 17:23:47 loss: 0.2616 loss_seg: 0.1633 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:16:42,242 INFO misc.py line 117 726] Train: [16/20][338/510] Data 1.304 (3.769) Batch 19.144 (28.273) Remain 17:22:18 loss: 0.2944 loss_seg: 0.1903 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:17:02,497 INFO misc.py line 117 726] Train: [16/20][339/510] Data 2.418 (3.765) Batch 20.254 (28.249) Remain 17:20:57 loss: 0.2150 loss_seg: 0.1264 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:17:37,178 INFO misc.py line 117 726] Train: [16/20][340/510] Data 3.614 (3.765) Batch 34.682 (28.268) Remain 17:21:11 loss: 0.1943 loss_seg: 0.1085 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:18:10,474 INFO misc.py line 117 726] Train: [16/20][341/510] Data 4.801 (3.768) Batch 33.296 (28.283) Remain 17:21:16 loss: 0.2958 loss_seg: 0.2003 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:18:34,989 INFO misc.py line 117 726] Train: [16/20][342/510] Data 2.399 (3.764) Batch 24.514 (28.272) Remain 17:20:23 loss: 0.2366 loss_seg: 0.1383 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:19:10,066 INFO misc.py line 117 726] Train: [16/20][343/510] Data 3.574 (3.763) Batch 35.077 (28.292) Remain 17:20:39 loss: 0.2348 loss_seg: 0.1374 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:19:38,862 INFO misc.py line 117 726] Train: [16/20][344/510] Data 3.226 (3.762) Batch 28.797 (28.293) Remain 17:20:14 loss: 0.2788 loss_seg: 0.1772 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:20:09,561 INFO misc.py line 117 726] Train: [16/20][345/510] Data 5.117 (3.766) Batch 30.699 (28.300) Remain 17:20:01 loss: 0.2142 loss_seg: 0.1255 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:20:37,547 INFO misc.py line 117 726] Train: [16/20][346/510] Data 3.635 (3.765) Batch 27.986 (28.299) Remain 17:19:31 loss: 0.2661 loss_seg: 0.1739 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:21:01,792 INFO misc.py line 117 726] Train: [16/20][347/510] Data 4.957 (3.769) Batch 24.245 (28.287) Remain 17:18:37 loss: 0.3265 loss_seg: 0.2322 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:21:19,837 INFO misc.py line 117 726] Train: [16/20][348/510] Data 1.836 (3.763) Batch 18.045 (28.258) Remain 17:17:03 loss: 0.3216 loss_seg: 0.2192 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:21:55,790 INFO misc.py line 117 726] Train: [16/20][349/510] Data 9.970 (3.781) Batch 35.953 (28.280) Remain 17:17:24 loss: 0.2599 loss_seg: 0.1690 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:22:30,823 INFO misc.py line 117 726] Train: [16/20][350/510] Data 4.264 (3.782) Batch 35.032 (28.299) Remain 17:17:38 loss: 0.1768 loss_seg: 0.0956 loss_superpoint_edge: 0.0135 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:22:30,823 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 08:23:03,033 INFO misc.py line 117 726] Train: [16/20][351/510] Data 4.939 (3.786) Batch 32.211 (28.311) Remain 17:17:35 loss: 0.2059 loss_seg: 0.1181 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:23:36,871 INFO misc.py line 117 726] Train: [16/20][352/510] Data 5.640 (3.791) Batch 33.838 (28.327) Remain 17:17:41 loss: 0.2568 loss_seg: 0.1631 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:24:12,626 INFO misc.py line 117 726] Train: [16/20][353/510] Data 5.018 (3.795) Batch 35.754 (28.348) Remain 17:17:59 loss: 0.2669 loss_seg: 0.1721 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:24:44,692 INFO misc.py line 117 726] Train: [16/20][354/510] Data 3.463 (3.794) Batch 32.066 (28.358) Remain 17:17:54 loss: 0.2281 loss_seg: 0.1358 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:25:03,146 INFO misc.py line 117 726] Train: [16/20][355/510] Data 1.921 (3.788) Batch 18.455 (28.330) Remain 17:16:24 loss: 0.2101 loss_seg: 0.1213 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:25:31,542 INFO misc.py line 117 726] Train: [16/20][356/510] Data 3.384 (3.787) Batch 28.396 (28.330) Remain 17:15:56 loss: 0.2011 loss_seg: 0.1097 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:25:59,370 INFO misc.py line 117 726] Train: [16/20][357/510] Data 3.039 (3.785) Batch 27.828 (28.329) Remain 17:15:25 loss: 0.3221 loss_seg: 0.2228 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:26:21,043 INFO misc.py line 117 726] Train: [16/20][358/510] Data 3.645 (3.785) Batch 21.673 (28.310) Remain 17:14:15 loss: 0.2381 loss_seg: 0.1479 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:26:50,756 INFO misc.py line 117 726] Train: [16/20][359/510] Data 4.433 (3.786) Batch 29.713 (28.314) Remain 17:13:56 loss: 0.2939 loss_seg: 0.1934 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:27:19,479 INFO misc.py line 117 726] Train: [16/20][360/510] Data 3.267 (3.785) Batch 28.723 (28.315) Remain 17:13:30 loss: 0.2099 loss_seg: 0.1202 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:27:41,187 INFO misc.py line 117 726] Train: [16/20][361/510] Data 2.265 (3.781) Batch 21.708 (28.297) Remain 17:12:21 loss: 0.2079 loss_seg: 0.1166 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:28:04,590 INFO misc.py line 117 726] Train: [16/20][362/510] Data 2.101 (3.776) Batch 23.403 (28.283) Remain 17:11:23 loss: 0.1994 loss_seg: 0.1103 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:28:30,490 INFO misc.py line 117 726] Train: [16/20][363/510] Data 2.494 (3.773) Batch 25.900 (28.277) Remain 17:10:40 loss: 0.2299 loss_seg: 0.1380 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:28:59,249 INFO misc.py line 117 726] Train: [16/20][364/510] Data 4.172 (3.774) Batch 28.759 (28.278) Remain 17:10:15 loss: 0.2124 loss_seg: 0.1248 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:29:20,468 INFO misc.py line 117 726] Train: [16/20][365/510] Data 2.469 (3.770) Batch 21.219 (28.258) Remain 17:09:04 loss: 0.2758 loss_seg: 0.1736 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:29:52,240 INFO misc.py line 117 726] Train: [16/20][366/510] Data 4.566 (3.772) Batch 31.772 (28.268) Remain 17:08:57 loss: 0.2294 loss_seg: 0.1451 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:30:30,830 INFO misc.py line 117 726] Train: [16/20][367/510] Data 4.911 (3.775) Batch 38.590 (28.296) Remain 17:09:31 loss: 0.2305 loss_seg: 0.1353 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:30:59,806 INFO misc.py line 117 726] Train: [16/20][368/510] Data 2.783 (3.773) Batch 28.976 (28.298) Remain 17:09:06 loss: 0.2333 loss_seg: 0.1385 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:31:25,640 INFO misc.py line 117 726] Train: [16/20][369/510] Data 3.320 (3.771) Batch 25.835 (28.292) Remain 17:08:23 loss: 0.2654 loss_seg: 0.1633 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:31:54,571 INFO misc.py line 117 726] Train: [16/20][370/510] Data 5.552 (3.776) Batch 28.931 (28.293) Remain 17:07:59 loss: 0.4576 loss_seg: 0.3492 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:32:28,239 INFO misc.py line 117 726] Train: [16/20][371/510] Data 4.712 (3.779) Batch 33.668 (28.308) Remain 17:08:02 loss: 0.1902 loss_seg: 0.1043 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:32:48,811 INFO misc.py line 117 726] Train: [16/20][372/510] Data 2.629 (3.776) Batch 20.572 (28.287) Remain 17:06:49 loss: 0.2430 loss_seg: 0.1481 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:33:01,837 INFO misc.py line 117 726] Train: [16/20][373/510] Data 1.775 (3.770) Batch 13.026 (28.246) Remain 17:04:50 loss: 0.2321 loss_seg: 0.1330 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:33:23,818 INFO misc.py line 117 726] Train: [16/20][374/510] Data 2.495 (3.767) Batch 21.980 (28.229) Remain 17:03:45 loss: 0.2122 loss_seg: 0.1192 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:33:51,550 INFO misc.py line 117 726] Train: [16/20][375/510] Data 3.073 (3.765) Batch 27.733 (28.227) Remain 17:03:14 loss: 0.2703 loss_seg: 0.1767 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:34:22,835 INFO misc.py line 117 726] Train: [16/20][376/510] Data 4.201 (3.766) Batch 31.285 (28.236) Remain 17:03:04 loss: 0.2740 loss_seg: 0.1734 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:34:48,962 INFO misc.py line 117 726] Train: [16/20][377/510] Data 3.982 (3.767) Batch 26.127 (28.230) Remain 17:02:23 loss: 0.2084 loss_seg: 0.1196 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:35:19,877 INFO misc.py line 117 726] Train: [16/20][378/510] Data 3.437 (3.766) Batch 30.916 (28.237) Remain 17:02:11 loss: 0.2589 loss_seg: 0.1605 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0320 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:35:45,714 INFO misc.py line 117 726] Train: [16/20][379/510] Data 2.964 (3.764) Batch 25.837 (28.231) Remain 17:01:29 loss: 0.2079 loss_seg: 0.1155 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:36:11,881 INFO misc.py line 117 726] Train: [16/20][380/510] Data 6.358 (3.771) Batch 26.167 (28.225) Remain 17:00:49 loss: 0.2003 loss_seg: 0.1055 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:36:42,354 INFO misc.py line 117 726] Train: [16/20][381/510] Data 3.837 (3.771) Batch 30.473 (28.231) Remain 17:00:33 loss: 0.2319 loss_seg: 0.1359 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:37:14,337 INFO misc.py line 117 726] Train: [16/20][382/510] Data 3.364 (3.770) Batch 31.983 (28.241) Remain 17:00:26 loss: 0.2426 loss_seg: 0.1464 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:37:37,071 INFO misc.py line 117 726] Train: [16/20][383/510] Data 2.250 (3.766) Batch 22.734 (28.227) Remain 16:59:27 loss: 0.2559 loss_seg: 0.1546 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:38:06,412 INFO misc.py line 117 726] Train: [16/20][384/510] Data 3.251 (3.764) Batch 29.341 (28.230) Remain 16:59:05 loss: 0.2760 loss_seg: 0.1672 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:38:32,410 INFO misc.py line 117 726] Train: [16/20][385/510] Data 2.324 (3.761) Batch 25.998 (28.224) Remain 16:58:24 loss: 0.2791 loss_seg: 0.1789 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:38:53,025 INFO misc.py line 117 726] Train: [16/20][386/510] Data 2.419 (3.757) Batch 20.614 (28.204) Remain 16:57:13 loss: 0.2591 loss_seg: 0.1551 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:39:16,464 INFO misc.py line 117 726] Train: [16/20][387/510] Data 3.703 (3.757) Batch 23.439 (28.192) Remain 16:56:18 loss: 0.2588 loss_seg: 0.1565 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:39:43,745 INFO misc.py line 117 726] Train: [16/20][388/510] Data 2.799 (3.754) Batch 27.281 (28.189) Remain 16:55:44 loss: 0.2343 loss_seg: 0.1416 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:40:04,570 INFO misc.py line 117 726] Train: [16/20][389/510] Data 3.420 (3.754) Batch 20.825 (28.170) Remain 16:54:35 loss: 0.2712 loss_seg: 0.1843 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:40:37,512 INFO misc.py line 117 726] Train: [16/20][390/510] Data 4.762 (3.756) Batch 32.943 (28.182) Remain 16:54:33 loss: 0.2293 loss_seg: 0.1373 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:41:08,866 INFO misc.py line 117 726] Train: [16/20][391/510] Data 4.315 (3.758) Batch 31.353 (28.191) Remain 16:54:23 loss: 0.1849 loss_seg: 0.1018 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:41:42,835 INFO misc.py line 117 726] Train: [16/20][392/510] Data 10.407 (3.775) Batch 33.969 (28.205) Remain 16:54:27 loss: 0.2681 loss_seg: 0.1794 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:42:12,605 INFO misc.py line 117 726] Train: [16/20][393/510] Data 4.150 (3.776) Batch 29.770 (28.209) Remain 16:54:07 loss: 0.1922 loss_seg: 0.1080 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:42:39,767 INFO misc.py line 117 726] Train: [16/20][394/510] Data 3.131 (3.774) Batch 27.162 (28.207) Remain 16:53:33 loss: 0.2278 loss_seg: 0.1353 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:43:05,630 INFO misc.py line 117 726] Train: [16/20][395/510] Data 3.473 (3.773) Batch 25.863 (28.201) Remain 16:52:52 loss: 0.2263 loss_seg: 0.1359 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:43:39,760 INFO misc.py line 117 726] Train: [16/20][396/510] Data 5.981 (3.779) Batch 34.130 (28.216) Remain 16:52:56 loss: 0.2918 loss_seg: 0.1934 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:44:07,852 INFO misc.py line 117 726] Train: [16/20][397/510] Data 3.162 (3.777) Batch 28.092 (28.216) Remain 16:52:28 loss: 0.2510 loss_seg: 0.1570 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:44:38,981 INFO misc.py line 117 726] Train: [16/20][398/510] Data 4.397 (3.779) Batch 31.129 (28.223) Remain 16:52:15 loss: 0.2170 loss_seg: 0.1228 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:44:58,934 INFO misc.py line 117 726] Train: [16/20][399/510] Data 3.955 (3.779) Batch 19.954 (28.202) Remain 16:51:02 loss: 0.2266 loss_seg: 0.1319 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:45:25,149 INFO misc.py line 117 726] Train: [16/20][400/510] Data 2.982 (3.777) Batch 26.214 (28.197) Remain 16:50:23 loss: 0.2364 loss_seg: 0.1409 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:45:25,149 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 08:45:47,887 INFO misc.py line 117 726] Train: [16/20][401/510] Data 4.405 (3.779) Batch 22.739 (28.183) Remain 16:49:25 loss: 0.1999 loss_seg: 0.1120 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:46:08,056 INFO misc.py line 117 726] Train: [16/20][402/510] Data 2.060 (3.775) Batch 20.168 (28.163) Remain 16:48:14 loss: 0.2123 loss_seg: 0.1245 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:46:35,030 INFO misc.py line 117 726] Train: [16/20][403/510] Data 2.892 (3.772) Batch 26.975 (28.160) Remain 16:47:40 loss: 0.2470 loss_seg: 0.1554 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:47:12,659 INFO misc.py line 117 726] Train: [16/20][404/510] Data 4.519 (3.774) Batch 37.629 (28.184) Remain 16:48:02 loss: 0.2582 loss_seg: 0.1688 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:47:33,252 INFO misc.py line 117 726] Train: [16/20][405/510] Data 2.272 (3.771) Batch 20.593 (28.165) Remain 16:46:53 loss: 0.2052 loss_seg: 0.1173 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:47:56,185 INFO misc.py line 117 726] Train: [16/20][406/510] Data 3.032 (3.769) Batch 22.933 (28.152) Remain 16:45:57 loss: 0.2932 loss_seg: 0.1842 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:48:25,966 INFO misc.py line 117 726] Train: [16/20][407/510] Data 3.109 (3.767) Batch 29.781 (28.156) Remain 16:45:38 loss: 0.2214 loss_seg: 0.1282 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:48:50,728 INFO misc.py line 117 726] Train: [16/20][408/510] Data 2.789 (3.765) Batch 24.762 (28.148) Remain 16:44:52 loss: 0.2270 loss_seg: 0.1373 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:49:11,085 INFO misc.py line 117 726] Train: [16/20][409/510] Data 4.013 (3.765) Batch 20.357 (28.128) Remain 16:43:43 loss: 0.2431 loss_seg: 0.1388 loss_superpoint_edge: 0.0342 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:49:48,190 INFO misc.py line 117 726] Train: [16/20][410/510] Data 7.100 (3.773) Batch 37.105 (28.151) Remain 16:44:02 loss: 0.2161 loss_seg: 0.1255 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:50:23,455 INFO misc.py line 117 726] Train: [16/20][411/510] Data 4.651 (3.776) Batch 35.265 (28.168) Remain 16:44:11 loss: 0.2548 loss_seg: 0.1615 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:50:47,930 INFO misc.py line 117 726] Train: [16/20][412/510] Data 2.587 (3.773) Batch 24.475 (28.159) Remain 16:43:23 loss: 0.2494 loss_seg: 0.1684 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:51:18,773 INFO misc.py line 117 726] Train: [16/20][413/510] Data 4.178 (3.774) Batch 30.843 (28.165) Remain 16:43:09 loss: 0.2938 loss_seg: 0.1914 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:51:46,342 INFO misc.py line 117 726] Train: [16/20][414/510] Data 2.911 (3.772) Batch 27.569 (28.164) Remain 16:42:38 loss: 0.2612 loss_seg: 0.1575 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:52:16,619 INFO misc.py line 117 726] Train: [16/20][415/510] Data 3.475 (3.771) Batch 30.277 (28.169) Remain 16:42:21 loss: 0.2256 loss_seg: 0.1326 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:52:45,102 INFO misc.py line 117 726] Train: [16/20][416/510] Data 5.427 (3.775) Batch 28.483 (28.170) Remain 16:41:54 loss: 0.3282 loss_seg: 0.2210 loss_superpoint_edge: 0.0398 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0339 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:53:09,273 INFO misc.py line 117 726] Train: [16/20][417/510] Data 2.540 (3.772) Batch 24.171 (28.160) Remain 16:41:05 loss: 0.1797 loss_seg: 0.0983 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:53:37,788 INFO misc.py line 117 726] Train: [16/20][418/510] Data 3.314 (3.771) Batch 28.514 (28.161) Remain 16:40:39 loss: 0.2137 loss_seg: 0.1179 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:54:15,892 INFO misc.py line 117 726] Train: [16/20][419/510] Data 6.796 (3.778) Batch 38.105 (28.185) Remain 16:41:02 loss: 0.2628 loss_seg: 0.1663 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:54:43,301 INFO misc.py line 117 726] Train: [16/20][420/510] Data 3.142 (3.777) Batch 27.408 (28.183) Remain 16:40:30 loss: 0.2452 loss_seg: 0.1481 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:55:13,618 INFO misc.py line 117 726] Train: [16/20][421/510] Data 5.078 (3.780) Batch 30.318 (28.188) Remain 16:40:12 loss: 0.2371 loss_seg: 0.1420 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:55:46,041 INFO misc.py line 117 726] Train: [16/20][422/510] Data 3.127 (3.778) Batch 32.423 (28.198) Remain 16:40:06 loss: 0.2205 loss_seg: 0.1275 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:56:14,455 INFO misc.py line 117 726] Train: [16/20][423/510] Data 4.545 (3.780) Batch 28.414 (28.199) Remain 16:39:39 loss: 0.3687 loss_seg: 0.2559 loss_superpoint_edge: 0.0432 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:56:52,981 INFO misc.py line 117 726] Train: [16/20][424/510] Data 5.463 (3.784) Batch 38.526 (28.223) Remain 16:40:02 loss: 0.2241 loss_seg: 0.1287 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:57:12,502 INFO misc.py line 117 726] Train: [16/20][425/510] Data 2.179 (3.780) Batch 19.521 (28.203) Remain 16:38:50 loss: 0.2722 loss_seg: 0.1710 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:57:45,975 INFO misc.py line 117 726] Train: [16/20][426/510] Data 5.703 (3.785) Batch 33.473 (28.215) Remain 16:38:49 loss: 0.4317 loss_seg: 0.3296 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:58:21,664 INFO misc.py line 117 726] Train: [16/20][427/510] Data 5.887 (3.790) Batch 35.689 (28.233) Remain 16:38:58 loss: 0.2265 loss_seg: 0.1344 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:58:46,584 INFO misc.py line 117 726] Train: [16/20][428/510] Data 2.675 (3.787) Batch 24.920 (28.225) Remain 16:38:13 loss: 0.2435 loss_seg: 0.1494 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:59:11,062 INFO misc.py line 117 726] Train: [16/20][429/510] Data 4.491 (3.789) Batch 24.478 (28.216) Remain 16:37:26 loss: 0.2467 loss_seg: 0.1511 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 08:59:43,750 INFO misc.py line 117 726] Train: [16/20][430/510] Data 5.179 (3.792) Batch 32.688 (28.227) Remain 16:37:20 loss: 0.2176 loss_seg: 0.1310 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:00:15,800 INFO misc.py line 117 726] Train: [16/20][431/510] Data 4.093 (3.793) Batch 32.051 (28.236) Remain 16:37:11 loss: 0.2698 loss_seg: 0.1701 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:00:49,927 INFO misc.py line 117 726] Train: [16/20][432/510] Data 4.616 (3.795) Batch 34.127 (28.249) Remain 16:37:12 loss: 0.2833 loss_seg: 0.1869 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:01:19,911 INFO misc.py line 117 726] Train: [16/20][433/510] Data 3.327 (3.793) Batch 29.984 (28.253) Remain 16:36:52 loss: 0.1989 loss_seg: 0.1147 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:01:56,114 INFO misc.py line 117 726] Train: [16/20][434/510] Data 7.246 (3.801) Batch 36.203 (28.272) Remain 16:37:03 loss: 0.2892 loss_seg: 0.1943 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:02:25,262 INFO misc.py line 117 726] Train: [16/20][435/510] Data 3.891 (3.802) Batch 29.148 (28.274) Remain 16:36:39 loss: 0.2288 loss_seg: 0.1376 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:02:46,957 INFO misc.py line 117 726] Train: [16/20][436/510] Data 2.006 (3.798) Batch 21.695 (28.259) Remain 16:35:38 loss: 0.2014 loss_seg: 0.1132 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:03:18,235 INFO misc.py line 117 726] Train: [16/20][437/510] Data 2.913 (3.795) Batch 31.278 (28.266) Remain 16:35:25 loss: 0.2929 loss_seg: 0.1852 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:03:49,943 INFO misc.py line 117 726] Train: [16/20][438/510] Data 3.974 (3.796) Batch 31.708 (28.274) Remain 16:35:13 loss: 0.1867 loss_seg: 0.1021 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:04:14,557 INFO misc.py line 117 726] Train: [16/20][439/510] Data 2.962 (3.794) Batch 24.614 (28.265) Remain 16:34:27 loss: 0.2270 loss_seg: 0.1327 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:04:38,400 INFO misc.py line 117 726] Train: [16/20][440/510] Data 2.287 (3.791) Batch 23.843 (28.255) Remain 16:33:38 loss: 0.2506 loss_seg: 0.1545 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:05:09,345 INFO misc.py line 117 726] Train: [16/20][441/510] Data 6.539 (3.797) Batch 30.945 (28.261) Remain 16:33:22 loss: 0.2663 loss_seg: 0.1739 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:05:31,858 INFO misc.py line 117 726] Train: [16/20][442/510] Data 3.091 (3.795) Batch 22.513 (28.248) Remain 16:32:27 loss: 0.2635 loss_seg: 0.1603 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:05:55,601 INFO misc.py line 117 726] Train: [16/20][443/510] Data 3.456 (3.794) Batch 23.743 (28.238) Remain 16:31:37 loss: 0.2194 loss_seg: 0.1289 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:06:20,622 INFO misc.py line 117 726] Train: [16/20][444/510] Data 2.823 (3.792) Batch 25.021 (28.231) Remain 16:30:53 loss: 0.3403 loss_seg: 0.2273 loss_superpoint_edge: 0.0463 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:06:46,257 INFO misc.py line 117 726] Train: [16/20][445/510] Data 2.516 (3.789) Batch 25.636 (28.225) Remain 16:30:13 loss: 0.2384 loss_seg: 0.1518 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:07:03,836 INFO misc.py line 117 726] Train: [16/20][446/510] Data 2.281 (3.786) Batch 17.579 (28.201) Remain 16:28:54 loss: 0.2470 loss_seg: 0.1524 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:07:23,464 INFO misc.py line 117 726] Train: [16/20][447/510] Data 3.791 (3.786) Batch 19.628 (28.181) Remain 16:27:45 loss: 0.2140 loss_seg: 0.1277 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:07:38,840 INFO misc.py line 117 726] Train: [16/20][448/510] Data 2.013 (3.782) Batch 15.376 (28.153) Remain 16:26:16 loss: 0.2511 loss_seg: 0.1588 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:08:12,385 INFO misc.py line 117 726] Train: [16/20][449/510] Data 6.514 (3.788) Batch 33.545 (28.165) Remain 16:26:14 loss: 0.3775 loss_seg: 0.2685 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:08:34,190 INFO misc.py line 117 726] Train: [16/20][450/510] Data 2.449 (3.785) Batch 21.805 (28.150) Remain 16:25:16 loss: 0.2059 loss_seg: 0.1147 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:08:34,190 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 09:08:59,004 INFO misc.py line 117 726] Train: [16/20][451/510] Data 3.015 (3.783) Batch 24.814 (28.143) Remain 16:24:32 loss: 0.2084 loss_seg: 0.1221 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:09:30,449 INFO misc.py line 117 726] Train: [16/20][452/510] Data 5.667 (3.788) Batch 31.445 (28.150) Remain 16:24:19 loss: 0.1771 loss_seg: 0.0918 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:09:50,339 INFO misc.py line 117 726] Train: [16/20][453/510] Data 2.157 (3.784) Batch 19.889 (28.132) Remain 16:23:12 loss: 0.2919 loss_seg: 0.1962 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:10:12,282 INFO misc.py line 117 726] Train: [16/20][454/510] Data 2.533 (3.781) Batch 21.943 (28.118) Remain 16:22:15 loss: 0.1932 loss_seg: 0.1049 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:10:37,030 INFO misc.py line 117 726] Train: [16/20][455/510] Data 2.693 (3.779) Batch 24.748 (28.111) Remain 16:21:32 loss: 0.2091 loss_seg: 0.1170 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:11:04,408 INFO misc.py line 117 726] Train: [16/20][456/510] Data 7.354 (3.787) Batch 27.378 (28.109) Remain 16:21:00 loss: 0.3150 loss_seg: 0.2069 loss_superpoint_edge: 0.0386 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:11:36,749 INFO misc.py line 117 726] Train: [16/20][457/510] Data 5.067 (3.789) Batch 32.341 (28.119) Remain 16:20:52 loss: 0.2251 loss_seg: 0.1323 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:12:06,460 INFO misc.py line 117 726] Train: [16/20][458/510] Data 3.946 (3.790) Batch 29.711 (28.122) Remain 16:20:31 loss: 0.2666 loss_seg: 0.1646 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:12:31,274 INFO misc.py line 117 726] Train: [16/20][459/510] Data 2.676 (3.787) Batch 24.815 (28.115) Remain 16:19:48 loss: 0.2374 loss_seg: 0.1412 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:13:01,758 INFO misc.py line 117 726] Train: [16/20][460/510] Data 3.674 (3.787) Batch 30.483 (28.120) Remain 16:19:30 loss: 0.3104 loss_seg: 0.2132 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:13:27,022 INFO misc.py line 117 726] Train: [16/20][461/510] Data 3.055 (3.786) Batch 25.264 (28.114) Remain 16:18:49 loss: 0.3039 loss_seg: 0.1991 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:13:52,908 INFO misc.py line 117 726] Train: [16/20][462/510] Data 2.717 (3.783) Batch 25.886 (28.109) Remain 16:18:11 loss: 0.1991 loss_seg: 0.1130 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:14:22,074 INFO misc.py line 117 726] Train: [16/20][463/510] Data 2.970 (3.781) Batch 29.166 (28.111) Remain 16:17:48 loss: 0.2368 loss_seg: 0.1396 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:14:55,922 INFO misc.py line 117 726] Train: [16/20][464/510] Data 3.937 (3.782) Batch 33.848 (28.124) Remain 16:17:45 loss: 0.2827 loss_seg: 0.1766 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:15:20,496 INFO misc.py line 117 726] Train: [16/20][465/510] Data 2.771 (3.780) Batch 24.574 (28.116) Remain 16:17:01 loss: 0.2137 loss_seg: 0.1233 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:15:44,846 INFO misc.py line 117 726] Train: [16/20][466/510] Data 2.852 (3.778) Batch 24.350 (28.108) Remain 16:16:16 loss: 0.2236 loss_seg: 0.1308 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:16:17,208 INFO misc.py line 117 726] Train: [16/20][467/510] Data 4.895 (3.780) Batch 32.361 (28.117) Remain 16:16:07 loss: 0.2429 loss_seg: 0.1506 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:16:43,195 INFO misc.py line 117 726] Train: [16/20][468/510] Data 2.459 (3.777) Batch 25.987 (28.112) Remain 16:15:30 loss: 0.2030 loss_seg: 0.1173 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:17:00,344 INFO misc.py line 117 726] Train: [16/20][469/510] Data 1.893 (3.773) Batch 17.149 (28.089) Remain 16:14:12 loss: 0.2038 loss_seg: 0.1124 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:17:28,049 INFO misc.py line 117 726] Train: [16/20][470/510] Data 2.491 (3.770) Batch 27.705 (28.088) Remain 16:13:43 loss: 0.2015 loss_seg: 0.1142 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:17:54,704 INFO misc.py line 117 726] Train: [16/20][471/510] Data 2.533 (3.768) Batch 26.653 (28.085) Remain 16:13:08 loss: 0.2138 loss_seg: 0.1206 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:18:24,047 INFO misc.py line 117 726] Train: [16/20][472/510] Data 3.073 (3.766) Batch 29.345 (28.088) Remain 16:12:46 loss: 0.2604 loss_seg: 0.1586 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:18:55,546 INFO misc.py line 117 726] Train: [16/20][473/510] Data 4.360 (3.767) Batch 31.499 (28.095) Remain 16:12:33 loss: 0.2374 loss_seg: 0.1499 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:19:23,670 INFO misc.py line 117 726] Train: [16/20][474/510] Data 3.259 (3.766) Batch 28.124 (28.095) Remain 16:12:05 loss: 0.2710 loss_seg: 0.1637 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:20:06,013 INFO misc.py line 117 726] Train: [16/20][475/510] Data 9.464 (3.778) Batch 42.343 (28.125) Remain 16:12:39 loss: 0.2380 loss_seg: 0.1373 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:20:25,300 INFO misc.py line 117 726] Train: [16/20][476/510] Data 1.926 (3.775) Batch 19.287 (28.107) Remain 16:11:32 loss: 0.2231 loss_seg: 0.1332 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:20:49,324 INFO misc.py line 117 726] Train: [16/20][477/510] Data 2.170 (3.771) Batch 24.024 (28.098) Remain 16:10:46 loss: 0.2129 loss_seg: 0.1261 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:21:14,329 INFO misc.py line 117 726] Train: [16/20][478/510] Data 3.018 (3.770) Batch 25.006 (28.091) Remain 16:10:05 loss: 0.1809 loss_seg: 0.0983 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:21:40,230 INFO misc.py line 117 726] Train: [16/20][479/510] Data 3.936 (3.770) Batch 25.901 (28.087) Remain 16:09:27 loss: 0.2872 loss_seg: 0.1835 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:22:13,332 INFO misc.py line 117 726] Train: [16/20][480/510] Data 5.699 (3.774) Batch 33.102 (28.097) Remain 16:09:21 loss: 0.3239 loss_seg: 0.2252 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:22:42,327 INFO misc.py line 117 726] Train: [16/20][481/510] Data 2.801 (3.772) Batch 28.995 (28.099) Remain 16:08:57 loss: 0.2351 loss_seg: 0.1417 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:23:09,973 INFO misc.py line 117 726] Train: [16/20][482/510] Data 8.927 (3.783) Batch 27.646 (28.098) Remain 16:08:27 loss: 0.2866 loss_seg: 0.1843 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:23:41,587 INFO misc.py line 117 726] Train: [16/20][483/510] Data 3.186 (3.781) Batch 31.614 (28.106) Remain 16:08:14 loss: 0.2006 loss_seg: 0.1164 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:24:10,308 INFO misc.py line 117 726] Train: [16/20][484/510] Data 3.311 (3.780) Batch 28.720 (28.107) Remain 16:07:48 loss: 0.2447 loss_seg: 0.1448 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:24:44,266 INFO misc.py line 117 726] Train: [16/20][485/510] Data 6.289 (3.786) Batch 33.959 (28.119) Remain 16:07:45 loss: 0.2946 loss_seg: 0.1989 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:25:21,019 INFO misc.py line 117 726] Train: [16/20][486/510] Data 4.727 (3.788) Batch 36.752 (28.137) Remain 16:07:54 loss: 0.2114 loss_seg: 0.1233 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:25:47,153 INFO misc.py line 117 726] Train: [16/20][487/510] Data 3.855 (3.788) Batch 26.134 (28.133) Remain 16:07:17 loss: 0.3062 loss_seg: 0.2098 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:26:17,277 INFO misc.py line 117 726] Train: [16/20][488/510] Data 3.592 (3.787) Batch 30.124 (28.137) Remain 16:06:58 loss: 0.2475 loss_seg: 0.1496 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:26:44,198 INFO misc.py line 117 726] Train: [16/20][489/510] Data 2.819 (3.785) Batch 26.921 (28.134) Remain 16:06:24 loss: 0.2844 loss_seg: 0.1822 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:27:15,637 INFO misc.py line 117 726] Train: [16/20][490/510] Data 3.840 (3.786) Batch 31.439 (28.141) Remain 16:06:10 loss: 0.2805 loss_seg: 0.1888 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:27:58,320 INFO misc.py line 117 726] Train: [16/20][491/510] Data 11.718 (3.802) Batch 42.683 (28.171) Remain 16:06:43 loss: 0.2117 loss_seg: 0.1238 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:28:14,489 INFO misc.py line 117 726] Train: [16/20][492/510] Data 1.797 (3.798) Batch 16.169 (28.146) Remain 16:05:25 loss: 0.2350 loss_seg: 0.1406 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:28:35,692 INFO misc.py line 117 726] Train: [16/20][493/510] Data 2.044 (3.794) Batch 21.203 (28.132) Remain 16:04:27 loss: 0.2500 loss_seg: 0.1506 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:29:01,168 INFO misc.py line 117 726] Train: [16/20][494/510] Data 3.071 (3.793) Batch 25.476 (28.127) Remain 16:03:48 loss: 0.2027 loss_seg: 0.1136 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:29:29,656 INFO misc.py line 117 726] Train: [16/20][495/510] Data 3.801 (3.793) Batch 28.488 (28.128) Remain 16:03:22 loss: 0.2503 loss_seg: 0.1566 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:29:48,302 INFO misc.py line 117 726] Train: [16/20][496/510] Data 2.154 (3.789) Batch 18.646 (28.108) Remain 16:02:14 loss: 0.2540 loss_seg: 0.1574 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:30:24,776 INFO misc.py line 117 726] Train: [16/20][497/510] Data 6.746 (3.795) Batch 36.474 (28.125) Remain 16:02:21 loss: 0.3470 loss_seg: 0.2362 loss_superpoint_edge: 0.0448 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:30:52,756 INFO misc.py line 117 726] Train: [16/20][498/510] Data 3.182 (3.794) Batch 27.980 (28.125) Remain 16:01:52 loss: 0.2578 loss_seg: 0.1615 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:31:11,463 INFO misc.py line 117 726] Train: [16/20][499/510] Data 2.389 (3.791) Batch 18.707 (28.106) Remain 16:00:45 loss: 0.2901 loss_seg: 0.1857 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:31:38,026 INFO misc.py line 117 726] Train: [16/20][500/510] Data 2.326 (3.788) Batch 26.564 (28.103) Remain 16:00:10 loss: 0.2273 loss_seg: 0.1337 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:31:38,027 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 09:32:20,525 INFO misc.py line 117 726] Train: [16/20][501/510] Data 11.315 (3.803) Batch 42.499 (28.132) Remain 16:00:41 loss: 0.3090 loss_seg: 0.2208 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:32:45,727 INFO misc.py line 117 726] Train: [16/20][502/510] Data 2.304 (3.800) Batch 25.202 (28.126) Remain 16:00:01 loss: 0.2601 loss_seg: 0.1606 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:33:16,258 INFO misc.py line 117 726] Train: [16/20][503/510] Data 2.967 (3.799) Batch 30.531 (28.131) Remain 15:59:43 loss: 0.2117 loss_seg: 0.1217 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:33:37,798 INFO misc.py line 117 726] Train: [16/20][504/510] Data 2.908 (3.797) Batch 21.540 (28.118) Remain 15:58:48 loss: 0.2531 loss_seg: 0.1592 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:34:02,378 INFO misc.py line 117 726] Train: [16/20][505/510] Data 4.259 (3.798) Batch 24.581 (28.110) Remain 15:58:05 loss: 0.2494 loss_seg: 0.1592 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:34:29,348 INFO misc.py line 117 726] Train: [16/20][506/510] Data 2.785 (3.796) Batch 26.970 (28.108) Remain 15:57:33 loss: 0.2353 loss_seg: 0.1418 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:34:52,404 INFO misc.py line 117 726] Train: [16/20][507/510] Data 2.513 (3.793) Batch 23.056 (28.098) Remain 15:56:44 loss: 0.3890 loss_seg: 0.2795 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:35:09,247 INFO misc.py line 117 726] Train: [16/20][508/510] Data 1.889 (3.790) Batch 16.843 (28.076) Remain 15:55:30 loss: 0.2790 loss_seg: 0.1816 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:35:35,720 INFO misc.py line 117 726] Train: [16/20][509/510] Data 3.473 (3.789) Batch 26.472 (28.073) Remain 15:54:56 loss: 0.2358 loss_seg: 0.1424 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:36:08,931 INFO misc.py line 117 726] Train: [16/20][510/510] Data 6.587 (3.794) Batch 33.212 (28.083) Remain 15:54:49 loss: 0.2176 loss_seg: 0.1274 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:36:08,935 INFO misc.py line 147 726] Train result: loss: 0.2480 loss_seg: 0.1530 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 [2026-06-12 09:36:08,935 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-12 09:36:24,463 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6679 [2026-06-12 09:36:41,338 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7052 [2026-06-12 09:37:55,503 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8801 [2026-06-12 09:38:35,675 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9441 [2026-06-12 09:38:54,821 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9463 [2026-06-12 09:39:30,644 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.1452 [2026-06-12 09:40:16,907 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1539 [2026-06-12 09:40:32,235 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3034 [2026-06-12 09:40:49,948 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9881 [2026-06-12 09:41:08,500 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4217 [2026-06-12 09:41:24,237 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4950 [2026-06-12 09:41:45,767 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7282 [2026-06-12 09:42:11,591 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.9823 [2026-06-12 09:42:22,837 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6752 [2026-06-12 09:42:54,119 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0722 [2026-06-12 09:43:20,106 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3293 [2026-06-12 09:43:46,909 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.4031 [2026-06-12 09:44:29,500 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.2154 [2026-06-12 09:44:50,446 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4355 [2026-06-12 09:45:06,885 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8077 [2026-06-12 09:45:37,942 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9096 [2026-06-12 09:45:54,091 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4656 [2026-06-12 09:46:15,816 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3127 [2026-06-12 09:46:37,422 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8535 [2026-06-12 09:46:50,643 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.5917 [2026-06-12 09:47:18,507 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.4739 [2026-06-12 09:47:59,874 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1109 [2026-06-12 09:48:17,309 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5247 [2026-06-12 09:48:35,775 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4566 [2026-06-12 09:48:52,495 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.3980 [2026-06-12 09:49:17,258 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2364 [2026-06-12 09:49:35,451 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6798 [2026-06-12 09:49:52,680 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1130 [2026-06-12 09:50:16,914 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7565 [2026-06-12 09:50:16,933 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6724/0.7431/0.8982. [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9265/0.9600 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9764/0.9882 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8438/0.9715 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0018/0.0139 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3212/0.3774 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6184/0.6428 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6064/0.7003 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7985/0.9037 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9101/0.9531 [2026-06-12 09:50:16,933 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6736/0.7276 [2026-06-12 09:50:16,934 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7647/0.8527 [2026-06-12 09:50:16,934 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7010/0.8649 [2026-06-12 09:50:16,934 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5986/0.7046 [2026-06-12 09:50:16,934 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-12 09:50:16,934 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-12 09:50:16,935 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 09:50:39,162 INFO misc.py line 117 726] Train: [17/20][1/510] Data 2.267 (2.267) Batch 20.695 (20.695) Remain 11:43:17 loss: 0.2246 loss_seg: 0.1277 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:51:05,827 INFO misc.py line 117 726] Train: [17/20][2/510] Data 2.708 (2.708) Batch 26.665 (26.665) Remain 15:05:43 loss: 0.2787 loss_seg: 0.1767 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:51:25,358 INFO misc.py line 117 726] Train: [17/20][3/510] Data 2.195 (2.195) Batch 19.530 (19.530) Remain 11:03:03 loss: 0.3331 loss_seg: 0.2317 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:51:58,397 INFO misc.py line 117 726] Train: [17/20][4/510] Data 3.927 (3.927) Batch 33.039 (33.039) Remain 18:41:07 loss: 0.2011 loss_seg: 0.1132 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:52:36,812 INFO misc.py line 117 726] Train: [17/20][5/510] Data 5.977 (4.952) Batch 38.415 (35.727) Remain 20:11:44 loss: 0.2675 loss_seg: 0.1703 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:53:17,918 INFO misc.py line 117 726] Train: [17/20][6/510] Data 11.988 (7.297) Batch 41.107 (37.520) Remain 21:11:56 loss: 0.2347 loss_seg: 0.1461 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:53:37,952 INFO misc.py line 117 726] Train: [17/20][7/510] Data 2.315 (6.052) Batch 20.033 (33.148) Remain 18:43:10 loss: 0.2185 loss_seg: 0.1287 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:54:01,219 INFO misc.py line 117 726] Train: [17/20][8/510] Data 2.686 (5.379) Batch 23.267 (31.172) Remain 17:35:41 loss: 0.2297 loss_seg: 0.1367 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:54:29,532 INFO misc.py line 117 726] Train: [17/20][9/510] Data 3.373 (5.044) Batch 28.314 (30.696) Remain 17:19:03 loss: 0.3271 loss_seg: 0.2250 loss_superpoint_edge: 0.0343 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:55:00,276 INFO misc.py line 117 726] Train: [17/20][10/510] Data 4.716 (4.997) Batch 30.743 (30.703) Remain 17:18:46 loss: 0.1716 loss_seg: 0.0890 loss_superpoint_edge: 0.0142 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:55:30,396 INFO misc.py line 117 726] Train: [17/20][11/510] Data 2.830 (4.727) Batch 30.120 (30.630) Remain 17:15:47 loss: 0.2363 loss_seg: 0.1418 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:56:04,641 INFO misc.py line 117 726] Train: [17/20][12/510] Data 5.031 (4.760) Batch 34.244 (31.031) Remain 17:28:51 loss: 0.2333 loss_seg: 0.1391 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:56:36,257 INFO misc.py line 117 726] Train: [17/20][13/510] Data 3.466 (4.631) Batch 31.616 (31.090) Remain 17:30:19 loss: 0.2945 loss_seg: 0.1972 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:56:54,443 INFO misc.py line 117 726] Train: [17/20][14/510] Data 1.751 (4.369) Batch 18.187 (29.917) Remain 16:50:11 loss: 0.1847 loss_seg: 0.0967 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:57:18,207 INFO misc.py line 117 726] Train: [17/20][15/510] Data 2.999 (4.255) Batch 23.764 (29.404) Remain 16:32:23 loss: 0.2734 loss_seg: 0.1738 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:57:45,321 INFO misc.py line 117 726] Train: [17/20][16/510] Data 2.532 (4.122) Batch 27.114 (29.228) Remain 16:25:57 loss: 0.1800 loss_seg: 0.0948 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:58:07,544 INFO misc.py line 117 726] Train: [17/20][17/510] Data 2.826 (4.030) Batch 22.223 (28.728) Remain 16:08:35 loss: 0.2527 loss_seg: 0.1562 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:58:43,645 INFO misc.py line 117 726] Train: [17/20][18/510] Data 4.111 (4.035) Batch 36.101 (29.219) Remain 16:24:41 loss: 0.1868 loss_seg: 0.1003 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:59:02,594 INFO misc.py line 117 726] Train: [17/20][19/510] Data 2.250 (3.924) Batch 18.950 (28.577) Remain 16:02:34 loss: 0.2824 loss_seg: 0.1744 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:59:25,140 INFO misc.py line 117 726] Train: [17/20][20/510] Data 2.478 (3.839) Batch 22.545 (28.222) Remain 15:50:09 loss: 0.3046 loss_seg: 0.2096 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 09:59:49,886 INFO misc.py line 117 726] Train: [17/20][21/510] Data 2.495 (3.764) Batch 24.747 (28.029) Remain 15:43:11 loss: 0.2200 loss_seg: 0.1275 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:00:23,333 INFO misc.py line 117 726] Train: [17/20][22/510] Data 4.463 (3.801) Batch 33.446 (28.314) Remain 15:52:18 loss: 0.2777 loss_seg: 0.1773 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:00:53,252 INFO misc.py line 117 726] Train: [17/20][23/510] Data 5.287 (3.875) Batch 29.919 (28.395) Remain 15:54:32 loss: 0.2102 loss_seg: 0.1209 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:01:24,450 INFO misc.py line 117 726] Train: [17/20][24/510] Data 4.238 (3.892) Batch 31.198 (28.528) Remain 15:58:32 loss: 0.2232 loss_seg: 0.1359 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:01:51,798 INFO misc.py line 117 726] Train: [17/20][25/510] Data 3.563 (3.877) Batch 27.347 (28.475) Remain 15:56:16 loss: 0.2531 loss_seg: 0.1571 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:02:16,851 INFO misc.py line 117 726] Train: [17/20][26/510] Data 2.549 (3.820) Batch 25.054 (28.326) Remain 15:50:48 loss: 0.3245 loss_seg: 0.2149 loss_superpoint_edge: 0.0442 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:02:39,626 INFO misc.py line 117 726] Train: [17/20][27/510] Data 2.935 (3.783) Batch 22.775 (28.095) Remain 15:42:34 loss: 0.2141 loss_seg: 0.1231 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:03:07,181 INFO misc.py line 117 726] Train: [17/20][28/510] Data 2.964 (3.750) Batch 27.555 (28.073) Remain 15:41:22 loss: 0.2252 loss_seg: 0.1330 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:03:26,274 INFO misc.py line 117 726] Train: [17/20][29/510] Data 2.229 (3.692) Batch 19.093 (27.728) Remain 15:29:20 loss: 0.2133 loss_seg: 0.1183 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:03:47,274 INFO misc.py line 117 726] Train: [17/20][30/510] Data 2.371 (3.643) Batch 21.000 (27.478) Remain 15:20:31 loss: 0.2587 loss_seg: 0.1601 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:04:15,087 INFO misc.py line 117 726] Train: [17/20][31/510] Data 4.351 (3.668) Batch 27.812 (27.490) Remain 15:20:28 loss: 0.3275 loss_seg: 0.2200 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:04:43,540 INFO misc.py line 117 726] Train: [17/20][32/510] Data 2.944 (3.643) Batch 28.453 (27.524) Remain 15:21:07 loss: 0.2436 loss_seg: 0.1460 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:05:13,207 INFO misc.py line 117 726] Train: [17/20][33/510] Data 3.358 (3.634) Batch 29.667 (27.595) Remain 15:23:03 loss: 0.2463 loss_seg: 0.1549 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:05:50,950 INFO misc.py line 117 726] Train: [17/20][34/510] Data 9.784 (3.832) Batch 37.743 (27.922) Remain 15:33:32 loss: 0.2003 loss_seg: 0.1126 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:06:10,895 INFO misc.py line 117 726] Train: [17/20][35/510] Data 2.176 (3.780) Batch 19.945 (27.673) Remain 15:24:44 loss: 0.2432 loss_seg: 0.1433 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:06:31,883 INFO misc.py line 117 726] Train: [17/20][36/510] Data 1.541 (3.712) Batch 20.988 (27.470) Remain 15:17:30 loss: 0.1966 loss_seg: 0.1073 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:06:53,091 INFO misc.py line 117 726] Train: [17/20][37/510] Data 2.061 (3.664) Batch 21.208 (27.286) Remain 15:10:54 loss: 0.1814 loss_seg: 0.1005 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:07:25,207 INFO misc.py line 117 726] Train: [17/20][38/510] Data 4.016 (3.674) Batch 32.116 (27.424) Remain 15:15:03 loss: 0.1969 loss_seg: 0.1095 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:07:49,956 INFO misc.py line 117 726] Train: [17/20][39/510] Data 2.981 (3.655) Batch 24.749 (27.350) Remain 15:12:07 loss: 0.2499 loss_seg: 0.1542 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:08:17,279 INFO misc.py line 117 726] Train: [17/20][40/510] Data 3.461 (3.649) Batch 27.322 (27.349) Remain 15:11:38 loss: 0.2091 loss_seg: 0.1155 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:08:31,383 INFO misc.py line 117 726] Train: [17/20][41/510] Data 1.963 (3.605) Batch 14.104 (27.001) Remain 14:59:34 loss: 0.3225 loss_seg: 0.2282 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:08:56,735 INFO misc.py line 117 726] Train: [17/20][42/510] Data 2.922 (3.587) Batch 25.352 (26.958) Remain 14:57:42 loss: 0.2251 loss_seg: 0.1343 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:09:22,808 INFO misc.py line 117 726] Train: [17/20][43/510] Data 3.403 (3.583) Batch 26.073 (26.936) Remain 14:56:31 loss: 0.2333 loss_seg: 0.1439 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:09:46,160 INFO misc.py line 117 726] Train: [17/20][44/510] Data 3.571 (3.583) Batch 23.353 (26.849) Remain 14:53:10 loss: 0.2432 loss_seg: 0.1452 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:10:12,494 INFO misc.py line 117 726] Train: [17/20][45/510] Data 3.050 (3.570) Batch 26.333 (26.837) Remain 14:52:18 loss: 0.2743 loss_seg: 0.1708 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0321 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:10:31,513 INFO misc.py line 117 726] Train: [17/20][46/510] Data 2.427 (3.543) Batch 19.019 (26.655) Remain 14:45:49 loss: 0.2166 loss_seg: 0.1291 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:11:02,832 INFO misc.py line 117 726] Train: [17/20][47/510] Data 5.349 (3.584) Batch 31.319 (26.761) Remain 14:48:54 loss: 0.2286 loss_seg: 0.1346 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:11:24,089 INFO misc.py line 117 726] Train: [17/20][48/510] Data 2.218 (3.554) Batch 21.256 (26.638) Remain 14:44:23 loss: 0.2494 loss_seg: 0.1581 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:11:48,135 INFO misc.py line 117 726] Train: [17/20][49/510] Data 2.502 (3.531) Batch 24.046 (26.582) Remain 14:42:04 loss: 0.3870 loss_seg: 0.2788 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:12:15,562 INFO misc.py line 117 726] Train: [17/20][50/510] Data 5.159 (3.566) Batch 27.428 (26.600) Remain 14:42:14 loss: 0.2579 loss_seg: 0.1578 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0409 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:12:15,563 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 10:12:50,620 INFO misc.py line 117 726] Train: [17/20][51/510] Data 5.524 (3.607) Batch 35.058 (26.776) Remain 14:47:38 loss: 0.3114 loss_seg: 0.2086 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:13:11,740 INFO misc.py line 117 726] Train: [17/20][52/510] Data 2.207 (3.578) Batch 21.119 (26.661) Remain 14:43:21 loss: 0.2416 loss_seg: 0.1450 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:13:43,170 INFO misc.py line 117 726] Train: [17/20][53/510] Data 2.910 (3.565) Batch 31.431 (26.756) Remain 14:46:04 loss: 0.2733 loss_seg: 0.1835 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:14:01,201 INFO misc.py line 117 726] Train: [17/20][54/510] Data 1.970 (3.533) Batch 18.030 (26.585) Remain 14:39:58 loss: 0.3186 loss_seg: 0.2112 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:14:31,553 INFO misc.py line 117 726] Train: [17/20][55/510] Data 3.629 (3.535) Batch 30.353 (26.658) Remain 14:41:55 loss: 0.2240 loss_seg: 0.1344 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:15:01,375 INFO misc.py line 117 726] Train: [17/20][56/510] Data 2.859 (3.522) Batch 29.822 (26.717) Remain 14:43:27 loss: 0.2692 loss_seg: 0.1663 loss_superpoint_edge: 0.0391 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:15:27,146 INFO misc.py line 117 726] Train: [17/20][57/510] Data 5.675 (3.562) Batch 25.771 (26.700) Remain 14:42:25 loss: 0.3550 loss_seg: 0.2437 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0345 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:15:50,347 INFO misc.py line 117 726] Train: [17/20][58/510] Data 3.054 (3.553) Batch 23.201 (26.636) Remain 14:39:52 loss: 0.2422 loss_seg: 0.1485 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:16:15,847 INFO misc.py line 117 726] Train: [17/20][59/510] Data 2.512 (3.534) Batch 25.500 (26.616) Remain 14:38:46 loss: 0.2766 loss_seg: 0.1850 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:16:44,870 INFO misc.py line 117 726] Train: [17/20][60/510] Data 3.560 (3.535) Batch 29.023 (26.658) Remain 14:39:43 loss: 0.3068 loss_seg: 0.2024 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:17:05,423 INFO misc.py line 117 726] Train: [17/20][61/510] Data 1.959 (3.508) Batch 20.553 (26.553) Remain 14:35:48 loss: 0.2129 loss_seg: 0.1216 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:17:33,762 INFO misc.py line 117 726] Train: [17/20][62/510] Data 3.334 (3.505) Batch 28.338 (26.583) Remain 14:36:21 loss: 0.2550 loss_seg: 0.1554 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:17:59,894 INFO misc.py line 117 726] Train: [17/20][63/510] Data 2.689 (3.491) Batch 26.132 (26.576) Remain 14:35:39 loss: 0.2333 loss_seg: 0.1371 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:18:25,340 INFO misc.py line 117 726] Train: [17/20][64/510] Data 2.581 (3.476) Batch 25.445 (26.557) Remain 14:34:36 loss: 0.2644 loss_seg: 0.1621 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:18:59,960 INFO misc.py line 117 726] Train: [17/20][65/510] Data 3.804 (3.482) Batch 34.621 (26.687) Remain 14:38:27 loss: 0.2059 loss_seg: 0.1212 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:19:26,935 INFO misc.py line 117 726] Train: [17/20][66/510] Data 6.704 (3.533) Batch 26.976 (26.692) Remain 14:38:09 loss: 0.2257 loss_seg: 0.1325 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:19:43,653 INFO misc.py line 117 726] Train: [17/20][67/510] Data 1.935 (3.508) Batch 16.717 (26.536) Remain 14:32:35 loss: 0.2400 loss_seg: 0.1466 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:20:07,141 INFO misc.py line 117 726] Train: [17/20][68/510] Data 2.247 (3.488) Batch 23.489 (26.489) Remain 14:30:36 loss: 0.2947 loss_seg: 0.2001 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:20:29,517 INFO misc.py line 117 726] Train: [17/20][69/510] Data 3.020 (3.481) Batch 22.376 (26.427) Remain 14:28:06 loss: 0.1825 loss_seg: 0.1007 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:20:59,597 INFO misc.py line 117 726] Train: [17/20][70/510] Data 4.221 (3.492) Batch 30.080 (26.481) Remain 14:29:27 loss: 0.2758 loss_seg: 0.1771 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:21:30,550 INFO misc.py line 117 726] Train: [17/20][71/510] Data 3.974 (3.499) Batch 30.953 (26.547) Remain 14:31:10 loss: 0.2574 loss_seg: 0.1622 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:21:58,809 INFO misc.py line 117 726] Train: [17/20][72/510] Data 3.373 (3.498) Batch 28.259 (26.572) Remain 14:31:33 loss: 0.2346 loss_seg: 0.1385 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:22:26,885 INFO misc.py line 117 726] Train: [17/20][73/510] Data 2.849 (3.488) Batch 28.075 (26.593) Remain 14:31:48 loss: 0.2252 loss_seg: 0.1326 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:22:57,288 INFO misc.py line 117 726] Train: [17/20][74/510] Data 3.129 (3.483) Batch 30.403 (26.647) Remain 14:33:07 loss: 0.2348 loss_seg: 0.1415 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:23:12,073 INFO misc.py line 117 726] Train: [17/20][75/510] Data 2.279 (3.466) Batch 14.785 (26.482) Remain 14:27:17 loss: 0.2437 loss_seg: 0.1479 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:23:48,457 INFO misc.py line 117 726] Train: [17/20][76/510] Data 4.587 (3.482) Batch 36.384 (26.618) Remain 14:31:17 loss: 0.2509 loss_seg: 0.1507 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:24:18,035 INFO misc.py line 117 726] Train: [17/20][77/510] Data 4.841 (3.500) Batch 29.578 (26.658) Remain 14:32:09 loss: 0.2108 loss_seg: 0.1206 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:24:45,990 INFO misc.py line 117 726] Train: [17/20][78/510] Data 3.059 (3.494) Batch 27.955 (26.675) Remain 14:32:16 loss: 0.3127 loss_seg: 0.2068 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:25:30,012 INFO misc.py line 117 726] Train: [17/20][79/510] Data 13.269 (3.623) Batch 44.022 (26.903) Remain 14:39:17 loss: 0.3220 loss_seg: 0.2139 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:26:03,471 INFO misc.py line 117 726] Train: [17/20][80/510] Data 3.714 (3.624) Batch 33.459 (26.988) Remain 14:41:37 loss: 0.2873 loss_seg: 0.1889 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:26:42,486 INFO misc.py line 117 726] Train: [17/20][81/510] Data 8.780 (3.690) Batch 39.015 (27.143) Remain 14:46:12 loss: 0.2786 loss_seg: 0.1767 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:27:05,071 INFO misc.py line 117 726] Train: [17/20][82/510] Data 3.090 (3.683) Batch 22.585 (27.085) Remain 14:43:52 loss: 0.1876 loss_seg: 0.1002 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:27:31,724 INFO misc.py line 117 726] Train: [17/20][83/510] Data 5.944 (3.711) Batch 26.653 (27.080) Remain 14:43:14 loss: 0.3223 loss_seg: 0.2202 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0339 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:27:56,149 INFO misc.py line 117 726] Train: [17/20][84/510] Data 2.168 (3.692) Batch 24.425 (27.047) Remain 14:41:43 loss: 0.2202 loss_seg: 0.1261 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:28:24,431 INFO misc.py line 117 726] Train: [17/20][85/510] Data 4.193 (3.698) Batch 28.282 (27.062) Remain 14:41:45 loss: 0.2089 loss_seg: 0.1189 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:28:46,919 INFO misc.py line 117 726] Train: [17/20][86/510] Data 4.304 (3.705) Batch 22.488 (27.007) Remain 14:39:31 loss: 0.2623 loss_seg: 0.1672 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:29:14,018 INFO misc.py line 117 726] Train: [17/20][87/510] Data 2.804 (3.695) Batch 27.099 (27.008) Remain 14:39:06 loss: 0.2315 loss_seg: 0.1391 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:29:38,050 INFO misc.py line 117 726] Train: [17/20][88/510] Data 2.365 (3.679) Batch 24.032 (26.973) Remain 14:37:30 loss: 0.2259 loss_seg: 0.1314 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:30:01,327 INFO misc.py line 117 726] Train: [17/20][89/510] Data 2.160 (3.661) Batch 23.277 (26.930) Remain 14:35:40 loss: 0.1968 loss_seg: 0.1108 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:30:30,902 INFO misc.py line 117 726] Train: [17/20][90/510] Data 3.700 (3.662) Batch 29.575 (26.960) Remain 14:36:12 loss: 0.2214 loss_seg: 0.1318 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:31:08,105 INFO misc.py line 117 726] Train: [17/20][91/510] Data 10.725 (3.742) Batch 37.204 (27.077) Remain 14:39:32 loss: 0.2091 loss_seg: 0.1243 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:31:33,107 INFO misc.py line 117 726] Train: [17/20][92/510] Data 2.577 (3.729) Batch 25.001 (27.053) Remain 14:38:19 loss: 0.2169 loss_seg: 0.1273 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:31:50,241 INFO misc.py line 117 726] Train: [17/20][93/510] Data 2.264 (3.713) Batch 17.134 (26.943) Remain 14:34:18 loss: 0.2488 loss_seg: 0.1563 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:32:26,597 INFO misc.py line 117 726] Train: [17/20][94/510] Data 3.998 (3.716) Batch 36.356 (27.047) Remain 14:37:12 loss: 0.2184 loss_seg: 0.1310 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:32:56,664 INFO misc.py line 117 726] Train: [17/20][95/510] Data 5.480 (3.735) Batch 30.067 (27.079) Remain 14:37:49 loss: 0.3008 loss_seg: 0.2026 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:33:25,471 INFO misc.py line 117 726] Train: [17/20][96/510] Data 4.190 (3.740) Batch 28.807 (27.098) Remain 14:37:58 loss: 0.2251 loss_seg: 0.1317 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:33:53,576 INFO misc.py line 117 726] Train: [17/20][97/510] Data 2.754 (3.729) Batch 28.105 (27.109) Remain 14:37:52 loss: 0.1974 loss_seg: 0.1083 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:34:26,999 INFO misc.py line 117 726] Train: [17/20][98/510] Data 6.039 (3.754) Batch 33.423 (27.175) Remain 14:39:34 loss: 0.3021 loss_seg: 0.2011 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:34:49,669 INFO misc.py line 117 726] Train: [17/20][99/510] Data 3.319 (3.749) Batch 22.670 (27.128) Remain 14:37:35 loss: 0.4489 loss_seg: 0.3308 loss_superpoint_edge: 0.0509 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:35:14,182 INFO misc.py line 117 726] Train: [17/20][100/510] Data 2.752 (3.739) Batch 24.513 (27.101) Remain 14:36:16 loss: 0.2996 loss_seg: 0.2047 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:35:14,183 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 10:35:43,307 INFO misc.py line 117 726] Train: [17/20][101/510] Data 3.225 (3.734) Batch 29.126 (27.122) Remain 14:36:29 loss: 0.2272 loss_seg: 0.1320 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:36:06,400 INFO misc.py line 117 726] Train: [17/20][102/510] Data 4.046 (3.737) Batch 23.093 (27.081) Remain 14:34:43 loss: 0.2509 loss_seg: 0.1546 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:36:36,637 INFO misc.py line 117 726] Train: [17/20][103/510] Data 3.959 (3.739) Batch 30.237 (27.113) Remain 14:35:17 loss: 0.2624 loss_seg: 0.1664 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:36:53,859 INFO misc.py line 117 726] Train: [17/20][104/510] Data 2.164 (3.723) Batch 17.221 (27.015) Remain 14:31:40 loss: 0.2484 loss_seg: 0.1504 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:37:26,139 INFO misc.py line 117 726] Train: [17/20][105/510] Data 10.886 (3.794) Batch 32.280 (27.066) Remain 14:32:53 loss: 0.2464 loss_seg: 0.1486 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0434 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:37:53,518 INFO misc.py line 117 726] Train: [17/20][106/510] Data 3.445 (3.790) Batch 27.379 (27.070) Remain 14:32:32 loss: 0.2274 loss_seg: 0.1338 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:38:18,854 INFO misc.py line 117 726] Train: [17/20][107/510] Data 3.138 (3.784) Batch 25.337 (27.053) Remain 14:31:33 loss: 0.2313 loss_seg: 0.1390 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:38:42,108 INFO misc.py line 117 726] Train: [17/20][108/510] Data 2.198 (3.769) Batch 23.254 (27.017) Remain 14:29:56 loss: 0.2084 loss_seg: 0.1176 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:39:07,809 INFO misc.py line 117 726] Train: [17/20][109/510] Data 4.271 (3.774) Batch 25.701 (27.004) Remain 14:29:05 loss: 0.1828 loss_seg: 0.0951 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0297 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:39:35,416 INFO misc.py line 117 726] Train: [17/20][110/510] Data 2.584 (3.762) Batch 27.607 (27.010) Remain 14:28:49 loss: 0.1998 loss_seg: 0.1131 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:40:07,795 INFO misc.py line 117 726] Train: [17/20][111/510] Data 3.620 (3.761) Batch 32.379 (27.060) Remain 14:29:57 loss: 0.2876 loss_seg: 0.1851 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:40:45,206 INFO misc.py line 117 726] Train: [17/20][112/510] Data 7.320 (3.794) Batch 37.412 (27.155) Remain 14:32:34 loss: 0.1775 loss_seg: 0.0957 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:41:03,626 INFO misc.py line 117 726] Train: [17/20][113/510] Data 2.315 (3.780) Batch 18.420 (27.075) Remain 14:29:33 loss: 0.2065 loss_seg: 0.1203 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:41:35,095 INFO misc.py line 117 726] Train: [17/20][114/510] Data 3.783 (3.780) Batch 31.469 (27.115) Remain 14:30:23 loss: 0.2214 loss_seg: 0.1288 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:41:52,822 INFO misc.py line 117 726] Train: [17/20][115/510] Data 2.130 (3.766) Batch 17.727 (27.031) Remain 14:27:14 loss: 0.2903 loss_seg: 0.1935 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:42:24,756 INFO misc.py line 117 726] Train: [17/20][116/510] Data 2.963 (3.758) Batch 31.934 (27.074) Remain 14:28:10 loss: 0.2258 loss_seg: 0.1303 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:42:57,242 INFO misc.py line 117 726] Train: [17/20][117/510] Data 5.358 (3.773) Batch 32.486 (27.122) Remain 14:29:15 loss: 0.2388 loss_seg: 0.1504 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:43:26,845 INFO misc.py line 117 726] Train: [17/20][118/510] Data 2.720 (3.763) Batch 29.603 (27.143) Remain 14:29:29 loss: 0.1908 loss_seg: 0.1013 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:43:49,827 INFO misc.py line 117 726] Train: [17/20][119/510] Data 4.781 (3.772) Batch 22.982 (27.107) Remain 14:27:53 loss: 0.2097 loss_seg: 0.1169 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:44:15,079 INFO misc.py line 117 726] Train: [17/20][120/510] Data 2.562 (3.762) Batch 25.252 (27.092) Remain 14:26:55 loss: 0.2505 loss_seg: 0.1560 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:44:48,048 INFO misc.py line 117 726] Train: [17/20][121/510] Data 2.918 (3.755) Batch 32.969 (27.141) Remain 14:28:04 loss: 0.1864 loss_seg: 0.1016 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:45:26,285 INFO misc.py line 117 726] Train: [17/20][122/510] Data 10.903 (3.815) Batch 38.237 (27.235) Remain 14:30:36 loss: 0.2128 loss_seg: 0.1264 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:45:50,298 INFO misc.py line 117 726] Train: [17/20][123/510] Data 2.937 (3.807) Batch 24.013 (27.208) Remain 14:29:17 loss: 0.3053 loss_seg: 0.2025 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:46:23,781 INFO misc.py line 117 726] Train: [17/20][124/510] Data 3.616 (3.806) Batch 33.483 (27.260) Remain 14:30:29 loss: 0.3830 loss_seg: 0.2801 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:47:01,093 INFO misc.py line 117 726] Train: [17/20][125/510] Data 9.386 (3.852) Batch 37.312 (27.342) Remain 14:32:40 loss: 0.2003 loss_seg: 0.1113 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:47:32,588 INFO misc.py line 117 726] Train: [17/20][126/510] Data 5.251 (3.863) Batch 31.495 (27.376) Remain 14:33:17 loss: 0.3801 loss_seg: 0.2801 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:47:56,725 INFO misc.py line 117 726] Train: [17/20][127/510] Data 3.038 (3.856) Batch 24.137 (27.350) Remain 14:32:00 loss: 0.3433 loss_seg: 0.2334 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:48:29,994 INFO misc.py line 117 726] Train: [17/20][128/510] Data 6.630 (3.878) Batch 33.269 (27.397) Remain 14:33:03 loss: 0.4026 loss_seg: 0.3069 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:48:59,696 INFO misc.py line 117 726] Train: [17/20][129/510] Data 4.906 (3.887) Batch 29.702 (27.415) Remain 14:33:10 loss: 0.2299 loss_seg: 0.1389 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:49:27,100 INFO misc.py line 117 726] Train: [17/20][130/510] Data 3.529 (3.884) Batch 27.403 (27.415) Remain 14:32:43 loss: 0.2343 loss_seg: 0.1417 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:49:56,806 INFO misc.py line 117 726] Train: [17/20][131/510] Data 3.329 (3.879) Batch 29.707 (27.433) Remain 14:32:49 loss: 0.2615 loss_seg: 0.1630 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:50:24,862 INFO misc.py line 117 726] Train: [17/20][132/510] Data 2.735 (3.871) Batch 28.056 (27.438) Remain 14:32:31 loss: 0.2429 loss_seg: 0.1484 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:50:58,628 INFO misc.py line 117 726] Train: [17/20][133/510] Data 3.359 (3.867) Batch 33.765 (27.487) Remain 14:33:37 loss: 0.2234 loss_seg: 0.1309 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:51:32,526 INFO misc.py line 117 726] Train: [17/20][134/510] Data 3.244 (3.862) Batch 33.899 (27.536) Remain 14:34:42 loss: 0.2152 loss_seg: 0.1252 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:52:10,085 INFO misc.py line 117 726] Train: [17/20][135/510] Data 6.326 (3.881) Batch 37.559 (27.612) Remain 14:36:40 loss: 0.2756 loss_seg: 0.1816 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:52:42,433 INFO misc.py line 117 726] Train: [17/20][136/510] Data 3.697 (3.879) Batch 32.348 (27.647) Remain 14:37:20 loss: 0.2644 loss_seg: 0.1685 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:53:06,819 INFO misc.py line 117 726] Train: [17/20][137/510] Data 2.761 (3.871) Batch 24.386 (27.623) Remain 14:36:06 loss: 0.2253 loss_seg: 0.1299 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:53:35,949 INFO misc.py line 117 726] Train: [17/20][138/510] Data 2.919 (3.864) Batch 29.130 (27.634) Remain 14:35:59 loss: 0.2705 loss_seg: 0.1756 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:54:05,634 INFO misc.py line 117 726] Train: [17/20][139/510] Data 4.009 (3.865) Batch 29.685 (27.649) Remain 14:36:00 loss: 0.1777 loss_seg: 0.0937 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:54:35,422 INFO misc.py line 117 726] Train: [17/20][140/510] Data 3.894 (3.865) Batch 29.788 (27.665) Remain 14:36:02 loss: 0.2936 loss_seg: 0.1921 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:55:05,117 INFO misc.py line 117 726] Train: [17/20][141/510] Data 3.626 (3.863) Batch 29.695 (27.679) Remain 14:36:03 loss: 0.2159 loss_seg: 0.1312 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:55:31,120 INFO misc.py line 117 726] Train: [17/20][142/510] Data 3.292 (3.859) Batch 26.003 (27.667) Remain 14:35:12 loss: 0.2569 loss_seg: 0.1576 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:55:48,753 INFO misc.py line 117 726] Train: [17/20][143/510] Data 1.832 (3.845) Batch 17.633 (27.596) Remain 14:32:29 loss: 0.2237 loss_seg: 0.1310 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:56:13,963 INFO misc.py line 117 726] Train: [17/20][144/510] Data 2.199 (3.833) Batch 25.210 (27.579) Remain 14:31:29 loss: 0.2827 loss_seg: 0.1785 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:56:30,880 INFO misc.py line 117 726] Train: [17/20][145/510] Data 2.236 (3.822) Batch 16.917 (27.504) Remain 14:28:39 loss: 0.2663 loss_seg: 0.1738 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:57:02,975 INFO misc.py line 117 726] Train: [17/20][146/510] Data 3.587 (3.820) Batch 32.095 (27.536) Remain 14:29:12 loss: 0.2962 loss_seg: 0.1979 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:57:22,466 INFO misc.py line 117 726] Train: [17/20][147/510] Data 2.617 (3.812) Batch 19.491 (27.480) Remain 14:26:59 loss: 0.2129 loss_seg: 0.1218 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:57:45,560 INFO misc.py line 117 726] Train: [17/20][148/510] Data 2.462 (3.803) Batch 23.093 (27.450) Remain 14:25:34 loss: 0.2079 loss_seg: 0.1170 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:58:09,523 INFO misc.py line 117 726] Train: [17/20][149/510] Data 2.751 (3.795) Batch 23.964 (27.426) Remain 14:24:22 loss: 0.2230 loss_seg: 0.1322 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:58:32,275 INFO misc.py line 117 726] Train: [17/20][150/510] Data 2.889 (3.789) Batch 22.751 (27.394) Remain 14:22:54 loss: 0.2008 loss_seg: 0.1129 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:58:32,275 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 10:58:59,825 INFO misc.py line 117 726] Train: [17/20][151/510] Data 3.511 (3.787) Batch 27.551 (27.395) Remain 14:22:29 loss: 0.2172 loss_seg: 0.1305 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 10:59:30,576 INFO misc.py line 117 726] Train: [17/20][152/510] Data 3.509 (3.785) Batch 30.751 (27.418) Remain 14:22:44 loss: 0.2262 loss_seg: 0.1331 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:00:01,504 INFO misc.py line 117 726] Train: [17/20][153/510] Data 3.398 (3.783) Batch 30.928 (27.441) Remain 14:23:01 loss: 0.1724 loss_seg: 0.0868 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:00:25,165 INFO misc.py line 117 726] Train: [17/20][154/510] Data 2.602 (3.775) Batch 23.661 (27.416) Remain 14:21:46 loss: 0.2016 loss_seg: 0.1138 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:00:46,057 INFO misc.py line 117 726] Train: [17/20][155/510] Data 3.439 (3.773) Batch 20.891 (27.373) Remain 14:19:58 loss: 0.2633 loss_seg: 0.1689 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:01:21,210 INFO misc.py line 117 726] Train: [17/20][156/510] Data 5.635 (3.785) Batch 35.153 (27.424) Remain 14:21:06 loss: 0.3299 loss_seg: 0.2180 loss_superpoint_edge: 0.0452 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:02:02,188 INFO misc.py line 117 726] Train: [17/20][157/510] Data 9.079 (3.819) Batch 40.977 (27.512) Remain 14:23:24 loss: 0.2867 loss_seg: 0.1948 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:02:36,768 INFO misc.py line 117 726] Train: [17/20][158/510] Data 3.419 (3.817) Batch 34.581 (27.557) Remain 14:24:23 loss: 0.2911 loss_seg: 0.1831 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:03:17,628 INFO misc.py line 117 726] Train: [17/20][159/510] Data 8.293 (3.845) Batch 40.861 (27.643) Remain 14:26:36 loss: 0.1862 loss_seg: 0.1034 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:03:58,790 INFO misc.py line 117 726] Train: [17/20][160/510] Data 7.652 (3.870) Batch 41.161 (27.729) Remain 14:28:50 loss: 0.3493 loss_seg: 0.2500 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:04:17,824 INFO misc.py line 117 726] Train: [17/20][161/510] Data 2.023 (3.858) Batch 19.034 (27.674) Remain 14:26:39 loss: 0.2443 loss_seg: 0.1499 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:04:45,987 INFO misc.py line 117 726] Train: [17/20][162/510] Data 3.251 (3.854) Batch 28.163 (27.677) Remain 14:26:17 loss: 0.2587 loss_seg: 0.1623 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:05:17,885 INFO misc.py line 117 726] Train: [17/20][163/510] Data 4.270 (3.857) Batch 31.898 (27.703) Remain 14:26:39 loss: 0.2454 loss_seg: 0.1510 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:05:48,261 INFO misc.py line 117 726] Train: [17/20][164/510] Data 3.350 (3.854) Batch 30.376 (27.720) Remain 14:26:42 loss: 0.2375 loss_seg: 0.1417 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:06:10,975 INFO misc.py line 117 726] Train: [17/20][165/510] Data 2.737 (3.847) Batch 22.714 (27.689) Remain 14:25:16 loss: 0.2454 loss_seg: 0.1450 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:06:41,114 INFO misc.py line 117 726] Train: [17/20][166/510] Data 4.561 (3.851) Batch 30.139 (27.704) Remain 14:25:17 loss: 0.2977 loss_seg: 0.2005 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:07:10,357 INFO misc.py line 117 726] Train: [17/20][167/510] Data 2.692 (3.844) Batch 29.243 (27.713) Remain 14:25:07 loss: 0.2103 loss_seg: 0.1211 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:07:28,252 INFO misc.py line 117 726] Train: [17/20][168/510] Data 1.595 (3.830) Batch 17.896 (27.654) Remain 14:22:48 loss: 0.2102 loss_seg: 0.1197 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0405 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:07:59,957 INFO misc.py line 117 726] Train: [17/20][169/510] Data 6.066 (3.844) Batch 31.705 (27.678) Remain 14:23:06 loss: 0.3740 loss_seg: 0.2715 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:08:29,613 INFO misc.py line 117 726] Train: [17/20][170/510] Data 3.138 (3.840) Batch 29.656 (27.690) Remain 14:23:00 loss: 0.2311 loss_seg: 0.1375 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:08:56,949 INFO misc.py line 117 726] Train: [17/20][171/510] Data 3.136 (3.835) Batch 27.336 (27.688) Remain 14:22:28 loss: 0.2797 loss_seg: 0.1799 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:09:29,613 INFO misc.py line 117 726] Train: [17/20][172/510] Data 4.341 (3.838) Batch 32.665 (27.717) Remain 14:22:56 loss: 0.2455 loss_seg: 0.1481 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:09:54,988 INFO misc.py line 117 726] Train: [17/20][173/510] Data 3.835 (3.838) Batch 25.375 (27.704) Remain 14:22:02 loss: 0.2197 loss_seg: 0.1252 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:10:18,144 INFO misc.py line 117 726] Train: [17/20][174/510] Data 2.412 (3.830) Batch 23.156 (27.677) Remain 14:20:45 loss: 0.3428 loss_seg: 0.2344 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:10:43,902 INFO misc.py line 117 726] Train: [17/20][175/510] Data 4.006 (3.831) Batch 25.757 (27.666) Remain 14:19:56 loss: 0.2129 loss_seg: 0.1167 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:11:01,942 INFO misc.py line 117 726] Train: [17/20][176/510] Data 2.001 (3.821) Batch 18.040 (27.610) Remain 14:17:45 loss: 0.3101 loss_seg: 0.2208 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:11:31,730 INFO misc.py line 117 726] Train: [17/20][177/510] Data 3.325 (3.818) Batch 29.789 (27.623) Remain 14:17:41 loss: 0.3056 loss_seg: 0.2008 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:11:55,806 INFO misc.py line 117 726] Train: [17/20][178/510] Data 2.704 (3.811) Batch 24.076 (27.603) Remain 14:16:35 loss: 0.2595 loss_seg: 0.1646 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:12:15,004 INFO misc.py line 117 726] Train: [17/20][179/510] Data 2.009 (3.801) Batch 19.199 (27.555) Remain 14:14:39 loss: 0.2381 loss_seg: 0.1502 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:12:40,196 INFO misc.py line 117 726] Train: [17/20][180/510] Data 3.418 (3.799) Batch 25.192 (27.541) Remain 14:13:47 loss: 0.2111 loss_seg: 0.1296 loss_superpoint_edge: 0.0127 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:13:05,916 INFO misc.py line 117 726] Train: [17/20][181/510] Data 2.521 (3.792) Batch 25.720 (27.531) Remain 14:13:00 loss: 0.2320 loss_seg: 0.1403 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:13:36,455 INFO misc.py line 117 726] Train: [17/20][182/510] Data 4.062 (3.793) Batch 30.539 (27.548) Remain 14:13:04 loss: 0.4140 loss_seg: 0.2816 loss_superpoint_edge: 0.0646 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:14:15,878 INFO misc.py line 117 726] Train: [17/20][183/510] Data 9.170 (3.823) Batch 39.423 (27.614) Remain 14:14:39 loss: 0.2413 loss_seg: 0.1502 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:14:34,454 INFO misc.py line 117 726] Train: [17/20][184/510] Data 2.616 (3.816) Batch 18.576 (27.564) Remain 14:12:38 loss: 0.2538 loss_seg: 0.1495 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:14:59,347 INFO misc.py line 117 726] Train: [17/20][185/510] Data 3.678 (3.816) Batch 24.893 (27.549) Remain 14:11:44 loss: 0.2540 loss_seg: 0.1581 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:15:11,283 INFO misc.py line 117 726] Train: [17/20][186/510] Data 1.475 (3.803) Batch 11.936 (27.464) Remain 14:08:38 loss: 0.1961 loss_seg: 0.1063 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:15:46,000 INFO misc.py line 117 726] Train: [17/20][187/510] Data 4.015 (3.804) Batch 34.717 (27.503) Remain 14:09:23 loss: 0.1826 loss_seg: 0.0984 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:16:14,553 INFO misc.py line 117 726] Train: [17/20][188/510] Data 2.945 (3.799) Batch 28.552 (27.509) Remain 14:09:06 loss: 0.1767 loss_seg: 0.0912 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:16:43,356 INFO misc.py line 117 726] Train: [17/20][189/510] Data 3.579 (3.798) Batch 28.803 (27.516) Remain 14:08:52 loss: 0.2334 loss_seg: 0.1394 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:17:11,637 INFO misc.py line 117 726] Train: [17/20][190/510] Data 3.566 (3.797) Batch 28.281 (27.520) Remain 14:08:32 loss: 0.2723 loss_seg: 0.1664 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:17:42,066 INFO misc.py line 117 726] Train: [17/20][191/510] Data 3.651 (3.796) Batch 30.429 (27.536) Remain 14:08:33 loss: 0.2389 loss_seg: 0.1436 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:18:09,899 INFO misc.py line 117 726] Train: [17/20][192/510] Data 2.864 (3.791) Batch 27.833 (27.537) Remain 14:08:08 loss: 0.2655 loss_seg: 0.1678 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:18:41,368 INFO misc.py line 117 726] Train: [17/20][193/510] Data 3.798 (3.791) Batch 31.468 (27.558) Remain 14:08:19 loss: 0.2771 loss_seg: 0.1776 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:19:05,913 INFO misc.py line 117 726] Train: [17/20][194/510] Data 2.562 (3.785) Batch 24.546 (27.542) Remain 14:07:22 loss: 0.2153 loss_seg: 0.1249 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:19:30,278 INFO misc.py line 117 726] Train: [17/20][195/510] Data 2.599 (3.779) Batch 24.366 (27.526) Remain 14:06:24 loss: 0.2230 loss_seg: 0.1287 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:19:54,763 INFO misc.py line 117 726] Train: [17/20][196/510] Data 2.292 (3.771) Batch 24.485 (27.510) Remain 14:05:28 loss: 0.2095 loss_seg: 0.1172 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:20:11,649 INFO misc.py line 117 726] Train: [17/20][197/510] Data 1.943 (3.762) Batch 16.886 (27.455) Remain 14:03:19 loss: 0.1818 loss_seg: 0.0950 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:20:36,141 INFO misc.py line 117 726] Train: [17/20][198/510] Data 2.245 (3.754) Batch 24.492 (27.440) Remain 14:02:24 loss: 0.3165 loss_seg: 0.2169 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0341 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:20:58,799 INFO misc.py line 117 726] Train: [17/20][199/510] Data 2.241 (3.746) Batch 22.658 (27.416) Remain 14:01:11 loss: 0.2177 loss_seg: 0.1218 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:21:37,414 INFO misc.py line 117 726] Train: [17/20][200/510] Data 5.955 (3.757) Batch 38.614 (27.472) Remain 14:02:29 loss: 0.2165 loss_seg: 0.1271 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:21:37,414 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 11:22:02,958 INFO misc.py line 117 726] Train: [17/20][201/510] Data 2.850 (3.753) Batch 25.545 (27.463) Remain 14:01:43 loss: 0.2578 loss_seg: 0.1610 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:22:30,144 INFO misc.py line 117 726] Train: [17/20][202/510] Data 2.994 (3.749) Batch 27.186 (27.461) Remain 14:01:13 loss: 0.2308 loss_seg: 0.1403 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:23:02,998 INFO misc.py line 117 726] Train: [17/20][203/510] Data 4.579 (3.753) Batch 32.853 (27.488) Remain 14:01:35 loss: 0.2834 loss_seg: 0.1895 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:23:33,587 INFO misc.py line 117 726] Train: [17/20][204/510] Data 4.393 (3.756) Batch 30.590 (27.504) Remain 14:01:36 loss: 0.2665 loss_seg: 0.1676 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:24:00,473 INFO misc.py line 117 726] Train: [17/20][205/510] Data 3.286 (3.754) Batch 26.885 (27.501) Remain 14:01:03 loss: 0.2199 loss_seg: 0.1288 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:24:30,242 INFO misc.py line 117 726] Train: [17/20][206/510] Data 2.823 (3.749) Batch 29.769 (27.512) Remain 14:00:56 loss: 0.2392 loss_seg: 0.1408 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:24:55,788 INFO misc.py line 117 726] Train: [17/20][207/510] Data 3.293 (3.747) Batch 25.546 (27.502) Remain 14:00:11 loss: 0.1856 loss_seg: 0.0960 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:25:20,830 INFO misc.py line 117 726] Train: [17/20][208/510] Data 2.760 (3.742) Batch 25.042 (27.490) Remain 13:59:21 loss: 0.2452 loss_seg: 0.1479 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:25:52,616 INFO misc.py line 117 726] Train: [17/20][209/510] Data 3.036 (3.739) Batch 31.786 (27.511) Remain 13:59:32 loss: 0.2243 loss_seg: 0.1420 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:26:19,297 INFO misc.py line 117 726] Train: [17/20][210/510] Data 5.307 (3.746) Batch 26.680 (27.507) Remain 13:58:57 loss: 0.2276 loss_seg: 0.1400 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:26:46,126 INFO misc.py line 117 726] Train: [17/20][211/510] Data 4.212 (3.749) Batch 26.830 (27.504) Remain 13:58:24 loss: 0.2809 loss_seg: 0.1841 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:27:15,972 INFO misc.py line 117 726] Train: [17/20][212/510] Data 5.959 (3.759) Batch 29.846 (27.515) Remain 13:58:17 loss: 0.2323 loss_seg: 0.1411 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:27:45,172 INFO misc.py line 117 726] Train: [17/20][213/510] Data 2.546 (3.753) Batch 29.200 (27.523) Remain 13:58:04 loss: 0.2224 loss_seg: 0.1318 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:28:08,675 INFO misc.py line 117 726] Train: [17/20][214/510] Data 2.538 (3.748) Batch 23.504 (27.504) Remain 13:57:02 loss: 0.2265 loss_seg: 0.1362 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:28:43,525 INFO misc.py line 117 726] Train: [17/20][215/510] Data 6.452 (3.760) Batch 34.850 (27.539) Remain 13:57:37 loss: 0.2968 loss_seg: 0.2025 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:29:14,124 INFO misc.py line 117 726] Train: [17/20][216/510] Data 3.695 (3.760) Batch 30.599 (27.553) Remain 13:57:36 loss: 0.2414 loss_seg: 0.1469 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:29:38,015 INFO misc.py line 117 726] Train: [17/20][217/510] Data 3.137 (3.757) Batch 23.891 (27.536) Remain 13:56:37 loss: 0.2392 loss_seg: 0.1452 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:30:07,084 INFO misc.py line 117 726] Train: [17/20][218/510] Data 3.290 (3.755) Batch 29.069 (27.543) Remain 13:56:23 loss: 0.2587 loss_seg: 0.1589 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:30:34,542 INFO misc.py line 117 726] Train: [17/20][219/510] Data 5.564 (3.763) Batch 27.458 (27.543) Remain 13:55:54 loss: 0.3947 loss_seg: 0.2800 loss_superpoint_edge: 0.0441 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:31:02,677 INFO misc.py line 117 726] Train: [17/20][220/510] Data 3.475 (3.762) Batch 28.134 (27.545) Remain 13:55:32 loss: 0.2533 loss_seg: 0.1554 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:31:31,245 INFO misc.py line 117 726] Train: [17/20][221/510] Data 2.773 (3.758) Batch 28.569 (27.550) Remain 13:55:13 loss: 0.2041 loss_seg: 0.1125 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:31:59,702 INFO misc.py line 117 726] Train: [17/20][222/510] Data 3.424 (3.756) Batch 28.457 (27.554) Remain 13:54:53 loss: 0.2173 loss_seg: 0.1259 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:32:35,600 INFO misc.py line 117 726] Train: [17/20][223/510] Data 9.186 (3.781) Batch 35.898 (27.592) Remain 13:55:34 loss: 0.2261 loss_seg: 0.1328 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:33:04,704 INFO misc.py line 117 726] Train: [17/20][224/510] Data 5.138 (3.787) Batch 29.104 (27.599) Remain 13:55:19 loss: 0.2284 loss_seg: 0.1378 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:33:34,661 INFO misc.py line 117 726] Train: [17/20][225/510] Data 3.678 (3.786) Batch 29.957 (27.609) Remain 13:55:11 loss: 0.2185 loss_seg: 0.1280 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:34:02,341 INFO misc.py line 117 726] Train: [17/20][226/510] Data 3.691 (3.786) Batch 27.680 (27.610) Remain 13:54:44 loss: 0.2432 loss_seg: 0.1531 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:34:29,638 INFO misc.py line 117 726] Train: [17/20][227/510] Data 4.289 (3.788) Batch 27.297 (27.608) Remain 13:54:14 loss: 0.2479 loss_seg: 0.1549 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:34:56,121 INFO misc.py line 117 726] Train: [17/20][228/510] Data 4.513 (3.791) Batch 26.483 (27.603) Remain 13:53:37 loss: 0.1888 loss_seg: 0.1033 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:35:27,742 INFO misc.py line 117 726] Train: [17/20][229/510] Data 4.026 (3.792) Batch 31.620 (27.621) Remain 13:53:41 loss: 0.2464 loss_seg: 0.1504 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:35:55,603 INFO misc.py line 117 726] Train: [17/20][230/510] Data 3.970 (3.793) Batch 27.862 (27.622) Remain 13:53:16 loss: 0.2578 loss_seg: 0.1593 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:36:30,405 INFO misc.py line 117 726] Train: [17/20][231/510] Data 5.093 (3.799) Batch 34.802 (27.654) Remain 13:53:45 loss: 0.2141 loss_seg: 0.1239 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:37:01,313 INFO misc.py line 117 726] Train: [17/20][232/510] Data 4.618 (3.803) Batch 30.908 (27.668) Remain 13:53:43 loss: 0.2233 loss_seg: 0.1308 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:37:34,627 INFO misc.py line 117 726] Train: [17/20][233/510] Data 6.249 (3.813) Batch 33.314 (27.692) Remain 13:54:00 loss: 0.4344 loss_seg: 0.3299 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:38:03,260 INFO misc.py line 117 726] Train: [17/20][234/510] Data 3.032 (3.810) Batch 28.633 (27.697) Remain 13:53:39 loss: 0.2182 loss_seg: 0.1224 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:38:28,801 INFO misc.py line 117 726] Train: [17/20][235/510] Data 3.163 (3.807) Batch 25.541 (27.687) Remain 13:52:55 loss: 0.1908 loss_seg: 0.1065 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:38:52,557 INFO misc.py line 117 726] Train: [17/20][236/510] Data 2.674 (3.802) Batch 23.756 (27.670) Remain 13:51:57 loss: 0.2061 loss_seg: 0.1152 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:39:18,531 INFO misc.py line 117 726] Train: [17/20][237/510] Data 1.995 (3.794) Batch 25.974 (27.663) Remain 13:51:16 loss: 0.2500 loss_seg: 0.1492 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:39:45,788 INFO misc.py line 117 726] Train: [17/20][238/510] Data 2.748 (3.790) Batch 27.257 (27.661) Remain 13:50:45 loss: 0.3847 loss_seg: 0.2669 loss_superpoint_edge: 0.0512 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:40:04,226 INFO misc.py line 117 726] Train: [17/20][239/510] Data 2.397 (3.784) Batch 18.438 (27.622) Remain 13:49:07 loss: 0.2392 loss_seg: 0.1436 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:40:25,935 INFO misc.py line 117 726] Train: [17/20][240/510] Data 2.109 (3.777) Batch 21.708 (27.597) Remain 13:47:55 loss: 0.2596 loss_seg: 0.1580 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:40:56,195 INFO misc.py line 117 726] Train: [17/20][241/510] Data 3.597 (3.776) Batch 30.260 (27.609) Remain 13:47:47 loss: 0.2605 loss_seg: 0.1657 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:41:19,714 INFO misc.py line 117 726] Train: [17/20][242/510] Data 2.428 (3.771) Batch 23.519 (27.591) Remain 13:46:49 loss: 0.1857 loss_seg: 0.0978 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:41:50,030 INFO misc.py line 117 726] Train: [17/20][243/510] Data 4.147 (3.772) Batch 30.317 (27.603) Remain 13:46:42 loss: 0.1938 loss_seg: 0.1050 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:42:11,003 INFO misc.py line 117 726] Train: [17/20][244/510] Data 2.493 (3.767) Batch 20.972 (27.575) Remain 13:45:25 loss: 0.2280 loss_seg: 0.1293 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0423 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:42:47,689 INFO misc.py line 117 726] Train: [17/20][245/510] Data 6.003 (3.776) Batch 36.686 (27.613) Remain 13:46:05 loss: 0.3368 loss_seg: 0.2322 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:43:15,814 INFO misc.py line 117 726] Train: [17/20][246/510] Data 2.923 (3.773) Batch 28.126 (27.615) Remain 13:45:41 loss: 0.3157 loss_seg: 0.2083 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:43:49,643 INFO misc.py line 117 726] Train: [17/20][247/510] Data 10.169 (3.799) Batch 33.828 (27.641) Remain 13:45:59 loss: 0.3217 loss_seg: 0.2330 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:44:18,018 INFO misc.py line 117 726] Train: [17/20][248/510] Data 3.549 (3.798) Batch 28.375 (27.644) Remain 13:45:37 loss: 0.1886 loss_seg: 0.1009 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:44:46,362 INFO misc.py line 117 726] Train: [17/20][249/510] Data 3.264 (3.796) Batch 28.344 (27.646) Remain 13:45:14 loss: 0.2315 loss_seg: 0.1366 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:45:15,822 INFO misc.py line 117 726] Train: [17/20][250/510] Data 3.344 (3.794) Batch 29.460 (27.654) Remain 13:45:00 loss: 0.2354 loss_seg: 0.1415 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:45:15,822 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 11:45:39,517 INFO misc.py line 117 726] Train: [17/20][251/510] Data 3.086 (3.791) Batch 23.695 (27.638) Remain 13:44:03 loss: 0.2767 loss_seg: 0.1765 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:46:02,735 INFO misc.py line 117 726] Train: [17/20][252/510] Data 2.948 (3.788) Batch 23.217 (27.620) Remain 13:43:04 loss: 0.3228 loss_seg: 0.2128 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:46:33,193 INFO misc.py line 117 726] Train: [17/20][253/510] Data 3.491 (3.786) Batch 30.459 (27.631) Remain 13:42:57 loss: 0.2384 loss_seg: 0.1450 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:46:59,589 INFO misc.py line 117 726] Train: [17/20][254/510] Data 3.004 (3.783) Batch 26.395 (27.626) Remain 13:42:20 loss: 0.2484 loss_seg: 0.1554 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:47:22,577 INFO misc.py line 117 726] Train: [17/20][255/510] Data 2.773 (3.779) Batch 22.988 (27.608) Remain 13:41:20 loss: 0.2088 loss_seg: 0.1169 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:47:54,260 INFO misc.py line 117 726] Train: [17/20][256/510] Data 5.300 (3.785) Batch 31.683 (27.624) Remain 13:41:21 loss: 0.2774 loss_seg: 0.1732 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:48:30,886 INFO misc.py line 117 726] Train: [17/20][257/510] Data 5.053 (3.790) Batch 36.627 (27.660) Remain 13:41:56 loss: 0.1739 loss_seg: 0.0910 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:48:59,488 INFO misc.py line 117 726] Train: [17/20][258/510] Data 3.633 (3.790) Batch 28.601 (27.663) Remain 13:41:35 loss: 0.2520 loss_seg: 0.1561 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:49:41,888 INFO misc.py line 117 726] Train: [17/20][259/510] Data 10.895 (3.817) Batch 42.400 (27.721) Remain 13:42:50 loss: 0.2750 loss_seg: 0.1764 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:50:15,398 INFO misc.py line 117 726] Train: [17/20][260/510] Data 4.402 (3.820) Batch 33.509 (27.743) Remain 13:43:03 loss: 0.2420 loss_seg: 0.1428 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:50:40,548 INFO misc.py line 117 726] Train: [17/20][261/510] Data 3.131 (3.817) Batch 25.151 (27.733) Remain 13:42:17 loss: 0.3304 loss_seg: 0.2103 loss_superpoint_edge: 0.0516 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:51:08,457 INFO misc.py line 117 726] Train: [17/20][262/510] Data 2.924 (3.814) Batch 27.909 (27.734) Remain 13:41:51 loss: 0.2381 loss_seg: 0.1403 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:51:33,657 INFO misc.py line 117 726] Train: [17/20][263/510] Data 2.945 (3.810) Batch 25.200 (27.724) Remain 13:41:05 loss: 0.2148 loss_seg: 0.1240 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:51:58,020 INFO misc.py line 117 726] Train: [17/20][264/510] Data 3.249 (3.808) Batch 24.364 (27.711) Remain 13:40:15 loss: 0.2454 loss_seg: 0.1534 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:52:32,299 INFO misc.py line 117 726] Train: [17/20][265/510] Data 5.410 (3.814) Batch 34.279 (27.736) Remain 13:40:32 loss: 0.2471 loss_seg: 0.1497 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:52:55,501 INFO misc.py line 117 726] Train: [17/20][266/510] Data 3.915 (3.815) Batch 23.201 (27.719) Remain 13:39:33 loss: 0.2707 loss_seg: 0.1709 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:53:28,368 INFO misc.py line 117 726] Train: [17/20][267/510] Data 6.195 (3.824) Batch 32.867 (27.739) Remain 13:39:40 loss: 0.2565 loss_seg: 0.1566 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:54:04,336 INFO misc.py line 117 726] Train: [17/20][268/510] Data 5.633 (3.830) Batch 35.968 (27.770) Remain 13:40:07 loss: 0.2378 loss_seg: 0.1453 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:54:39,696 INFO misc.py line 117 726] Train: [17/20][269/510] Data 5.549 (3.837) Batch 35.360 (27.798) Remain 13:40:30 loss: 0.1993 loss_seg: 0.1110 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:55:07,745 INFO misc.py line 117 726] Train: [17/20][270/510] Data 4.236 (3.838) Batch 28.049 (27.799) Remain 13:40:04 loss: 0.1985 loss_seg: 0.1076 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:55:36,786 INFO misc.py line 117 726] Train: [17/20][271/510] Data 3.066 (3.835) Batch 29.040 (27.804) Remain 13:39:44 loss: 0.2033 loss_seg: 0.1120 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:56:06,582 INFO misc.py line 117 726] Train: [17/20][272/510] Data 3.128 (3.833) Batch 29.797 (27.811) Remain 13:39:30 loss: 0.2370 loss_seg: 0.1431 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:56:36,758 INFO misc.py line 117 726] Train: [17/20][273/510] Data 3.937 (3.833) Batch 30.175 (27.820) Remain 13:39:17 loss: 0.2265 loss_seg: 0.1357 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:57:09,985 INFO misc.py line 117 726] Train: [17/20][274/510] Data 6.896 (3.844) Batch 33.227 (27.840) Remain 13:39:25 loss: 0.1852 loss_seg: 0.1017 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:57:36,658 INFO misc.py line 117 726] Train: [17/20][275/510] Data 2.631 (3.840) Batch 26.674 (27.836) Remain 13:38:49 loss: 0.2440 loss_seg: 0.1512 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:57:58,887 INFO misc.py line 117 726] Train: [17/20][276/510] Data 2.638 (3.836) Batch 22.229 (27.815) Remain 13:37:45 loss: 0.2064 loss_seg: 0.1188 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:58:33,411 INFO misc.py line 117 726] Train: [17/20][277/510] Data 3.585 (3.835) Batch 34.524 (27.840) Remain 13:38:01 loss: 0.2096 loss_seg: 0.1238 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:59:07,346 INFO misc.py line 117 726] Train: [17/20][278/510] Data 3.675 (3.834) Batch 33.935 (27.862) Remain 13:38:12 loss: 0.2131 loss_seg: 0.1234 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 11:59:32,721 INFO misc.py line 117 726] Train: [17/20][279/510] Data 5.145 (3.839) Batch 25.375 (27.853) Remain 13:37:28 loss: 0.3310 loss_seg: 0.2254 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:00:11,214 INFO misc.py line 117 726] Train: [17/20][280/510] Data 8.370 (3.855) Batch 38.493 (27.891) Remain 13:38:08 loss: 0.2909 loss_seg: 0.1899 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:00:43,964 INFO misc.py line 117 726] Train: [17/20][281/510] Data 4.511 (3.858) Batch 32.749 (27.909) Remain 13:38:11 loss: 0.2157 loss_seg: 0.1258 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:01:16,227 INFO misc.py line 117 726] Train: [17/20][282/510] Data 4.856 (3.861) Batch 32.263 (27.924) Remain 13:38:10 loss: 0.3020 loss_seg: 0.1975 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:01:34,007 INFO misc.py line 117 726] Train: [17/20][283/510] Data 1.484 (3.853) Batch 17.780 (27.888) Remain 13:36:39 loss: 0.2422 loss_seg: 0.1487 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:01:57,639 INFO misc.py line 117 726] Train: [17/20][284/510] Data 2.543 (3.848) Batch 23.631 (27.873) Remain 13:35:44 loss: 0.2455 loss_seg: 0.1460 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:02:35,337 INFO misc.py line 117 726] Train: [17/20][285/510] Data 6.305 (3.857) Batch 37.699 (27.908) Remain 13:36:18 loss: 0.2180 loss_seg: 0.1270 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:03:01,086 INFO misc.py line 117 726] Train: [17/20][286/510] Data 2.439 (3.852) Batch 25.749 (27.900) Remain 13:35:36 loss: 0.2420 loss_seg: 0.1502 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:03:31,706 INFO misc.py line 117 726] Train: [17/20][287/510] Data 3.205 (3.849) Batch 30.620 (27.910) Remain 13:35:25 loss: 0.1956 loss_seg: 0.1059 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:04:03,771 INFO misc.py line 117 726] Train: [17/20][288/510] Data 4.276 (3.851) Batch 32.065 (27.924) Remain 13:35:23 loss: 0.2953 loss_seg: 0.1884 loss_superpoint_edge: 0.0388 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:04:26,321 INFO misc.py line 117 726] Train: [17/20][289/510] Data 2.418 (3.846) Batch 22.550 (27.905) Remain 13:34:22 loss: 0.3028 loss_seg: 0.1929 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:04:59,205 INFO misc.py line 117 726] Train: [17/20][290/510] Data 6.045 (3.854) Batch 32.883 (27.923) Remain 13:34:24 loss: 0.2447 loss_seg: 0.1554 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:05:21,136 INFO misc.py line 117 726] Train: [17/20][291/510] Data 2.242 (3.848) Batch 21.931 (27.902) Remain 13:33:20 loss: 0.2271 loss_seg: 0.1327 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:05:54,548 INFO misc.py line 117 726] Train: [17/20][292/510] Data 3.644 (3.847) Batch 33.412 (27.921) Remain 13:33:26 loss: 0.2019 loss_seg: 0.1154 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:06:21,222 INFO misc.py line 117 726] Train: [17/20][293/510] Data 3.696 (3.847) Batch 26.674 (27.917) Remain 13:32:50 loss: 0.2066 loss_seg: 0.1155 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:06:50,204 INFO misc.py line 117 726] Train: [17/20][294/510] Data 3.363 (3.845) Batch 28.982 (27.920) Remain 13:32:29 loss: 0.2535 loss_seg: 0.1601 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:07:20,102 INFO misc.py line 117 726] Train: [17/20][295/510] Data 2.930 (3.842) Batch 29.898 (27.927) Remain 13:32:12 loss: 0.2552 loss_seg: 0.1572 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:07:56,811 INFO misc.py line 117 726] Train: [17/20][296/510] Data 4.798 (3.845) Batch 36.709 (27.957) Remain 13:32:37 loss: 0.2644 loss_seg: 0.1644 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:08:34,326 INFO misc.py line 117 726] Train: [17/20][297/510] Data 7.480 (3.858) Batch 37.515 (27.990) Remain 13:33:06 loss: 0.2394 loss_seg: 0.1440 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:08:50,937 INFO misc.py line 117 726] Train: [17/20][298/510] Data 1.960 (3.851) Batch 16.611 (27.951) Remain 13:31:30 loss: 0.2533 loss_seg: 0.1527 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:09:15,640 INFO misc.py line 117 726] Train: [17/20][299/510] Data 3.058 (3.849) Batch 24.703 (27.940) Remain 13:30:43 loss: 0.1760 loss_seg: 0.0926 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:09:49,696 INFO misc.py line 117 726] Train: [17/20][300/510] Data 3.498 (3.847) Batch 34.056 (27.961) Remain 13:30:51 loss: 0.2404 loss_seg: 0.1424 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:09:49,697 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 12:10:14,712 INFO misc.py line 117 726] Train: [17/20][301/510] Data 5.984 (3.854) Batch 25.015 (27.951) Remain 13:30:06 loss: 0.2022 loss_seg: 0.1134 loss_superpoint_edge: 0.0143 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:10:48,435 INFO misc.py line 117 726] Train: [17/20][302/510] Data 4.097 (3.855) Batch 33.723 (27.970) Remain 13:30:12 loss: 0.2175 loss_seg: 0.1263 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:11:14,898 INFO misc.py line 117 726] Train: [17/20][303/510] Data 3.431 (3.854) Batch 26.463 (27.965) Remain 13:29:35 loss: 0.2074 loss_seg: 0.1133 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:11:47,777 INFO misc.py line 117 726] Train: [17/20][304/510] Data 3.329 (3.852) Batch 32.879 (27.981) Remain 13:29:35 loss: 0.2357 loss_seg: 0.1400 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:12:15,387 INFO misc.py line 117 726] Train: [17/20][305/510] Data 3.081 (3.850) Batch 27.610 (27.980) Remain 13:29:05 loss: 0.2625 loss_seg: 0.1679 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:12:37,457 INFO misc.py line 117 726] Train: [17/20][306/510] Data 1.675 (3.842) Batch 22.070 (27.961) Remain 13:28:03 loss: 0.2226 loss_seg: 0.1305 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:13:01,999 INFO misc.py line 117 726] Train: [17/20][307/510] Data 2.437 (3.838) Batch 24.543 (27.949) Remain 13:27:16 loss: 0.3281 loss_seg: 0.2129 loss_superpoint_edge: 0.0470 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:13:32,210 INFO misc.py line 117 726] Train: [17/20][308/510] Data 7.889 (3.851) Batch 30.210 (27.957) Remain 13:27:01 loss: 0.3355 loss_seg: 0.2297 loss_superpoint_edge: 0.0401 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:14:05,203 INFO misc.py line 117 726] Train: [17/20][309/510] Data 3.285 (3.849) Batch 32.993 (27.973) Remain 13:27:01 loss: 0.1909 loss_seg: 0.1028 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:14:28,650 INFO misc.py line 117 726] Train: [17/20][310/510] Data 2.604 (3.845) Batch 23.446 (27.959) Remain 13:26:08 loss: 0.2004 loss_seg: 0.1125 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:14:55,819 INFO misc.py line 117 726] Train: [17/20][311/510] Data 2.456 (3.841) Batch 27.169 (27.956) Remain 13:25:35 loss: 0.2876 loss_seg: 0.1845 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:15:30,297 INFO misc.py line 117 726] Train: [17/20][312/510] Data 5.310 (3.845) Batch 34.478 (27.977) Remain 13:25:44 loss: 0.2125 loss_seg: 0.1192 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:16:05,514 INFO misc.py line 117 726] Train: [17/20][313/510] Data 5.196 (3.850) Batch 35.217 (28.001) Remain 13:25:56 loss: 0.1889 loss_seg: 0.1030 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:16:32,180 INFO misc.py line 117 726] Train: [17/20][314/510] Data 4.472 (3.852) Batch 26.666 (27.996) Remain 13:25:21 loss: 0.2595 loss_seg: 0.1620 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:17:01,028 INFO misc.py line 117 726] Train: [17/20][315/510] Data 2.561 (3.848) Batch 28.848 (27.999) Remain 13:24:58 loss: 0.2287 loss_seg: 0.1367 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:17:35,403 INFO misc.py line 117 726] Train: [17/20][316/510] Data 3.461 (3.846) Batch 34.375 (28.019) Remain 13:25:05 loss: 0.2672 loss_seg: 0.1726 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:18:10,393 INFO misc.py line 117 726] Train: [17/20][317/510] Data 2.992 (3.844) Batch 34.989 (28.042) Remain 13:25:15 loss: 0.2231 loss_seg: 0.1349 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:18:31,989 INFO misc.py line 117 726] Train: [17/20][318/510] Data 2.790 (3.840) Batch 21.596 (28.021) Remain 13:24:12 loss: 0.1814 loss_seg: 0.0923 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:18:56,070 INFO misc.py line 117 726] Train: [17/20][319/510] Data 2.279 (3.835) Batch 24.081 (28.009) Remain 13:23:22 loss: 0.2094 loss_seg: 0.1194 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:19:20,209 INFO misc.py line 117 726] Train: [17/20][320/510] Data 2.764 (3.832) Batch 24.139 (27.996) Remain 13:22:33 loss: 0.2385 loss_seg: 0.1364 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:19:46,669 INFO misc.py line 117 726] Train: [17/20][321/510] Data 3.298 (3.830) Batch 26.460 (27.992) Remain 13:21:57 loss: 0.2498 loss_seg: 0.1578 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:20:11,721 INFO misc.py line 117 726] Train: [17/20][322/510] Data 3.573 (3.830) Batch 25.052 (27.982) Remain 13:21:13 loss: 0.1767 loss_seg: 0.0913 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:20:43,375 INFO misc.py line 117 726] Train: [17/20][323/510] Data 4.912 (3.833) Batch 31.654 (27.994) Remain 13:21:05 loss: 0.2431 loss_seg: 0.1474 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:21:14,490 INFO misc.py line 117 726] Train: [17/20][324/510] Data 4.546 (3.835) Batch 31.115 (28.004) Remain 13:20:54 loss: 0.2399 loss_seg: 0.1514 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:21:40,755 INFO misc.py line 117 726] Train: [17/20][325/510] Data 3.117 (3.833) Batch 26.265 (27.998) Remain 13:20:16 loss: 0.1987 loss_seg: 0.1085 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:22:06,874 INFO misc.py line 117 726] Train: [17/20][326/510] Data 3.433 (3.832) Batch 26.119 (27.992) Remain 13:19:38 loss: 0.1811 loss_seg: 0.0965 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:22:41,289 INFO misc.py line 117 726] Train: [17/20][327/510] Data 3.759 (3.831) Batch 34.415 (28.012) Remain 13:19:44 loss: 0.2394 loss_seg: 0.1440 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:23:03,633 INFO misc.py line 117 726] Train: [17/20][328/510] Data 2.503 (3.827) Batch 22.345 (27.995) Remain 13:18:46 loss: 0.3814 loss_seg: 0.2840 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:23:36,798 INFO misc.py line 117 726] Train: [17/20][329/510] Data 4.345 (3.829) Batch 33.164 (28.011) Remain 13:18:46 loss: 0.2133 loss_seg: 0.1234 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:24:03,730 INFO misc.py line 117 726] Train: [17/20][330/510] Data 2.506 (3.825) Batch 26.933 (28.007) Remain 13:18:12 loss: 0.2474 loss_seg: 0.1509 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:24:39,724 INFO misc.py line 117 726] Train: [17/20][331/510] Data 7.560 (3.836) Batch 35.994 (28.032) Remain 13:18:26 loss: 0.2353 loss_seg: 0.1425 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:25:17,272 INFO misc.py line 117 726] Train: [17/20][332/510] Data 7.437 (3.847) Batch 37.548 (28.061) Remain 13:18:47 loss: 0.2083 loss_seg: 0.1209 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:25:46,214 INFO misc.py line 117 726] Train: [17/20][333/510] Data 4.331 (3.849) Batch 28.942 (28.063) Remain 13:18:23 loss: 0.2226 loss_seg: 0.1306 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:26:18,191 INFO misc.py line 117 726] Train: [17/20][334/510] Data 5.971 (3.855) Batch 31.977 (28.075) Remain 13:18:15 loss: 0.2391 loss_seg: 0.1475 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:26:51,007 INFO misc.py line 117 726] Train: [17/20][335/510] Data 3.772 (3.855) Batch 32.816 (28.089) Remain 13:18:12 loss: 0.1755 loss_seg: 0.0929 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0294 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:27:21,362 INFO misc.py line 117 726] Train: [17/20][336/510] Data 3.016 (3.852) Batch 30.355 (28.096) Remain 13:17:55 loss: 0.2835 loss_seg: 0.1793 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:27:48,330 INFO misc.py line 117 726] Train: [17/20][337/510] Data 2.467 (3.848) Batch 26.968 (28.093) Remain 13:17:21 loss: 0.1672 loss_seg: 0.0836 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:28:22,532 INFO misc.py line 117 726] Train: [17/20][338/510] Data 4.097 (3.849) Batch 34.203 (28.111) Remain 13:17:24 loss: 0.3371 loss_seg: 0.2290 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:28:44,137 INFO misc.py line 117 726] Train: [17/20][339/510] Data 1.609 (3.842) Batch 21.605 (28.092) Remain 13:16:23 loss: 0.2632 loss_seg: 0.1631 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:29:19,480 INFO misc.py line 117 726] Train: [17/20][340/510] Data 6.643 (3.851) Batch 35.343 (28.113) Remain 13:16:32 loss: 0.3422 loss_seg: 0.2423 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:29:42,926 INFO misc.py line 117 726] Train: [17/20][341/510] Data 2.364 (3.846) Batch 23.446 (28.099) Remain 13:15:40 loss: 0.2374 loss_seg: 0.1435 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:30:10,819 INFO misc.py line 117 726] Train: [17/20][342/510] Data 3.062 (3.844) Batch 27.893 (28.099) Remain 13:15:11 loss: 0.2636 loss_seg: 0.1726 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:30:36,749 INFO misc.py line 117 726] Train: [17/20][343/510] Data 3.925 (3.844) Batch 25.930 (28.092) Remain 13:14:32 loss: 0.2504 loss_seg: 0.1550 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:31:05,073 INFO misc.py line 117 726] Train: [17/20][344/510] Data 3.668 (3.844) Batch 28.325 (28.093) Remain 13:14:05 loss: 0.2248 loss_seg: 0.1303 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:31:35,952 INFO misc.py line 117 726] Train: [17/20][345/510] Data 3.754 (3.843) Batch 30.878 (28.101) Remain 13:13:51 loss: 0.2487 loss_seg: 0.1579 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:32:09,853 INFO misc.py line 117 726] Train: [17/20][346/510] Data 4.848 (3.846) Batch 33.902 (28.118) Remain 13:13:51 loss: 0.1960 loss_seg: 0.1076 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:32:46,364 INFO misc.py line 117 726] Train: [17/20][347/510] Data 9.125 (3.862) Batch 36.511 (28.142) Remain 13:14:05 loss: 0.2104 loss_seg: 0.1172 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:33:18,896 INFO misc.py line 117 726] Train: [17/20][348/510] Data 3.509 (3.861) Batch 32.531 (28.155) Remain 13:13:58 loss: 0.2668 loss_seg: 0.1738 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:33:37,817 INFO misc.py line 117 726] Train: [17/20][349/510] Data 2.527 (3.857) Batch 18.921 (28.128) Remain 13:12:45 loss: 0.2784 loss_seg: 0.1772 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:34:00,196 INFO misc.py line 117 726] Train: [17/20][350/510] Data 2.405 (3.853) Batch 22.379 (28.112) Remain 13:11:49 loss: 0.1957 loss_seg: 0.1063 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:34:00,196 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 12:34:35,218 INFO misc.py line 117 726] Train: [17/20][351/510] Data 5.525 (3.857) Batch 35.023 (28.132) Remain 13:11:54 loss: 0.2466 loss_seg: 0.1481 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:34:59,754 INFO misc.py line 117 726] Train: [17/20][352/510] Data 2.863 (3.854) Batch 24.536 (28.121) Remain 13:11:09 loss: 0.1878 loss_seg: 0.1013 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:35:35,237 INFO misc.py line 117 726] Train: [17/20][353/510] Data 5.852 (3.860) Batch 35.483 (28.143) Remain 13:11:16 loss: 0.2350 loss_seg: 0.1447 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:36:02,917 INFO misc.py line 117 726] Train: [17/20][354/510] Data 2.925 (3.858) Batch 27.680 (28.141) Remain 13:10:46 loss: 0.2068 loss_seg: 0.1165 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:36:32,232 INFO misc.py line 117 726] Train: [17/20][355/510] Data 3.311 (3.856) Batch 29.315 (28.145) Remain 13:10:23 loss: 0.1729 loss_seg: 0.0885 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:37:06,605 INFO misc.py line 117 726] Train: [17/20][356/510] Data 4.060 (3.857) Batch 34.373 (28.162) Remain 13:10:25 loss: 0.2076 loss_seg: 0.1179 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:37:37,218 INFO misc.py line 117 726] Train: [17/20][357/510] Data 3.265 (3.855) Batch 30.613 (28.169) Remain 13:10:08 loss: 0.3230 loss_seg: 0.2214 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:38:06,237 INFO misc.py line 117 726] Train: [17/20][358/510] Data 2.645 (3.851) Batch 29.019 (28.171) Remain 13:09:44 loss: 0.1859 loss_seg: 0.1035 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:38:24,771 INFO misc.py line 117 726] Train: [17/20][359/510] Data 1.861 (3.846) Batch 18.534 (28.144) Remain 13:08:30 loss: 0.2371 loss_seg: 0.1428 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:39:02,391 INFO misc.py line 117 726] Train: [17/20][360/510] Data 4.095 (3.847) Batch 37.620 (28.171) Remain 13:08:47 loss: 0.1865 loss_seg: 0.0993 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:39:24,568 INFO misc.py line 117 726] Train: [17/20][361/510] Data 2.486 (3.843) Batch 22.177 (28.154) Remain 13:07:50 loss: 0.2724 loss_seg: 0.1712 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:39:55,215 INFO misc.py line 117 726] Train: [17/20][362/510] Data 3.521 (3.842) Batch 30.648 (28.161) Remain 13:07:34 loss: 0.2784 loss_seg: 0.1740 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:40:26,244 INFO misc.py line 117 726] Train: [17/20][363/510] Data 3.330 (3.840) Batch 31.028 (28.169) Remain 13:07:19 loss: 0.2307 loss_seg: 0.1335 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:41:04,612 INFO misc.py line 117 726] Train: [17/20][364/510] Data 7.445 (3.850) Batch 38.368 (28.197) Remain 13:07:38 loss: 0.2326 loss_seg: 0.1418 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:41:30,079 INFO misc.py line 117 726] Train: [17/20][365/510] Data 2.550 (3.847) Batch 25.468 (28.190) Remain 13:06:57 loss: 0.2128 loss_seg: 0.1253 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:41:55,644 INFO misc.py line 117 726] Train: [17/20][366/510] Data 3.848 (3.847) Batch 25.564 (28.183) Remain 13:06:17 loss: 0.1919 loss_seg: 0.0992 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:42:20,722 INFO misc.py line 117 726] Train: [17/20][367/510] Data 2.294 (3.843) Batch 25.078 (28.174) Remain 13:05:35 loss: 0.2539 loss_seg: 0.1543 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:42:54,761 INFO misc.py line 117 726] Train: [17/20][368/510] Data 4.550 (3.845) Batch 34.039 (28.190) Remain 13:05:33 loss: 0.2406 loss_seg: 0.1460 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:43:18,528 INFO misc.py line 117 726] Train: [17/20][369/510] Data 3.892 (3.845) Batch 23.767 (28.178) Remain 13:04:45 loss: 0.2913 loss_seg: 0.1947 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0448 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:43:31,911 INFO misc.py line 117 726] Train: [17/20][370/510] Data 2.172 (3.840) Batch 13.383 (28.138) Remain 13:03:10 loss: 0.2673 loss_seg: 0.1658 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0445 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:43:59,316 INFO misc.py line 117 726] Train: [17/20][371/510] Data 2.958 (3.838) Batch 27.405 (28.136) Remain 13:02:38 loss: 0.2898 loss_seg: 0.1883 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:44:25,353 INFO misc.py line 117 726] Train: [17/20][372/510] Data 3.259 (3.836) Batch 26.037 (28.130) Remain 13:02:00 loss: 0.2060 loss_seg: 0.1170 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:44:49,838 INFO misc.py line 117 726] Train: [17/20][373/510] Data 4.683 (3.838) Batch 24.485 (28.120) Remain 13:01:16 loss: 0.2882 loss_seg: 0.1889 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:45:13,207 INFO misc.py line 117 726] Train: [17/20][374/510] Data 2.824 (3.836) Batch 23.369 (28.107) Remain 13:00:26 loss: 0.1669 loss_seg: 0.0821 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:45:44,761 INFO misc.py line 117 726] Train: [17/20][375/510] Data 4.417 (3.837) Batch 31.554 (28.117) Remain 13:00:14 loss: 0.3610 loss_seg: 0.2600 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:46:18,134 INFO misc.py line 117 726] Train: [17/20][376/510] Data 3.284 (3.836) Batch 33.373 (28.131) Remain 13:00:09 loss: 0.2448 loss_seg: 0.1517 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0317 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:46:46,454 INFO misc.py line 117 726] Train: [17/20][377/510] Data 4.053 (3.836) Batch 28.320 (28.131) Remain 12:59:42 loss: 0.2451 loss_seg: 0.1515 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:47:13,790 INFO misc.py line 117 726] Train: [17/20][378/510] Data 3.937 (3.837) Batch 27.337 (28.129) Remain 12:59:10 loss: 0.2410 loss_seg: 0.1451 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:47:46,540 INFO misc.py line 117 726] Train: [17/20][379/510] Data 5.205 (3.840) Batch 32.749 (28.141) Remain 12:59:02 loss: 0.2173 loss_seg: 0.1227 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:48:11,488 INFO misc.py line 117 726] Train: [17/20][380/510] Data 3.178 (3.839) Batch 24.948 (28.133) Remain 12:58:20 loss: 0.2114 loss_seg: 0.1214 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:48:37,233 INFO misc.py line 117 726] Train: [17/20][381/510] Data 2.954 (3.836) Batch 25.745 (28.127) Remain 12:57:42 loss: 0.1877 loss_seg: 0.1039 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:49:09,986 INFO misc.py line 117 726] Train: [17/20][382/510] Data 4.152 (3.837) Batch 32.753 (28.139) Remain 12:57:34 loss: 0.2173 loss_seg: 0.1218 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:49:43,480 INFO misc.py line 117 726] Train: [17/20][383/510] Data 5.441 (3.841) Batch 33.495 (28.153) Remain 12:57:29 loss: 0.2052 loss_seg: 0.1176 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:50:13,404 INFO misc.py line 117 726] Train: [17/20][384/510] Data 2.694 (3.838) Batch 29.924 (28.158) Remain 12:57:08 loss: 0.2816 loss_seg: 0.1813 loss_superpoint_edge: 0.0350 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:50:36,081 INFO misc.py line 117 726] Train: [17/20][385/510] Data 3.626 (3.838) Batch 22.677 (28.143) Remain 12:56:17 loss: 0.2381 loss_seg: 0.1433 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:51:07,861 INFO misc.py line 117 726] Train: [17/20][386/510] Data 5.195 (3.841) Batch 31.780 (28.153) Remain 12:56:04 loss: 0.2313 loss_seg: 0.1356 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:51:30,991 INFO misc.py line 117 726] Train: [17/20][387/510] Data 2.717 (3.838) Batch 23.130 (28.140) Remain 12:55:14 loss: 0.2253 loss_seg: 0.1324 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:51:54,168 INFO misc.py line 117 726] Train: [17/20][388/510] Data 2.838 (3.836) Batch 23.177 (28.127) Remain 12:54:25 loss: 0.2604 loss_seg: 0.1674 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:52:24,873 INFO misc.py line 117 726] Train: [17/20][389/510] Data 3.220 (3.834) Batch 30.705 (28.133) Remain 12:54:08 loss: 0.2597 loss_seg: 0.1566 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:52:55,864 INFO misc.py line 117 726] Train: [17/20][390/510] Data 3.438 (3.833) Batch 30.991 (28.141) Remain 12:53:52 loss: 0.1775 loss_seg: 0.0930 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:53:18,219 INFO misc.py line 117 726] Train: [17/20][391/510] Data 2.278 (3.829) Batch 22.355 (28.126) Remain 12:52:59 loss: 0.1621 loss_seg: 0.0798 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:53:49,762 INFO misc.py line 117 726] Train: [17/20][392/510] Data 4.556 (3.831) Batch 31.543 (28.135) Remain 12:52:46 loss: 0.2127 loss_seg: 0.1217 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:54:22,274 INFO misc.py line 117 726] Train: [17/20][393/510] Data 3.722 (3.831) Batch 32.513 (28.146) Remain 12:52:36 loss: 0.2318 loss_seg: 0.1409 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:54:42,763 INFO misc.py line 117 726] Train: [17/20][394/510] Data 1.982 (3.826) Batch 20.489 (28.126) Remain 12:51:35 loss: 0.2625 loss_seg: 0.1647 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:55:16,091 INFO misc.py line 117 726] Train: [17/20][395/510] Data 4.860 (3.829) Batch 33.327 (28.140) Remain 12:51:29 loss: 0.2211 loss_seg: 0.1264 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:55:40,702 INFO misc.py line 117 726] Train: [17/20][396/510] Data 2.749 (3.826) Batch 24.611 (28.131) Remain 12:50:46 loss: 0.2078 loss_seg: 0.1181 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:56:08,476 INFO misc.py line 117 726] Train: [17/20][397/510] Data 2.922 (3.824) Batch 27.774 (28.130) Remain 12:50:17 loss: 0.1708 loss_seg: 0.0882 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:56:27,336 INFO misc.py line 117 726] Train: [17/20][398/510] Data 2.202 (3.819) Batch 18.860 (28.106) Remain 12:49:10 loss: 0.2438 loss_seg: 0.1470 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:56:59,455 INFO misc.py line 117 726] Train: [17/20][399/510] Data 3.182 (3.818) Batch 32.119 (28.116) Remain 12:48:59 loss: 0.2451 loss_seg: 0.1505 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:57:33,731 INFO misc.py line 117 726] Train: [17/20][400/510] Data 5.147 (3.821) Batch 34.276 (28.132) Remain 12:48:56 loss: 0.1985 loss_seg: 0.1081 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:57:33,732 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 12:57:56,756 INFO misc.py line 117 726] Train: [17/20][401/510] Data 3.033 (3.819) Batch 23.024 (28.119) Remain 12:48:07 loss: 0.2162 loss_seg: 0.1287 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:58:19,142 INFO misc.py line 117 726] Train: [17/20][402/510] Data 2.178 (3.815) Batch 22.386 (28.105) Remain 12:47:15 loss: 0.2326 loss_seg: 0.1424 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:58:36,735 INFO misc.py line 117 726] Train: [17/20][403/510] Data 2.445 (3.812) Batch 17.594 (28.078) Remain 12:46:04 loss: 0.2100 loss_seg: 0.1241 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:59:15,145 INFO misc.py line 117 726] Train: [17/20][404/510] Data 9.541 (3.826) Batch 38.410 (28.104) Remain 12:46:18 loss: 0.2117 loss_seg: 0.1199 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 12:59:39,603 INFO misc.py line 117 726] Train: [17/20][405/510] Data 3.073 (3.824) Batch 24.458 (28.095) Remain 12:45:35 loss: 0.2183 loss_seg: 0.1252 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:00:06,457 INFO misc.py line 117 726] Train: [17/20][406/510] Data 2.826 (3.822) Batch 26.854 (28.092) Remain 12:45:02 loss: 0.2627 loss_seg: 0.1617 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:00:40,508 INFO misc.py line 117 726] Train: [17/20][407/510] Data 9.293 (3.835) Batch 34.051 (28.107) Remain 12:44:58 loss: 0.1600 loss_seg: 0.0782 loss_superpoint_edge: 0.0129 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:01:11,861 INFO misc.py line 117 726] Train: [17/20][408/510] Data 3.717 (3.835) Batch 31.353 (28.115) Remain 12:44:43 loss: 0.2469 loss_seg: 0.1624 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:01:42,055 INFO misc.py line 117 726] Train: [17/20][409/510] Data 2.972 (3.833) Batch 30.194 (28.120) Remain 12:44:23 loss: 0.2429 loss_seg: 0.1464 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:02:03,207 INFO misc.py line 117 726] Train: [17/20][410/510] Data 2.527 (3.829) Batch 21.152 (28.103) Remain 12:43:27 loss: 0.2766 loss_seg: 0.1766 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:02:24,513 INFO misc.py line 117 726] Train: [17/20][411/510] Data 3.031 (3.828) Batch 21.306 (28.086) Remain 12:42:32 loss: 0.3021 loss_seg: 0.2051 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:02:40,970 INFO misc.py line 117 726] Train: [17/20][412/510] Data 2.543 (3.824) Batch 16.457 (28.058) Remain 12:41:17 loss: 0.2692 loss_seg: 0.1623 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:03:07,494 INFO misc.py line 117 726] Train: [17/20][413/510] Data 3.869 (3.824) Batch 26.524 (28.054) Remain 12:40:43 loss: 0.2091 loss_seg: 0.1180 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:03:29,344 INFO misc.py line 117 726] Train: [17/20][414/510] Data 2.708 (3.822) Batch 21.850 (28.039) Remain 12:39:51 loss: 0.2348 loss_seg: 0.1396 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:03:49,951 INFO misc.py line 117 726] Train: [17/20][415/510] Data 2.701 (3.819) Batch 20.607 (28.021) Remain 12:38:53 loss: 0.2734 loss_seg: 0.1738 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:04:08,553 INFO misc.py line 117 726] Train: [17/20][416/510] Data 2.781 (3.817) Batch 18.602 (27.998) Remain 12:37:48 loss: 0.2277 loss_seg: 0.1364 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:04:32,591 INFO misc.py line 117 726] Train: [17/20][417/510] Data 3.030 (3.815) Batch 24.038 (27.988) Remain 12:37:05 loss: 0.2822 loss_seg: 0.1846 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:04:59,431 INFO misc.py line 117 726] Train: [17/20][418/510] Data 2.478 (3.811) Batch 26.841 (27.986) Remain 12:36:32 loss: 0.3606 loss_seg: 0.2603 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:05:25,862 INFO misc.py line 117 726] Train: [17/20][419/510] Data 2.115 (3.807) Batch 26.431 (27.982) Remain 12:35:58 loss: 0.2801 loss_seg: 0.1731 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:05:56,208 INFO misc.py line 117 726] Train: [17/20][420/510] Data 4.120 (3.808) Batch 30.346 (27.988) Remain 12:35:39 loss: 0.2249 loss_seg: 0.1302 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0454 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:06:20,794 INFO misc.py line 117 726] Train: [17/20][421/510] Data 2.795 (3.806) Batch 24.585 (27.980) Remain 12:34:58 loss: 0.2589 loss_seg: 0.1598 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:06:44,646 INFO misc.py line 117 726] Train: [17/20][422/510] Data 2.444 (3.802) Batch 23.853 (27.970) Remain 12:34:14 loss: 0.2550 loss_seg: 0.1569 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:07:08,011 INFO misc.py line 117 726] Train: [17/20][423/510] Data 2.451 (3.799) Batch 23.365 (27.959) Remain 12:33:29 loss: 0.2298 loss_seg: 0.1345 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:07:33,855 INFO misc.py line 117 726] Train: [17/20][424/510] Data 4.686 (3.801) Batch 25.845 (27.954) Remain 12:32:53 loss: 0.2608 loss_seg: 0.1644 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:07:57,254 INFO misc.py line 117 726] Train: [17/20][425/510] Data 3.915 (3.802) Batch 23.399 (27.943) Remain 12:32:07 loss: 0.2293 loss_seg: 0.1362 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:08:24,225 INFO misc.py line 117 726] Train: [17/20][426/510] Data 3.369 (3.801) Batch 26.970 (27.941) Remain 12:31:36 loss: 0.2719 loss_seg: 0.1719 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:08:57,809 INFO misc.py line 117 726] Train: [17/20][427/510] Data 6.347 (3.807) Batch 33.585 (27.954) Remain 12:31:29 loss: 0.1858 loss_seg: 0.0999 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:09:24,780 INFO misc.py line 117 726] Train: [17/20][428/510] Data 3.561 (3.806) Batch 26.971 (27.952) Remain 12:30:57 loss: 0.2656 loss_seg: 0.1647 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:09:44,549 INFO misc.py line 117 726] Train: [17/20][429/510] Data 3.951 (3.806) Batch 19.768 (27.932) Remain 12:29:59 loss: 0.2892 loss_seg: 0.1974 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:10:16,295 INFO misc.py line 117 726] Train: [17/20][430/510] Data 6.022 (3.812) Batch 31.746 (27.941) Remain 12:29:45 loss: 0.2184 loss_seg: 0.1241 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:10:48,728 INFO misc.py line 117 726] Train: [17/20][431/510] Data 4.938 (3.814) Batch 32.433 (27.952) Remain 12:29:34 loss: 0.2176 loss_seg: 0.1241 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:11:16,397 INFO misc.py line 117 726] Train: [17/20][432/510] Data 4.657 (3.816) Batch 27.669 (27.951) Remain 12:29:05 loss: 0.1912 loss_seg: 0.1068 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:11:48,105 INFO misc.py line 117 726] Train: [17/20][433/510] Data 2.705 (3.814) Batch 31.709 (27.960) Remain 12:28:51 loss: 0.2431 loss_seg: 0.1453 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:12:16,130 INFO misc.py line 117 726] Train: [17/20][434/510] Data 4.122 (3.814) Batch 28.025 (27.960) Remain 12:28:23 loss: 0.2709 loss_seg: 0.1749 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:12:43,580 INFO misc.py line 117 726] Train: [17/20][435/510] Data 3.103 (3.813) Batch 27.450 (27.959) Remain 12:27:53 loss: 0.2427 loss_seg: 0.1454 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:13:13,018 INFO misc.py line 117 726] Train: [17/20][436/510] Data 2.928 (3.811) Batch 29.438 (27.962) Remain 12:27:31 loss: 0.2975 loss_seg: 0.2081 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:13:46,017 INFO misc.py line 117 726] Train: [17/20][437/510] Data 3.614 (3.810) Batch 32.999 (27.974) Remain 12:27:22 loss: 0.3130 loss_seg: 0.2181 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:14:09,532 INFO misc.py line 117 726] Train: [17/20][438/510] Data 2.780 (3.808) Batch 23.516 (27.964) Remain 12:26:37 loss: 0.4162 loss_seg: 0.3062 loss_superpoint_edge: 0.0424 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:14:31,454 INFO misc.py line 117 726] Train: [17/20][439/510] Data 2.663 (3.805) Batch 21.922 (27.950) Remain 12:25:47 loss: 0.2041 loss_seg: 0.1147 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:15:00,479 INFO misc.py line 117 726] Train: [17/20][440/510] Data 3.470 (3.804) Batch 29.025 (27.952) Remain 12:25:23 loss: 0.2168 loss_seg: 0.1256 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:15:26,514 INFO misc.py line 117 726] Train: [17/20][441/510] Data 2.654 (3.802) Batch 26.035 (27.948) Remain 12:24:48 loss: 0.2185 loss_seg: 0.1244 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:15:52,865 INFO misc.py line 117 726] Train: [17/20][442/510] Data 2.948 (3.800) Batch 26.351 (27.944) Remain 12:24:14 loss: 0.2124 loss_seg: 0.1219 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:16:20,287 INFO misc.py line 117 726] Train: [17/20][443/510] Data 4.963 (3.802) Batch 27.422 (27.943) Remain 12:23:45 loss: 0.2899 loss_seg: 0.1828 loss_superpoint_edge: 0.0370 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:16:54,989 INFO misc.py line 117 726] Train: [17/20][444/510] Data 5.571 (3.806) Batch 34.702 (27.958) Remain 12:23:41 loss: 0.2257 loss_seg: 0.1366 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:17:29,662 INFO misc.py line 117 726] Train: [17/20][445/510] Data 4.340 (3.808) Batch 34.672 (27.974) Remain 12:23:37 loss: 0.2383 loss_seg: 0.1419 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:17:55,885 INFO misc.py line 117 726] Train: [17/20][446/510] Data 3.556 (3.807) Batch 26.223 (27.970) Remain 12:23:03 loss: 0.3246 loss_seg: 0.2200 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:18:12,606 INFO misc.py line 117 726] Train: [17/20][447/510] Data 2.021 (3.803) Batch 16.721 (27.944) Remain 12:21:55 loss: 0.3066 loss_seg: 0.2128 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:18:30,448 INFO misc.py line 117 726] Train: [17/20][448/510] Data 2.689 (3.801) Batch 17.842 (27.922) Remain 12:20:51 loss: 0.2755 loss_seg: 0.1821 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:19:02,257 INFO misc.py line 117 726] Train: [17/20][449/510] Data 5.975 (3.805) Batch 31.809 (27.930) Remain 12:20:37 loss: 0.2853 loss_seg: 0.1926 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:19:26,805 INFO misc.py line 117 726] Train: [17/20][450/510] Data 3.073 (3.804) Batch 24.549 (27.923) Remain 12:19:57 loss: 0.2374 loss_seg: 0.1415 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:19:26,806 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 13:19:50,280 INFO misc.py line 117 726] Train: [17/20][451/510] Data 2.444 (3.801) Batch 23.475 (27.913) Remain 12:19:13 loss: 0.2234 loss_seg: 0.1326 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:20:13,626 INFO misc.py line 117 726] Train: [17/20][452/510] Data 2.909 (3.799) Batch 23.346 (27.903) Remain 12:18:29 loss: 0.2537 loss_seg: 0.1562 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:20:45,219 INFO misc.py line 117 726] Train: [17/20][453/510] Data 3.615 (3.798) Batch 31.593 (27.911) Remain 12:18:14 loss: 0.1883 loss_seg: 0.1037 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:21:22,006 INFO misc.py line 117 726] Train: [17/20][454/510] Data 4.541 (3.800) Batch 36.786 (27.930) Remain 12:18:17 loss: 0.2300 loss_seg: 0.1361 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:21:58,214 INFO misc.py line 117 726] Train: [17/20][455/510] Data 5.773 (3.804) Batch 36.208 (27.949) Remain 12:18:18 loss: 0.2379 loss_seg: 0.1469 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:22:14,630 INFO misc.py line 117 726] Train: [17/20][456/510] Data 1.497 (3.799) Batch 16.416 (27.923) Remain 12:17:10 loss: 0.1953 loss_seg: 0.1051 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:22:37,655 INFO misc.py line 117 726] Train: [17/20][457/510] Data 2.100 (3.796) Batch 23.026 (27.913) Remain 12:16:25 loss: 0.2580 loss_seg: 0.1563 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:23:13,378 INFO misc.py line 117 726] Train: [17/20][458/510] Data 7.471 (3.804) Batch 35.722 (27.930) Remain 12:16:24 loss: 0.4394 loss_seg: 0.3317 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:23:44,209 INFO misc.py line 117 726] Train: [17/20][459/510] Data 4.121 (3.804) Batch 30.831 (27.936) Remain 12:16:06 loss: 0.2034 loss_seg: 0.1146 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:24:10,166 INFO misc.py line 117 726] Train: [17/20][460/510] Data 3.169 (3.803) Batch 25.957 (27.932) Remain 12:15:32 loss: 0.3132 loss_seg: 0.2022 loss_superpoint_edge: 0.0408 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:24:35,032 INFO misc.py line 117 726] Train: [17/20][461/510] Data 2.641 (3.800) Batch 24.867 (27.925) Remain 12:14:53 loss: 0.2056 loss_seg: 0.1181 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:25:04,347 INFO misc.py line 117 726] Train: [17/20][462/510] Data 2.977 (3.799) Batch 29.314 (27.928) Remain 12:14:30 loss: 0.2526 loss_seg: 0.1487 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:25:30,762 INFO misc.py line 117 726] Train: [17/20][463/510] Data 3.179 (3.797) Batch 26.416 (27.925) Remain 12:13:57 loss: 0.2446 loss_seg: 0.1521 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:26:06,226 INFO misc.py line 117 726] Train: [17/20][464/510] Data 5.104 (3.800) Batch 35.463 (27.941) Remain 12:13:55 loss: 0.2342 loss_seg: 0.1426 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:26:33,491 INFO misc.py line 117 726] Train: [17/20][465/510] Data 3.709 (3.800) Batch 27.265 (27.940) Remain 12:13:24 loss: 0.2005 loss_seg: 0.1125 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:26:51,170 INFO misc.py line 117 726] Train: [17/20][466/510] Data 2.142 (3.796) Batch 17.680 (27.918) Remain 12:12:22 loss: 0.2350 loss_seg: 0.1446 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:27:14,445 INFO misc.py line 117 726] Train: [17/20][467/510] Data 2.724 (3.794) Batch 23.275 (27.908) Remain 12:11:38 loss: 0.2551 loss_seg: 0.1574 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:27:45,134 INFO misc.py line 117 726] Train: [17/20][468/510] Data 3.283 (3.793) Batch 30.689 (27.913) Remain 12:11:20 loss: 0.2835 loss_seg: 0.1804 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:28:14,954 INFO misc.py line 117 726] Train: [17/20][469/510] Data 2.986 (3.791) Batch 29.820 (27.918) Remain 12:10:58 loss: 0.2418 loss_seg: 0.1458 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:28:39,680 INFO misc.py line 117 726] Train: [17/20][470/510] Data 3.156 (3.790) Batch 24.727 (27.911) Remain 12:10:19 loss: 0.3132 loss_seg: 0.2173 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:29:12,995 INFO misc.py line 117 726] Train: [17/20][471/510] Data 3.103 (3.788) Batch 33.315 (27.922) Remain 12:10:10 loss: 0.2904 loss_seg: 0.2000 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:29:43,883 INFO misc.py line 117 726] Train: [17/20][472/510] Data 3.726 (3.788) Batch 30.887 (27.929) Remain 12:09:52 loss: 0.2167 loss_seg: 0.1293 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:30:13,352 INFO misc.py line 117 726] Train: [17/20][473/510] Data 4.951 (3.791) Batch 29.469 (27.932) Remain 12:09:29 loss: 0.2157 loss_seg: 0.1286 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:30:40,050 INFO misc.py line 117 726] Train: [17/20][474/510] Data 2.934 (3.789) Batch 26.698 (27.929) Remain 12:08:57 loss: 0.3299 loss_seg: 0.2372 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:31:20,095 INFO misc.py line 117 726] Train: [17/20][475/510] Data 9.782 (3.802) Batch 40.045 (27.955) Remain 12:09:09 loss: 0.3797 loss_seg: 0.2848 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:31:53,478 INFO misc.py line 117 726] Train: [17/20][476/510] Data 2.788 (3.799) Batch 33.383 (27.966) Remain 12:08:59 loss: 0.2712 loss_seg: 0.1695 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:32:22,493 INFO misc.py line 117 726] Train: [17/20][477/510] Data 5.435 (3.803) Batch 29.015 (27.969) Remain 12:08:34 loss: 0.2176 loss_seg: 0.1215 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:32:55,049 INFO misc.py line 117 726] Train: [17/20][478/510] Data 4.950 (3.805) Batch 32.556 (27.978) Remain 12:08:22 loss: 0.2535 loss_seg: 0.1545 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:33:18,135 INFO misc.py line 117 726] Train: [17/20][479/510] Data 2.293 (3.802) Batch 23.086 (27.968) Remain 12:07:38 loss: 0.2101 loss_seg: 0.1186 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:34:01,203 INFO misc.py line 117 726] Train: [17/20][480/510] Data 10.707 (3.817) Batch 43.069 (28.000) Remain 12:07:59 loss: 0.2192 loss_seg: 0.1291 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:34:38,046 INFO misc.py line 117 726] Train: [17/20][481/510] Data 4.931 (3.819) Batch 36.843 (28.018) Remain 12:08:00 loss: 0.3492 loss_seg: 0.2525 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:35:11,626 INFO misc.py line 117 726] Train: [17/20][482/510] Data 4.837 (3.821) Batch 33.580 (28.030) Remain 12:07:50 loss: 0.2006 loss_seg: 0.1096 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:35:52,503 INFO misc.py line 117 726] Train: [17/20][483/510] Data 10.466 (3.835) Batch 40.877 (28.057) Remain 12:08:04 loss: 0.2154 loss_seg: 0.1236 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:36:22,213 INFO misc.py line 117 726] Train: [17/20][484/510] Data 3.876 (3.835) Batch 29.710 (28.060) Remain 12:07:41 loss: 0.2787 loss_seg: 0.1800 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:36:45,759 INFO misc.py line 117 726] Train: [17/20][485/510] Data 2.972 (3.833) Batch 23.546 (28.051) Remain 12:06:58 loss: 0.1803 loss_seg: 0.0941 loss_superpoint_edge: 0.0172 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:37:14,240 INFO misc.py line 117 726] Train: [17/20][486/510] Data 2.843 (3.831) Batch 28.480 (28.052) Remain 12:06:32 loss: 0.2114 loss_seg: 0.1220 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:37:44,572 INFO misc.py line 117 726] Train: [17/20][487/510] Data 6.187 (3.836) Batch 30.333 (28.056) Remain 12:06:11 loss: 0.3099 loss_seg: 0.2052 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:38:22,424 INFO misc.py line 117 726] Train: [17/20][488/510] Data 6.974 (3.842) Batch 37.851 (28.076) Remain 12:06:14 loss: 0.2817 loss_seg: 0.1828 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:38:49,792 INFO misc.py line 117 726] Train: [17/20][489/510] Data 3.166 (3.841) Batch 27.368 (28.075) Remain 12:05:44 loss: 0.2014 loss_seg: 0.1119 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:39:01,546 INFO misc.py line 117 726] Train: [17/20][490/510] Data 1.411 (3.836) Batch 11.754 (28.041) Remain 12:04:24 loss: 0.2482 loss_seg: 0.1484 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:39:33,593 INFO misc.py line 117 726] Train: [17/20][491/510] Data 4.864 (3.838) Batch 32.048 (28.050) Remain 12:04:08 loss: 0.3386 loss_seg: 0.2342 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:39:58,206 INFO misc.py line 117 726] Train: [17/20][492/510] Data 2.806 (3.836) Batch 24.613 (28.043) Remain 12:03:29 loss: 0.2119 loss_seg: 0.1209 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:40:22,302 INFO misc.py line 117 726] Train: [17/20][493/510] Data 2.548 (3.833) Batch 24.095 (28.035) Remain 12:02:49 loss: 0.2092 loss_seg: 0.1180 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:41:00,819 INFO misc.py line 117 726] Train: [17/20][494/510] Data 6.048 (3.838) Batch 38.517 (28.056) Remain 12:02:54 loss: 0.2900 loss_seg: 0.1871 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:41:22,074 INFO misc.py line 117 726] Train: [17/20][495/510] Data 2.207 (3.835) Batch 21.255 (28.042) Remain 12:02:05 loss: 0.2303 loss_seg: 0.1382 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:41:54,035 INFO misc.py line 117 726] Train: [17/20][496/510] Data 3.347 (3.834) Batch 31.962 (28.050) Remain 12:01:49 loss: 0.1915 loss_seg: 0.1059 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:42:20,773 INFO misc.py line 117 726] Train: [17/20][497/510] Data 3.223 (3.832) Batch 26.738 (28.047) Remain 12:01:17 loss: 0.2941 loss_seg: 0.2020 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:42:48,470 INFO misc.py line 117 726] Train: [17/20][498/510] Data 5.079 (3.835) Batch 27.697 (28.047) Remain 12:00:47 loss: 0.2205 loss_seg: 0.1305 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:43:16,500 INFO misc.py line 117 726] Train: [17/20][499/510] Data 3.592 (3.834) Batch 28.029 (28.047) Remain 12:00:19 loss: 0.1997 loss_seg: 0.1143 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:43:44,626 INFO misc.py line 117 726] Train: [17/20][500/510] Data 4.085 (3.835) Batch 28.127 (28.047) Remain 11:59:52 loss: 0.2040 loss_seg: 0.1180 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:43:44,627 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 13:44:15,565 INFO misc.py line 117 726] Train: [17/20][501/510] Data 4.480 (3.836) Batch 30.939 (28.053) Remain 11:59:32 loss: 0.3080 loss_seg: 0.2006 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:44:49,313 INFO misc.py line 117 726] Train: [17/20][502/510] Data 3.622 (3.836) Batch 33.748 (28.064) Remain 11:59:22 loss: 0.2384 loss_seg: 0.1488 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:45:14,426 INFO misc.py line 117 726] Train: [17/20][503/510] Data 3.712 (3.836) Batch 25.113 (28.058) Remain 11:58:45 loss: 0.3221 loss_seg: 0.2098 loss_superpoint_edge: 0.0412 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:45:36,126 INFO misc.py line 117 726] Train: [17/20][504/510] Data 2.656 (3.833) Batch 21.699 (28.045) Remain 11:57:57 loss: 0.2827 loss_seg: 0.1918 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:45:59,868 INFO misc.py line 117 726] Train: [17/20][505/510] Data 2.805 (3.831) Batch 23.742 (28.037) Remain 11:57:16 loss: 0.1815 loss_seg: 0.0966 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:46:26,158 INFO misc.py line 117 726] Train: [17/20][506/510] Data 3.387 (3.830) Batch 26.290 (28.033) Remain 11:56:43 loss: 0.2546 loss_seg: 0.1529 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:46:51,764 INFO misc.py line 117 726] Train: [17/20][507/510] Data 3.567 (3.830) Batch 25.606 (28.029) Remain 11:56:07 loss: 0.1894 loss_seg: 0.1020 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:47:26,145 INFO misc.py line 117 726] Train: [17/20][508/510] Data 3.461 (3.829) Batch 34.381 (28.041) Remain 11:55:59 loss: 0.3266 loss_seg: 0.2173 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:47:58,450 INFO misc.py line 117 726] Train: [17/20][509/510] Data 3.162 (3.828) Batch 32.305 (28.050) Remain 11:55:43 loss: 0.2130 loss_seg: 0.1201 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:48:29,271 INFO misc.py line 117 726] Train: [17/20][510/510] Data 3.551 (3.827) Batch 30.822 (28.055) Remain 11:55:24 loss: 0.2780 loss_seg: 0.1801 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 13:48:29,273 INFO misc.py line 147 726] Train result: loss: 0.2464 loss_seg: 0.1518 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 [2026-06-12 13:48:29,273 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-12 13:48:44,912 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6757 [2026-06-12 13:49:00,755 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6634 [2026-06-12 13:50:14,995 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8755 [2026-06-12 13:50:55,227 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0257 [2026-06-12 13:51:14,446 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 1.0479 [2026-06-12 13:51:50,483 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2514 [2026-06-12 13:52:36,565 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1959 [2026-06-12 13:52:51,993 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.4030 [2026-06-12 13:53:09,835 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.9322 [2026-06-12 13:53:28,379 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4248 [2026-06-12 13:53:44,118 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4665 [2026-06-12 13:54:05,772 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7478 [2026-06-12 13:54:31,525 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8846 [2026-06-12 13:54:42,928 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6906 [2026-06-12 13:55:14,162 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.1215 [2026-06-12 13:55:40,111 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.2945 [2026-06-12 13:56:06,683 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.2965 [2026-06-12 13:56:49,956 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1843 [2026-06-12 13:57:11,126 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4536 [2026-06-12 13:57:27,633 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 2.0393 [2026-06-12 13:57:58,765 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9351 [2026-06-12 13:58:15,038 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.5494 [2026-06-12 13:58:36,914 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2898 [2026-06-12 13:58:58,410 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8685 [2026-06-12 13:59:11,798 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6471 [2026-06-12 13:59:39,534 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5440 [2026-06-12 14:00:21,288 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1603 [2026-06-12 14:00:38,612 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5064 [2026-06-12 14:00:57,210 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4475 [2026-06-12 14:01:14,094 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4990 [2026-06-12 14:01:39,119 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2418 [2026-06-12 14:01:57,354 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6995 [2026-06-12 14:02:14,700 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.0950 [2026-06-12 14:02:39,131 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7573 [2026-06-12 14:02:39,148 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6703/0.7418/0.8966. [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9236/0.9573 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9763/0.9882 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8399/0.9713 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0016/0.0133 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3184/0.3789 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6036/0.6249 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6072/0.6978 [2026-06-12 14:02:39,148 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7933/0.9001 [2026-06-12 14:02:39,149 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9094/0.9516 [2026-06-12 14:02:39,149 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6768/0.7437 [2026-06-12 14:02:39,149 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7631/0.8494 [2026-06-12 14:02:39,149 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7018/0.8616 [2026-06-12 14:02:39,149 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5988/0.7059 [2026-06-12 14:02:39,149 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-12 14:02:39,150 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-12 14:02:39,150 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 14:03:16,305 INFO misc.py line 117 726] Train: [18/20][1/510] Data 5.292 (5.292) Batch 35.564 (35.564) Remain 15:06:17 loss: 0.2563 loss_seg: 0.1597 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:03:39,124 INFO misc.py line 117 726] Train: [18/20][2/510] Data 2.859 (2.859) Batch 22.820 (22.820) Remain 09:41:08 loss: 0.2657 loss_seg: 0.1636 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:04:07,192 INFO misc.py line 117 726] Train: [18/20][3/510] Data 3.772 (3.772) Batch 28.067 (28.067) Remain 11:54:19 loss: 0.2109 loss_seg: 0.1196 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:04:36,145 INFO misc.py line 117 726] Train: [18/20][4/510] Data 3.739 (3.739) Batch 28.953 (28.953) Remain 12:16:22 loss: 0.2665 loss_seg: 0.1704 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:05:00,247 INFO misc.py line 117 726] Train: [18/20][5/510] Data 2.922 (3.331) Batch 24.102 (26.528) Remain 11:14:14 loss: 0.2153 loss_seg: 0.1238 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:05:25,987 INFO misc.py line 117 726] Train: [18/20][6/510] Data 3.855 (3.505) Batch 25.740 (26.265) Remain 11:07:08 loss: 0.2033 loss_seg: 0.1151 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:05:56,982 INFO misc.py line 117 726] Train: [18/20][7/510] Data 4.157 (3.668) Batch 30.995 (27.448) Remain 11:36:42 loss: 0.2959 loss_seg: 0.1899 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:06:17,764 INFO misc.py line 117 726] Train: [18/20][8/510] Data 1.976 (3.330) Batch 20.781 (26.114) Remain 11:02:26 loss: 0.2976 loss_seg: 0.2038 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:06:42,415 INFO misc.py line 117 726] Train: [18/20][9/510] Data 2.098 (3.125) Batch 24.652 (25.871) Remain 10:55:49 loss: 0.2337 loss_seg: 0.1369 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:07:06,173 INFO misc.py line 117 726] Train: [18/20][10/510] Data 2.725 (3.068) Batch 23.757 (25.569) Remain 10:47:44 loss: 0.2535 loss_seg: 0.1632 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:07:37,744 INFO misc.py line 117 726] Train: [18/20][11/510] Data 4.012 (3.186) Batch 31.571 (26.319) Remain 11:06:18 loss: 0.3921 loss_seg: 0.2883 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0428 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:07:57,222 INFO misc.py line 117 726] Train: [18/20][12/510] Data 2.024 (3.057) Batch 19.478 (25.559) Remain 10:46:38 loss: 0.2336 loss_seg: 0.1376 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:08:26,036 INFO misc.py line 117 726] Train: [18/20][13/510] Data 2.978 (3.049) Batch 28.814 (25.884) Remain 10:54:26 loss: 0.2169 loss_seg: 0.1246 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:08:50,020 INFO misc.py line 117 726] Train: [18/20][14/510] Data 2.691 (3.016) Batch 23.983 (25.712) Remain 10:49:38 loss: 0.2084 loss_seg: 0.1195 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:09:09,768 INFO misc.py line 117 726] Train: [18/20][15/510] Data 2.187 (2.947) Batch 19.748 (25.215) Remain 10:36:40 loss: 0.2284 loss_seg: 0.1380 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:09:32,031 INFO misc.py line 117 726] Train: [18/20][16/510] Data 2.626 (2.922) Batch 22.264 (24.988) Remain 10:30:31 loss: 0.2479 loss_seg: 0.1471 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:10:01,754 INFO misc.py line 117 726] Train: [18/20][17/510] Data 4.069 (3.004) Batch 29.723 (25.326) Remain 10:38:38 loss: 0.2053 loss_seg: 0.1097 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:10:31,633 INFO misc.py line 117 726] Train: [18/20][18/510] Data 3.109 (3.011) Batch 29.879 (25.629) Remain 10:45:51 loss: 0.2464 loss_seg: 0.1482 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:10:59,792 INFO misc.py line 117 726] Train: [18/20][19/510] Data 4.755 (3.120) Batch 28.158 (25.787) Remain 10:49:24 loss: 0.2218 loss_seg: 0.1278 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:11:27,309 INFO misc.py line 117 726] Train: [18/20][20/510] Data 3.606 (3.149) Batch 27.517 (25.889) Remain 10:51:32 loss: 0.2633 loss_seg: 0.1674 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:11:54,840 INFO misc.py line 117 726] Train: [18/20][21/510] Data 2.656 (3.121) Batch 27.532 (25.980) Remain 10:53:24 loss: 0.2453 loss_seg: 0.1529 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:12:26,010 INFO misc.py line 117 726] Train: [18/20][22/510] Data 2.700 (3.099) Batch 31.170 (26.254) Remain 10:59:50 loss: 0.3131 loss_seg: 0.2075 loss_superpoint_edge: 0.0365 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:13:02,425 INFO misc.py line 117 726] Train: [18/20][23/510] Data 4.350 (3.162) Batch 36.415 (26.762) Remain 11:12:09 loss: 0.2073 loss_seg: 0.1172 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:13:33,260 INFO misc.py line 117 726] Train: [18/20][24/510] Data 3.415 (3.174) Batch 30.835 (26.956) Remain 11:16:35 loss: 0.2355 loss_seg: 0.1400 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:14:05,647 INFO misc.py line 117 726] Train: [18/20][25/510] Data 3.573 (3.192) Batch 32.387 (27.202) Remain 11:22:19 loss: 0.2481 loss_seg: 0.1492 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:14:33,158 INFO misc.py line 117 726] Train: [18/20][26/510] Data 2.820 (3.176) Batch 27.511 (27.216) Remain 11:22:12 loss: 0.2547 loss_seg: 0.1569 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:14:56,370 INFO misc.py line 117 726] Train: [18/20][27/510] Data 2.102 (3.131) Batch 23.212 (27.049) Remain 11:17:34 loss: 0.2996 loss_seg: 0.2039 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:15:26,077 INFO misc.py line 117 726] Train: [18/20][28/510] Data 4.873 (3.201) Batch 29.707 (27.155) Remain 11:19:47 loss: 0.2447 loss_seg: 0.1493 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:15:45,211 INFO misc.py line 117 726] Train: [18/20][29/510] Data 2.056 (3.157) Batch 19.134 (26.847) Remain 11:11:37 loss: 0.2171 loss_seg: 0.1211 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:16:09,998 INFO misc.py line 117 726] Train: [18/20][30/510] Data 2.246 (3.123) Batch 24.787 (26.771) Remain 11:09:15 loss: 0.2495 loss_seg: 0.1602 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:16:35,858 INFO misc.py line 117 726] Train: [18/20][31/510] Data 2.896 (3.115) Batch 25.860 (26.738) Remain 11:08:00 loss: 0.3024 loss_seg: 0.2123 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:17:09,662 INFO misc.py line 117 726] Train: [18/20][32/510] Data 4.364 (3.158) Batch 33.804 (26.982) Remain 11:13:38 loss: 0.3490 loss_seg: 0.2532 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:17:35,068 INFO misc.py line 117 726] Train: [18/20][33/510] Data 2.161 (3.125) Batch 25.406 (26.929) Remain 11:11:53 loss: 0.2425 loss_seg: 0.1495 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:17:56,700 INFO misc.py line 117 726] Train: [18/20][34/510] Data 2.409 (3.102) Batch 21.631 (26.758) Remain 11:07:10 loss: 0.2054 loss_seg: 0.1127 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:18:26,948 INFO misc.py line 117 726] Train: [18/20][35/510] Data 3.821 (3.124) Batch 30.249 (26.867) Remain 11:09:26 loss: 0.2651 loss_seg: 0.1687 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:19:01,781 INFO misc.py line 117 726] Train: [18/20][36/510] Data 4.016 (3.151) Batch 34.832 (27.109) Remain 11:15:00 loss: 0.2856 loss_seg: 0.1823 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:19:24,395 INFO misc.py line 117 726] Train: [18/20][37/510] Data 2.485 (3.132) Batch 22.614 (26.977) Remain 11:11:15 loss: 0.2824 loss_seg: 0.1855 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:19:52,798 INFO misc.py line 117 726] Train: [18/20][38/510] Data 5.004 (3.185) Batch 28.403 (27.017) Remain 11:11:49 loss: 0.2369 loss_seg: 0.1481 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:20:15,174 INFO misc.py line 117 726] Train: [18/20][39/510] Data 2.452 (3.165) Batch 22.376 (26.888) Remain 11:08:10 loss: 0.2258 loss_seg: 0.1322 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:20:44,634 INFO misc.py line 117 726] Train: [18/20][40/510] Data 3.813 (3.182) Batch 29.460 (26.958) Remain 11:09:27 loss: 0.2249 loss_seg: 0.1332 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:21:19,418 INFO misc.py line 117 726] Train: [18/20][41/510] Data 4.076 (3.206) Batch 34.784 (27.164) Remain 11:14:06 loss: 0.2506 loss_seg: 0.1526 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:21:48,261 INFO misc.py line 117 726] Train: [18/20][42/510] Data 4.318 (3.234) Batch 28.844 (27.207) Remain 11:14:43 loss: 0.2880 loss_seg: 0.1866 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:22:12,967 INFO misc.py line 117 726] Train: [18/20][43/510] Data 2.483 (3.215) Batch 24.706 (27.144) Remain 11:12:43 loss: 0.1899 loss_seg: 0.1025 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:22:45,796 INFO misc.py line 117 726] Train: [18/20][44/510] Data 5.134 (3.262) Batch 32.829 (27.283) Remain 11:15:42 loss: 0.2314 loss_seg: 0.1420 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:23:13,961 INFO misc.py line 117 726] Train: [18/20][45/510] Data 3.283 (3.263) Batch 28.166 (27.304) Remain 11:15:46 loss: 0.2365 loss_seg: 0.1459 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:23:40,264 INFO misc.py line 117 726] Train: [18/20][46/510] Data 3.036 (3.257) Batch 26.303 (27.281) Remain 11:14:44 loss: 0.2250 loss_seg: 0.1333 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:24:12,888 INFO misc.py line 117 726] Train: [18/20][47/510] Data 9.419 (3.398) Batch 32.623 (27.402) Remain 11:17:17 loss: 0.2371 loss_seg: 0.1399 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:24:39,792 INFO misc.py line 117 726] Train: [18/20][48/510] Data 3.607 (3.402) Batch 26.903 (27.391) Remain 11:16:33 loss: 0.2494 loss_seg: 0.1490 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:25:08,296 INFO misc.py line 117 726] Train: [18/20][49/510] Data 3.542 (3.405) Batch 28.505 (27.415) Remain 11:16:42 loss: 0.2998 loss_seg: 0.1875 loss_superpoint_edge: 0.0433 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:25:35,451 INFO misc.py line 117 726] Train: [18/20][50/510] Data 2.827 (3.393) Batch 27.155 (27.410) Remain 11:16:06 loss: 0.2761 loss_seg: 0.1664 loss_superpoint_edge: 0.0412 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:25:35,451 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 14:26:06,359 INFO misc.py line 117 726] Train: [18/20][51/510] Data 6.854 (3.465) Batch 30.908 (27.483) Remain 11:17:26 loss: 0.2206 loss_seg: 0.1250 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:26:29,198 INFO misc.py line 117 726] Train: [18/20][52/510] Data 2.540 (3.446) Batch 22.839 (27.388) Remain 11:14:39 loss: 0.2246 loss_seg: 0.1310 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:26:56,238 INFO misc.py line 117 726] Train: [18/20][53/510] Data 3.331 (3.444) Batch 27.041 (27.381) Remain 11:14:01 loss: 0.1939 loss_seg: 0.1070 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:27:18,740 INFO misc.py line 117 726] Train: [18/20][54/510] Data 2.466 (3.425) Batch 22.502 (27.285) Remain 11:11:13 loss: 0.1879 loss_seg: 0.0986 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:27:45,395 INFO misc.py line 117 726] Train: [18/20][55/510] Data 2.427 (3.405) Batch 26.654 (27.273) Remain 11:10:27 loss: 0.2297 loss_seg: 0.1328 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:28:05,856 INFO misc.py line 117 726] Train: [18/20][56/510] Data 1.755 (3.374) Batch 20.461 (27.145) Remain 11:06:51 loss: 0.1789 loss_seg: 0.0885 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:28:35,532 INFO misc.py line 117 726] Train: [18/20][57/510] Data 3.148 (3.370) Batch 29.677 (27.191) Remain 11:07:33 loss: 0.1944 loss_seg: 0.1053 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:29:03,113 INFO misc.py line 117 726] Train: [18/20][58/510] Data 2.799 (3.360) Batch 27.580 (27.199) Remain 11:07:16 loss: 0.1700 loss_seg: 0.0882 loss_superpoint_edge: 0.0146 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:29:31,382 INFO misc.py line 117 726] Train: [18/20][59/510] Data 3.670 (3.365) Batch 28.269 (27.218) Remain 11:07:17 loss: 0.2181 loss_seg: 0.1256 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:30:05,359 INFO misc.py line 117 726] Train: [18/20][60/510] Data 3.945 (3.375) Batch 33.977 (27.336) Remain 11:09:44 loss: 0.2418 loss_seg: 0.1535 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:30:36,199 INFO misc.py line 117 726] Train: [18/20][61/510] Data 8.426 (3.463) Batch 30.840 (27.397) Remain 11:10:45 loss: 0.5784 loss_seg: 0.4281 loss_superpoint_edge: 0.0798 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:31:00,501 INFO misc.py line 117 726] Train: [18/20][62/510] Data 2.636 (3.449) Batch 24.302 (27.344) Remain 11:09:01 loss: 0.2872 loss_seg: 0.1795 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:31:21,358 INFO misc.py line 117 726] Train: [18/20][63/510] Data 1.933 (3.423) Batch 20.857 (27.236) Remain 11:05:55 loss: 0.2500 loss_seg: 0.1539 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:31:55,790 INFO misc.py line 117 726] Train: [18/20][64/510] Data 2.614 (3.410) Batch 34.431 (27.354) Remain 11:08:21 loss: 0.1839 loss_seg: 0.0996 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:32:11,716 INFO misc.py line 117 726] Train: [18/20][65/510] Data 1.970 (3.387) Batch 15.926 (27.170) Remain 11:03:23 loss: 0.2207 loss_seg: 0.1273 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:32:44,832 INFO misc.py line 117 726] Train: [18/20][66/510] Data 4.546 (3.405) Batch 33.116 (27.264) Remain 11:05:14 loss: 0.2475 loss_seg: 0.1561 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:33:12,166 INFO misc.py line 117 726] Train: [18/20][67/510] Data 3.842 (3.412) Batch 27.334 (27.265) Remain 11:04:49 loss: 0.2886 loss_seg: 0.1811 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:33:30,909 INFO misc.py line 117 726] Train: [18/20][68/510] Data 2.281 (3.395) Batch 18.743 (27.134) Remain 11:01:10 loss: 0.1999 loss_seg: 0.1144 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:34:05,231 INFO misc.py line 117 726] Train: [18/20][69/510] Data 5.631 (3.429) Batch 34.323 (27.243) Remain 11:03:22 loss: 0.2438 loss_seg: 0.1513 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:34:29,432 INFO misc.py line 117 726] Train: [18/20][70/510] Data 2.769 (3.419) Batch 24.201 (27.198) Remain 11:01:48 loss: 0.2170 loss_seg: 0.1266 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:34:50,731 INFO misc.py line 117 726] Train: [18/20][71/510] Data 2.535 (3.406) Batch 21.298 (27.111) Remain 10:59:14 loss: 0.1678 loss_seg: 0.0852 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:35:15,175 INFO misc.py line 117 726] Train: [18/20][72/510] Data 3.087 (3.401) Batch 24.444 (27.072) Remain 10:57:51 loss: 0.2496 loss_seg: 0.1550 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:35:32,789 INFO misc.py line 117 726] Train: [18/20][73/510] Data 2.315 (3.386) Batch 17.614 (26.937) Remain 10:54:07 loss: 0.2303 loss_seg: 0.1453 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:35:59,128 INFO misc.py line 117 726] Train: [18/20][74/510] Data 2.953 (3.379) Batch 26.339 (26.929) Remain 10:53:28 loss: 0.2405 loss_seg: 0.1509 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:36:25,382 INFO misc.py line 117 726] Train: [18/20][75/510] Data 3.985 (3.388) Batch 26.254 (26.919) Remain 10:52:47 loss: 0.2116 loss_seg: 0.1224 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:36:54,730 INFO misc.py line 117 726] Train: [18/20][76/510] Data 5.718 (3.420) Batch 29.348 (26.953) Remain 10:53:09 loss: 0.2389 loss_seg: 0.1432 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:37:34,269 INFO misc.py line 117 726] Train: [18/20][77/510] Data 7.464 (3.474) Batch 39.539 (27.123) Remain 10:56:49 loss: 0.2490 loss_seg: 0.1525 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:37:56,591 INFO misc.py line 117 726] Train: [18/20][78/510] Data 2.564 (3.462) Batch 22.322 (27.059) Remain 10:54:49 loss: 0.1923 loss_seg: 0.1033 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:38:18,515 INFO misc.py line 117 726] Train: [18/20][79/510] Data 3.102 (3.458) Batch 21.925 (26.991) Remain 10:52:44 loss: 0.2564 loss_seg: 0.1586 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:38:48,613 INFO misc.py line 117 726] Train: [18/20][80/510] Data 3.604 (3.459) Batch 30.097 (27.031) Remain 10:53:15 loss: 0.3053 loss_seg: 0.1941 loss_superpoint_edge: 0.0436 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:39:23,227 INFO misc.py line 117 726] Train: [18/20][81/510] Data 4.317 (3.470) Batch 34.614 (27.129) Remain 10:55:09 loss: 0.2388 loss_seg: 0.1408 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:39:50,611 INFO misc.py line 117 726] Train: [18/20][82/510] Data 2.100 (3.453) Batch 27.384 (27.132) Remain 10:54:46 loss: 0.2110 loss_seg: 0.1195 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:40:12,021 INFO misc.py line 117 726] Train: [18/20][83/510] Data 3.637 (3.455) Batch 21.410 (27.060) Remain 10:52:36 loss: 0.2572 loss_seg: 0.1620 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:40:42,279 INFO misc.py line 117 726] Train: [18/20][84/510] Data 4.317 (3.466) Batch 30.258 (27.100) Remain 10:53:06 loss: 0.2507 loss_seg: 0.1573 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:41:12,186 INFO misc.py line 117 726] Train: [18/20][85/510] Data 2.795 (3.458) Batch 29.907 (27.134) Remain 10:53:28 loss: 0.2426 loss_seg: 0.1436 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:41:37,615 INFO misc.py line 117 726] Train: [18/20][86/510] Data 2.731 (3.449) Batch 25.429 (27.114) Remain 10:52:31 loss: 0.1904 loss_seg: 0.1039 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:42:01,065 INFO misc.py line 117 726] Train: [18/20][87/510] Data 2.345 (3.436) Batch 23.449 (27.070) Remain 10:51:01 loss: 0.2519 loss_seg: 0.1513 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:42:30,591 INFO misc.py line 117 726] Train: [18/20][88/510] Data 3.919 (3.442) Batch 29.527 (27.099) Remain 10:51:16 loss: 0.2725 loss_seg: 0.1759 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:43:04,134 INFO misc.py line 117 726] Train: [18/20][89/510] Data 4.099 (3.449) Batch 33.542 (27.174) Remain 10:52:37 loss: 0.2745 loss_seg: 0.1718 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:43:33,832 INFO misc.py line 117 726] Train: [18/20][90/510] Data 3.126 (3.446) Batch 29.698 (27.203) Remain 10:52:51 loss: 0.2423 loss_seg: 0.1483 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:44:06,946 INFO misc.py line 117 726] Train: [18/20][91/510] Data 4.879 (3.462) Batch 33.114 (27.270) Remain 10:54:01 loss: 0.2839 loss_seg: 0.1844 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:44:37,989 INFO misc.py line 117 726] Train: [18/20][92/510] Data 4.992 (3.479) Batch 31.043 (27.312) Remain 10:54:35 loss: 0.2183 loss_seg: 0.1220 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:45:13,549 INFO misc.py line 117 726] Train: [18/20][93/510] Data 5.232 (3.499) Batch 35.560 (27.404) Remain 10:56:19 loss: 0.2697 loss_seg: 0.1700 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:45:30,162 INFO misc.py line 117 726] Train: [18/20][94/510] Data 2.231 (3.485) Batch 16.613 (27.285) Remain 10:53:01 loss: 0.2522 loss_seg: 0.1538 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:45:56,764 INFO misc.py line 117 726] Train: [18/20][95/510] Data 3.384 (3.483) Batch 26.603 (27.278) Remain 10:52:23 loss: 0.2228 loss_seg: 0.1303 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:46:29,361 INFO misc.py line 117 726] Train: [18/20][96/510] Data 3.678 (3.486) Batch 32.597 (27.335) Remain 10:53:18 loss: 0.3570 loss_seg: 0.2645 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:46:52,856 INFO misc.py line 117 726] Train: [18/20][97/510] Data 2.669 (3.477) Batch 23.495 (27.294) Remain 10:51:52 loss: 0.2410 loss_seg: 0.1467 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:47:24,722 INFO misc.py line 117 726] Train: [18/20][98/510] Data 6.214 (3.506) Batch 31.866 (27.342) Remain 10:52:34 loss: 0.2828 loss_seg: 0.1830 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:47:52,535 INFO misc.py line 117 726] Train: [18/20][99/510] Data 2.771 (3.498) Batch 27.813 (27.347) Remain 10:52:14 loss: 0.1768 loss_seg: 0.0934 loss_superpoint_edge: 0.0141 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:48:28,670 INFO misc.py line 117 726] Train: [18/20][100/510] Data 3.452 (3.498) Batch 36.135 (27.438) Remain 10:53:56 loss: 0.2019 loss_seg: 0.1117 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:48:28,670 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 14:48:55,840 INFO misc.py line 117 726] Train: [18/20][101/510] Data 3.825 (3.501) Batch 27.170 (27.435) Remain 10:53:24 loss: 0.2135 loss_seg: 0.1224 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:49:28,990 INFO misc.py line 117 726] Train: [18/20][102/510] Data 6.866 (3.535) Batch 33.150 (27.493) Remain 10:54:19 loss: 0.2183 loss_seg: 0.1264 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:49:56,387 INFO misc.py line 117 726] Train: [18/20][103/510] Data 3.704 (3.537) Batch 27.397 (27.492) Remain 10:53:51 loss: 0.2267 loss_seg: 0.1310 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:50:27,799 INFO misc.py line 117 726] Train: [18/20][104/510] Data 3.124 (3.533) Batch 31.412 (27.531) Remain 10:54:18 loss: 0.2119 loss_seg: 0.1218 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:50:55,638 INFO misc.py line 117 726] Train: [18/20][105/510] Data 3.289 (3.530) Batch 27.840 (27.534) Remain 10:53:55 loss: 0.2064 loss_seg: 0.1173 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:51:33,367 INFO misc.py line 117 726] Train: [18/20][106/510] Data 9.208 (3.585) Batch 37.729 (27.633) Remain 10:55:49 loss: 0.2775 loss_seg: 0.1745 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:52:06,741 INFO misc.py line 117 726] Train: [18/20][107/510] Data 4.009 (3.589) Batch 33.374 (27.688) Remain 10:56:39 loss: 0.2599 loss_seg: 0.1638 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:52:35,612 INFO misc.py line 117 726] Train: [18/20][108/510] Data 2.963 (3.583) Batch 28.871 (27.699) Remain 10:56:28 loss: 0.2032 loss_seg: 0.1143 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:53:02,042 INFO misc.py line 117 726] Train: [18/20][109/510] Data 2.611 (3.574) Batch 26.430 (27.687) Remain 10:55:43 loss: 0.2350 loss_seg: 0.1375 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:53:33,585 INFO misc.py line 117 726] Train: [18/20][110/510] Data 4.647 (3.584) Batch 31.543 (27.723) Remain 10:56:07 loss: 0.2486 loss_seg: 0.1552 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:53:56,257 INFO misc.py line 117 726] Train: [18/20][111/510] Data 2.543 (3.575) Batch 22.672 (27.677) Remain 10:54:32 loss: 0.2215 loss_seg: 0.1298 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:54:30,634 INFO misc.py line 117 726] Train: [18/20][112/510] Data 5.028 (3.588) Batch 34.377 (27.738) Remain 10:55:32 loss: 0.2541 loss_seg: 0.1544 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:55:04,185 INFO misc.py line 117 726] Train: [18/20][113/510] Data 4.949 (3.600) Batch 33.552 (27.791) Remain 10:56:19 loss: 0.2074 loss_seg: 0.1181 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:55:42,041 INFO misc.py line 117 726] Train: [18/20][114/510] Data 5.190 (3.615) Batch 37.855 (27.882) Remain 10:58:00 loss: 0.2529 loss_seg: 0.1578 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:56:04,070 INFO misc.py line 117 726] Train: [18/20][115/510] Data 2.656 (3.606) Batch 22.029 (27.829) Remain 10:56:18 loss: 0.2270 loss_seg: 0.1391 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:56:29,935 INFO misc.py line 117 726] Train: [18/20][116/510] Data 3.664 (3.607) Batch 25.866 (27.812) Remain 10:55:26 loss: 0.1715 loss_seg: 0.0893 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:56:55,954 INFO misc.py line 117 726] Train: [18/20][117/510] Data 3.249 (3.603) Batch 26.019 (27.796) Remain 10:54:35 loss: 0.2473 loss_seg: 0.1529 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:57:28,106 INFO misc.py line 117 726] Train: [18/20][118/510] Data 4.600 (3.612) Batch 32.152 (27.834) Remain 10:55:01 loss: 0.2613 loss_seg: 0.1592 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:57:56,165 INFO misc.py line 117 726] Train: [18/20][119/510] Data 3.548 (3.612) Batch 28.059 (27.836) Remain 10:54:36 loss: 0.3018 loss_seg: 0.1998 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:58:14,539 INFO misc.py line 117 726] Train: [18/20][120/510] Data 1.993 (3.598) Batch 18.374 (27.755) Remain 10:52:14 loss: 0.2049 loss_seg: 0.1121 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:58:47,129 INFO misc.py line 117 726] Train: [18/20][121/510] Data 3.948 (3.601) Batch 32.590 (27.796) Remain 10:52:44 loss: 0.2500 loss_seg: 0.1598 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:59:12,132 INFO misc.py line 117 726] Train: [18/20][122/510] Data 3.148 (3.597) Batch 25.003 (27.773) Remain 10:51:43 loss: 0.2404 loss_seg: 0.1426 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 14:59:33,017 INFO misc.py line 117 726] Train: [18/20][123/510] Data 2.704 (3.589) Batch 20.885 (27.715) Remain 10:49:55 loss: 0.3050 loss_seg: 0.1993 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:00:02,958 INFO misc.py line 117 726] Train: [18/20][124/510] Data 4.736 (3.599) Batch 29.942 (27.734) Remain 10:49:53 loss: 0.2730 loss_seg: 0.1800 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:00:34,296 INFO misc.py line 117 726] Train: [18/20][125/510] Data 5.045 (3.611) Batch 31.338 (27.763) Remain 10:50:07 loss: 0.2295 loss_seg: 0.1345 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:00:55,834 INFO misc.py line 117 726] Train: [18/20][126/510] Data 2.157 (3.599) Batch 21.538 (27.713) Remain 10:48:28 loss: 0.2301 loss_seg: 0.1360 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:01:24,904 INFO misc.py line 117 726] Train: [18/20][127/510] Data 3.482 (3.598) Batch 29.070 (27.723) Remain 10:48:16 loss: 0.2004 loss_seg: 0.1093 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:01:50,809 INFO misc.py line 117 726] Train: [18/20][128/510] Data 3.086 (3.594) Batch 25.906 (27.709) Remain 10:47:27 loss: 0.2186 loss_seg: 0.1254 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:02:11,889 INFO misc.py line 117 726] Train: [18/20][129/510] Data 2.784 (3.587) Batch 21.080 (27.656) Remain 10:45:46 loss: 0.2093 loss_seg: 0.1201 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:02:44,496 INFO misc.py line 117 726] Train: [18/20][130/510] Data 4.307 (3.593) Batch 32.606 (27.695) Remain 10:46:13 loss: 0.2440 loss_seg: 0.1501 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:03:20,463 INFO misc.py line 117 726] Train: [18/20][131/510] Data 5.139 (3.605) Batch 35.968 (27.760) Remain 10:47:16 loss: 0.2436 loss_seg: 0.1501 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:03:53,561 INFO misc.py line 117 726] Train: [18/20][132/510] Data 3.820 (3.607) Batch 33.097 (27.801) Remain 10:47:46 loss: 0.2221 loss_seg: 0.1388 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:04:20,955 INFO misc.py line 117 726] Train: [18/20][133/510] Data 5.286 (3.620) Batch 27.394 (27.798) Remain 10:47:14 loss: 0.2939 loss_seg: 0.1906 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:04:46,087 INFO misc.py line 117 726] Train: [18/20][134/510] Data 3.065 (3.616) Batch 25.132 (27.778) Remain 10:46:17 loss: 0.2959 loss_seg: 0.2111 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:05:09,765 INFO misc.py line 117 726] Train: [18/20][135/510] Data 2.325 (3.606) Batch 23.678 (27.747) Remain 10:45:06 loss: 0.3028 loss_seg: 0.2048 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:05:39,026 INFO misc.py line 117 726] Train: [18/20][136/510] Data 4.896 (3.615) Batch 29.261 (27.758) Remain 10:44:54 loss: 0.3137 loss_seg: 0.2150 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:06:08,473 INFO misc.py line 117 726] Train: [18/20][137/510] Data 3.039 (3.611) Batch 29.447 (27.771) Remain 10:44:44 loss: 0.2076 loss_seg: 0.1222 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:06:38,811 INFO misc.py line 117 726] Train: [18/20][138/510] Data 3.637 (3.611) Batch 30.338 (27.790) Remain 10:44:43 loss: 0.2424 loss_seg: 0.1432 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:07:08,359 INFO misc.py line 117 726] Train: [18/20][139/510] Data 4.929 (3.621) Batch 29.548 (27.803) Remain 10:44:33 loss: 0.2392 loss_seg: 0.1445 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:07:24,619 INFO misc.py line 117 726] Train: [18/20][140/510] Data 2.383 (3.612) Batch 16.260 (27.718) Remain 10:42:08 loss: 0.2830 loss_seg: 0.1821 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:07:44,455 INFO misc.py line 117 726] Train: [18/20][141/510] Data 1.435 (3.596) Batch 19.835 (27.661) Remain 10:40:21 loss: 0.2617 loss_seg: 0.1653 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:08:18,279 INFO misc.py line 117 726] Train: [18/20][142/510] Data 5.508 (3.610) Batch 33.824 (27.706) Remain 10:40:55 loss: 0.2643 loss_seg: 0.1657 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:08:52,493 INFO misc.py line 117 726] Train: [18/20][143/510] Data 5.069 (3.620) Batch 34.214 (27.752) Remain 10:41:32 loss: 0.2158 loss_seg: 0.1268 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:09:32,949 INFO misc.py line 117 726] Train: [18/20][144/510] Data 6.831 (3.643) Batch 40.456 (27.842) Remain 10:43:09 loss: 0.2051 loss_seg: 0.1148 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:09:56,899 INFO misc.py line 117 726] Train: [18/20][145/510] Data 2.516 (3.635) Batch 23.951 (27.815) Remain 10:42:03 loss: 0.2157 loss_seg: 0.1229 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:10:20,575 INFO misc.py line 117 726] Train: [18/20][146/510] Data 2.417 (3.627) Batch 23.676 (27.786) Remain 10:40:55 loss: 0.3206 loss_seg: 0.2116 loss_superpoint_edge: 0.0421 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:10:47,555 INFO misc.py line 117 726] Train: [18/20][147/510] Data 3.131 (3.623) Batch 26.980 (27.780) Remain 10:40:20 loss: 0.2821 loss_seg: 0.1867 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:11:19,890 INFO misc.py line 117 726] Train: [18/20][148/510] Data 5.016 (3.633) Batch 32.335 (27.812) Remain 10:40:35 loss: 0.2720 loss_seg: 0.1804 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:11:49,673 INFO misc.py line 117 726] Train: [18/20][149/510] Data 4.094 (3.636) Batch 29.783 (27.825) Remain 10:40:26 loss: 0.2137 loss_seg: 0.1256 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:12:19,687 INFO misc.py line 117 726] Train: [18/20][150/510] Data 3.038 (3.632) Batch 30.013 (27.840) Remain 10:40:19 loss: 0.2339 loss_seg: 0.1349 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:12:19,687 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 15:12:45,913 INFO misc.py line 117 726] Train: [18/20][151/510] Data 2.949 (3.627) Batch 26.226 (27.829) Remain 10:39:36 loss: 0.2231 loss_seg: 0.1329 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:13:14,618 INFO misc.py line 117 726] Train: [18/20][152/510] Data 3.567 (3.627) Batch 28.705 (27.835) Remain 10:39:16 loss: 0.2157 loss_seg: 0.1260 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:13:40,058 INFO misc.py line 117 726] Train: [18/20][153/510] Data 2.733 (3.621) Batch 25.440 (27.819) Remain 10:38:26 loss: 0.2462 loss_seg: 0.1476 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:14:12,175 INFO misc.py line 117 726] Train: [18/20][154/510] Data 4.011 (3.624) Batch 32.116 (27.848) Remain 10:38:38 loss: 0.2721 loss_seg: 0.1674 loss_superpoint_edge: 0.0382 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:14:47,548 INFO misc.py line 117 726] Train: [18/20][155/510] Data 4.126 (3.627) Batch 35.373 (27.897) Remain 10:39:18 loss: 0.2764 loss_seg: 0.1710 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:15:12,119 INFO misc.py line 117 726] Train: [18/20][156/510] Data 2.554 (3.620) Batch 24.571 (27.875) Remain 10:38:20 loss: 0.1901 loss_seg: 0.1034 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:15:43,726 INFO misc.py line 117 726] Train: [18/20][157/510] Data 3.175 (3.617) Batch 31.607 (27.900) Remain 10:38:26 loss: 0.2635 loss_seg: 0.1698 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:16:03,941 INFO misc.py line 117 726] Train: [18/20][158/510] Data 2.497 (3.610) Batch 20.215 (27.850) Remain 10:36:50 loss: 0.2158 loss_seg: 0.1219 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0426 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:16:30,320 INFO misc.py line 117 726] Train: [18/20][159/510] Data 2.590 (3.603) Batch 26.379 (27.841) Remain 10:36:09 loss: 0.2254 loss_seg: 0.1305 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:16:53,782 INFO misc.py line 117 726] Train: [18/20][160/510] Data 3.134 (3.600) Batch 23.462 (27.813) Remain 10:35:03 loss: 0.2220 loss_seg: 0.1284 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:17:30,246 INFO misc.py line 117 726] Train: [18/20][161/510] Data 4.333 (3.605) Batch 36.464 (27.867) Remain 10:35:50 loss: 0.2358 loss_seg: 0.1417 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:17:58,529 INFO misc.py line 117 726] Train: [18/20][162/510] Data 2.195 (3.596) Batch 28.283 (27.870) Remain 10:35:26 loss: 0.1902 loss_seg: 0.1035 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:18:24,349 INFO misc.py line 117 726] Train: [18/20][163/510] Data 2.779 (3.591) Batch 25.819 (27.857) Remain 10:34:40 loss: 0.1997 loss_seg: 0.1121 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:19:01,966 INFO misc.py line 117 726] Train: [18/20][164/510] Data 8.821 (3.623) Batch 37.618 (27.918) Remain 10:35:35 loss: 0.4416 loss_seg: 0.3445 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:19:26,743 INFO misc.py line 117 726] Train: [18/20][165/510] Data 3.367 (3.622) Batch 24.776 (27.898) Remain 10:34:41 loss: 0.2320 loss_seg: 0.1377 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:19:50,810 INFO misc.py line 117 726] Train: [18/20][166/510] Data 3.078 (3.618) Batch 24.067 (27.875) Remain 10:33:41 loss: 0.2600 loss_seg: 0.1516 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:20:20,485 INFO misc.py line 117 726] Train: [18/20][167/510] Data 2.715 (3.613) Batch 29.675 (27.886) Remain 10:33:28 loss: 0.2432 loss_seg: 0.1420 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:20:52,103 INFO misc.py line 117 726] Train: [18/20][168/510] Data 3.718 (3.614) Batch 31.618 (27.909) Remain 10:33:31 loss: 0.2300 loss_seg: 0.1332 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:21:13,732 INFO misc.py line 117 726] Train: [18/20][169/510] Data 2.849 (3.609) Batch 21.629 (27.871) Remain 10:32:12 loss: 0.2293 loss_seg: 0.1380 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:21:35,822 INFO misc.py line 117 726] Train: [18/20][170/510] Data 2.520 (3.602) Batch 22.090 (27.836) Remain 10:30:57 loss: 0.2353 loss_seg: 0.1412 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:21:59,871 INFO misc.py line 117 726] Train: [18/20][171/510] Data 2.412 (3.595) Batch 24.049 (27.814) Remain 10:29:58 loss: 0.2356 loss_seg: 0.1380 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:22:28,520 INFO misc.py line 117 726] Train: [18/20][172/510] Data 5.117 (3.604) Batch 28.649 (27.819) Remain 10:29:37 loss: 0.2871 loss_seg: 0.1790 loss_superpoint_edge: 0.0396 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:22:47,978 INFO misc.py line 117 726] Train: [18/20][173/510] Data 2.312 (3.597) Batch 19.457 (27.769) Remain 10:28:02 loss: 0.2325 loss_seg: 0.1358 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:23:17,849 INFO misc.py line 117 726] Train: [18/20][174/510] Data 2.821 (3.592) Batch 29.872 (27.782) Remain 10:27:51 loss: 0.2311 loss_seg: 0.1395 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:23:43,746 INFO misc.py line 117 726] Train: [18/20][175/510] Data 2.930 (3.588) Batch 25.897 (27.771) Remain 10:27:09 loss: 0.2396 loss_seg: 0.1457 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:24:15,215 INFO misc.py line 117 726] Train: [18/20][176/510] Data 3.633 (3.589) Batch 31.468 (27.792) Remain 10:27:10 loss: 0.2352 loss_seg: 0.1412 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:24:41,860 INFO misc.py line 117 726] Train: [18/20][177/510] Data 5.015 (3.597) Batch 26.645 (27.785) Remain 10:26:33 loss: 0.3007 loss_seg: 0.2042 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:25:16,825 INFO misc.py line 117 726] Train: [18/20][178/510] Data 3.755 (3.598) Batch 34.965 (27.826) Remain 10:27:01 loss: 0.2207 loss_seg: 0.1296 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:25:51,219 INFO misc.py line 117 726] Train: [18/20][179/510] Data 3.436 (3.597) Batch 34.394 (27.864) Remain 10:27:23 loss: 0.2996 loss_seg: 0.2059 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:26:27,345 INFO misc.py line 117 726] Train: [18/20][180/510] Data 6.589 (3.614) Batch 36.126 (27.910) Remain 10:27:59 loss: 0.2042 loss_seg: 0.1176 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:26:45,313 INFO misc.py line 117 726] Train: [18/20][181/510] Data 1.871 (3.604) Batch 17.968 (27.855) Remain 10:26:15 loss: 0.2231 loss_seg: 0.1316 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:27:16,999 INFO misc.py line 117 726] Train: [18/20][182/510] Data 3.555 (3.604) Batch 31.686 (27.876) Remain 10:26:16 loss: 0.2061 loss_seg: 0.1160 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:27:47,680 INFO misc.py line 117 726] Train: [18/20][183/510] Data 3.171 (3.601) Batch 30.682 (27.892) Remain 10:26:09 loss: 0.2410 loss_seg: 0.1524 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:28:17,834 INFO misc.py line 117 726] Train: [18/20][184/510] Data 3.152 (3.599) Batch 30.154 (27.904) Remain 10:25:58 loss: 0.2179 loss_seg: 0.1285 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:28:41,300 INFO misc.py line 117 726] Train: [18/20][185/510] Data 3.379 (3.598) Batch 23.466 (27.880) Remain 10:24:58 loss: 0.3186 loss_seg: 0.2217 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:29:10,080 INFO misc.py line 117 726] Train: [18/20][186/510] Data 3.375 (3.596) Batch 28.780 (27.885) Remain 10:24:36 loss: 0.2183 loss_seg: 0.1288 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:29:36,763 INFO misc.py line 117 726] Train: [18/20][187/510] Data 2.726 (3.592) Batch 26.683 (27.878) Remain 10:24:00 loss: 0.2180 loss_seg: 0.1256 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:30:04,862 INFO misc.py line 117 726] Train: [18/20][188/510] Data 5.384 (3.601) Batch 28.099 (27.879) Remain 10:23:34 loss: 0.2347 loss_seg: 0.1440 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:30:39,920 INFO misc.py line 117 726] Train: [18/20][189/510] Data 7.193 (3.621) Batch 35.058 (27.918) Remain 10:23:57 loss: 0.2760 loss_seg: 0.1824 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0449 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:31:03,445 INFO misc.py line 117 726] Train: [18/20][190/510] Data 3.612 (3.621) Batch 23.526 (27.894) Remain 10:22:58 loss: 0.3120 loss_seg: 0.2052 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:31:33,701 INFO misc.py line 117 726] Train: [18/20][191/510] Data 5.303 (3.630) Batch 30.255 (27.907) Remain 10:22:47 loss: 0.2592 loss_seg: 0.1596 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:32:00,759 INFO misc.py line 117 726] Train: [18/20][192/510] Data 3.195 (3.627) Batch 27.058 (27.902) Remain 10:22:13 loss: 0.2264 loss_seg: 0.1319 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:32:23,017 INFO misc.py line 117 726] Train: [18/20][193/510] Data 2.849 (3.623) Batch 22.258 (27.873) Remain 10:21:05 loss: 0.2839 loss_seg: 0.1789 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:32:40,977 INFO misc.py line 117 726] Train: [18/20][194/510] Data 2.145 (3.615) Batch 17.959 (27.821) Remain 10:19:28 loss: 0.3217 loss_seg: 0.2259 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:33:03,862 INFO misc.py line 117 726] Train: [18/20][195/510] Data 2.366 (3.609) Batch 22.885 (27.795) Remain 10:18:26 loss: 0.2182 loss_seg: 0.1240 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:33:37,519 INFO misc.py line 117 726] Train: [18/20][196/510] Data 3.853 (3.610) Batch 33.657 (27.826) Remain 10:18:39 loss: 0.2477 loss_seg: 0.1539 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:34:00,269 INFO misc.py line 117 726] Train: [18/20][197/510] Data 3.185 (3.608) Batch 22.750 (27.799) Remain 10:17:36 loss: 0.2278 loss_seg: 0.1336 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:34:29,108 INFO misc.py line 117 726] Train: [18/20][198/510] Data 3.546 (3.608) Batch 28.839 (27.805) Remain 10:17:15 loss: 0.3646 loss_seg: 0.2620 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:34:59,934 INFO misc.py line 117 726] Train: [18/20][199/510] Data 3.303 (3.606) Batch 30.826 (27.820) Remain 10:17:08 loss: 0.2095 loss_seg: 0.1165 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:35:32,113 INFO misc.py line 117 726] Train: [18/20][200/510] Data 3.043 (3.603) Batch 32.179 (27.842) Remain 10:17:10 loss: 0.2270 loss_seg: 0.1355 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:35:32,114 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 15:35:57,318 INFO misc.py line 117 726] Train: [18/20][201/510] Data 3.350 (3.602) Batch 25.205 (27.829) Remain 10:16:24 loss: 0.2883 loss_seg: 0.1853 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:36:25,157 INFO misc.py line 117 726] Train: [18/20][202/510] Data 3.721 (3.603) Batch 27.838 (27.829) Remain 10:15:56 loss: 0.2001 loss_seg: 0.1105 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:36:55,177 INFO misc.py line 117 726] Train: [18/20][203/510] Data 3.883 (3.604) Batch 30.020 (27.840) Remain 10:15:43 loss: 0.2075 loss_seg: 0.1195 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:37:36,807 INFO misc.py line 117 726] Train: [18/20][204/510] Data 8.169 (3.627) Batch 41.630 (27.909) Remain 10:16:46 loss: 0.3216 loss_seg: 0.2154 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:38:03,693 INFO misc.py line 117 726] Train: [18/20][205/510] Data 2.284 (3.620) Batch 26.886 (27.903) Remain 10:16:12 loss: 0.2140 loss_seg: 0.1213 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:38:30,032 INFO misc.py line 117 726] Train: [18/20][206/510] Data 5.806 (3.631) Batch 26.339 (27.896) Remain 10:15:33 loss: 0.2016 loss_seg: 0.1114 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:39:04,419 INFO misc.py line 117 726] Train: [18/20][207/510] Data 3.861 (3.632) Batch 34.387 (27.928) Remain 10:15:48 loss: 0.2395 loss_seg: 0.1464 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:39:39,052 INFO misc.py line 117 726] Train: [18/20][208/510] Data 8.353 (3.655) Batch 34.633 (27.960) Remain 10:16:03 loss: 0.2591 loss_seg: 0.1656 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:40:09,036 INFO misc.py line 117 726] Train: [18/20][209/510] Data 3.299 (3.653) Batch 29.984 (27.970) Remain 10:15:48 loss: 0.2574 loss_seg: 0.1689 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:40:40,759 INFO misc.py line 117 726] Train: [18/20][210/510] Data 3.549 (3.653) Batch 31.724 (27.988) Remain 10:15:44 loss: 0.2160 loss_seg: 0.1230 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:41:09,128 INFO misc.py line 117 726] Train: [18/20][211/510] Data 4.107 (3.655) Batch 28.368 (27.990) Remain 10:15:18 loss: 0.2303 loss_seg: 0.1419 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:41:34,282 INFO misc.py line 117 726] Train: [18/20][212/510] Data 3.793 (3.656) Batch 25.154 (27.977) Remain 10:14:33 loss: 0.1891 loss_seg: 0.1022 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:42:10,442 INFO misc.py line 117 726] Train: [18/20][213/510] Data 2.873 (3.652) Batch 36.160 (28.015) Remain 10:14:56 loss: 0.1754 loss_seg: 0.0896 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:42:28,175 INFO misc.py line 117 726] Train: [18/20][214/510] Data 2.113 (3.645) Batch 17.733 (27.967) Remain 10:13:24 loss: 0.2700 loss_seg: 0.1651 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:42:59,167 INFO misc.py line 117 726] Train: [18/20][215/510] Data 4.532 (3.649) Batch 30.991 (27.981) Remain 10:13:15 loss: 0.2266 loss_seg: 0.1341 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:43:27,664 INFO misc.py line 117 726] Train: [18/20][216/510] Data 3.543 (3.648) Batch 28.497 (27.983) Remain 10:12:50 loss: 0.2492 loss_seg: 0.1557 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:44:05,499 INFO misc.py line 117 726] Train: [18/20][217/510] Data 6.161 (3.660) Batch 37.836 (28.029) Remain 10:13:22 loss: 0.2240 loss_seg: 0.1343 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:44:38,386 INFO misc.py line 117 726] Train: [18/20][218/510] Data 6.189 (3.672) Batch 32.887 (28.052) Remain 10:13:24 loss: 0.2195 loss_seg: 0.1287 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:45:02,883 INFO misc.py line 117 726] Train: [18/20][219/510] Data 2.778 (3.668) Batch 24.497 (28.036) Remain 10:12:34 loss: 0.2394 loss_seg: 0.1436 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:45:37,838 INFO misc.py line 117 726] Train: [18/20][220/510] Data 6.051 (3.679) Batch 34.955 (28.067) Remain 10:12:48 loss: 0.2363 loss_seg: 0.1424 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:45:58,975 INFO misc.py line 117 726] Train: [18/20][221/510] Data 2.899 (3.675) Batch 21.138 (28.036) Remain 10:11:38 loss: 0.2113 loss_seg: 0.1235 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:46:27,116 INFO misc.py line 117 726] Train: [18/20][222/510] Data 4.717 (3.680) Batch 28.141 (28.036) Remain 10:11:11 loss: 0.2486 loss_seg: 0.1572 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:46:52,882 INFO misc.py line 117 726] Train: [18/20][223/510] Data 5.679 (3.689) Batch 25.766 (28.026) Remain 10:10:29 loss: 0.3522 loss_seg: 0.2363 loss_superpoint_edge: 0.0449 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:47:28,565 INFO misc.py line 117 726] Train: [18/20][224/510] Data 4.660 (3.693) Batch 35.682 (28.061) Remain 10:10:47 loss: 0.2804 loss_seg: 0.1787 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:48:00,319 INFO misc.py line 117 726] Train: [18/20][225/510] Data 5.266 (3.700) Batch 31.755 (28.077) Remain 10:10:40 loss: 0.2536 loss_seg: 0.1591 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:48:33,541 INFO misc.py line 117 726] Train: [18/20][226/510] Data 10.001 (3.729) Batch 33.222 (28.100) Remain 10:10:42 loss: 0.2345 loss_seg: 0.1444 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:48:57,283 INFO misc.py line 117 726] Train: [18/20][227/510] Data 3.288 (3.727) Batch 23.742 (28.081) Remain 10:09:49 loss: 0.3377 loss_seg: 0.2371 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:49:30,468 INFO misc.py line 117 726] Train: [18/20][228/510] Data 4.639 (3.731) Batch 33.185 (28.103) Remain 10:09:50 loss: 0.2121 loss_seg: 0.1207 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:50:12,742 INFO misc.py line 117 726] Train: [18/20][229/510] Data 9.651 (3.757) Batch 42.274 (28.166) Remain 10:10:44 loss: 0.2358 loss_seg: 0.1453 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:50:33,675 INFO misc.py line 117 726] Train: [18/20][230/510] Data 2.363 (3.751) Batch 20.933 (28.134) Remain 10:09:34 loss: 0.3053 loss_seg: 0.2003 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:50:57,384 INFO misc.py line 117 726] Train: [18/20][231/510] Data 3.543 (3.750) Batch 23.709 (28.115) Remain 10:08:41 loss: 0.2136 loss_seg: 0.1230 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:51:20,801 INFO misc.py line 117 726] Train: [18/20][232/510] Data 3.929 (3.751) Batch 23.417 (28.094) Remain 10:07:46 loss: 0.2779 loss_seg: 0.1817 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:51:46,110 INFO misc.py line 117 726] Train: [18/20][233/510] Data 3.921 (3.751) Batch 25.309 (28.082) Remain 10:07:02 loss: 0.3192 loss_seg: 0.2201 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:52:08,594 INFO misc.py line 117 726] Train: [18/20][234/510] Data 2.794 (3.747) Batch 22.484 (28.058) Remain 10:06:03 loss: 0.2028 loss_seg: 0.1141 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:52:41,345 INFO misc.py line 117 726] Train: [18/20][235/510] Data 3.530 (3.746) Batch 32.750 (28.078) Remain 10:06:01 loss: 0.1901 loss_seg: 0.1054 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:53:04,656 INFO misc.py line 117 726] Train: [18/20][236/510] Data 3.300 (3.744) Batch 23.312 (28.058) Remain 10:05:06 loss: 0.2331 loss_seg: 0.1413 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:53:30,489 INFO misc.py line 117 726] Train: [18/20][237/510] Data 2.709 (3.740) Batch 25.833 (28.048) Remain 10:04:26 loss: 0.2218 loss_seg: 0.1255 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:54:03,366 INFO misc.py line 117 726] Train: [18/20][238/510] Data 10.218 (3.767) Batch 32.877 (28.069) Remain 10:04:24 loss: 0.2916 loss_seg: 0.1959 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:54:23,240 INFO misc.py line 117 726] Train: [18/20][239/510] Data 1.945 (3.760) Batch 19.874 (28.034) Remain 10:03:12 loss: 0.1999 loss_seg: 0.1094 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0424 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:54:46,442 INFO misc.py line 117 726] Train: [18/20][240/510] Data 2.923 (3.756) Batch 23.202 (28.014) Remain 10:02:17 loss: 0.2125 loss_seg: 0.1213 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:55:32,335 INFO misc.py line 117 726] Train: [18/20][241/510] Data 11.717 (3.790) Batch 45.892 (28.089) Remain 10:03:26 loss: 0.2274 loss_seg: 0.1376 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:56:00,448 INFO misc.py line 117 726] Train: [18/20][242/510] Data 2.913 (3.786) Batch 28.114 (28.089) Remain 10:02:58 loss: 0.1998 loss_seg: 0.1127 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:56:34,734 INFO misc.py line 117 726] Train: [18/20][243/510] Data 4.302 (3.788) Batch 34.286 (28.115) Remain 10:03:03 loss: 0.2904 loss_seg: 0.1951 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:56:55,768 INFO misc.py line 117 726] Train: [18/20][244/510] Data 1.916 (3.780) Batch 21.034 (28.085) Remain 10:01:57 loss: 0.2308 loss_seg: 0.1329 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:57:33,966 INFO misc.py line 117 726] Train: [18/20][245/510] Data 4.207 (3.782) Batch 38.197 (28.127) Remain 10:02:23 loss: 0.2125 loss_seg: 0.1193 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:58:04,283 INFO misc.py line 117 726] Train: [18/20][246/510] Data 2.839 (3.778) Batch 30.317 (28.136) Remain 10:02:06 loss: 0.2054 loss_seg: 0.1183 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:58:35,028 INFO misc.py line 117 726] Train: [18/20][247/510] Data 2.970 (3.775) Batch 30.745 (28.147) Remain 10:01:52 loss: 0.2376 loss_seg: 0.1431 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:59:07,168 INFO misc.py line 117 726] Train: [18/20][248/510] Data 3.582 (3.774) Batch 32.140 (28.163) Remain 10:01:45 loss: 0.3018 loss_seg: 0.1933 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 15:59:41,192 INFO misc.py line 117 726] Train: [18/20][249/510] Data 4.440 (3.777) Batch 34.024 (28.187) Remain 10:01:47 loss: 0.2435 loss_seg: 0.1530 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:00:09,610 INFO misc.py line 117 726] Train: [18/20][250/510] Data 4.227 (3.779) Batch 28.418 (28.188) Remain 10:01:20 loss: 0.3245 loss_seg: 0.2196 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:00:09,610 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 16:00:35,043 INFO misc.py line 117 726] Train: [18/20][251/510] Data 3.635 (3.778) Batch 25.433 (28.177) Remain 10:00:38 loss: 0.2315 loss_seg: 0.1379 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:01:10,228 INFO misc.py line 117 726] Train: [18/20][252/510] Data 4.461 (3.781) Batch 35.185 (28.205) Remain 10:00:45 loss: 0.2140 loss_seg: 0.1267 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:01:43,377 INFO misc.py line 117 726] Train: [18/20][253/510] Data 3.857 (3.781) Batch 33.149 (28.225) Remain 10:00:42 loss: 0.2934 loss_seg: 0.1858 loss_superpoint_edge: 0.0427 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:02:10,839 INFO misc.py line 117 726] Train: [18/20][254/510] Data 3.632 (3.781) Batch 27.462 (28.222) Remain 10:00:10 loss: 0.2225 loss_seg: 0.1368 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:02:45,480 INFO misc.py line 117 726] Train: [18/20][255/510] Data 7.450 (3.795) Batch 34.640 (28.247) Remain 10:00:15 loss: 0.3423 loss_seg: 0.2343 loss_superpoint_edge: 0.0418 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:03:17,209 INFO misc.py line 117 726] Train: [18/20][256/510] Data 11.207 (3.824) Batch 31.729 (28.261) Remain 10:00:04 loss: 0.2150 loss_seg: 0.1238 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0446 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:03:45,190 INFO misc.py line 117 726] Train: [18/20][257/510] Data 3.176 (3.822) Batch 27.981 (28.260) Remain 09:59:34 loss: 0.2457 loss_seg: 0.1510 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:04:17,625 INFO misc.py line 117 726] Train: [18/20][258/510] Data 4.127 (3.823) Batch 32.435 (28.276) Remain 09:59:27 loss: 0.1837 loss_seg: 0.1000 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:04:49,776 INFO misc.py line 117 726] Train: [18/20][259/510] Data 3.956 (3.824) Batch 32.150 (28.291) Remain 09:59:18 loss: 0.2542 loss_seg: 0.1611 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:05:09,738 INFO misc.py line 117 726] Train: [18/20][260/510] Data 2.697 (3.819) Batch 19.963 (28.259) Remain 09:58:08 loss: 0.3121 loss_seg: 0.2020 loss_superpoint_edge: 0.0406 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:05:39,111 INFO misc.py line 117 726] Train: [18/20][261/510] Data 3.316 (3.817) Batch 29.372 (28.263) Remain 09:57:46 loss: 0.2073 loss_seg: 0.1222 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:06:07,010 INFO misc.py line 117 726] Train: [18/20][262/510] Data 3.531 (3.816) Batch 27.899 (28.262) Remain 09:57:16 loss: 0.2399 loss_seg: 0.1444 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:06:35,864 INFO misc.py line 117 726] Train: [18/20][263/510] Data 3.115 (3.813) Batch 28.855 (28.264) Remain 09:56:50 loss: 0.2443 loss_seg: 0.1557 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:07:01,703 INFO misc.py line 117 726] Train: [18/20][264/510] Data 3.493 (3.812) Batch 25.839 (28.255) Remain 09:56:10 loss: 0.2610 loss_seg: 0.1604 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:07:18,204 INFO misc.py line 117 726] Train: [18/20][265/510] Data 2.568 (3.807) Batch 16.501 (28.210) Remain 09:54:45 loss: 0.2462 loss_seg: 0.1497 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:07:47,397 INFO misc.py line 117 726] Train: [18/20][266/510] Data 3.445 (3.806) Batch 29.193 (28.214) Remain 09:54:22 loss: 0.2743 loss_seg: 0.1715 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:08:13,585 INFO misc.py line 117 726] Train: [18/20][267/510] Data 2.191 (3.800) Batch 26.188 (28.206) Remain 09:53:44 loss: 0.2187 loss_seg: 0.1281 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:08:43,162 INFO misc.py line 117 726] Train: [18/20][268/510] Data 3.503 (3.799) Batch 29.577 (28.211) Remain 09:53:22 loss: 0.2299 loss_seg: 0.1359 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:09:16,205 INFO misc.py line 117 726] Train: [18/20][269/510] Data 5.037 (3.804) Batch 33.043 (28.229) Remain 09:53:17 loss: 0.2153 loss_seg: 0.1256 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:09:37,819 INFO misc.py line 117 726] Train: [18/20][270/510] Data 2.035 (3.797) Batch 21.614 (28.205) Remain 09:52:17 loss: 0.2388 loss_seg: 0.1447 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:10:08,897 INFO misc.py line 117 726] Train: [18/20][271/510] Data 3.826 (3.797) Batch 31.079 (28.215) Remain 09:52:03 loss: 0.2266 loss_seg: 0.1359 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:10:38,055 INFO misc.py line 117 726] Train: [18/20][272/510] Data 3.416 (3.796) Batch 29.158 (28.219) Remain 09:51:39 loss: 0.2038 loss_seg: 0.1158 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:11:06,777 INFO misc.py line 117 726] Train: [18/20][273/510] Data 4.025 (3.796) Batch 28.721 (28.221) Remain 09:51:13 loss: 0.2073 loss_seg: 0.1189 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:11:32,676 INFO misc.py line 117 726] Train: [18/20][274/510] Data 3.114 (3.794) Batch 25.899 (28.212) Remain 09:50:34 loss: 0.2743 loss_seg: 0.1692 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:12:00,482 INFO misc.py line 117 726] Train: [18/20][275/510] Data 3.031 (3.791) Batch 27.807 (28.211) Remain 09:50:04 loss: 0.2530 loss_seg: 0.1558 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:12:35,053 INFO misc.py line 117 726] Train: [18/20][276/510] Data 7.221 (3.804) Batch 34.571 (28.234) Remain 09:50:05 loss: 0.2310 loss_seg: 0.1366 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:13:03,613 INFO misc.py line 117 726] Train: [18/20][277/510] Data 2.526 (3.799) Batch 28.560 (28.235) Remain 09:49:38 loss: 0.1860 loss_seg: 0.0994 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:13:31,775 INFO misc.py line 117 726] Train: [18/20][278/510] Data 2.738 (3.795) Batch 28.162 (28.235) Remain 09:49:10 loss: 0.2455 loss_seg: 0.1491 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:13:56,285 INFO misc.py line 117 726] Train: [18/20][279/510] Data 4.639 (3.798) Batch 24.510 (28.221) Remain 09:48:24 loss: 0.3904 loss_seg: 0.2811 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:14:28,188 INFO misc.py line 117 726] Train: [18/20][280/510] Data 3.593 (3.797) Batch 31.902 (28.235) Remain 09:48:13 loss: 0.2237 loss_seg: 0.1339 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:14:48,602 INFO misc.py line 117 726] Train: [18/20][281/510] Data 1.990 (3.791) Batch 20.414 (28.207) Remain 09:47:09 loss: 0.1857 loss_seg: 0.1008 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:15:19,315 INFO misc.py line 117 726] Train: [18/20][282/510] Data 3.028 (3.788) Batch 30.713 (28.215) Remain 09:46:52 loss: 0.2141 loss_seg: 0.1250 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:15:42,419 INFO misc.py line 117 726] Train: [18/20][283/510] Data 2.835 (3.785) Batch 23.103 (28.197) Remain 09:46:01 loss: 0.2329 loss_seg: 0.1362 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:16:08,903 INFO misc.py line 117 726] Train: [18/20][284/510] Data 3.097 (3.782) Batch 26.484 (28.191) Remain 09:45:26 loss: 0.2653 loss_seg: 0.1633 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:16:33,193 INFO misc.py line 117 726] Train: [18/20][285/510] Data 3.840 (3.783) Batch 24.290 (28.177) Remain 09:44:40 loss: 0.3297 loss_seg: 0.2271 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:16:55,753 INFO misc.py line 117 726] Train: [18/20][286/510] Data 3.014 (3.780) Batch 22.560 (28.157) Remain 09:43:47 loss: 0.2479 loss_seg: 0.1534 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:17:26,443 INFO misc.py line 117 726] Train: [18/20][287/510] Data 4.936 (3.784) Batch 30.690 (28.166) Remain 09:43:30 loss: 0.3162 loss_seg: 0.2105 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:17:53,331 INFO misc.py line 117 726] Train: [18/20][288/510] Data 2.328 (3.779) Batch 26.887 (28.162) Remain 09:42:57 loss: 0.1925 loss_seg: 0.1029 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:18:18,570 INFO misc.py line 117 726] Train: [18/20][289/510] Data 2.887 (3.776) Batch 25.239 (28.152) Remain 09:42:16 loss: 0.2543 loss_seg: 0.1562 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:18:39,093 INFO misc.py line 117 726] Train: [18/20][290/510] Data 2.347 (3.771) Batch 20.524 (28.125) Remain 09:41:15 loss: 0.2498 loss_seg: 0.1551 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:19:00,684 INFO misc.py line 117 726] Train: [18/20][291/510] Data 2.911 (3.768) Batch 21.591 (28.102) Remain 09:40:18 loss: 0.2670 loss_seg: 0.1683 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:19:34,643 INFO misc.py line 117 726] Train: [18/20][292/510] Data 4.156 (3.769) Batch 33.959 (28.123) Remain 09:40:15 loss: 0.2819 loss_seg: 0.1807 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:19:58,761 INFO misc.py line 117 726] Train: [18/20][293/510] Data 3.094 (3.767) Batch 24.118 (28.109) Remain 09:39:30 loss: 0.2221 loss_seg: 0.1290 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:20:30,124 INFO misc.py line 117 726] Train: [18/20][294/510] Data 5.158 (3.772) Batch 31.363 (28.120) Remain 09:39:16 loss: 0.2675 loss_seg: 0.1792 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:20:59,430 INFO misc.py line 117 726] Train: [18/20][295/510] Data 2.608 (3.768) Batch 29.307 (28.124) Remain 09:38:53 loss: 0.2395 loss_seg: 0.1422 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:21:28,672 INFO misc.py line 117 726] Train: [18/20][296/510] Data 3.032 (3.765) Batch 29.241 (28.128) Remain 09:38:29 loss: 0.2271 loss_seg: 0.1372 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:21:58,717 INFO misc.py line 117 726] Train: [18/20][297/510] Data 3.041 (3.763) Batch 30.045 (28.134) Remain 09:38:09 loss: 0.2059 loss_seg: 0.1173 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:22:26,794 INFO misc.py line 117 726] Train: [18/20][298/510] Data 3.103 (3.760) Batch 28.078 (28.134) Remain 09:37:41 loss: 0.2534 loss_seg: 0.1538 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0322 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:22:58,316 INFO misc.py line 117 726] Train: [18/20][299/510] Data 3.319 (3.759) Batch 31.522 (28.146) Remain 09:37:27 loss: 0.2456 loss_seg: 0.1482 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:23:31,344 INFO misc.py line 117 726] Train: [18/20][300/510] Data 3.457 (3.758) Batch 33.028 (28.162) Remain 09:37:19 loss: 0.2297 loss_seg: 0.1413 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:23:31,345 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 16:24:07,878 INFO misc.py line 117 726] Train: [18/20][301/510] Data 6.306 (3.766) Batch 36.534 (28.190) Remain 09:37:25 loss: 0.2106 loss_seg: 0.1200 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:24:46,612 INFO misc.py line 117 726] Train: [18/20][302/510] Data 9.270 (3.785) Batch 38.734 (28.225) Remain 09:37:40 loss: 0.2609 loss_seg: 0.1644 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:25:19,872 INFO misc.py line 117 726] Train: [18/20][303/510] Data 5.404 (3.790) Batch 33.260 (28.242) Remain 09:37:33 loss: 0.2126 loss_seg: 0.1200 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:25:46,621 INFO misc.py line 117 726] Train: [18/20][304/510] Data 4.417 (3.792) Batch 26.750 (28.237) Remain 09:36:58 loss: 0.2370 loss_seg: 0.1469 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:26:21,521 INFO misc.py line 117 726] Train: [18/20][305/510] Data 4.553 (3.795) Batch 34.899 (28.259) Remain 09:36:57 loss: 0.2354 loss_seg: 0.1430 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:26:43,524 INFO misc.py line 117 726] Train: [18/20][306/510] Data 1.846 (3.788) Batch 22.003 (28.239) Remain 09:36:04 loss: 0.2078 loss_seg: 0.1197 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:27:10,069 INFO misc.py line 117 726] Train: [18/20][307/510] Data 3.195 (3.786) Batch 26.545 (28.233) Remain 09:35:29 loss: 0.2828 loss_seg: 0.1816 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:27:35,132 INFO misc.py line 117 726] Train: [18/20][308/510] Data 2.914 (3.784) Batch 25.063 (28.223) Remain 09:34:48 loss: 0.2273 loss_seg: 0.1357 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:28:06,908 INFO misc.py line 117 726] Train: [18/20][309/510] Data 5.735 (3.790) Batch 31.776 (28.234) Remain 09:34:34 loss: 0.2007 loss_seg: 0.1125 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:28:30,295 INFO misc.py line 117 726] Train: [18/20][310/510] Data 3.758 (3.790) Batch 23.387 (28.219) Remain 09:33:46 loss: 0.2030 loss_seg: 0.1139 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:28:48,115 INFO misc.py line 117 726] Train: [18/20][311/510] Data 2.053 (3.784) Batch 17.821 (28.185) Remain 09:32:37 loss: 0.1956 loss_seg: 0.1065 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:29:23,117 INFO misc.py line 117 726] Train: [18/20][312/510] Data 4.761 (3.787) Batch 35.002 (28.207) Remain 09:32:35 loss: 0.2176 loss_seg: 0.1304 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:29:58,223 INFO misc.py line 117 726] Train: [18/20][313/510] Data 11.470 (3.812) Batch 35.106 (28.229) Remain 09:32:34 loss: 0.2449 loss_seg: 0.1438 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:30:23,672 INFO misc.py line 117 726] Train: [18/20][314/510] Data 2.240 (3.807) Batch 25.449 (28.220) Remain 09:31:55 loss: 0.2563 loss_seg: 0.1580 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:30:50,413 INFO misc.py line 117 726] Train: [18/20][315/510] Data 3.278 (3.805) Batch 26.741 (28.215) Remain 09:31:21 loss: 0.2259 loss_seg: 0.1339 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:31:15,051 INFO misc.py line 117 726] Train: [18/20][316/510] Data 2.969 (3.803) Batch 24.638 (28.204) Remain 09:30:39 loss: 0.2863 loss_seg: 0.1774 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:31:35,511 INFO misc.py line 117 726] Train: [18/20][317/510] Data 2.569 (3.799) Batch 20.460 (28.179) Remain 09:29:41 loss: 0.2070 loss_seg: 0.1164 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:32:07,694 INFO misc.py line 117 726] Train: [18/20][318/510] Data 8.002 (3.812) Batch 32.183 (28.192) Remain 09:29:28 loss: 0.2526 loss_seg: 0.1587 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:32:40,467 INFO misc.py line 117 726] Train: [18/20][319/510] Data 5.190 (3.816) Batch 32.772 (28.207) Remain 09:29:18 loss: 0.2142 loss_seg: 0.1213 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:33:02,215 INFO misc.py line 117 726] Train: [18/20][320/510] Data 2.819 (3.813) Batch 21.748 (28.186) Remain 09:28:25 loss: 0.2907 loss_seg: 0.1910 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:33:35,271 INFO misc.py line 117 726] Train: [18/20][321/510] Data 4.994 (3.817) Batch 33.056 (28.202) Remain 09:28:15 loss: 0.2630 loss_seg: 0.1630 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:33:52,160 INFO misc.py line 117 726] Train: [18/20][322/510] Data 1.979 (3.811) Batch 16.889 (28.166) Remain 09:27:04 loss: 0.2289 loss_seg: 0.1340 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:34:26,333 INFO misc.py line 117 726] Train: [18/20][323/510] Data 6.168 (3.819) Batch 34.173 (28.185) Remain 09:26:59 loss: 0.3473 loss_seg: 0.2530 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:34:55,220 INFO misc.py line 117 726] Train: [18/20][324/510] Data 2.914 (3.816) Batch 28.887 (28.187) Remain 09:26:33 loss: 0.2480 loss_seg: 0.1525 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:35:17,973 INFO misc.py line 117 726] Train: [18/20][325/510] Data 2.761 (3.813) Batch 22.753 (28.170) Remain 09:25:44 loss: 0.2734 loss_seg: 0.1744 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:35:48,099 INFO misc.py line 117 726] Train: [18/20][326/510] Data 5.205 (3.817) Batch 30.126 (28.176) Remain 09:25:24 loss: 0.2672 loss_seg: 0.1690 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:36:14,643 INFO misc.py line 117 726] Train: [18/20][327/510] Data 2.995 (3.814) Batch 26.544 (28.171) Remain 09:24:49 loss: 0.2095 loss_seg: 0.1191 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:36:50,384 INFO misc.py line 117 726] Train: [18/20][328/510] Data 3.863 (3.814) Batch 35.741 (28.194) Remain 09:24:49 loss: 0.2302 loss_seg: 0.1368 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:37:18,644 INFO misc.py line 117 726] Train: [18/20][329/510] Data 3.836 (3.815) Batch 28.260 (28.195) Remain 09:24:21 loss: 0.2208 loss_seg: 0.1279 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:37:48,341 INFO misc.py line 117 726] Train: [18/20][330/510] Data 3.423 (3.813) Batch 29.697 (28.199) Remain 09:23:59 loss: 0.2036 loss_seg: 0.1155 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:38:22,103 INFO misc.py line 117 726] Train: [18/20][331/510] Data 8.633 (3.828) Batch 33.763 (28.216) Remain 09:23:51 loss: 0.2394 loss_seg: 0.1439 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:38:52,050 INFO misc.py line 117 726] Train: [18/20][332/510] Data 3.043 (3.826) Batch 29.946 (28.221) Remain 09:23:29 loss: 0.1875 loss_seg: 0.1003 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:39:11,846 INFO misc.py line 117 726] Train: [18/20][333/510] Data 2.270 (3.821) Batch 19.796 (28.196) Remain 09:22:30 loss: 0.2032 loss_seg: 0.1151 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:39:45,732 INFO misc.py line 117 726] Train: [18/20][334/510] Data 5.667 (3.827) Batch 33.886 (28.213) Remain 09:22:22 loss: 0.2483 loss_seg: 0.1504 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:40:12,066 INFO misc.py line 117 726] Train: [18/20][335/510] Data 3.825 (3.827) Batch 26.334 (28.207) Remain 09:21:47 loss: 0.2427 loss_seg: 0.1478 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:40:43,807 INFO misc.py line 117 726] Train: [18/20][336/510] Data 3.482 (3.825) Batch 31.741 (28.218) Remain 09:21:32 loss: 0.2345 loss_seg: 0.1456 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:41:21,047 INFO misc.py line 117 726] Train: [18/20][337/510] Data 6.216 (3.833) Batch 37.239 (28.245) Remain 09:21:36 loss: 0.2836 loss_seg: 0.1807 loss_superpoint_edge: 0.0361 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:41:46,426 INFO misc.py line 117 726] Train: [18/20][338/510] Data 2.314 (3.828) Batch 25.379 (28.237) Remain 09:20:57 loss: 0.2058 loss_seg: 0.1160 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:42:18,936 INFO misc.py line 117 726] Train: [18/20][339/510] Data 3.391 (3.827) Batch 32.510 (28.249) Remain 09:20:44 loss: 0.2786 loss_seg: 0.1748 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:42:47,420 INFO misc.py line 117 726] Train: [18/20][340/510] Data 3.428 (3.826) Batch 28.484 (28.250) Remain 09:20:17 loss: 0.2617 loss_seg: 0.1692 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:43:17,626 INFO misc.py line 117 726] Train: [18/20][341/510] Data 2.719 (3.822) Batch 30.206 (28.256) Remain 09:19:56 loss: 0.2277 loss_seg: 0.1355 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:43:54,664 INFO misc.py line 117 726] Train: [18/20][342/510] Data 7.015 (3.832) Batch 37.038 (28.282) Remain 09:19:58 loss: 0.2700 loss_seg: 0.1765 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:44:22,548 INFO misc.py line 117 726] Train: [18/20][343/510] Data 3.654 (3.831) Batch 27.884 (28.280) Remain 09:19:28 loss: 0.2333 loss_seg: 0.1407 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:44:54,526 INFO misc.py line 117 726] Train: [18/20][344/510] Data 3.887 (3.831) Batch 31.978 (28.291) Remain 09:19:13 loss: 0.2238 loss_seg: 0.1332 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:45:23,452 INFO misc.py line 117 726] Train: [18/20][345/510] Data 3.019 (3.829) Batch 28.926 (28.293) Remain 09:18:47 loss: 0.2471 loss_seg: 0.1556 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:45:50,318 INFO misc.py line 117 726] Train: [18/20][346/510] Data 3.083 (3.827) Batch 26.866 (28.289) Remain 09:18:14 loss: 0.3126 loss_seg: 0.2049 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:46:22,924 INFO misc.py line 117 726] Train: [18/20][347/510] Data 2.943 (3.824) Batch 32.605 (28.302) Remain 09:18:00 loss: 0.1919 loss_seg: 0.1063 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:46:47,210 INFO misc.py line 117 726] Train: [18/20][348/510] Data 2.133 (3.819) Batch 24.286 (28.290) Remain 09:17:18 loss: 0.1792 loss_seg: 0.0944 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:47:09,870 INFO misc.py line 117 726] Train: [18/20][349/510] Data 2.488 (3.816) Batch 22.660 (28.274) Remain 09:16:31 loss: 0.2155 loss_seg: 0.1230 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:47:38,285 INFO misc.py line 117 726] Train: [18/20][350/510] Data 3.163 (3.814) Batch 28.415 (28.274) Remain 09:16:03 loss: 0.2279 loss_seg: 0.1390 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:47:38,286 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 16:48:07,532 INFO misc.py line 117 726] Train: [18/20][351/510] Data 4.093 (3.814) Batch 29.247 (28.277) Remain 09:15:38 loss: 0.2255 loss_seg: 0.1364 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:48:28,747 INFO misc.py line 117 726] Train: [18/20][352/510] Data 2.233 (3.810) Batch 21.214 (28.257) Remain 09:14:46 loss: 0.3672 loss_seg: 0.2561 loss_superpoint_edge: 0.0378 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:49:09,450 INFO misc.py line 117 726] Train: [18/20][353/510] Data 10.299 (3.828) Batch 40.703 (28.292) Remain 09:14:59 loss: 0.2719 loss_seg: 0.1798 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:49:29,228 INFO misc.py line 117 726] Train: [18/20][354/510] Data 2.203 (3.824) Batch 19.778 (28.268) Remain 09:14:03 loss: 0.1885 loss_seg: 0.1070 loss_superpoint_edge: 0.0155 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:49:57,054 INFO misc.py line 117 726] Train: [18/20][355/510] Data 4.019 (3.824) Batch 27.826 (28.267) Remain 09:13:33 loss: 0.2234 loss_seg: 0.1314 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:50:31,218 INFO misc.py line 117 726] Train: [18/20][356/510] Data 5.055 (3.828) Batch 34.164 (28.283) Remain 09:13:24 loss: 0.2406 loss_seg: 0.1453 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:50:59,178 INFO misc.py line 117 726] Train: [18/20][357/510] Data 3.339 (3.826) Batch 27.959 (28.282) Remain 09:12:55 loss: 0.2083 loss_seg: 0.1209 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:51:27,225 INFO misc.py line 117 726] Train: [18/20][358/510] Data 3.654 (3.826) Batch 28.048 (28.282) Remain 09:12:26 loss: 0.2223 loss_seg: 0.1284 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:51:52,192 INFO misc.py line 117 726] Train: [18/20][359/510] Data 2.741 (3.823) Batch 24.967 (28.272) Remain 09:11:47 loss: 0.2151 loss_seg: 0.1237 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:52:29,003 INFO misc.py line 117 726] Train: [18/20][360/510] Data 7.741 (3.834) Batch 36.810 (28.296) Remain 09:11:46 loss: 0.5788 loss_seg: 0.4461 loss_superpoint_edge: 0.0629 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:52:58,092 INFO misc.py line 117 726] Train: [18/20][361/510] Data 3.132 (3.832) Batch 29.091 (28.299) Remain 09:11:21 loss: 0.2451 loss_seg: 0.1466 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:53:33,604 INFO misc.py line 117 726] Train: [18/20][362/510] Data 10.052 (3.849) Batch 35.512 (28.319) Remain 09:11:16 loss: 0.2778 loss_seg: 0.1722 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:54:04,282 INFO misc.py line 117 726] Train: [18/20][363/510] Data 5.184 (3.853) Batch 30.677 (28.325) Remain 09:10:55 loss: 0.2375 loss_seg: 0.1420 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:54:30,766 INFO misc.py line 117 726] Train: [18/20][364/510] Data 5.926 (3.859) Batch 26.485 (28.320) Remain 09:10:21 loss: 0.2651 loss_seg: 0.1726 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:55:09,716 INFO misc.py line 117 726] Train: [18/20][365/510] Data 8.027 (3.870) Batch 38.950 (28.350) Remain 09:10:27 loss: 0.2335 loss_seg: 0.1392 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:55:28,644 INFO misc.py line 117 726] Train: [18/20][366/510] Data 2.195 (3.866) Batch 18.928 (28.324) Remain 09:09:28 loss: 0.2245 loss_seg: 0.1297 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:55:57,225 INFO misc.py line 117 726] Train: [18/20][367/510] Data 5.245 (3.869) Batch 28.581 (28.324) Remain 09:09:01 loss: 0.2781 loss_seg: 0.1770 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:56:36,056 INFO misc.py line 117 726] Train: [18/20][368/510] Data 5.918 (3.875) Batch 38.831 (28.353) Remain 09:09:06 loss: 0.2976 loss_seg: 0.1992 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:57:05,322 INFO misc.py line 117 726] Train: [18/20][369/510] Data 6.774 (3.883) Batch 29.266 (28.356) Remain 09:08:40 loss: 0.1979 loss_seg: 0.1050 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0439 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:57:38,481 INFO misc.py line 117 726] Train: [18/20][370/510] Data 2.845 (3.880) Batch 33.158 (28.369) Remain 09:08:27 loss: 0.2333 loss_seg: 0.1392 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:57:59,408 INFO misc.py line 117 726] Train: [18/20][371/510] Data 2.897 (3.877) Batch 20.928 (28.348) Remain 09:07:35 loss: 0.2267 loss_seg: 0.1341 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:58:33,549 INFO misc.py line 117 726] Train: [18/20][372/510] Data 3.112 (3.875) Batch 34.140 (28.364) Remain 09:07:25 loss: 0.3043 loss_seg: 0.1932 loss_superpoint_edge: 0.0460 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:58:59,590 INFO misc.py line 117 726] Train: [18/20][373/510] Data 4.748 (3.878) Batch 26.041 (28.358) Remain 09:06:50 loss: 0.1915 loss_seg: 0.1062 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:59:19,227 INFO misc.py line 117 726] Train: [18/20][374/510] Data 2.126 (3.873) Batch 19.637 (28.334) Remain 09:05:54 loss: 0.3410 loss_seg: 0.2313 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 16:59:53,956 INFO misc.py line 117 726] Train: [18/20][375/510] Data 5.699 (3.878) Batch 34.730 (28.352) Remain 09:05:45 loss: 0.2467 loss_seg: 0.1554 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:00:34,006 INFO misc.py line 117 726] Train: [18/20][376/510] Data 8.117 (3.889) Batch 40.050 (28.383) Remain 09:05:53 loss: 0.2761 loss_seg: 0.1729 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:01:03,665 INFO misc.py line 117 726] Train: [18/20][377/510] Data 3.507 (3.888) Batch 29.659 (28.386) Remain 09:05:29 loss: 0.1937 loss_seg: 0.1121 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:01:19,076 INFO misc.py line 117 726] Train: [18/20][378/510] Data 1.797 (3.883) Batch 15.412 (28.352) Remain 09:04:21 loss: 0.2256 loss_seg: 0.1311 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:01:46,630 INFO misc.py line 117 726] Train: [18/20][379/510] Data 2.557 (3.879) Batch 27.553 (28.350) Remain 09:03:50 loss: 0.2130 loss_seg: 0.1223 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:02:15,608 INFO misc.py line 117 726] Train: [18/20][380/510] Data 3.356 (3.878) Batch 28.978 (28.351) Remain 09:03:23 loss: 0.2630 loss_seg: 0.1682 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:02:41,119 INFO misc.py line 117 726] Train: [18/20][381/510] Data 2.765 (3.875) Batch 25.511 (28.344) Remain 09:02:46 loss: 0.2446 loss_seg: 0.1451 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:03:09,749 INFO misc.py line 117 726] Train: [18/20][382/510] Data 3.359 (3.873) Batch 28.631 (28.344) Remain 09:02:19 loss: 0.3168 loss_seg: 0.2195 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:03:28,691 INFO misc.py line 117 726] Train: [18/20][383/510] Data 2.387 (3.870) Batch 18.942 (28.320) Remain 09:01:22 loss: 0.1940 loss_seg: 0.1091 loss_superpoint_edge: 0.0138 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:04:10,603 INFO misc.py line 117 726] Train: [18/20][384/510] Data 9.079 (3.883) Batch 41.912 (28.355) Remain 09:01:35 loss: 0.2312 loss_seg: 0.1418 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:04:32,832 INFO misc.py line 117 726] Train: [18/20][385/510] Data 2.980 (3.881) Batch 22.229 (28.339) Remain 09:00:48 loss: 0.2086 loss_seg: 0.1175 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:05:03,620 INFO misc.py line 117 726] Train: [18/20][386/510] Data 3.566 (3.880) Batch 30.788 (28.346) Remain 09:00:27 loss: 0.2488 loss_seg: 0.1539 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:05:24,594 INFO misc.py line 117 726] Train: [18/20][387/510] Data 2.159 (3.876) Batch 20.975 (28.327) Remain 08:59:37 loss: 0.2492 loss_seg: 0.1469 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:05:43,663 INFO misc.py line 117 726] Train: [18/20][388/510] Data 2.468 (3.872) Batch 19.069 (28.303) Remain 08:58:41 loss: 0.2160 loss_seg: 0.1255 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:06:16,858 INFO misc.py line 117 726] Train: [18/20][389/510] Data 5.484 (3.876) Batch 33.195 (28.315) Remain 08:58:27 loss: 0.2637 loss_seg: 0.1681 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:06:41,238 INFO misc.py line 117 726] Train: [18/20][390/510] Data 2.018 (3.871) Batch 24.381 (28.305) Remain 08:57:47 loss: 0.2074 loss_seg: 0.1161 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:07:16,502 INFO misc.py line 117 726] Train: [18/20][391/510] Data 4.712 (3.873) Batch 35.264 (28.323) Remain 08:57:39 loss: 0.1975 loss_seg: 0.1135 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:07:47,468 INFO misc.py line 117 726] Train: [18/20][392/510] Data 3.882 (3.873) Batch 30.966 (28.330) Remain 08:57:19 loss: 0.2289 loss_seg: 0.1377 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:08:09,695 INFO misc.py line 117 726] Train: [18/20][393/510] Data 3.627 (3.873) Batch 22.227 (28.314) Remain 08:56:33 loss: 0.2294 loss_seg: 0.1332 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:08:31,941 INFO misc.py line 117 726] Train: [18/20][394/510] Data 2.448 (3.869) Batch 22.246 (28.299) Remain 08:55:47 loss: 0.2239 loss_seg: 0.1300 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:08:59,631 INFO misc.py line 117 726] Train: [18/20][395/510] Data 3.473 (3.868) Batch 27.690 (28.297) Remain 08:55:17 loss: 0.2258 loss_seg: 0.1315 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:09:21,186 INFO misc.py line 117 726] Train: [18/20][396/510] Data 3.057 (3.866) Batch 21.556 (28.280) Remain 08:54:29 loss: 0.2256 loss_seg: 0.1325 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:09:58,035 INFO misc.py line 117 726] Train: [18/20][397/510] Data 9.948 (3.882) Batch 36.849 (28.302) Remain 08:54:25 loss: 0.2061 loss_seg: 0.1173 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:10:23,731 INFO misc.py line 117 726] Train: [18/20][398/510] Data 2.915 (3.879) Batch 25.696 (28.295) Remain 08:53:49 loss: 0.2291 loss_seg: 0.1409 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:10:47,060 INFO misc.py line 117 726] Train: [18/20][399/510] Data 2.357 (3.875) Batch 23.329 (28.282) Remain 08:53:07 loss: 0.2039 loss_seg: 0.1128 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:11:17,807 INFO misc.py line 117 726] Train: [18/20][400/510] Data 3.498 (3.874) Batch 30.746 (28.289) Remain 08:52:46 loss: 0.2379 loss_seg: 0.1447 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:11:17,807 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 17:11:45,965 INFO misc.py line 117 726] Train: [18/20][401/510] Data 3.444 (3.873) Batch 28.158 (28.288) Remain 08:52:17 loss: 0.1933 loss_seg: 0.1042 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:12:10,532 INFO misc.py line 117 726] Train: [18/20][402/510] Data 3.066 (3.871) Batch 24.567 (28.279) Remain 08:51:38 loss: 0.2200 loss_seg: 0.1283 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:12:41,327 INFO misc.py line 117 726] Train: [18/20][403/510] Data 3.967 (3.871) Batch 30.795 (28.285) Remain 08:51:17 loss: 0.1697 loss_seg: 0.0859 loss_superpoint_edge: 0.0129 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:13:13,682 INFO misc.py line 117 726] Train: [18/20][404/510] Data 5.977 (3.877) Batch 32.355 (28.295) Remain 08:51:00 loss: 0.2808 loss_seg: 0.1928 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:13:37,646 INFO misc.py line 117 726] Train: [18/20][405/510] Data 2.940 (3.874) Batch 23.964 (28.285) Remain 08:50:20 loss: 0.2365 loss_seg: 0.1425 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:14:00,044 INFO misc.py line 117 726] Train: [18/20][406/510] Data 2.198 (3.870) Batch 22.398 (28.270) Remain 08:49:35 loss: 0.1916 loss_seg: 0.1058 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:14:22,565 INFO misc.py line 117 726] Train: [18/20][407/510] Data 1.733 (3.865) Batch 22.521 (28.256) Remain 08:48:51 loss: 0.2699 loss_seg: 0.1708 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:14:49,132 INFO misc.py line 117 726] Train: [18/20][408/510] Data 5.600 (3.869) Batch 26.567 (28.252) Remain 08:48:18 loss: 0.2177 loss_seg: 0.1291 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:15:06,719 INFO misc.py line 117 726] Train: [18/20][409/510] Data 1.951 (3.864) Batch 17.587 (28.225) Remain 08:47:20 loss: 0.2312 loss_seg: 0.1352 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:15:37,024 INFO misc.py line 117 726] Train: [18/20][410/510] Data 3.683 (3.864) Batch 30.305 (28.231) Remain 08:46:58 loss: 0.2651 loss_seg: 0.1617 loss_superpoint_edge: 0.0373 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:15:56,600 INFO misc.py line 117 726] Train: [18/20][411/510] Data 2.261 (3.860) Batch 19.576 (28.209) Remain 08:46:06 loss: 0.2796 loss_seg: 0.1733 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:16:26,118 INFO misc.py line 117 726] Train: [18/20][412/510] Data 2.872 (3.858) Batch 29.518 (28.213) Remain 08:45:41 loss: 0.1962 loss_seg: 0.1093 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:16:42,482 INFO misc.py line 117 726] Train: [18/20][413/510] Data 2.498 (3.854) Batch 16.364 (28.184) Remain 08:44:41 loss: 0.2406 loss_seg: 0.1425 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:17:16,063 INFO misc.py line 117 726] Train: [18/20][414/510] Data 3.550 (3.854) Batch 33.580 (28.197) Remain 08:44:27 loss: 0.2107 loss_seg: 0.1215 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:17:41,788 INFO misc.py line 117 726] Train: [18/20][415/510] Data 2.708 (3.851) Batch 25.725 (28.191) Remain 08:43:52 loss: 0.2418 loss_seg: 0.1442 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:18:02,110 INFO misc.py line 117 726] Train: [18/20][416/510] Data 2.194 (3.847) Batch 20.323 (28.172) Remain 08:43:03 loss: 0.2154 loss_seg: 0.1259 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:18:34,265 INFO misc.py line 117 726] Train: [18/20][417/510] Data 3.717 (3.847) Batch 32.154 (28.181) Remain 08:42:45 loss: 0.2312 loss_seg: 0.1362 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:19:03,387 INFO misc.py line 117 726] Train: [18/20][418/510] Data 3.018 (3.845) Batch 29.122 (28.184) Remain 08:42:20 loss: 0.1773 loss_seg: 0.0936 loss_superpoint_edge: 0.0151 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:19:30,523 INFO misc.py line 117 726] Train: [18/20][419/510] Data 2.194 (3.841) Batch 27.136 (28.181) Remain 08:41:49 loss: 0.2296 loss_seg: 0.1344 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:19:54,665 INFO misc.py line 117 726] Train: [18/20][420/510] Data 2.848 (3.838) Batch 24.142 (28.171) Remain 08:41:10 loss: 0.3023 loss_seg: 0.1951 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:20:20,579 INFO misc.py line 117 726] Train: [18/20][421/510] Data 3.057 (3.836) Batch 25.914 (28.166) Remain 08:40:36 loss: 0.1848 loss_seg: 0.0976 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:20:57,699 INFO misc.py line 117 726] Train: [18/20][422/510] Data 4.105 (3.837) Batch 37.119 (28.187) Remain 08:40:31 loss: 0.2533 loss_seg: 0.1587 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:21:28,024 INFO misc.py line 117 726] Train: [18/20][423/510] Data 4.103 (3.838) Batch 30.326 (28.192) Remain 08:40:09 loss: 0.1814 loss_seg: 0.0955 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:21:59,239 INFO misc.py line 117 726] Train: [18/20][424/510] Data 3.161 (3.836) Batch 31.215 (28.200) Remain 08:39:48 loss: 0.2373 loss_seg: 0.1425 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:22:29,646 INFO misc.py line 117 726] Train: [18/20][425/510] Data 4.453 (3.837) Batch 30.407 (28.205) Remain 08:39:26 loss: 0.2958 loss_seg: 0.1949 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:22:57,324 INFO misc.py line 117 726] Train: [18/20][426/510] Data 10.408 (3.853) Batch 27.678 (28.204) Remain 08:38:56 loss: 0.2382 loss_seg: 0.1431 loss_superpoint_edge: 0.0169 loss_superpoint_contrast: 0.0468 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:23:29,470 INFO misc.py line 117 726] Train: [18/20][427/510] Data 3.780 (3.853) Batch 32.146 (28.213) Remain 08:38:38 loss: 0.3135 loss_seg: 0.2072 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:23:49,434 INFO misc.py line 117 726] Train: [18/20][428/510] Data 2.533 (3.850) Batch 19.963 (28.194) Remain 08:37:49 loss: 0.2171 loss_seg: 0.1231 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:24:21,016 INFO misc.py line 117 726] Train: [18/20][429/510] Data 4.591 (3.851) Batch 31.582 (28.201) Remain 08:37:29 loss: 0.2906 loss_seg: 0.1915 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:24:49,598 INFO misc.py line 117 726] Train: [18/20][430/510] Data 2.883 (3.849) Batch 28.582 (28.202) Remain 08:37:02 loss: 0.2200 loss_seg: 0.1295 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:25:10,791 INFO misc.py line 117 726] Train: [18/20][431/510] Data 2.961 (3.847) Batch 21.193 (28.186) Remain 08:36:16 loss: 0.2282 loss_seg: 0.1364 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:25:40,729 INFO misc.py line 117 726] Train: [18/20][432/510] Data 3.134 (3.845) Batch 29.938 (28.190) Remain 08:35:52 loss: 0.3803 loss_seg: 0.2860 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:26:18,346 INFO misc.py line 117 726] Train: [18/20][433/510] Data 5.997 (3.850) Batch 37.617 (28.212) Remain 08:35:48 loss: 0.2544 loss_seg: 0.1551 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:26:49,615 INFO misc.py line 117 726] Train: [18/20][434/510] Data 4.716 (3.852) Batch 31.269 (28.219) Remain 08:35:28 loss: 0.2589 loss_seg: 0.1615 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:27:23,325 INFO misc.py line 117 726] Train: [18/20][435/510] Data 5.273 (3.856) Batch 33.710 (28.232) Remain 08:35:13 loss: 0.1597 loss_seg: 0.0761 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:27:45,400 INFO misc.py line 117 726] Train: [18/20][436/510] Data 2.556 (3.853) Batch 22.075 (28.218) Remain 08:34:30 loss: 0.3169 loss_seg: 0.2133 loss_superpoint_edge: 0.0364 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:28:16,506 INFO misc.py line 117 726] Train: [18/20][437/510] Data 8.742 (3.864) Batch 31.106 (28.224) Remain 08:34:09 loss: 0.2326 loss_seg: 0.1379 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:28:38,420 INFO misc.py line 117 726] Train: [18/20][438/510] Data 2.631 (3.861) Batch 21.914 (28.210) Remain 08:33:25 loss: 0.2332 loss_seg: 0.1412 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:29:06,653 INFO misc.py line 117 726] Train: [18/20][439/510] Data 4.295 (3.862) Batch 28.233 (28.210) Remain 08:32:56 loss: 0.2375 loss_seg: 0.1450 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:29:39,995 INFO misc.py line 117 726] Train: [18/20][440/510] Data 3.366 (3.861) Batch 33.342 (28.222) Remain 08:32:41 loss: 0.1811 loss_seg: 0.0932 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:29:59,700 INFO misc.py line 117 726] Train: [18/20][441/510] Data 2.326 (3.858) Batch 19.705 (28.202) Remain 08:31:52 loss: 0.2448 loss_seg: 0.1473 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:30:33,730 INFO misc.py line 117 726] Train: [18/20][442/510] Data 5.387 (3.861) Batch 34.030 (28.215) Remain 08:31:38 loss: 0.2547 loss_seg: 0.1597 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:31:03,513 INFO misc.py line 117 726] Train: [18/20][443/510] Data 8.265 (3.871) Batch 29.783 (28.219) Remain 08:31:13 loss: 0.2446 loss_seg: 0.1518 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:31:34,007 INFO misc.py line 117 726] Train: [18/20][444/510] Data 3.153 (3.869) Batch 30.494 (28.224) Remain 08:30:51 loss: 0.2339 loss_seg: 0.1362 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:32:01,490 INFO misc.py line 117 726] Train: [18/20][445/510] Data 7.997 (3.879) Batch 27.483 (28.222) Remain 08:30:21 loss: 0.2066 loss_seg: 0.1157 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0458 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:32:26,427 INFO misc.py line 117 726] Train: [18/20][446/510] Data 3.532 (3.878) Batch 24.937 (28.215) Remain 08:29:45 loss: 0.2254 loss_seg: 0.1343 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:32:58,065 INFO misc.py line 117 726] Train: [18/20][447/510] Data 4.159 (3.879) Batch 31.638 (28.223) Remain 08:29:25 loss: 0.1837 loss_seg: 0.0990 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:33:20,845 INFO misc.py line 117 726] Train: [18/20][448/510] Data 2.154 (3.875) Batch 22.780 (28.210) Remain 08:28:43 loss: 0.2504 loss_seg: 0.1500 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:33:44,814 INFO misc.py line 117 726] Train: [18/20][449/510] Data 3.578 (3.874) Batch 23.969 (28.201) Remain 08:28:05 loss: 0.2324 loss_seg: 0.1360 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:34:13,149 INFO misc.py line 117 726] Train: [18/20][450/510] Data 3.653 (3.874) Batch 28.335 (28.201) Remain 08:27:37 loss: 0.1980 loss_seg: 0.1107 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:34:13,149 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 17:34:35,871 INFO misc.py line 117 726] Train: [18/20][451/510] Data 3.030 (3.872) Batch 22.722 (28.189) Remain 08:26:55 loss: 0.1873 loss_seg: 0.1003 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:34:56,608 INFO misc.py line 117 726] Train: [18/20][452/510] Data 2.945 (3.870) Batch 20.736 (28.172) Remain 08:26:09 loss: 0.2680 loss_seg: 0.1798 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:35:22,097 INFO misc.py line 117 726] Train: [18/20][453/510] Data 2.383 (3.866) Batch 25.489 (28.166) Remain 08:25:35 loss: 0.2064 loss_seg: 0.1171 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:35:53,808 INFO misc.py line 117 726] Train: [18/20][454/510] Data 3.121 (3.865) Batch 31.711 (28.174) Remain 08:25:15 loss: 0.2586 loss_seg: 0.1632 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:36:20,583 INFO misc.py line 117 726] Train: [18/20][455/510] Data 3.029 (3.863) Batch 26.775 (28.171) Remain 08:24:44 loss: 0.2315 loss_seg: 0.1432 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:36:44,333 INFO misc.py line 117 726] Train: [18/20][456/510] Data 2.180 (3.859) Batch 23.750 (28.161) Remain 08:24:05 loss: 0.1901 loss_seg: 0.1049 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:37:13,220 INFO misc.py line 117 726] Train: [18/20][457/510] Data 3.553 (3.858) Batch 28.887 (28.163) Remain 08:23:38 loss: 0.2729 loss_seg: 0.1735 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:37:32,887 INFO misc.py line 117 726] Train: [18/20][458/510] Data 2.228 (3.855) Batch 19.667 (28.144) Remain 08:22:50 loss: 0.2370 loss_seg: 0.1428 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:37:49,296 INFO misc.py line 117 726] Train: [18/20][459/510] Data 1.963 (3.851) Batch 16.409 (28.119) Remain 08:21:55 loss: 0.2518 loss_seg: 0.1496 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:38:19,964 INFO misc.py line 117 726] Train: [18/20][460/510] Data 4.040 (3.851) Batch 30.669 (28.124) Remain 08:21:32 loss: 0.2168 loss_seg: 0.1230 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:38:44,324 INFO misc.py line 117 726] Train: [18/20][461/510] Data 2.881 (3.849) Batch 24.360 (28.116) Remain 08:20:56 loss: 0.2986 loss_seg: 0.2007 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:39:08,824 INFO misc.py line 117 726] Train: [18/20][462/510] Data 3.161 (3.847) Batch 24.500 (28.108) Remain 08:20:19 loss: 0.2051 loss_seg: 0.1167 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:39:35,945 INFO misc.py line 117 726] Train: [18/20][463/510] Data 3.266 (3.846) Batch 27.121 (28.106) Remain 08:19:49 loss: 0.3117 loss_seg: 0.2015 loss_superpoint_edge: 0.0426 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:39:59,677 INFO misc.py line 117 726] Train: [18/20][464/510] Data 2.856 (3.844) Batch 23.732 (28.096) Remain 08:19:10 loss: 0.2649 loss_seg: 0.1639 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:40:28,020 INFO misc.py line 117 726] Train: [18/20][465/510] Data 3.229 (3.843) Batch 28.343 (28.097) Remain 08:18:43 loss: 0.2253 loss_seg: 0.1318 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:40:48,474 INFO misc.py line 117 726] Train: [18/20][466/510] Data 2.511 (3.840) Batch 20.454 (28.081) Remain 08:17:57 loss: 0.1789 loss_seg: 0.0924 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:41:23,476 INFO misc.py line 117 726] Train: [18/20][467/510] Data 5.730 (3.844) Batch 35.003 (28.095) Remain 08:17:45 loss: 0.2395 loss_seg: 0.1419 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:41:52,580 INFO misc.py line 117 726] Train: [18/20][468/510] Data 3.286 (3.843) Batch 29.104 (28.098) Remain 08:17:19 loss: 0.2095 loss_seg: 0.1212 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:42:28,747 INFO misc.py line 117 726] Train: [18/20][469/510] Data 5.741 (3.847) Batch 36.167 (28.115) Remain 08:17:09 loss: 0.2191 loss_seg: 0.1285 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:43:00,985 INFO misc.py line 117 726] Train: [18/20][470/510] Data 3.670 (3.846) Batch 32.237 (28.124) Remain 08:16:51 loss: 0.2364 loss_seg: 0.1390 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:43:33,953 INFO misc.py line 117 726] Train: [18/20][471/510] Data 5.046 (3.849) Batch 32.969 (28.134) Remain 08:16:34 loss: 0.2376 loss_seg: 0.1472 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:44:08,540 INFO misc.py line 117 726] Train: [18/20][472/510] Data 7.904 (3.858) Batch 34.588 (28.148) Remain 08:16:20 loss: 0.1719 loss_seg: 0.0890 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:44:30,938 INFO misc.py line 117 726] Train: [18/20][473/510] Data 2.394 (3.855) Batch 22.398 (28.136) Remain 08:15:39 loss: 0.2668 loss_seg: 0.1715 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:45:00,657 INFO misc.py line 117 726] Train: [18/20][474/510] Data 3.906 (3.855) Batch 29.719 (28.139) Remain 08:15:14 loss: 0.2025 loss_seg: 0.1153 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:45:22,892 INFO misc.py line 117 726] Train: [18/20][475/510] Data 2.680 (3.852) Batch 22.236 (28.126) Remain 08:14:33 loss: 0.2074 loss_seg: 0.1179 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:45:53,796 INFO misc.py line 117 726] Train: [18/20][476/510] Data 3.496 (3.851) Batch 30.904 (28.132) Remain 08:14:11 loss: 0.2482 loss_seg: 0.1575 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:46:13,892 INFO misc.py line 117 726] Train: [18/20][477/510] Data 2.903 (3.849) Batch 20.096 (28.115) Remain 08:13:25 loss: 0.2659 loss_seg: 0.1682 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:46:48,363 INFO misc.py line 117 726] Train: [18/20][478/510] Data 6.787 (3.856) Batch 34.471 (28.129) Remain 08:13:11 loss: 0.3342 loss_seg: 0.2235 loss_superpoint_edge: 0.0441 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:47:18,875 INFO misc.py line 117 726] Train: [18/20][479/510] Data 4.054 (3.856) Batch 30.511 (28.134) Remain 08:12:48 loss: 0.3527 loss_seg: 0.2364 loss_superpoint_edge: 0.0483 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:47:46,516 INFO misc.py line 117 726] Train: [18/20][480/510] Data 4.307 (3.857) Batch 27.641 (28.133) Remain 08:12:19 loss: 0.2281 loss_seg: 0.1334 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:48:10,591 INFO misc.py line 117 726] Train: [18/20][481/510] Data 2.525 (3.854) Batch 24.075 (28.124) Remain 08:11:42 loss: 0.2118 loss_seg: 0.1214 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:48:40,540 INFO misc.py line 117 726] Train: [18/20][482/510] Data 3.314 (3.853) Batch 29.949 (28.128) Remain 08:11:18 loss: 0.2047 loss_seg: 0.1151 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:49:05,706 INFO misc.py line 117 726] Train: [18/20][483/510] Data 4.244 (3.854) Batch 25.166 (28.122) Remain 08:10:43 loss: 0.2201 loss_seg: 0.1253 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:49:36,766 INFO misc.py line 117 726] Train: [18/20][484/510] Data 5.387 (3.857) Batch 31.060 (28.128) Remain 08:10:21 loss: 0.2658 loss_seg: 0.1691 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:49:59,989 INFO misc.py line 117 726] Train: [18/20][485/510] Data 2.451 (3.854) Batch 23.222 (28.118) Remain 08:09:43 loss: 0.2766 loss_seg: 0.1830 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:50:25,682 INFO misc.py line 117 726] Train: [18/20][486/510] Data 2.227 (3.851) Batch 25.693 (28.113) Remain 08:09:09 loss: 0.2963 loss_seg: 0.2023 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:50:51,826 INFO misc.py line 117 726] Train: [18/20][487/510] Data 3.008 (3.849) Batch 26.144 (28.109) Remain 08:08:37 loss: 0.2009 loss_seg: 0.1141 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:51:17,051 INFO misc.py line 117 726] Train: [18/20][488/510] Data 2.639 (3.847) Batch 25.225 (28.103) Remain 08:08:03 loss: 0.2207 loss_seg: 0.1268 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:51:40,957 INFO misc.py line 117 726] Train: [18/20][489/510] Data 2.390 (3.844) Batch 23.906 (28.094) Remain 08:07:26 loss: 0.3162 loss_seg: 0.2080 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:52:05,189 INFO misc.py line 117 726] Train: [18/20][490/510] Data 3.994 (3.844) Batch 24.232 (28.086) Remain 08:06:49 loss: 0.2325 loss_seg: 0.1369 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:52:29,217 INFO misc.py line 117 726] Train: [18/20][491/510] Data 2.994 (3.842) Batch 24.027 (28.078) Remain 08:06:12 loss: 0.2714 loss_seg: 0.1728 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:53:02,344 INFO misc.py line 117 726] Train: [18/20][492/510] Data 3.215 (3.841) Batch 33.128 (28.088) Remain 08:05:55 loss: 0.1971 loss_seg: 0.1118 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:53:25,819 INFO misc.py line 117 726] Train: [18/20][493/510] Data 2.973 (3.839) Batch 23.474 (28.079) Remain 08:05:17 loss: 0.3023 loss_seg: 0.2058 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:53:55,050 INFO misc.py line 117 726] Train: [18/20][494/510] Data 2.705 (3.837) Batch 29.231 (28.081) Remain 08:04:52 loss: 0.2487 loss_seg: 0.1509 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:54:24,036 INFO misc.py line 117 726] Train: [18/20][495/510] Data 3.116 (3.835) Batch 28.986 (28.083) Remain 08:04:25 loss: 0.2250 loss_seg: 0.1340 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:54:47,690 INFO misc.py line 117 726] Train: [18/20][496/510] Data 2.482 (3.832) Batch 23.654 (28.074) Remain 08:03:48 loss: 0.1895 loss_seg: 0.1022 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:55:03,936 INFO misc.py line 117 726] Train: [18/20][497/510] Data 1.695 (3.828) Batch 16.246 (28.050) Remain 08:02:55 loss: 0.3957 loss_seg: 0.3067 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:55:31,293 INFO misc.py line 117 726] Train: [18/20][498/510] Data 4.139 (3.829) Batch 27.357 (28.049) Remain 08:02:26 loss: 0.1950 loss_seg: 0.1060 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:56:07,317 INFO misc.py line 117 726] Train: [18/20][499/510] Data 4.509 (3.830) Batch 36.024 (28.065) Remain 08:02:14 loss: 0.3239 loss_seg: 0.2283 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:56:32,334 INFO misc.py line 117 726] Train: [18/20][500/510] Data 3.413 (3.829) Batch 25.017 (28.059) Remain 08:01:40 loss: 0.2688 loss_seg: 0.1626 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:56:32,335 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 17:56:57,963 INFO misc.py line 117 726] Train: [18/20][501/510] Data 4.004 (3.830) Batch 25.629 (28.054) Remain 08:01:07 loss: 0.2296 loss_seg: 0.1391 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:57:19,845 INFO misc.py line 117 726] Train: [18/20][502/510] Data 2.767 (3.828) Batch 21.882 (28.041) Remain 08:00:26 loss: 0.2138 loss_seg: 0.1246 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:57:46,522 INFO misc.py line 117 726] Train: [18/20][503/510] Data 3.318 (3.827) Batch 26.677 (28.039) Remain 07:59:55 loss: 0.2005 loss_seg: 0.1095 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:58:15,513 INFO misc.py line 117 726] Train: [18/20][504/510] Data 3.747 (3.826) Batch 28.991 (28.041) Remain 07:59:29 loss: 0.2506 loss_seg: 0.1492 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:58:31,664 INFO misc.py line 117 726] Train: [18/20][505/510] Data 1.885 (3.823) Batch 16.151 (28.017) Remain 07:58:37 loss: 0.2221 loss_seg: 0.1309 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:58:57,754 INFO misc.py line 117 726] Train: [18/20][506/510] Data 2.795 (3.820) Batch 26.090 (28.013) Remain 07:58:05 loss: 0.2663 loss_seg: 0.1638 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:59:22,471 INFO misc.py line 117 726] Train: [18/20][507/510] Data 3.430 (3.820) Batch 24.717 (28.007) Remain 07:57:30 loss: 0.2506 loss_seg: 0.1585 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 17:59:45,951 INFO misc.py line 117 726] Train: [18/20][508/510] Data 2.458 (3.817) Batch 23.481 (27.998) Remain 07:56:53 loss: 0.2155 loss_seg: 0.1255 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:00:20,721 INFO misc.py line 117 726] Train: [18/20][509/510] Data 4.408 (3.818) Batch 34.770 (28.011) Remain 07:56:39 loss: 0.2866 loss_seg: 0.1841 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:00:40,172 INFO misc.py line 117 726] Train: [18/20][510/510] Data 1.979 (3.815) Batch 19.451 (27.994) Remain 07:55:53 loss: 0.2441 loss_seg: 0.1456 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:00:40,173 INFO misc.py line 147 726] Train result: loss: 0.2437 loss_seg: 0.1492 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 [2026-06-12 18:00:40,174 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-12 18:00:55,774 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6628 [2026-06-12 18:01:12,687 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6579 [2026-06-12 18:02:27,087 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8700 [2026-06-12 18:03:07,173 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9906 [2026-06-12 18:03:26,386 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9398 [2026-06-12 18:04:02,535 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.2223 [2026-06-12 18:04:49,083 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1584 [2026-06-12 18:05:04,739 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3780 [2026-06-12 18:05:22,478 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.0366 [2026-06-12 18:05:41,137 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4139 [2026-06-12 18:05:56,963 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.4664 [2026-06-12 18:06:18,538 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7352 [2026-06-12 18:06:44,615 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 2.0267 [2026-06-12 18:06:55,937 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6896 [2026-06-12 18:07:27,702 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0417 [2026-06-12 18:07:53,747 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3992 [2026-06-12 18:08:20,500 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3414 [2026-06-12 18:09:03,120 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.2110 [2026-06-12 18:09:23,996 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.4093 [2026-06-12 18:09:40,495 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.8613 [2026-06-12 18:10:11,413 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9937 [2026-06-12 18:10:27,600 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4817 [2026-06-12 18:10:49,547 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3556 [2026-06-12 18:11:11,055 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8655 [2026-06-12 18:11:24,350 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6365 [2026-06-12 18:11:51,940 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5236 [2026-06-12 18:12:33,172 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1361 [2026-06-12 18:12:50,398 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5067 [2026-06-12 18:13:09,065 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4636 [2026-06-12 18:13:25,866 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4878 [2026-06-12 18:13:50,634 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2213 [2026-06-12 18:14:08,800 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6177 [2026-06-12 18:14:26,107 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1071 [2026-06-12 18:14:50,427 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7142 [2026-06-12 18:14:50,442 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6701/0.7430/0.8969. [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9231/0.9577 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9766/0.9880 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8406/0.9693 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0037/0.0252 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3159/0.3803 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6038/0.6268 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6085/0.6998 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7951/0.8993 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9187/0.9595 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6667/0.7259 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7644/0.8528 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.6960/0.8672 [2026-06-12 18:14:50,442 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5985/0.7075 [2026-06-12 18:14:50,443 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-12 18:14:50,443 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-12 18:14:50,443 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 18:15:03,857 INFO misc.py line 117 726] Train: [19/20][1/510] Data 2.192 (2.192) Batch 11.875 (11.875) Remain 03:21:40 loss: 0.2005 loss_seg: 0.1113 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:15:19,349 INFO misc.py line 117 726] Train: [19/20][2/510] Data 1.992 (1.992) Batch 15.492 (15.492) Remain 04:22:50 loss: 0.2160 loss_seg: 0.1210 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:15:45,465 INFO misc.py line 117 726] Train: [19/20][3/510] Data 4.908 (4.908) Batch 26.117 (26.117) Remain 07:22:40 loss: 0.2394 loss_seg: 0.1469 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:16:17,120 INFO misc.py line 117 726] Train: [19/20][4/510] Data 2.930 (2.930) Batch 31.655 (31.655) Remain 08:56:01 loss: 0.2397 loss_seg: 0.1484 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:16:48,474 INFO misc.py line 117 726] Train: [19/20][5/510] Data 3.967 (3.448) Batch 31.353 (31.504) Remain 08:52:56 loss: 0.2964 loss_seg: 0.1933 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:17:16,210 INFO misc.py line 117 726] Train: [19/20][6/510] Data 3.229 (3.375) Batch 27.737 (30.248) Remain 08:31:11 loss: 0.2633 loss_seg: 0.1660 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:17:47,811 INFO misc.py line 117 726] Train: [19/20][7/510] Data 3.071 (3.299) Batch 31.601 (30.586) Remain 08:36:24 loss: 0.2599 loss_seg: 0.1719 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:18:17,740 INFO misc.py line 117 726] Train: [19/20][8/510] Data 4.041 (3.447) Batch 29.929 (30.455) Remain 08:33:40 loss: 0.2081 loss_seg: 0.1191 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:18:47,690 INFO misc.py line 117 726] Train: [19/20][9/510] Data 2.817 (3.342) Batch 29.950 (30.371) Remain 08:31:44 loss: 0.2730 loss_seg: 0.1660 loss_superpoint_edge: 0.0422 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:19:22,460 INFO misc.py line 117 726] Train: [19/20][10/510] Data 4.697 (3.536) Batch 34.769 (30.999) Remain 08:41:49 loss: 0.2590 loss_seg: 0.1627 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:19:59,780 INFO misc.py line 117 726] Train: [19/20][11/510] Data 8.598 (4.169) Batch 37.320 (31.789) Remain 08:54:35 loss: 0.3959 loss_seg: 0.2927 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:20:32,662 INFO misc.py line 117 726] Train: [19/20][12/510] Data 5.310 (4.296) Batch 32.882 (31.911) Remain 08:56:05 loss: 0.2524 loss_seg: 0.1537 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:20:48,752 INFO misc.py line 117 726] Train: [19/20][13/510] Data 1.298 (3.996) Batch 16.090 (30.329) Remain 08:29:00 loss: 0.2221 loss_seg: 0.1321 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:21:12,126 INFO misc.py line 117 726] Train: [19/20][14/510] Data 2.336 (3.845) Batch 23.374 (29.696) Remain 08:17:54 loss: 0.1641 loss_seg: 0.0813 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:21:35,979 INFO misc.py line 117 726] Train: [19/20][15/510] Data 1.681 (3.665) Batch 23.854 (29.209) Remain 08:09:15 loss: 0.2678 loss_seg: 0.1712 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:22:08,184 INFO misc.py line 117 726] Train: [19/20][16/510] Data 3.511 (3.653) Batch 32.204 (29.440) Remain 08:12:37 loss: 0.2412 loss_seg: 0.1432 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:22:39,582 INFO misc.py line 117 726] Train: [19/20][17/510] Data 3.243 (3.623) Batch 31.398 (29.580) Remain 08:14:28 loss: 0.2515 loss_seg: 0.1542 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:23:05,164 INFO misc.py line 117 726] Train: [19/20][18/510] Data 3.035 (3.584) Batch 25.582 (29.313) Remain 08:09:31 loss: 0.2425 loss_seg: 0.1483 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:23:32,587 INFO misc.py line 117 726] Train: [19/20][19/510] Data 3.070 (3.552) Batch 27.423 (29.195) Remain 08:07:04 loss: 0.2724 loss_seg: 0.1759 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:24:03,196 INFO misc.py line 117 726] Train: [19/20][20/510] Data 5.264 (3.653) Batch 30.609 (29.278) Remain 08:07:58 loss: 0.3565 loss_seg: 0.2476 loss_superpoint_edge: 0.0417 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:24:27,693 INFO misc.py line 117 726] Train: [19/20][21/510] Data 3.125 (3.623) Batch 24.496 (29.013) Remain 08:03:03 loss: 0.2228 loss_seg: 0.1305 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:24:59,361 INFO misc.py line 117 726] Train: [19/20][22/510] Data 5.187 (3.706) Batch 31.669 (29.152) Remain 08:04:54 loss: 0.1889 loss_seg: 0.1005 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:25:31,726 INFO misc.py line 117 726] Train: [19/20][23/510] Data 4.334 (3.737) Batch 32.365 (29.313) Remain 08:07:05 loss: 0.2185 loss_seg: 0.1298 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:26:00,760 INFO misc.py line 117 726] Train: [19/20][24/510] Data 3.190 (3.711) Batch 29.034 (29.300) Remain 08:06:22 loss: 0.2331 loss_seg: 0.1408 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:26:26,070 INFO misc.py line 117 726] Train: [19/20][25/510] Data 2.090 (3.637) Batch 25.310 (29.118) Remain 08:02:52 loss: 0.2500 loss_seg: 0.1552 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:26:50,421 INFO misc.py line 117 726] Train: [19/20][26/510] Data 2.821 (3.602) Batch 24.350 (28.911) Remain 07:58:57 loss: 0.2531 loss_seg: 0.1519 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:27:14,877 INFO misc.py line 117 726] Train: [19/20][27/510] Data 4.624 (3.645) Batch 24.456 (28.725) Remain 07:55:24 loss: 0.4065 loss_seg: 0.2968 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:27:47,642 INFO misc.py line 117 726] Train: [19/20][28/510] Data 6.671 (3.766) Batch 32.765 (28.887) Remain 07:57:35 loss: 0.4317 loss_seg: 0.3274 loss_superpoint_edge: 0.0374 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:28:16,574 INFO misc.py line 117 726] Train: [19/20][29/510] Data 2.717 (3.725) Batch 28.932 (28.889) Remain 07:57:08 loss: 0.2413 loss_seg: 0.1520 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:28:42,522 INFO misc.py line 117 726] Train: [19/20][30/510] Data 3.248 (3.708) Batch 25.948 (28.780) Remain 07:54:52 loss: 0.2087 loss_seg: 0.1185 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:29:05,001 INFO misc.py line 117 726] Train: [19/20][31/510] Data 2.568 (3.667) Batch 22.480 (28.555) Remain 07:50:40 loss: 0.2595 loss_seg: 0.1642 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:29:31,135 INFO misc.py line 117 726] Train: [19/20][32/510] Data 3.478 (3.660) Batch 26.134 (28.471) Remain 07:48:49 loss: 0.2276 loss_seg: 0.1418 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:29:59,689 INFO misc.py line 117 726] Train: [19/20][33/510] Data 4.243 (3.680) Batch 28.554 (28.474) Remain 07:48:23 loss: 0.2581 loss_seg: 0.1655 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:30:27,986 INFO misc.py line 117 726] Train: [19/20][34/510] Data 4.742 (3.714) Batch 28.298 (28.468) Remain 07:47:49 loss: 0.3357 loss_seg: 0.2436 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:30:59,705 INFO misc.py line 117 726] Train: [19/20][35/510] Data 6.004 (3.786) Batch 31.719 (28.570) Remain 07:49:01 loss: 0.1980 loss_seg: 0.1122 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:31:34,233 INFO misc.py line 117 726] Train: [19/20][36/510] Data 3.429 (3.775) Batch 34.527 (28.751) Remain 07:51:30 loss: 0.2007 loss_seg: 0.1116 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:32:11,140 INFO misc.py line 117 726] Train: [19/20][37/510] Data 7.655 (3.889) Batch 36.907 (28.990) Remain 07:54:57 loss: 0.2776 loss_seg: 0.1759 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:32:46,016 INFO misc.py line 117 726] Train: [19/20][38/510] Data 6.578 (3.966) Batch 34.875 (29.159) Remain 07:57:13 loss: 0.2282 loss_seg: 0.1359 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:33:25,123 INFO misc.py line 117 726] Train: [19/20][39/510] Data 4.630 (3.984) Batch 39.108 (29.435) Remain 08:01:15 loss: 0.2233 loss_seg: 0.1324 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:33:47,508 INFO misc.py line 117 726] Train: [19/20][40/510] Data 2.952 (3.956) Batch 22.385 (29.244) Remain 07:57:39 loss: 0.2467 loss_seg: 0.1514 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:34:14,634 INFO misc.py line 117 726] Train: [19/20][41/510] Data 2.401 (3.915) Batch 27.126 (29.189) Remain 07:56:15 loss: 0.2066 loss_seg: 0.1194 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:34:31,101 INFO misc.py line 117 726] Train: [19/20][42/510] Data 2.539 (3.880) Batch 16.466 (28.862) Remain 07:50:27 loss: 0.2870 loss_seg: 0.1830 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:35:00,851 INFO misc.py line 117 726] Train: [19/20][43/510] Data 3.309 (3.866) Batch 29.751 (28.885) Remain 07:50:20 loss: 0.2358 loss_seg: 0.1409 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:35:23,240 INFO misc.py line 117 726] Train: [19/20][44/510] Data 5.251 (3.900) Batch 22.389 (28.726) Remain 07:47:16 loss: 0.2116 loss_seg: 0.1169 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:35:43,166 INFO misc.py line 117 726] Train: [19/20][45/510] Data 2.552 (3.867) Batch 19.926 (28.517) Remain 07:43:23 loss: 0.2525 loss_seg: 0.1558 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:36:08,872 INFO misc.py line 117 726] Train: [19/20][46/510] Data 4.185 (3.875) Batch 25.705 (28.451) Remain 07:41:51 loss: 0.3544 loss_seg: 0.2460 loss_superpoint_edge: 0.0402 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:36:32,627 INFO misc.py line 117 726] Train: [19/20][47/510] Data 3.705 (3.871) Batch 23.756 (28.345) Remain 07:39:39 loss: 0.1730 loss_seg: 0.0866 loss_superpoint_edge: 0.0133 loss_superpoint_contrast: 0.0431 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:37:06,523 INFO misc.py line 117 726] Train: [19/20][48/510] Data 4.699 (3.889) Batch 33.895 (28.468) Remain 07:41:10 loss: 0.1962 loss_seg: 0.1080 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:37:38,697 INFO misc.py line 117 726] Train: [19/20][49/510] Data 7.937 (3.977) Batch 32.175 (28.549) Remain 07:42:00 loss: 0.2612 loss_seg: 0.1608 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:38:06,043 INFO misc.py line 117 726] Train: [19/20][50/510] Data 2.597 (3.948) Batch 27.346 (28.523) Remain 07:41:07 loss: 0.2325 loss_seg: 0.1386 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:38:06,044 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 18:38:36,443 INFO misc.py line 117 726] Train: [19/20][51/510] Data 3.772 (3.944) Batch 30.400 (28.562) Remain 07:41:16 loss: 0.2511 loss_seg: 0.1534 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:39:12,246 INFO misc.py line 117 726] Train: [19/20][52/510] Data 9.737 (4.063) Batch 35.802 (28.710) Remain 07:43:11 loss: 0.2056 loss_seg: 0.1181 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:39:34,459 INFO misc.py line 117 726] Train: [19/20][53/510] Data 2.241 (4.026) Batch 22.214 (28.580) Remain 07:40:36 loss: 0.3198 loss_seg: 0.1995 loss_superpoint_edge: 0.0534 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:40:07,750 INFO misc.py line 117 726] Train: [19/20][54/510] Data 3.594 (4.018) Batch 33.291 (28.672) Remain 07:41:37 loss: 0.2619 loss_seg: 0.1682 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:40:37,878 INFO misc.py line 117 726] Train: [19/20][55/510] Data 5.829 (4.052) Batch 30.128 (28.700) Remain 07:41:35 loss: 0.1904 loss_seg: 0.1054 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:41:04,465 INFO misc.py line 117 726] Train: [19/20][56/510] Data 2.874 (4.030) Batch 26.587 (28.660) Remain 07:40:28 loss: 0.2690 loss_seg: 0.1767 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:41:32,062 INFO misc.py line 117 726] Train: [19/20][57/510] Data 3.578 (4.022) Batch 27.596 (28.641) Remain 07:39:40 loss: 0.2830 loss_seg: 0.1763 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:42:03,872 INFO misc.py line 117 726] Train: [19/20][58/510] Data 5.148 (4.042) Batch 31.811 (28.698) Remain 07:40:07 loss: 0.2675 loss_seg: 0.1729 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:42:32,569 INFO misc.py line 117 726] Train: [19/20][59/510] Data 3.605 (4.035) Batch 28.697 (28.698) Remain 07:39:39 loss: 0.2652 loss_seg: 0.1651 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:43:00,851 INFO misc.py line 117 726] Train: [19/20][60/510] Data 3.072 (4.018) Batch 28.282 (28.691) Remain 07:39:03 loss: 0.1996 loss_seg: 0.1114 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:43:22,769 INFO misc.py line 117 726] Train: [19/20][61/510] Data 2.757 (3.996) Batch 21.918 (28.574) Remain 07:36:42 loss: 0.2198 loss_seg: 0.1236 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:43:50,130 INFO misc.py line 117 726] Train: [19/20][62/510] Data 2.562 (3.972) Batch 27.361 (28.554) Remain 07:35:54 loss: 0.2002 loss_seg: 0.1135 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:44:20,178 INFO misc.py line 117 726] Train: [19/20][63/510] Data 5.454 (3.996) Batch 30.048 (28.579) Remain 07:35:49 loss: 0.2117 loss_seg: 0.1222 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:44:57,316 INFO misc.py line 117 726] Train: [19/20][64/510] Data 5.074 (4.014) Batch 37.138 (28.719) Remain 07:37:35 loss: 0.1965 loss_seg: 0.1131 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:45:25,366 INFO misc.py line 117 726] Train: [19/20][65/510] Data 2.769 (3.994) Batch 28.051 (28.708) Remain 07:36:56 loss: 0.2350 loss_seg: 0.1410 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:45:50,130 INFO misc.py line 117 726] Train: [19/20][66/510] Data 3.286 (3.983) Batch 24.763 (28.645) Remain 07:35:27 loss: 0.2055 loss_seg: 0.1146 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:46:15,690 INFO misc.py line 117 726] Train: [19/20][67/510] Data 2.789 (3.964) Batch 25.560 (28.597) Remain 07:34:13 loss: 0.1849 loss_seg: 0.1023 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:46:35,873 INFO misc.py line 117 726] Train: [19/20][68/510] Data 2.244 (3.938) Batch 20.183 (28.468) Remain 07:31:41 loss: 0.2563 loss_seg: 0.1608 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:47:03,090 INFO misc.py line 117 726] Train: [19/20][69/510] Data 4.749 (3.950) Batch 27.217 (28.449) Remain 07:30:54 loss: 0.2037 loss_seg: 0.1139 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:47:35,751 INFO misc.py line 117 726] Train: [19/20][70/510] Data 5.792 (3.977) Batch 32.661 (28.512) Remain 07:31:26 loss: 0.2222 loss_seg: 0.1321 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:47:58,468 INFO misc.py line 117 726] Train: [19/20][71/510] Data 2.163 (3.951) Batch 22.718 (28.427) Remain 07:29:36 loss: 0.2671 loss_seg: 0.1767 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:48:26,808 INFO misc.py line 117 726] Train: [19/20][72/510] Data 4.973 (3.966) Batch 28.340 (28.425) Remain 07:29:07 loss: 0.2108 loss_seg: 0.1190 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:48:53,175 INFO misc.py line 117 726] Train: [19/20][73/510] Data 2.529 (3.945) Batch 26.368 (28.396) Remain 07:28:10 loss: 0.2447 loss_seg: 0.1465 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:49:25,495 INFO misc.py line 117 726] Train: [19/20][74/510] Data 2.825 (3.929) Batch 32.319 (28.451) Remain 07:28:34 loss: 0.2176 loss_seg: 0.1248 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:49:48,672 INFO misc.py line 117 726] Train: [19/20][75/510] Data 3.013 (3.916) Batch 23.177 (28.378) Remain 07:26:57 loss: 0.3533 loss_seg: 0.2592 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:50:14,005 INFO misc.py line 117 726] Train: [19/20][76/510] Data 3.774 (3.915) Batch 25.332 (28.336) Remain 07:25:49 loss: 0.2065 loss_seg: 0.1158 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:50:43,393 INFO misc.py line 117 726] Train: [19/20][77/510] Data 5.502 (3.936) Batch 29.389 (28.350) Remain 07:25:34 loss: 0.1913 loss_seg: 0.1043 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:51:15,752 INFO misc.py line 117 726] Train: [19/20][78/510] Data 3.364 (3.928) Batch 32.359 (28.404) Remain 07:25:56 loss: 0.2641 loss_seg: 0.1680 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:51:35,934 INFO misc.py line 117 726] Train: [19/20][79/510] Data 2.605 (3.911) Batch 20.181 (28.296) Remain 07:23:46 loss: 0.3042 loss_seg: 0.1971 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:52:01,488 INFO misc.py line 117 726] Train: [19/20][80/510] Data 2.679 (3.895) Batch 25.555 (28.260) Remain 07:22:44 loss: 0.2840 loss_seg: 0.1765 loss_superpoint_edge: 0.0392 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:52:22,066 INFO misc.py line 117 726] Train: [19/20][81/510] Data 2.144 (3.873) Batch 20.577 (28.162) Remain 07:20:43 loss: 0.1874 loss_seg: 0.1002 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:52:47,846 INFO misc.py line 117 726] Train: [19/20][82/510] Data 4.141 (3.876) Batch 25.780 (28.131) Remain 07:19:47 loss: 0.2232 loss_seg: 0.1295 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:53:11,419 INFO misc.py line 117 726] Train: [19/20][83/510] Data 2.543 (3.859) Batch 23.572 (28.074) Remain 07:18:25 loss: 0.2043 loss_seg: 0.1176 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:53:47,494 INFO misc.py line 117 726] Train: [19/20][84/510] Data 10.332 (3.939) Batch 36.076 (28.173) Remain 07:19:30 loss: 0.3540 loss_seg: 0.2454 loss_superpoint_edge: 0.0400 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0343 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:54:20,361 INFO misc.py line 117 726] Train: [19/20][85/510] Data 10.414 (4.018) Batch 32.867 (28.230) Remain 07:19:55 loss: 0.2142 loss_seg: 0.1223 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:54:50,590 INFO misc.py line 117 726] Train: [19/20][86/510] Data 3.825 (4.016) Batch 30.228 (28.255) Remain 07:19:49 loss: 0.2496 loss_seg: 0.1523 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:55:17,668 INFO misc.py line 117 726] Train: [19/20][87/510] Data 2.402 (3.997) Batch 27.079 (28.241) Remain 07:19:08 loss: 0.2666 loss_seg: 0.1699 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:55:47,463 INFO misc.py line 117 726] Train: [19/20][88/510] Data 3.354 (3.989) Batch 29.794 (28.259) Remain 07:18:57 loss: 0.2121 loss_seg: 0.1201 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:56:14,315 INFO misc.py line 117 726] Train: [19/20][89/510] Data 3.047 (3.978) Batch 26.852 (28.242) Remain 07:18:13 loss: 0.2715 loss_seg: 0.1777 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:56:49,391 INFO misc.py line 117 726] Train: [19/20][90/510] Data 3.945 (3.978) Batch 35.076 (28.321) Remain 07:18:58 loss: 0.2264 loss_seg: 0.1363 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:57:27,087 INFO misc.py line 117 726] Train: [19/20][91/510] Data 7.296 (4.015) Batch 37.696 (28.428) Remain 07:20:09 loss: 0.4401 loss_seg: 0.3270 loss_superpoint_edge: 0.0462 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:57:56,577 INFO misc.py line 117 726] Train: [19/20][92/510] Data 4.128 (4.017) Batch 29.490 (28.439) Remain 07:19:51 loss: 0.2705 loss_seg: 0.1700 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:58:23,378 INFO misc.py line 117 726] Train: [19/20][93/510] Data 3.039 (4.006) Batch 26.801 (28.421) Remain 07:19:06 loss: 0.3432 loss_seg: 0.2300 loss_superpoint_edge: 0.0459 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:58:44,191 INFO misc.py line 117 726] Train: [19/20][94/510] Data 2.354 (3.988) Batch 20.813 (28.338) Remain 07:17:20 loss: 0.3335 loss_seg: 0.2214 loss_superpoint_edge: 0.0453 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:59:12,978 INFO misc.py line 117 726] Train: [19/20][95/510] Data 4.045 (3.988) Batch 28.787 (28.343) Remain 07:16:56 loss: 0.2431 loss_seg: 0.1479 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 18:59:52,699 INFO misc.py line 117 726] Train: [19/20][96/510] Data 10.188 (4.055) Batch 39.721 (28.465) Remain 07:18:21 loss: 0.1961 loss_seg: 0.1098 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:00:33,563 INFO misc.py line 117 726] Train: [19/20][97/510] Data 6.390 (4.080) Batch 40.864 (28.597) Remain 07:19:54 loss: 0.2292 loss_seg: 0.1401 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:01:02,994 INFO misc.py line 117 726] Train: [19/20][98/510] Data 3.423 (4.073) Batch 29.431 (28.606) Remain 07:19:34 loss: 0.2863 loss_seg: 0.1903 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:01:32,176 INFO misc.py line 117 726] Train: [19/20][99/510] Data 3.499 (4.067) Batch 29.182 (28.612) Remain 07:19:11 loss: 0.2745 loss_seg: 0.1775 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:02:08,877 INFO misc.py line 117 726] Train: [19/20][100/510] Data 6.207 (4.089) Batch 36.701 (28.695) Remain 07:19:59 loss: 0.2398 loss_seg: 0.1435 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:02:08,877 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 19:02:42,744 INFO misc.py line 117 726] Train: [19/20][101/510] Data 3.527 (4.083) Batch 33.867 (28.748) Remain 07:20:19 loss: 0.3048 loss_seg: 0.2140 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:03:06,907 INFO misc.py line 117 726] Train: [19/20][102/510] Data 5.062 (4.093) Batch 24.163 (28.701) Remain 07:19:07 loss: 0.2216 loss_seg: 0.1244 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:03:41,509 INFO misc.py line 117 726] Train: [19/20][103/510] Data 3.057 (4.083) Batch 34.601 (28.760) Remain 07:19:33 loss: 0.2597 loss_seg: 0.1617 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:04:08,705 INFO misc.py line 117 726] Train: [19/20][104/510] Data 2.622 (4.068) Batch 27.197 (28.745) Remain 07:18:50 loss: 0.2437 loss_seg: 0.1492 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:04:34,327 INFO misc.py line 117 726] Train: [19/20][105/510] Data 3.485 (4.063) Batch 25.621 (28.714) Remain 07:17:53 loss: 0.2794 loss_seg: 0.1769 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:05:03,370 INFO misc.py line 117 726] Train: [19/20][106/510] Data 3.075 (4.053) Batch 29.043 (28.718) Remain 07:17:27 loss: 0.2463 loss_seg: 0.1559 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:05:29,421 INFO misc.py line 117 726] Train: [19/20][107/510] Data 2.748 (4.040) Batch 26.052 (28.692) Remain 07:16:35 loss: 0.2446 loss_seg: 0.1470 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:05:59,094 INFO misc.py line 117 726] Train: [19/20][108/510] Data 3.581 (4.036) Batch 29.672 (28.701) Remain 07:16:15 loss: 0.3457 loss_seg: 0.2405 loss_superpoint_edge: 0.0389 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:06:25,251 INFO misc.py line 117 726] Train: [19/20][109/510] Data 2.240 (4.019) Batch 26.157 (28.677) Remain 07:15:24 loss: 0.2284 loss_seg: 0.1343 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:06:48,129 INFO misc.py line 117 726] Train: [19/20][110/510] Data 2.852 (4.008) Batch 22.878 (28.623) Remain 07:14:06 loss: 0.2989 loss_seg: 0.1935 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:07:26,984 INFO misc.py line 117 726] Train: [19/20][111/510] Data 6.754 (4.034) Batch 38.855 (28.718) Remain 07:15:04 loss: 0.1633 loss_seg: 0.0806 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:08:04,579 INFO misc.py line 117 726] Train: [19/20][112/510] Data 5.576 (4.048) Batch 37.595 (28.799) Remain 07:15:49 loss: 0.2528 loss_seg: 0.1605 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:08:28,765 INFO misc.py line 117 726] Train: [19/20][113/510] Data 2.405 (4.033) Batch 24.186 (28.757) Remain 07:14:42 loss: 0.3606 loss_seg: 0.2468 loss_superpoint_edge: 0.0449 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:08:43,427 INFO misc.py line 117 726] Train: [19/20][114/510] Data 1.853 (4.013) Batch 14.662 (28.630) Remain 07:12:19 loss: 0.2370 loss_seg: 0.1410 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:09:06,704 INFO misc.py line 117 726] Train: [19/20][115/510] Data 4.455 (4.017) Batch 23.277 (28.582) Remain 07:11:07 loss: 0.2723 loss_seg: 0.1655 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:09:36,526 INFO misc.py line 117 726] Train: [19/20][116/510] Data 5.039 (4.026) Batch 29.822 (28.593) Remain 07:10:48 loss: 0.2055 loss_seg: 0.1201 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:09:58,559 INFO misc.py line 117 726] Train: [19/20][117/510] Data 2.471 (4.013) Batch 22.033 (28.536) Remain 07:09:27 loss: 0.2264 loss_seg: 0.1377 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:10:32,221 INFO misc.py line 117 726] Train: [19/20][118/510] Data 3.234 (4.006) Batch 33.662 (28.580) Remain 07:09:39 loss: 0.2388 loss_seg: 0.1461 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:10:51,806 INFO misc.py line 117 726] Train: [19/20][119/510] Data 2.041 (3.989) Batch 19.585 (28.503) Remain 07:08:01 loss: 0.3046 loss_seg: 0.1980 loss_superpoint_edge: 0.0397 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:11:17,205 INFO misc.py line 117 726] Train: [19/20][120/510] Data 2.294 (3.974) Batch 25.398 (28.476) Remain 07:07:08 loss: 0.2329 loss_seg: 0.1422 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:11:40,750 INFO misc.py line 117 726] Train: [19/20][121/510] Data 5.039 (3.983) Batch 23.546 (28.435) Remain 07:06:02 loss: 0.2158 loss_seg: 0.1276 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:12:01,810 INFO misc.py line 117 726] Train: [19/20][122/510] Data 2.111 (3.968) Batch 21.060 (28.373) Remain 07:04:38 loss: 0.2475 loss_seg: 0.1514 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:12:32,844 INFO misc.py line 117 726] Train: [19/20][123/510] Data 3.908 (3.967) Batch 31.033 (28.395) Remain 07:04:30 loss: 0.2220 loss_seg: 0.1286 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:12:55,143 INFO misc.py line 117 726] Train: [19/20][124/510] Data 2.462 (3.955) Batch 22.299 (28.344) Remain 07:03:16 loss: 0.2535 loss_seg: 0.1518 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:13:27,823 INFO misc.py line 117 726] Train: [19/20][125/510] Data 3.040 (3.947) Batch 32.680 (28.380) Remain 07:03:20 loss: 0.2970 loss_seg: 0.1917 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:14:02,481 INFO misc.py line 117 726] Train: [19/20][126/510] Data 6.448 (3.968) Batch 34.659 (28.431) Remain 07:03:37 loss: 0.2134 loss_seg: 0.1236 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:14:31,289 INFO misc.py line 117 726] Train: [19/20][127/510] Data 3.769 (3.966) Batch 28.808 (28.434) Remain 07:03:11 loss: 0.2726 loss_seg: 0.1691 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:15:09,486 INFO misc.py line 117 726] Train: [19/20][128/510] Data 6.593 (3.987) Batch 38.196 (28.512) Remain 07:03:52 loss: 0.2902 loss_seg: 0.1892 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:15:42,755 INFO misc.py line 117 726] Train: [19/20][129/510] Data 3.848 (3.986) Batch 33.269 (28.550) Remain 07:03:57 loss: 0.2808 loss_seg: 0.1851 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:16:15,745 INFO misc.py line 117 726] Train: [19/20][130/510] Data 3.079 (3.979) Batch 32.991 (28.585) Remain 07:04:00 loss: 0.1986 loss_seg: 0.1107 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:16:41,452 INFO misc.py line 117 726] Train: [19/20][131/510] Data 3.193 (3.973) Batch 25.707 (28.562) Remain 07:03:11 loss: 0.2060 loss_seg: 0.1187 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:17:15,060 INFO misc.py line 117 726] Train: [19/20][132/510] Data 5.228 (3.982) Batch 33.608 (28.602) Remain 07:03:18 loss: 0.2759 loss_seg: 0.1761 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:17:49,672 INFO misc.py line 117 726] Train: [19/20][133/510] Data 5.437 (3.993) Batch 34.612 (28.648) Remain 07:03:30 loss: 0.2959 loss_seg: 0.1841 loss_superpoint_edge: 0.0452 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:18:01,479 INFO misc.py line 117 726] Train: [19/20][134/510] Data 1.627 (3.975) Batch 11.807 (28.519) Remain 07:01:07 loss: 0.2101 loss_seg: 0.1204 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:18:31,765 INFO misc.py line 117 726] Train: [19/20][135/510] Data 3.114 (3.969) Batch 30.286 (28.533) Remain 07:00:51 loss: 0.2695 loss_seg: 0.1673 loss_superpoint_edge: 0.0360 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:18:57,052 INFO misc.py line 117 726] Train: [19/20][136/510] Data 3.167 (3.963) Batch 25.287 (28.508) Remain 07:00:01 loss: 0.2300 loss_seg: 0.1378 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:19:30,939 INFO misc.py line 117 726] Train: [19/20][137/510] Data 9.653 (4.005) Batch 33.887 (28.548) Remain 07:00:08 loss: 0.3727 loss_seg: 0.2778 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0443 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:19:58,601 INFO misc.py line 117 726] Train: [19/20][138/510] Data 8.325 (4.037) Batch 27.662 (28.542) Remain 06:59:33 loss: 0.5593 loss_seg: 0.4052 loss_superpoint_edge: 0.0859 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:20:29,227 INFO misc.py line 117 726] Train: [19/20][139/510] Data 3.108 (4.030) Batch 30.626 (28.557) Remain 06:59:18 loss: 0.1911 loss_seg: 0.1034 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:20:59,551 INFO misc.py line 117 726] Train: [19/20][140/510] Data 3.958 (4.030) Batch 30.324 (28.570) Remain 06:59:01 loss: 0.2499 loss_seg: 0.1522 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:21:29,062 INFO misc.py line 117 726] Train: [19/20][141/510] Data 4.599 (4.034) Batch 29.511 (28.577) Remain 06:58:38 loss: 0.2412 loss_seg: 0.1483 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:21:56,578 INFO misc.py line 117 726] Train: [19/20][142/510] Data 4.755 (4.039) Batch 27.516 (28.569) Remain 06:58:03 loss: 0.2921 loss_seg: 0.1954 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:22:24,063 INFO misc.py line 117 726] Train: [19/20][143/510] Data 4.743 (4.044) Batch 27.485 (28.561) Remain 06:57:28 loss: 0.1896 loss_seg: 0.1032 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:22:58,028 INFO misc.py line 117 726] Train: [19/20][144/510] Data 5.261 (4.053) Batch 33.965 (28.600) Remain 06:57:33 loss: 0.3131 loss_seg: 0.2166 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:23:24,388 INFO misc.py line 117 726] Train: [19/20][145/510] Data 3.263 (4.047) Batch 26.360 (28.584) Remain 06:56:50 loss: 0.2080 loss_seg: 0.1162 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:23:55,950 INFO misc.py line 117 726] Train: [19/20][146/510] Data 2.570 (4.037) Batch 31.562 (28.605) Remain 06:56:40 loss: 0.3740 loss_seg: 0.2667 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:24:22,179 INFO misc.py line 117 726] Train: [19/20][147/510] Data 2.555 (4.027) Batch 26.229 (28.588) Remain 06:55:57 loss: 0.2135 loss_seg: 0.1201 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:24:59,961 INFO misc.py line 117 726] Train: [19/20][148/510] Data 6.394 (4.043) Batch 37.782 (28.652) Remain 06:56:24 loss: 0.2124 loss_seg: 0.1204 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:25:35,118 INFO misc.py line 117 726] Train: [19/20][149/510] Data 6.952 (4.063) Batch 35.156 (28.696) Remain 06:56:34 loss: 0.2096 loss_seg: 0.1243 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:26:01,551 INFO misc.py line 117 726] Train: [19/20][150/510] Data 3.372 (4.058) Batch 26.433 (28.681) Remain 06:55:52 loss: 0.2237 loss_seg: 0.1330 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:26:01,551 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 19:26:23,563 INFO misc.py line 117 726] Train: [19/20][151/510] Data 2.632 (4.049) Batch 22.012 (28.636) Remain 06:54:44 loss: 0.2899 loss_seg: 0.1808 loss_superpoint_edge: 0.0424 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:26:49,315 INFO misc.py line 117 726] Train: [19/20][152/510] Data 3.124 (4.042) Batch 25.752 (28.616) Remain 06:53:59 loss: 0.2488 loss_seg: 0.1528 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:27:27,462 INFO misc.py line 117 726] Train: [19/20][153/510] Data 10.240 (4.084) Batch 38.147 (28.680) Remain 06:54:25 loss: 0.3083 loss_seg: 0.2061 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:28:05,913 INFO misc.py line 117 726] Train: [19/20][154/510] Data 7.314 (4.105) Batch 38.450 (28.745) Remain 06:54:52 loss: 0.2413 loss_seg: 0.1493 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:28:19,315 INFO misc.py line 117 726] Train: [19/20][155/510] Data 1.656 (4.089) Batch 13.402 (28.644) Remain 06:52:56 loss: 0.2577 loss_seg: 0.1615 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:28:52,111 INFO misc.py line 117 726] Train: [19/20][156/510] Data 3.495 (4.085) Batch 32.797 (28.671) Remain 06:52:51 loss: 0.2056 loss_seg: 0.1138 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:29:26,656 INFO misc.py line 117 726] Train: [19/20][157/510] Data 4.846 (4.090) Batch 34.545 (28.709) Remain 06:52:55 loss: 0.2655 loss_seg: 0.1730 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:29:51,433 INFO misc.py line 117 726] Train: [19/20][158/510] Data 3.268 (4.085) Batch 24.777 (28.684) Remain 06:52:05 loss: 0.3074 loss_seg: 0.2068 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:30:20,703 INFO misc.py line 117 726] Train: [19/20][159/510] Data 3.638 (4.082) Batch 29.270 (28.687) Remain 06:51:39 loss: 0.2493 loss_seg: 0.1517 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:30:47,885 INFO misc.py line 117 726] Train: [19/20][160/510] Data 2.717 (4.073) Batch 27.182 (28.678) Remain 06:51:02 loss: 0.2498 loss_seg: 0.1544 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:31:18,080 INFO misc.py line 117 726] Train: [19/20][161/510] Data 3.353 (4.069) Batch 30.195 (28.687) Remain 06:50:42 loss: 0.2009 loss_seg: 0.1136 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:31:47,924 INFO misc.py line 117 726] Train: [19/20][162/510] Data 4.395 (4.071) Batch 29.844 (28.695) Remain 06:50:20 loss: 0.2687 loss_seg: 0.1677 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:32:20,586 INFO misc.py line 117 726] Train: [19/20][163/510] Data 4.988 (4.076) Batch 32.661 (28.719) Remain 06:50:12 loss: 0.1902 loss_seg: 0.1077 loss_superpoint_edge: 0.0115 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:32:50,588 INFO misc.py line 117 726] Train: [19/20][164/510] Data 3.151 (4.071) Batch 30.002 (28.727) Remain 06:49:50 loss: 0.1704 loss_seg: 0.0888 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:33:12,417 INFO misc.py line 117 726] Train: [19/20][165/510] Data 2.524 (4.061) Batch 21.829 (28.685) Remain 06:48:45 loss: 0.2377 loss_seg: 0.1396 loss_superpoint_edge: 0.0280 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:33:40,167 INFO misc.py line 117 726] Train: [19/20][166/510] Data 2.736 (4.053) Batch 27.750 (28.679) Remain 06:48:11 loss: 0.2628 loss_seg: 0.1562 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:34:16,917 INFO misc.py line 117 726] Train: [19/20][167/510] Data 7.867 (4.076) Batch 36.750 (28.728) Remain 06:48:25 loss: 0.3545 loss_seg: 0.2437 loss_superpoint_edge: 0.0431 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:34:38,737 INFO misc.py line 117 726] Train: [19/20][168/510] Data 2.030 (4.064) Batch 21.819 (28.686) Remain 06:47:20 loss: 0.2116 loss_seg: 0.1207 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:35:01,107 INFO misc.py line 117 726] Train: [19/20][169/510] Data 3.029 (4.058) Batch 22.371 (28.648) Remain 06:46:19 loss: 0.1560 loss_seg: 0.0711 loss_superpoint_edge: 0.0130 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:35:26,262 INFO misc.py line 117 726] Train: [19/20][170/510] Data 1.947 (4.045) Batch 25.154 (28.628) Remain 06:45:33 loss: 0.2803 loss_seg: 0.1740 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:35:57,590 INFO misc.py line 117 726] Train: [19/20][171/510] Data 3.851 (4.044) Batch 31.329 (28.644) Remain 06:45:18 loss: 0.2260 loss_seg: 0.1337 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:36:26,350 INFO misc.py line 117 726] Train: [19/20][172/510] Data 2.297 (4.034) Batch 28.760 (28.644) Remain 06:44:50 loss: 0.1947 loss_seg: 0.1070 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:36:49,240 INFO misc.py line 117 726] Train: [19/20][173/510] Data 2.291 (4.023) Batch 22.890 (28.610) Remain 06:43:53 loss: 0.2027 loss_seg: 0.1096 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0398 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:37:18,373 INFO misc.py line 117 726] Train: [19/20][174/510] Data 6.393 (4.037) Batch 29.133 (28.613) Remain 06:43:27 loss: 0.2848 loss_seg: 0.1871 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:37:47,871 INFO misc.py line 117 726] Train: [19/20][175/510] Data 2.244 (4.027) Batch 29.498 (28.619) Remain 06:43:02 loss: 0.2365 loss_seg: 0.1380 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:38:11,016 INFO misc.py line 117 726] Train: [19/20][176/510] Data 2.169 (4.016) Batch 23.145 (28.587) Remain 06:42:07 loss: 0.2132 loss_seg: 0.1205 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:38:44,899 INFO misc.py line 117 726] Train: [19/20][177/510] Data 4.666 (4.020) Batch 33.883 (28.617) Remain 06:42:04 loss: 0.2667 loss_seg: 0.1711 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:39:15,624 INFO misc.py line 117 726] Train: [19/20][178/510] Data 3.336 (4.016) Batch 30.725 (28.629) Remain 06:41:46 loss: 0.2485 loss_seg: 0.1503 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:39:45,690 INFO misc.py line 117 726] Train: [19/20][179/510] Data 7.508 (4.036) Batch 30.066 (28.638) Remain 06:41:24 loss: 0.2293 loss_seg: 0.1378 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:40:10,292 INFO misc.py line 117 726] Train: [19/20][180/510] Data 2.948 (4.029) Batch 24.602 (28.615) Remain 06:40:36 loss: 0.2266 loss_seg: 0.1346 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:40:36,478 INFO misc.py line 117 726] Train: [19/20][181/510] Data 2.842 (4.023) Batch 26.185 (28.601) Remain 06:39:56 loss: 0.2709 loss_seg: 0.1656 loss_superpoint_edge: 0.0377 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:41:08,881 INFO misc.py line 117 726] Train: [19/20][182/510] Data 5.178 (4.029) Batch 32.404 (28.622) Remain 06:39:45 loss: 0.2598 loss_seg: 0.1763 loss_superpoint_edge: 0.0171 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:41:33,322 INFO misc.py line 117 726] Train: [19/20][183/510] Data 2.891 (4.023) Batch 24.441 (28.599) Remain 06:38:57 loss: 0.2753 loss_seg: 0.1741 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:42:02,935 INFO misc.py line 117 726] Train: [19/20][184/510] Data 2.586 (4.015) Batch 29.612 (28.605) Remain 06:38:33 loss: 0.2395 loss_seg: 0.1418 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:42:34,688 INFO misc.py line 117 726] Train: [19/20][185/510] Data 4.094 (4.015) Batch 31.753 (28.622) Remain 06:38:19 loss: 0.2664 loss_seg: 0.1661 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:43:09,916 INFO misc.py line 117 726] Train: [19/20][186/510] Data 3.718 (4.014) Batch 35.229 (28.658) Remain 06:38:20 loss: 0.2241 loss_seg: 0.1332 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:43:41,934 INFO misc.py line 117 726] Train: [19/20][187/510] Data 4.225 (4.015) Batch 32.018 (28.676) Remain 06:38:07 loss: 0.3031 loss_seg: 0.2100 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:44:10,656 INFO misc.py line 117 726] Train: [19/20][188/510] Data 4.159 (4.016) Batch 28.722 (28.677) Remain 06:37:39 loss: 0.2407 loss_seg: 0.1519 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:44:27,061 INFO misc.py line 117 726] Train: [19/20][189/510] Data 2.125 (4.006) Batch 16.406 (28.611) Remain 06:36:15 loss: 0.2122 loss_seg: 0.1201 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0433 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:45:03,987 INFO misc.py line 117 726] Train: [19/20][190/510] Data 5.170 (4.012) Batch 36.925 (28.655) Remain 06:36:23 loss: 0.2000 loss_seg: 0.1144 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:45:29,851 INFO misc.py line 117 726] Train: [19/20][191/510] Data 3.174 (4.007) Batch 25.864 (28.640) Remain 06:35:42 loss: 0.2632 loss_seg: 0.1670 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:45:55,774 INFO misc.py line 117 726] Train: [19/20][192/510] Data 2.691 (4.000) Batch 25.923 (28.626) Remain 06:35:02 loss: 0.2425 loss_seg: 0.1486 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:46:38,350 INFO misc.py line 117 726] Train: [19/20][193/510] Data 10.193 (4.033) Batch 42.576 (28.699) Remain 06:35:34 loss: 0.1895 loss_seg: 0.1010 loss_superpoint_edge: 0.0174 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:47:09,417 INFO misc.py line 117 726] Train: [19/20][194/510] Data 4.839 (4.037) Batch 31.067 (28.712) Remain 06:35:15 loss: 0.2138 loss_seg: 0.1268 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:47:45,282 INFO misc.py line 117 726] Train: [19/20][195/510] Data 9.787 (4.067) Batch 35.865 (28.749) Remain 06:35:17 loss: 0.2290 loss_seg: 0.1373 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0455 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:48:15,027 INFO misc.py line 117 726] Train: [19/20][196/510] Data 4.301 (4.068) Batch 29.745 (28.754) Remain 06:34:53 loss: 0.2629 loss_seg: 0.1690 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:48:43,271 INFO misc.py line 117 726] Train: [19/20][197/510] Data 4.782 (4.072) Batch 28.244 (28.752) Remain 06:34:22 loss: 0.3928 loss_seg: 0.2867 loss_superpoint_edge: 0.0390 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:49:03,526 INFO misc.py line 117 726] Train: [19/20][198/510] Data 2.273 (4.063) Batch 20.256 (28.708) Remain 06:33:17 loss: 0.2095 loss_seg: 0.1175 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:49:29,793 INFO misc.py line 117 726] Train: [19/20][199/510] Data 3.460 (4.060) Batch 26.267 (28.696) Remain 06:32:39 loss: 0.2938 loss_seg: 0.2015 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:49:53,001 INFO misc.py line 117 726] Train: [19/20][200/510] Data 2.860 (4.054) Batch 23.208 (28.668) Remain 06:31:47 loss: 0.3257 loss_seg: 0.2353 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:49:53,002 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 19:50:21,156 INFO misc.py line 117 726] Train: [19/20][201/510] Data 3.548 (4.051) Batch 28.155 (28.665) Remain 06:31:16 loss: 0.2806 loss_seg: 0.1754 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:50:48,710 INFO misc.py line 117 726] Train: [19/20][202/510] Data 3.574 (4.049) Batch 27.554 (28.660) Remain 06:30:43 loss: 0.2150 loss_seg: 0.1243 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:51:21,157 INFO misc.py line 117 726] Train: [19/20][203/510] Data 4.115 (4.049) Batch 32.447 (28.678) Remain 06:30:30 loss: 0.2548 loss_seg: 0.1559 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:51:50,116 INFO misc.py line 117 726] Train: [19/20][204/510] Data 4.090 (4.049) Batch 28.959 (28.680) Remain 06:30:02 loss: 0.3339 loss_seg: 0.2405 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:52:20,526 INFO misc.py line 117 726] Train: [19/20][205/510] Data 3.171 (4.045) Batch 30.410 (28.688) Remain 06:29:41 loss: 0.1765 loss_seg: 0.0909 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:52:52,476 INFO misc.py line 117 726] Train: [19/20][206/510] Data 6.437 (4.057) Batch 31.950 (28.704) Remain 06:29:25 loss: 0.1894 loss_seg: 0.1049 loss_superpoint_edge: 0.0137 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:53:19,519 INFO misc.py line 117 726] Train: [19/20][207/510] Data 2.815 (4.051) Batch 27.043 (28.696) Remain 06:28:50 loss: 0.1989 loss_seg: 0.1132 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:53:50,904 INFO misc.py line 117 726] Train: [19/20][208/510] Data 3.223 (4.047) Batch 31.384 (28.709) Remain 06:28:32 loss: 0.2300 loss_seg: 0.1381 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:54:17,405 INFO misc.py line 117 726] Train: [19/20][209/510] Data 2.787 (4.040) Batch 26.501 (28.699) Remain 06:27:54 loss: 0.2645 loss_seg: 0.1639 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:54:44,504 INFO misc.py line 117 726] Train: [19/20][210/510] Data 3.075 (4.036) Batch 27.099 (28.691) Remain 06:27:19 loss: 0.2391 loss_seg: 0.1448 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:55:21,346 INFO misc.py line 117 726] Train: [19/20][211/510] Data 9.093 (4.060) Batch 36.842 (28.730) Remain 06:27:22 loss: 0.3351 loss_seg: 0.2229 loss_superpoint_edge: 0.0460 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:55:48,693 INFO misc.py line 117 726] Train: [19/20][212/510] Data 3.209 (4.056) Batch 27.346 (28.724) Remain 06:26:48 loss: 0.2293 loss_seg: 0.1324 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:56:22,490 INFO misc.py line 117 726] Train: [19/20][213/510] Data 7.015 (4.070) Batch 33.798 (28.748) Remain 06:26:39 loss: 0.3421 loss_seg: 0.2344 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:56:48,203 INFO misc.py line 117 726] Train: [19/20][214/510] Data 2.825 (4.064) Batch 25.713 (28.733) Remain 06:25:59 loss: 0.2829 loss_seg: 0.1801 loss_superpoint_edge: 0.0344 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:57:20,504 INFO misc.py line 117 726] Train: [19/20][215/510] Data 4.798 (4.068) Batch 32.301 (28.750) Remain 06:25:43 loss: 0.2151 loss_seg: 0.1256 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:57:40,434 INFO misc.py line 117 726] Train: [19/20][216/510] Data 2.324 (4.059) Batch 19.930 (28.709) Remain 06:24:41 loss: 0.2353 loss_seg: 0.1443 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:58:14,029 INFO misc.py line 117 726] Train: [19/20][217/510] Data 4.976 (4.064) Batch 33.595 (28.732) Remain 06:24:31 loss: 0.2318 loss_seg: 0.1392 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:58:42,570 INFO misc.py line 117 726] Train: [19/20][218/510] Data 3.424 (4.061) Batch 28.540 (28.731) Remain 06:24:02 loss: 0.1770 loss_seg: 0.0920 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:59:11,854 INFO misc.py line 117 726] Train: [19/20][219/510] Data 2.651 (4.054) Batch 29.284 (28.733) Remain 06:23:35 loss: 0.2242 loss_seg: 0.1297 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 19:59:37,025 INFO misc.py line 117 726] Train: [19/20][220/510] Data 3.069 (4.050) Batch 25.171 (28.717) Remain 06:22:53 loss: 0.2891 loss_seg: 0.1788 loss_superpoint_edge: 0.0399 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:00:05,709 INFO misc.py line 117 726] Train: [19/20][221/510] Data 3.361 (4.047) Batch 28.684 (28.717) Remain 06:22:24 loss: 0.1973 loss_seg: 0.1103 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0323 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:00:24,829 INFO misc.py line 117 726] Train: [19/20][222/510] Data 2.186 (4.038) Batch 19.119 (28.673) Remain 06:21:20 loss: 0.2056 loss_seg: 0.1117 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:00:50,267 INFO misc.py line 117 726] Train: [19/20][223/510] Data 2.588 (4.031) Batch 25.439 (28.658) Remain 06:20:40 loss: 0.3210 loss_seg: 0.2132 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:01:25,736 INFO misc.py line 117 726] Train: [19/20][224/510] Data 5.422 (4.038) Batch 35.468 (28.689) Remain 06:20:36 loss: 0.2762 loss_seg: 0.1784 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:01:50,743 INFO misc.py line 117 726] Train: [19/20][225/510] Data 2.868 (4.032) Batch 25.008 (28.672) Remain 06:19:54 loss: 0.2520 loss_seg: 0.1543 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:02:15,586 INFO misc.py line 117 726] Train: [19/20][226/510] Data 2.853 (4.027) Batch 24.843 (28.655) Remain 06:19:12 loss: 0.2413 loss_seg: 0.1452 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:02:39,911 INFO misc.py line 117 726] Train: [19/20][227/510] Data 3.158 (4.023) Batch 24.325 (28.636) Remain 06:18:28 loss: 0.2488 loss_seg: 0.1564 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:03:12,405 INFO misc.py line 117 726] Train: [19/20][228/510] Data 4.502 (4.025) Batch 32.494 (28.653) Remain 06:18:13 loss: 0.2357 loss_seg: 0.1444 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:03:37,004 INFO misc.py line 117 726] Train: [19/20][229/510] Data 2.407 (4.018) Batch 24.599 (28.635) Remain 06:17:30 loss: 0.2353 loss_seg: 0.1380 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:04:01,794 INFO misc.py line 117 726] Train: [19/20][230/510] Data 3.239 (4.015) Batch 24.790 (28.618) Remain 06:16:48 loss: 0.2229 loss_seg: 0.1369 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:04:36,096 INFO misc.py line 117 726] Train: [19/20][231/510] Data 3.311 (4.012) Batch 34.303 (28.643) Remain 06:16:39 loss: 0.2757 loss_seg: 0.1899 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:05:07,565 INFO misc.py line 117 726] Train: [19/20][232/510] Data 4.158 (4.012) Batch 31.469 (28.655) Remain 06:16:20 loss: 0.2682 loss_seg: 0.1717 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:05:36,375 INFO misc.py line 117 726] Train: [19/20][233/510] Data 3.556 (4.010) Batch 28.810 (28.656) Remain 06:15:52 loss: 0.2383 loss_seg: 0.1412 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0415 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:05:57,116 INFO misc.py line 117 726] Train: [19/20][234/510] Data 1.547 (4.000) Batch 20.741 (28.622) Remain 06:14:56 loss: 0.1984 loss_seg: 0.1128 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:06:23,249 INFO misc.py line 117 726] Train: [19/20][235/510] Data 2.603 (3.994) Batch 26.133 (28.611) Remain 06:14:19 loss: 0.2974 loss_seg: 0.2012 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0318 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:06:55,772 INFO misc.py line 117 726] Train: [19/20][236/510] Data 3.410 (3.991) Batch 32.522 (28.628) Remain 06:14:04 loss: 0.2448 loss_seg: 0.1422 loss_superpoint_edge: 0.0371 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:07:19,943 INFO misc.py line 117 726] Train: [19/20][237/510] Data 2.658 (3.986) Batch 24.172 (28.609) Remain 06:13:20 loss: 0.2461 loss_seg: 0.1496 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:07:42,361 INFO misc.py line 117 726] Train: [19/20][238/510] Data 3.130 (3.982) Batch 22.417 (28.583) Remain 06:12:31 loss: 0.1782 loss_seg: 0.0958 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:08:07,987 INFO misc.py line 117 726] Train: [19/20][239/510] Data 2.406 (3.975) Batch 25.626 (28.570) Remain 06:11:53 loss: 0.1833 loss_seg: 0.0979 loss_superpoint_edge: 0.0200 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:08:42,558 INFO misc.py line 117 726] Train: [19/20][240/510] Data 7.300 (3.989) Batch 34.571 (28.595) Remain 06:11:44 loss: 0.2190 loss_seg: 0.1247 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:09:15,522 INFO misc.py line 117 726] Train: [19/20][241/510] Data 3.768 (3.988) Batch 32.963 (28.614) Remain 06:11:30 loss: 0.2272 loss_seg: 0.1350 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:09:38,929 INFO misc.py line 117 726] Train: [19/20][242/510] Data 1.997 (3.980) Batch 23.407 (28.592) Remain 06:10:44 loss: 0.2411 loss_seg: 0.1408 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:10:21,356 INFO misc.py line 117 726] Train: [19/20][243/510] Data 12.309 (4.015) Batch 42.427 (28.650) Remain 06:11:00 loss: 0.2079 loss_seg: 0.1149 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0419 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:10:54,705 INFO misc.py line 117 726] Train: [19/20][244/510] Data 3.701 (4.013) Batch 33.349 (28.669) Remain 06:10:47 loss: 0.2534 loss_seg: 0.1582 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:11:12,316 INFO misc.py line 117 726] Train: [19/20][245/510] Data 2.461 (4.007) Batch 17.611 (28.623) Remain 06:09:43 loss: 0.3243 loss_seg: 0.2290 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:11:37,813 INFO misc.py line 117 726] Train: [19/20][246/510] Data 2.242 (4.000) Batch 25.496 (28.610) Remain 06:09:04 loss: 0.2112 loss_seg: 0.1184 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:11:58,827 INFO misc.py line 117 726] Train: [19/20][247/510] Data 2.170 (3.992) Batch 21.014 (28.579) Remain 06:08:11 loss: 0.2161 loss_seg: 0.1257 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:12:30,689 INFO misc.py line 117 726] Train: [19/20][248/510] Data 3.056 (3.988) Batch 31.863 (28.593) Remain 06:07:53 loss: 0.2429 loss_seg: 0.1459 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:12:49,431 INFO misc.py line 117 726] Train: [19/20][249/510] Data 2.038 (3.980) Batch 18.742 (28.553) Remain 06:06:54 loss: 0.2569 loss_seg: 0.1569 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:13:09,259 INFO misc.py line 117 726] Train: [19/20][250/510] Data 2.158 (3.973) Batch 19.828 (28.517) Remain 06:05:58 loss: 0.2402 loss_seg: 0.1432 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:13:09,259 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 20:13:37,213 INFO misc.py line 117 726] Train: [19/20][251/510] Data 3.285 (3.970) Batch 27.954 (28.515) Remain 06:05:28 loss: 0.2206 loss_seg: 0.1258 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:14:11,501 INFO misc.py line 117 726] Train: [19/20][252/510] Data 4.592 (3.973) Batch 34.287 (28.538) Remain 06:05:17 loss: 0.2564 loss_seg: 0.1569 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:14:41,003 INFO misc.py line 117 726] Train: [19/20][253/510] Data 3.331 (3.970) Batch 29.503 (28.542) Remain 06:04:51 loss: 0.2190 loss_seg: 0.1285 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:15:01,969 INFO misc.py line 117 726] Train: [19/20][254/510] Data 2.083 (3.963) Batch 20.966 (28.512) Remain 06:04:00 loss: 0.3211 loss_seg: 0.2079 loss_superpoint_edge: 0.0460 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:15:30,305 INFO misc.py line 117 726] Train: [19/20][255/510] Data 3.782 (3.962) Batch 28.336 (28.511) Remain 06:03:31 loss: 0.2348 loss_seg: 0.1445 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:15:53,960 INFO misc.py line 117 726] Train: [19/20][256/510] Data 2.616 (3.957) Batch 23.655 (28.492) Remain 06:02:47 loss: 0.2112 loss_seg: 0.1221 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:16:28,232 INFO misc.py line 117 726] Train: [19/20][257/510] Data 3.724 (3.956) Batch 34.272 (28.515) Remain 06:02:36 loss: 0.2141 loss_seg: 0.1242 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:16:58,441 INFO misc.py line 117 726] Train: [19/20][258/510] Data 4.088 (3.956) Batch 30.210 (28.521) Remain 06:02:13 loss: 0.2636 loss_seg: 0.1696 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:17:18,117 INFO misc.py line 117 726] Train: [19/20][259/510] Data 2.526 (3.951) Batch 19.676 (28.487) Remain 06:01:18 loss: 0.2624 loss_seg: 0.1593 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:17:32,226 INFO misc.py line 117 726] Train: [19/20][260/510] Data 1.514 (3.941) Batch 14.109 (28.431) Remain 06:00:07 loss: 0.2107 loss_seg: 0.1234 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:17:51,838 INFO misc.py line 117 726] Train: [19/20][261/510] Data 2.279 (3.935) Batch 19.612 (28.397) Remain 05:59:13 loss: 0.2484 loss_seg: 0.1508 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:18:24,018 INFO misc.py line 117 726] Train: [19/20][262/510] Data 5.181 (3.940) Batch 32.180 (28.411) Remain 05:58:55 loss: 0.4616 loss_seg: 0.3584 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:18:55,173 INFO misc.py line 117 726] Train: [19/20][263/510] Data 5.583 (3.946) Batch 31.156 (28.422) Remain 05:58:35 loss: 0.2149 loss_seg: 0.1252 loss_superpoint_edge: 0.0215 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:19:11,941 INFO misc.py line 117 726] Train: [19/20][264/510] Data 2.711 (3.941) Batch 16.767 (28.377) Remain 05:57:33 loss: 0.2768 loss_seg: 0.1755 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:19:37,256 INFO misc.py line 117 726] Train: [19/20][265/510] Data 3.054 (3.938) Batch 25.316 (28.366) Remain 05:56:56 loss: 0.2309 loss_seg: 0.1330 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:20:04,883 INFO misc.py line 117 726] Train: [19/20][266/510] Data 3.161 (3.935) Batch 27.627 (28.363) Remain 05:56:25 loss: 0.2665 loss_seg: 0.1743 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:20:30,664 INFO misc.py line 117 726] Train: [19/20][267/510] Data 2.929 (3.931) Batch 25.781 (28.353) Remain 05:55:49 loss: 0.2286 loss_seg: 0.1412 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:21:01,403 INFO misc.py line 117 726] Train: [19/20][268/510] Data 3.096 (3.928) Batch 30.739 (28.362) Remain 05:55:28 loss: 0.2378 loss_seg: 0.1435 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:21:20,094 INFO misc.py line 117 726] Train: [19/20][269/510] Data 1.973 (3.921) Batch 18.691 (28.326) Remain 05:54:32 loss: 0.3491 loss_seg: 0.2380 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:21:47,100 INFO misc.py line 117 726] Train: [19/20][270/510] Data 3.148 (3.918) Batch 27.005 (28.321) Remain 05:54:00 loss: 0.2353 loss_seg: 0.1364 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:22:13,373 INFO misc.py line 117 726] Train: [19/20][271/510] Data 3.487 (3.916) Batch 26.274 (28.313) Remain 05:53:26 loss: 0.3129 loss_seg: 0.2171 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:22:48,640 INFO misc.py line 117 726] Train: [19/20][272/510] Data 4.617 (3.919) Batch 35.267 (28.339) Remain 05:53:17 loss: 0.2926 loss_seg: 0.1927 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:23:16,950 INFO misc.py line 117 726] Train: [19/20][273/510] Data 2.909 (3.915) Batch 28.310 (28.339) Remain 05:52:49 loss: 0.2190 loss_seg: 0.1259 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:23:42,459 INFO misc.py line 117 726] Train: [19/20][274/510] Data 2.685 (3.910) Batch 25.509 (28.328) Remain 05:52:12 loss: 0.1720 loss_seg: 0.0908 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0296 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:23:56,765 INFO misc.py line 117 726] Train: [19/20][275/510] Data 1.928 (3.903) Batch 14.306 (28.277) Remain 05:51:06 loss: 0.2329 loss_seg: 0.1429 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:24:20,866 INFO misc.py line 117 726] Train: [19/20][276/510] Data 2.694 (3.899) Batch 24.101 (28.262) Remain 05:50:26 loss: 0.2253 loss_seg: 0.1383 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:24:49,128 INFO misc.py line 117 726] Train: [19/20][277/510] Data 3.059 (3.896) Batch 28.262 (28.262) Remain 05:49:58 loss: 0.2156 loss_seg: 0.1205 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:25:23,747 INFO misc.py line 117 726] Train: [19/20][278/510] Data 5.980 (3.903) Batch 34.620 (28.285) Remain 05:49:47 loss: 0.2308 loss_seg: 0.1398 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:25:49,566 INFO misc.py line 117 726] Train: [19/20][279/510] Data 2.950 (3.900) Batch 25.818 (28.276) Remain 05:49:12 loss: 0.2784 loss_seg: 0.1733 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:26:16,840 INFO misc.py line 117 726] Train: [19/20][280/510] Data 2.940 (3.896) Batch 27.274 (28.272) Remain 05:48:41 loss: 0.2327 loss_seg: 0.1392 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:26:43,240 INFO misc.py line 117 726] Train: [19/20][281/510] Data 3.377 (3.894) Batch 26.400 (28.265) Remain 05:48:08 loss: 0.2408 loss_seg: 0.1467 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:27:16,984 INFO misc.py line 117 726] Train: [19/20][282/510] Data 5.020 (3.898) Batch 33.745 (28.285) Remain 05:47:54 loss: 0.3575 loss_seg: 0.2541 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:27:49,424 INFO misc.py line 117 726] Train: [19/20][283/510] Data 5.800 (3.905) Batch 32.440 (28.300) Remain 05:47:36 loss: 0.4127 loss_seg: 0.3031 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0337 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:28:20,430 INFO misc.py line 117 726] Train: [19/20][284/510] Data 4.122 (3.906) Batch 31.006 (28.309) Remain 05:47:15 loss: 0.2167 loss_seg: 0.1226 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:28:48,626 INFO misc.py line 117 726] Train: [19/20][285/510] Data 3.241 (3.904) Batch 28.196 (28.309) Remain 05:46:47 loss: 0.2929 loss_seg: 0.1885 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:29:13,391 INFO misc.py line 117 726] Train: [19/20][286/510] Data 3.457 (3.902) Batch 24.766 (28.297) Remain 05:46:09 loss: 0.2936 loss_seg: 0.1932 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:29:39,885 INFO misc.py line 117 726] Train: [19/20][287/510] Data 3.442 (3.900) Batch 26.494 (28.290) Remain 05:45:36 loss: 0.2621 loss_seg: 0.1605 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:30:16,199 INFO misc.py line 117 726] Train: [19/20][288/510] Data 4.219 (3.902) Batch 36.314 (28.318) Remain 05:45:29 loss: 0.3294 loss_seg: 0.2347 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:30:49,687 INFO misc.py line 117 726] Train: [19/20][289/510] Data 6.365 (3.910) Batch 33.488 (28.336) Remain 05:45:13 loss: 0.2296 loss_seg: 0.1384 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:31:06,080 INFO misc.py line 117 726] Train: [19/20][290/510] Data 1.955 (3.903) Batch 16.394 (28.295) Remain 05:44:15 loss: 0.2102 loss_seg: 0.1143 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0416 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:31:29,190 INFO misc.py line 117 726] Train: [19/20][291/510] Data 4.251 (3.905) Batch 23.110 (28.277) Remain 05:43:33 loss: 0.2371 loss_seg: 0.1414 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:31:56,070 INFO misc.py line 117 726] Train: [19/20][292/510] Data 2.556 (3.900) Batch 26.880 (28.272) Remain 05:43:02 loss: 0.1950 loss_seg: 0.1094 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:32:24,375 INFO misc.py line 117 726] Train: [19/20][293/510] Data 3.530 (3.899) Batch 28.304 (28.272) Remain 05:42:33 loss: 0.2532 loss_seg: 0.1543 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:32:50,692 INFO misc.py line 117 726] Train: [19/20][294/510] Data 3.242 (3.896) Batch 26.317 (28.265) Remain 05:42:00 loss: 0.2254 loss_seg: 0.1294 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:33:11,781 INFO misc.py line 117 726] Train: [19/20][295/510] Data 2.902 (3.893) Batch 21.089 (28.241) Remain 05:41:14 loss: 0.1876 loss_seg: 0.1023 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:33:39,118 INFO misc.py line 117 726] Train: [19/20][296/510] Data 3.197 (3.891) Batch 27.337 (28.238) Remain 05:40:44 loss: 0.3009 loss_seg: 0.1996 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:34:10,408 INFO misc.py line 117 726] Train: [19/20][297/510] Data 3.674 (3.890) Batch 31.290 (28.248) Remain 05:40:23 loss: 0.1986 loss_seg: 0.1130 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:34:36,330 INFO misc.py line 117 726] Train: [19/20][298/510] Data 5.074 (3.894) Batch 25.922 (28.240) Remain 05:39:49 loss: 0.2313 loss_seg: 0.1452 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:35:09,444 INFO misc.py line 117 726] Train: [19/20][299/510] Data 5.269 (3.898) Batch 33.115 (28.257) Remain 05:39:33 loss: 0.1879 loss_seg: 0.1006 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:35:23,492 INFO misc.py line 117 726] Train: [19/20][300/510] Data 1.978 (3.892) Batch 14.048 (28.209) Remain 05:38:30 loss: 0.1892 loss_seg: 0.1048 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:35:23,493 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 20:35:55,544 INFO misc.py line 117 726] Train: [19/20][301/510] Data 4.322 (3.893) Batch 32.052 (28.222) Remain 05:38:11 loss: 0.2406 loss_seg: 0.1495 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:36:10,701 INFO misc.py line 117 726] Train: [19/20][302/510] Data 1.721 (3.886) Batch 15.158 (28.178) Remain 05:37:11 loss: 0.2618 loss_seg: 0.1622 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:36:50,515 INFO misc.py line 117 726] Train: [19/20][303/510] Data 7.366 (3.898) Batch 39.814 (28.217) Remain 05:37:11 loss: 0.2017 loss_seg: 0.1204 loss_superpoint_edge: 0.0124 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:37:14,718 INFO misc.py line 117 726] Train: [19/20][304/510] Data 3.994 (3.898) Batch 24.203 (28.203) Remain 05:36:33 loss: 0.1689 loss_seg: 0.0835 loss_superpoint_edge: 0.0135 loss_superpoint_contrast: 0.0421 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:37:50,260 INFO misc.py line 117 726] Train: [19/20][305/510] Data 4.361 (3.900) Batch 35.542 (28.228) Remain 05:36:22 loss: 0.3847 loss_seg: 0.2861 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:38:22,312 INFO misc.py line 117 726] Train: [19/20][306/510] Data 4.594 (3.902) Batch 32.052 (28.240) Remain 05:36:03 loss: 0.2420 loss_seg: 0.1483 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:38:56,002 INFO misc.py line 117 726] Train: [19/20][307/510] Data 3.505 (3.901) Batch 33.691 (28.258) Remain 05:35:48 loss: 0.2129 loss_seg: 0.1224 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:39:19,872 INFO misc.py line 117 726] Train: [19/20][308/510] Data 2.965 (3.898) Batch 23.870 (28.244) Remain 05:35:09 loss: 0.2666 loss_seg: 0.1671 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:39:46,820 INFO misc.py line 117 726] Train: [19/20][309/510] Data 5.408 (3.902) Batch 26.948 (28.240) Remain 05:34:38 loss: 0.2407 loss_seg: 0.1460 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:40:21,322 INFO misc.py line 117 726] Train: [19/20][310/510] Data 5.324 (3.907) Batch 34.502 (28.260) Remain 05:34:24 loss: 0.2708 loss_seg: 0.1733 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:40:58,393 INFO misc.py line 117 726] Train: [19/20][311/510] Data 4.059 (3.908) Batch 37.071 (28.289) Remain 05:34:16 loss: 0.3165 loss_seg: 0.2135 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:41:26,637 INFO misc.py line 117 726] Train: [19/20][312/510] Data 2.393 (3.903) Batch 28.244 (28.289) Remain 05:33:48 loss: 0.2069 loss_seg: 0.1205 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:41:52,712 INFO misc.py line 117 726] Train: [19/20][313/510] Data 2.655 (3.899) Batch 26.075 (28.281) Remain 05:33:14 loss: 0.4059 loss_seg: 0.2870 loss_superpoint_edge: 0.0518 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:42:19,773 INFO misc.py line 117 726] Train: [19/20][314/510] Data 3.988 (3.899) Batch 27.061 (28.278) Remain 05:32:43 loss: 0.2459 loss_seg: 0.1485 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:42:51,225 INFO misc.py line 117 726] Train: [19/20][315/510] Data 5.230 (3.903) Batch 31.452 (28.288) Remain 05:32:22 loss: 0.2338 loss_seg: 0.1445 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:43:19,490 INFO misc.py line 117 726] Train: [19/20][316/510] Data 2.882 (3.900) Batch 28.265 (28.288) Remain 05:31:54 loss: 0.2305 loss_seg: 0.1386 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:43:39,492 INFO misc.py line 117 726] Train: [19/20][317/510] Data 2.017 (3.894) Batch 20.002 (28.261) Remain 05:31:07 loss: 0.3311 loss_seg: 0.2272 loss_superpoint_edge: 0.0348 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:44:08,205 INFO misc.py line 117 726] Train: [19/20][318/510] Data 3.002 (3.891) Batch 28.713 (28.263) Remain 05:30:40 loss: 0.2016 loss_seg: 0.1119 loss_superpoint_edge: 0.0216 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:44:31,564 INFO misc.py line 117 726] Train: [19/20][319/510] Data 3.492 (3.890) Batch 23.360 (28.247) Remain 05:30:01 loss: 0.2457 loss_seg: 0.1535 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:45:08,013 INFO misc.py line 117 726] Train: [19/20][320/510] Data 4.140 (3.891) Batch 36.448 (28.273) Remain 05:29:51 loss: 0.2351 loss_seg: 0.1479 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:45:31,161 INFO misc.py line 117 726] Train: [19/20][321/510] Data 2.381 (3.886) Batch 23.148 (28.257) Remain 05:29:11 loss: 0.2314 loss_seg: 0.1366 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:46:05,918 INFO misc.py line 117 726] Train: [19/20][322/510] Data 5.490 (3.891) Batch 34.757 (28.277) Remain 05:28:57 loss: 0.2146 loss_seg: 0.1251 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:46:34,666 INFO misc.py line 117 726] Train: [19/20][323/510] Data 3.945 (3.891) Batch 28.748 (28.279) Remain 05:28:30 loss: 0.2064 loss_seg: 0.1168 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:46:58,650 INFO misc.py line 117 726] Train: [19/20][324/510] Data 2.912 (3.888) Batch 23.984 (28.265) Remain 05:27:52 loss: 0.2509 loss_seg: 0.1503 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:47:27,710 INFO misc.py line 117 726] Train: [19/20][325/510] Data 4.113 (3.889) Batch 29.060 (28.268) Remain 05:27:26 loss: 0.2379 loss_seg: 0.1423 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:47:52,158 INFO misc.py line 117 726] Train: [19/20][326/510] Data 3.728 (3.888) Batch 24.448 (28.256) Remain 05:26:49 loss: 0.2165 loss_seg: 0.1283 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:48:19,530 INFO misc.py line 117 726] Train: [19/20][327/510] Data 5.161 (3.892) Batch 27.372 (28.253) Remain 05:26:19 loss: 0.2813 loss_seg: 0.1837 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:48:50,393 INFO misc.py line 117 726] Train: [19/20][328/510] Data 4.717 (3.895) Batch 30.862 (28.261) Remain 05:25:56 loss: 0.3696 loss_seg: 0.2516 loss_superpoint_edge: 0.0483 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:49:27,973 INFO misc.py line 117 726] Train: [19/20][329/510] Data 6.195 (3.902) Batch 37.580 (28.290) Remain 05:25:48 loss: 0.2809 loss_seg: 0.1756 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:50:00,507 INFO misc.py line 117 726] Train: [19/20][330/510] Data 3.168 (3.900) Batch 32.534 (28.303) Remain 05:25:28 loss: 0.3395 loss_seg: 0.2274 loss_superpoint_edge: 0.0454 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:50:30,685 INFO misc.py line 117 726] Train: [19/20][331/510] Data 3.902 (3.900) Batch 30.178 (28.309) Remain 05:25:04 loss: 0.2069 loss_seg: 0.1145 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:50:53,441 INFO misc.py line 117 726] Train: [19/20][332/510] Data 2.502 (3.895) Batch 22.756 (28.292) Remain 05:24:24 loss: 0.2467 loss_seg: 0.1472 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:51:20,927 INFO misc.py line 117 726] Train: [19/20][333/510] Data 3.028 (3.893) Batch 27.485 (28.289) Remain 05:23:54 loss: 0.2561 loss_seg: 0.1561 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:51:54,707 INFO misc.py line 117 726] Train: [19/20][334/510] Data 4.291 (3.894) Batch 33.781 (28.306) Remain 05:23:37 loss: 0.2442 loss_seg: 0.1491 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:52:13,478 INFO misc.py line 117 726] Train: [19/20][335/510] Data 2.183 (3.889) Batch 18.771 (28.277) Remain 05:22:49 loss: 0.2411 loss_seg: 0.1570 loss_superpoint_edge: 0.0140 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:52:40,363 INFO misc.py line 117 726] Train: [19/20][336/510] Data 3.367 (3.887) Batch 26.884 (28.273) Remain 05:22:18 loss: 0.1941 loss_seg: 0.1054 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:53:09,382 INFO misc.py line 117 726] Train: [19/20][337/510] Data 3.482 (3.886) Batch 29.019 (28.275) Remain 05:21:51 loss: 0.2277 loss_seg: 0.1354 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:53:29,808 INFO misc.py line 117 726] Train: [19/20][338/510] Data 3.024 (3.883) Batch 20.426 (28.252) Remain 05:21:07 loss: 0.2556 loss_seg: 0.1591 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:53:56,908 INFO misc.py line 117 726] Train: [19/20][339/510] Data 2.821 (3.880) Batch 27.100 (28.248) Remain 05:20:37 loss: 0.1881 loss_seg: 0.1010 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:54:21,310 INFO misc.py line 117 726] Train: [19/20][340/510] Data 2.426 (3.876) Batch 24.402 (28.237) Remain 05:20:01 loss: 0.2674 loss_seg: 0.1694 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:54:55,768 INFO misc.py line 117 726] Train: [19/20][341/510] Data 4.511 (3.878) Batch 34.458 (28.255) Remain 05:19:45 loss: 0.2362 loss_seg: 0.1429 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:55:15,130 INFO misc.py line 117 726] Train: [19/20][342/510] Data 2.673 (3.874) Batch 19.362 (28.229) Remain 05:18:59 loss: 0.2960 loss_seg: 0.1976 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:55:42,174 INFO misc.py line 117 726] Train: [19/20][343/510] Data 3.079 (3.872) Batch 27.044 (28.226) Remain 05:18:28 loss: 0.2060 loss_seg: 0.1157 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:56:13,345 INFO misc.py line 117 726] Train: [19/20][344/510] Data 4.242 (3.873) Batch 31.170 (28.234) Remain 05:18:06 loss: 0.2027 loss_seg: 0.1123 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:56:43,278 INFO misc.py line 117 726] Train: [19/20][345/510] Data 3.406 (3.872) Batch 29.934 (28.239) Remain 05:17:41 loss: 0.2364 loss_seg: 0.1360 loss_superpoint_edge: 0.0353 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:57:08,392 INFO misc.py line 117 726] Train: [19/20][346/510] Data 2.667 (3.868) Batch 25.114 (28.230) Remain 05:17:07 loss: 0.2155 loss_seg: 0.1221 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:57:38,960 INFO misc.py line 117 726] Train: [19/20][347/510] Data 3.820 (3.868) Batch 30.568 (28.237) Remain 05:16:43 loss: 0.2758 loss_seg: 0.1707 loss_superpoint_edge: 0.0407 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:58:08,683 INFO misc.py line 117 726] Train: [19/20][348/510] Data 4.567 (3.870) Batch 29.723 (28.241) Remain 05:16:18 loss: 0.2081 loss_seg: 0.1175 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:58:34,880 INFO misc.py line 117 726] Train: [19/20][349/510] Data 3.291 (3.868) Batch 26.196 (28.235) Remain 05:15:45 loss: 0.2715 loss_seg: 0.1759 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:58:56,153 INFO misc.py line 117 726] Train: [19/20][350/510] Data 2.099 (3.863) Batch 21.273 (28.215) Remain 05:15:04 loss: 0.2803 loss_seg: 0.1769 loss_superpoint_edge: 0.0359 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:58:56,153 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 20:59:29,918 INFO misc.py line 117 726] Train: [19/20][351/510] Data 4.985 (3.866) Batch 33.765 (28.231) Remain 05:14:46 loss: 0.2052 loss_seg: 0.1206 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 20:59:52,168 INFO misc.py line 117 726] Train: [19/20][352/510] Data 2.634 (3.863) Batch 22.250 (28.214) Remain 05:14:06 loss: 0.2188 loss_seg: 0.1279 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:00:12,607 INFO misc.py line 117 726] Train: [19/20][353/510] Data 2.569 (3.859) Batch 20.439 (28.192) Remain 05:13:23 loss: 0.3016 loss_seg: 0.1949 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:00:46,047 INFO misc.py line 117 726] Train: [19/20][354/510] Data 10.526 (3.878) Batch 33.440 (28.207) Remain 05:13:05 loss: 0.2418 loss_seg: 0.1559 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:01:08,358 INFO misc.py line 117 726] Train: [19/20][355/510] Data 2.791 (3.875) Batch 22.311 (28.190) Remain 05:12:26 loss: 0.2691 loss_seg: 0.1693 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:01:30,303 INFO misc.py line 117 726] Train: [19/20][356/510] Data 2.822 (3.872) Batch 21.945 (28.172) Remain 05:11:46 loss: 0.1463 loss_seg: 0.0623 loss_superpoint_edge: 0.0117 loss_superpoint_contrast: 0.0417 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:02:03,200 INFO misc.py line 117 726] Train: [19/20][357/510] Data 4.140 (3.873) Batch 32.897 (28.186) Remain 05:11:27 loss: 0.1883 loss_seg: 0.0999 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:02:35,192 INFO misc.py line 117 726] Train: [19/20][358/510] Data 3.407 (3.872) Batch 31.992 (28.196) Remain 05:11:06 loss: 0.2306 loss_seg: 0.1402 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:03:04,943 INFO misc.py line 117 726] Train: [19/20][359/510] Data 3.216 (3.870) Batch 29.751 (28.201) Remain 05:10:40 loss: 0.2374 loss_seg: 0.1417 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:03:33,615 INFO misc.py line 117 726] Train: [19/20][360/510] Data 5.421 (3.874) Batch 28.671 (28.202) Remain 05:10:13 loss: 0.2224 loss_seg: 0.1321 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:04:10,316 INFO misc.py line 117 726] Train: [19/20][361/510] Data 4.441 (3.876) Batch 36.701 (28.226) Remain 05:10:00 loss: 0.2333 loss_seg: 0.1449 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:04:34,990 INFO misc.py line 117 726] Train: [19/20][362/510] Data 2.859 (3.873) Batch 24.674 (28.216) Remain 05:09:26 loss: 0.3402 loss_seg: 0.2386 loss_superpoint_edge: 0.0339 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:05:04,526 INFO misc.py line 117 726] Train: [19/20][363/510] Data 3.190 (3.871) Batch 29.536 (28.220) Remain 05:09:00 loss: 0.2700 loss_seg: 0.1774 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:05:28,055 INFO misc.py line 117 726] Train: [19/20][364/510] Data 3.083 (3.869) Batch 23.529 (28.207) Remain 05:08:23 loss: 0.2578 loss_seg: 0.1540 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:05:52,088 INFO misc.py line 117 726] Train: [19/20][365/510] Data 2.666 (3.865) Batch 24.033 (28.195) Remain 05:07:47 loss: 0.2077 loss_seg: 0.1161 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:06:16,520 INFO misc.py line 117 726] Train: [19/20][366/510] Data 2.770 (3.862) Batch 24.431 (28.185) Remain 05:07:12 loss: 0.2522 loss_seg: 0.1535 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:06:57,706 INFO misc.py line 117 726] Train: [19/20][367/510] Data 7.622 (3.873) Batch 41.186 (28.220) Remain 05:07:07 loss: 0.2691 loss_seg: 0.1690 loss_superpoint_edge: 0.0317 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:07:22,444 INFO misc.py line 117 726] Train: [19/20][368/510] Data 3.141 (3.871) Batch 24.738 (28.211) Remain 05:06:33 loss: 0.2116 loss_seg: 0.1110 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:07:46,278 INFO misc.py line 117 726] Train: [19/20][369/510] Data 2.669 (3.867) Batch 23.835 (28.199) Remain 05:05:57 loss: 0.2424 loss_seg: 0.1427 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:08:08,273 INFO misc.py line 117 726] Train: [19/20][370/510] Data 2.171 (3.863) Batch 21.995 (28.182) Remain 05:05:18 loss: 0.2601 loss_seg: 0.1610 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:08:29,986 INFO misc.py line 117 726] Train: [19/20][371/510] Data 2.722 (3.860) Batch 21.713 (28.164) Remain 05:04:38 loss: 0.3046 loss_seg: 0.2011 loss_superpoint_edge: 0.0355 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:08:48,353 INFO misc.py line 117 726] Train: [19/20][372/510] Data 1.813 (3.854) Batch 18.368 (28.138) Remain 05:03:53 loss: 0.2496 loss_seg: 0.1511 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:09:20,702 INFO misc.py line 117 726] Train: [19/20][373/510] Data 3.313 (3.853) Batch 32.349 (28.149) Remain 05:03:32 loss: 0.2244 loss_seg: 0.1404 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:09:55,665 INFO misc.py line 117 726] Train: [19/20][374/510] Data 4.723 (3.855) Batch 34.963 (28.168) Remain 05:03:16 loss: 0.2239 loss_seg: 0.1344 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:10:21,766 INFO misc.py line 117 726] Train: [19/20][375/510] Data 3.642 (3.854) Batch 26.101 (28.162) Remain 05:02:44 loss: 0.2786 loss_seg: 0.1836 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:10:47,041 INFO misc.py line 117 726] Train: [19/20][376/510] Data 2.083 (3.850) Batch 25.275 (28.154) Remain 05:02:11 loss: 0.2002 loss_seg: 0.1120 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:11:14,514 INFO misc.py line 117 726] Train: [19/20][377/510] Data 2.401 (3.846) Batch 27.474 (28.153) Remain 05:01:42 loss: 0.2216 loss_seg: 0.1324 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:11:48,750 INFO misc.py line 117 726] Train: [19/20][378/510] Data 5.609 (3.851) Batch 34.236 (28.169) Remain 05:01:24 loss: 0.4795 loss_seg: 0.3599 loss_superpoint_edge: 0.0534 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:12:12,132 INFO misc.py line 117 726] Train: [19/20][379/510] Data 2.444 (3.847) Batch 23.381 (28.156) Remain 05:00:48 loss: 0.2123 loss_seg: 0.1214 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:12:31,408 INFO misc.py line 117 726] Train: [19/20][380/510] Data 2.118 (3.842) Batch 19.276 (28.132) Remain 05:00:04 loss: 0.2663 loss_seg: 0.1701 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:13:00,952 INFO misc.py line 117 726] Train: [19/20][381/510] Data 3.279 (3.841) Batch 29.544 (28.136) Remain 04:59:39 loss: 0.2580 loss_seg: 0.1656 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:13:31,757 INFO misc.py line 117 726] Train: [19/20][382/510] Data 3.533 (3.840) Batch 30.805 (28.143) Remain 04:59:15 loss: 0.2537 loss_seg: 0.1570 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:14:00,457 INFO misc.py line 117 726] Train: [19/20][383/510] Data 3.514 (3.839) Batch 28.700 (28.145) Remain 04:58:48 loss: 0.2062 loss_seg: 0.1184 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:14:30,845 INFO misc.py line 117 726] Train: [19/20][384/510] Data 3.734 (3.839) Batch 30.389 (28.151) Remain 04:58:23 loss: 0.3080 loss_seg: 0.1991 loss_superpoint_edge: 0.0413 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0338 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:15:03,581 INFO misc.py line 117 726] Train: [19/20][385/510] Data 8.648 (3.851) Batch 32.735 (28.163) Remain 04:58:03 loss: 0.2033 loss_seg: 0.1130 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:15:36,865 INFO misc.py line 117 726] Train: [19/20][386/510] Data 4.080 (3.852) Batch 33.284 (28.176) Remain 04:57:43 loss: 0.2138 loss_seg: 0.1248 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:16:19,740 INFO misc.py line 117 726] Train: [19/20][387/510] Data 8.328 (3.864) Batch 42.876 (28.214) Remain 04:57:39 loss: 0.2813 loss_seg: 0.1852 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:16:54,470 INFO misc.py line 117 726] Train: [19/20][388/510] Data 4.023 (3.864) Batch 34.730 (28.231) Remain 04:57:22 loss: 0.1910 loss_seg: 0.1034 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:17:32,714 INFO misc.py line 117 726] Train: [19/20][389/510] Data 5.913 (3.869) Batch 38.244 (28.257) Remain 04:57:10 loss: 0.2618 loss_seg: 0.1670 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:18:06,111 INFO misc.py line 117 726] Train: [19/20][390/510] Data 3.161 (3.868) Batch 33.396 (28.270) Remain 04:56:50 loss: 0.1864 loss_seg: 0.1014 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:18:37,031 INFO misc.py line 117 726] Train: [19/20][391/510] Data 4.821 (3.870) Batch 30.920 (28.277) Remain 04:56:26 loss: 0.3601 loss_seg: 0.2643 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:19:03,157 INFO misc.py line 117 726] Train: [19/20][392/510] Data 4.698 (3.872) Batch 26.126 (28.272) Remain 04:55:54 loss: 0.3412 loss_seg: 0.2309 loss_superpoint_edge: 0.0419 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:19:23,455 INFO misc.py line 117 726] Train: [19/20][393/510] Data 1.904 (3.867) Batch 20.298 (28.251) Remain 04:55:13 loss: 0.2408 loss_seg: 0.1568 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:19:57,227 INFO misc.py line 117 726] Train: [19/20][394/510] Data 3.958 (3.867) Batch 33.772 (28.265) Remain 04:54:54 loss: 0.2641 loss_seg: 0.1707 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0325 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:20:28,305 INFO misc.py line 117 726] Train: [19/20][395/510] Data 3.826 (3.867) Batch 31.078 (28.273) Remain 04:54:30 loss: 0.2524 loss_seg: 0.1509 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:20:57,854 INFO misc.py line 117 726] Train: [19/20][396/510] Data 2.701 (3.864) Batch 29.549 (28.276) Remain 04:54:04 loss: 0.1817 loss_seg: 0.0960 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:21:33,866 INFO misc.py line 117 726] Train: [19/20][397/510] Data 6.645 (3.871) Batch 36.012 (28.295) Remain 04:53:48 loss: 0.2640 loss_seg: 0.1714 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:21:59,390 INFO misc.py line 117 726] Train: [19/20][398/510] Data 3.570 (3.871) Batch 25.524 (28.288) Remain 04:53:15 loss: 0.2063 loss_seg: 0.1203 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:22:23,117 INFO misc.py line 117 726] Train: [19/20][399/510] Data 2.556 (3.867) Batch 23.727 (28.277) Remain 04:52:39 loss: 0.3156 loss_seg: 0.2227 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:22:46,620 INFO misc.py line 117 726] Train: [19/20][400/510] Data 2.859 (3.865) Batch 23.502 (28.265) Remain 04:52:04 loss: 0.2694 loss_seg: 0.1695 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:22:46,620 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 21:23:19,200 INFO misc.py line 117 726] Train: [19/20][401/510] Data 3.457 (3.864) Batch 32.580 (28.276) Remain 04:51:42 loss: 0.2483 loss_seg: 0.1511 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:23:42,842 INFO misc.py line 117 726] Train: [19/20][402/510] Data 2.772 (3.861) Batch 23.642 (28.264) Remain 04:51:07 loss: 0.2151 loss_seg: 0.1250 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:24:13,529 INFO misc.py line 117 726] Train: [19/20][403/510] Data 3.357 (3.860) Batch 30.687 (28.270) Remain 04:50:42 loss: 0.1966 loss_seg: 0.1088 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:24:42,099 INFO misc.py line 117 726] Train: [19/20][404/510] Data 2.983 (3.857) Batch 28.570 (28.271) Remain 04:50:14 loss: 0.2281 loss_seg: 0.1346 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:25:19,218 INFO misc.py line 117 726] Train: [19/20][405/510] Data 3.858 (3.857) Batch 37.120 (28.293) Remain 04:50:00 loss: 0.2481 loss_seg: 0.1569 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:25:41,070 INFO misc.py line 117 726] Train: [19/20][406/510] Data 2.374 (3.854) Batch 21.851 (28.277) Remain 04:49:22 loss: 0.2149 loss_seg: 0.1235 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:26:07,523 INFO misc.py line 117 726] Train: [19/20][407/510] Data 3.358 (3.853) Batch 26.454 (28.272) Remain 04:48:50 loss: 0.1897 loss_seg: 0.1044 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:26:34,525 INFO misc.py line 117 726] Train: [19/20][408/510] Data 3.151 (3.851) Batch 27.002 (28.269) Remain 04:48:20 loss: 0.2660 loss_seg: 0.1669 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:27:00,301 INFO misc.py line 117 726] Train: [19/20][409/510] Data 2.617 (3.848) Batch 25.777 (28.263) Remain 04:47:48 loss: 0.2209 loss_seg: 0.1295 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:27:35,727 INFO misc.py line 117 726] Train: [19/20][410/510] Data 3.650 (3.847) Batch 35.426 (28.281) Remain 04:47:31 loss: 0.2411 loss_seg: 0.1496 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:28:05,143 INFO misc.py line 117 726] Train: [19/20][411/510] Data 2.990 (3.845) Batch 29.416 (28.284) Remain 04:47:04 loss: 0.2629 loss_seg: 0.1653 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:28:31,634 INFO misc.py line 117 726] Train: [19/20][412/510] Data 3.342 (3.844) Batch 26.491 (28.279) Remain 04:46:33 loss: 0.2149 loss_seg: 0.1230 loss_superpoint_edge: 0.0182 loss_superpoint_contrast: 0.0430 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:28:58,673 INFO misc.py line 117 726] Train: [19/20][413/510] Data 3.687 (3.844) Batch 27.038 (28.276) Remain 04:46:03 loss: 0.2122 loss_seg: 0.1178 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:29:26,366 INFO misc.py line 117 726] Train: [19/20][414/510] Data 3.252 (3.842) Batch 27.694 (28.275) Remain 04:45:34 loss: 0.1870 loss_seg: 0.1001 loss_superpoint_edge: 0.0195 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:29:50,324 INFO misc.py line 117 726] Train: [19/20][415/510] Data 3.400 (3.841) Batch 23.957 (28.264) Remain 04:44:59 loss: 0.2375 loss_seg: 0.1437 loss_superpoint_edge: 0.0262 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:30:13,164 INFO misc.py line 117 726] Train: [19/20][416/510] Data 2.314 (3.837) Batch 22.840 (28.251) Remain 04:44:23 loss: 0.2316 loss_seg: 0.1376 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:30:45,358 INFO misc.py line 117 726] Train: [19/20][417/510] Data 3.910 (3.838) Batch 32.194 (28.261) Remain 04:44:01 loss: 0.2820 loss_seg: 0.1811 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:31:18,789 INFO misc.py line 117 726] Train: [19/20][418/510] Data 3.494 (3.837) Batch 33.431 (28.273) Remain 04:43:40 loss: 0.2330 loss_seg: 0.1438 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:31:49,139 INFO misc.py line 117 726] Train: [19/20][419/510] Data 6.297 (3.843) Batch 30.351 (28.278) Remain 04:43:15 loss: 0.2989 loss_seg: 0.1977 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:32:08,931 INFO misc.py line 117 726] Train: [19/20][420/510] Data 1.964 (3.838) Batch 19.791 (28.258) Remain 04:42:34 loss: 0.3419 loss_seg: 0.2278 loss_superpoint_edge: 0.0470 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:32:43,822 INFO misc.py line 117 726] Train: [19/20][421/510] Data 9.236 (3.851) Batch 34.891 (28.274) Remain 04:42:15 loss: 0.2349 loss_seg: 0.1399 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:33:20,209 INFO misc.py line 117 726] Train: [19/20][422/510] Data 4.513 (3.853) Batch 36.387 (28.293) Remain 04:41:59 loss: 0.1991 loss_seg: 0.1078 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:33:39,160 INFO misc.py line 117 726] Train: [19/20][423/510] Data 1.888 (3.848) Batch 18.951 (28.271) Remain 04:41:17 loss: 0.1777 loss_seg: 0.0930 loss_superpoint_edge: 0.0152 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:34:02,404 INFO misc.py line 117 726] Train: [19/20][424/510] Data 4.206 (3.849) Batch 23.244 (28.259) Remain 04:40:42 loss: 0.2149 loss_seg: 0.1205 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:34:27,776 INFO misc.py line 117 726] Train: [19/20][425/510] Data 2.827 (3.846) Batch 25.372 (28.252) Remain 04:40:09 loss: 0.2308 loss_seg: 0.1367 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:35:01,317 INFO misc.py line 117 726] Train: [19/20][426/510] Data 6.045 (3.852) Batch 33.541 (28.264) Remain 04:39:49 loss: 0.2088 loss_seg: 0.1199 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:35:42,856 INFO misc.py line 117 726] Train: [19/20][427/510] Data 10.340 (3.867) Batch 41.539 (28.296) Remain 04:39:39 loss: 0.2468 loss_seg: 0.1537 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:36:09,233 INFO misc.py line 117 726] Train: [19/20][428/510] Data 2.747 (3.864) Batch 26.376 (28.291) Remain 04:39:08 loss: 0.2246 loss_seg: 0.1274 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:36:33,622 INFO misc.py line 117 726] Train: [19/20][429/510] Data 2.788 (3.862) Batch 24.389 (28.282) Remain 04:38:34 loss: 0.1842 loss_seg: 0.0988 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:37:01,212 INFO misc.py line 117 726] Train: [19/20][430/510] Data 3.961 (3.862) Batch 27.590 (28.280) Remain 04:38:05 loss: 0.3008 loss_seg: 0.2004 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:37:32,504 INFO misc.py line 117 726] Train: [19/20][431/510] Data 5.996 (3.867) Batch 31.292 (28.287) Remain 04:37:41 loss: 0.2661 loss_seg: 0.1600 loss_superpoint_edge: 0.0347 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:38:09,721 INFO misc.py line 117 726] Train: [19/20][432/510] Data 4.933 (3.869) Batch 37.217 (28.308) Remain 04:37:25 loss: 0.2510 loss_seg: 0.1559 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:38:34,012 INFO misc.py line 117 726] Train: [19/20][433/510] Data 3.007 (3.867) Batch 24.292 (28.299) Remain 04:36:51 loss: 0.1838 loss_seg: 0.0964 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:39:05,815 INFO misc.py line 117 726] Train: [19/20][434/510] Data 4.101 (3.868) Batch 31.802 (28.307) Remain 04:36:27 loss: 0.2441 loss_seg: 0.1550 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:39:36,507 INFO misc.py line 117 726] Train: [19/20][435/510] Data 5.329 (3.871) Batch 30.693 (28.313) Remain 04:36:02 loss: 0.2217 loss_seg: 0.1337 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:40:05,639 INFO misc.py line 117 726] Train: [19/20][436/510] Data 3.381 (3.870) Batch 29.131 (28.314) Remain 04:35:35 loss: 0.2249 loss_seg: 0.1291 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:40:33,110 INFO misc.py line 117 726] Train: [19/20][437/510] Data 2.625 (3.867) Batch 27.471 (28.313) Remain 04:35:06 loss: 0.2670 loss_seg: 0.1702 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:41:01,514 INFO misc.py line 117 726] Train: [19/20][438/510] Data 2.760 (3.865) Batch 28.404 (28.313) Remain 04:34:38 loss: 0.2725 loss_seg: 0.1687 loss_superpoint_edge: 0.0376 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:41:35,337 INFO misc.py line 117 726] Train: [19/20][439/510] Data 10.160 (3.879) Batch 33.824 (28.325) Remain 04:34:17 loss: 0.2817 loss_seg: 0.1845 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:42:06,722 INFO misc.py line 117 726] Train: [19/20][440/510] Data 3.115 (3.877) Batch 31.384 (28.332) Remain 04:33:52 loss: 0.2057 loss_seg: 0.1180 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0418 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:42:35,306 INFO misc.py line 117 726] Train: [19/20][441/510] Data 4.363 (3.879) Batch 28.585 (28.333) Remain 04:33:24 loss: 0.3186 loss_seg: 0.2072 loss_superpoint_edge: 0.0428 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:43:02,401 INFO misc.py line 117 726] Train: [19/20][442/510] Data 4.659 (3.880) Batch 27.095 (28.330) Remain 04:32:54 loss: 0.2435 loss_seg: 0.1528 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:43:31,054 INFO misc.py line 117 726] Train: [19/20][443/510] Data 3.706 (3.880) Batch 28.653 (28.331) Remain 04:32:26 loss: 0.2939 loss_seg: 0.1888 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:44:05,130 INFO misc.py line 117 726] Train: [19/20][444/510] Data 4.340 (3.881) Batch 34.076 (28.344) Remain 04:32:06 loss: 0.2632 loss_seg: 0.1820 loss_superpoint_edge: 0.0140 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:44:23,354 INFO misc.py line 117 726] Train: [19/20][445/510] Data 2.144 (3.877) Batch 18.225 (28.321) Remain 04:31:24 loss: 0.1888 loss_seg: 0.0972 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0420 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:44:39,002 INFO misc.py line 117 726] Train: [19/20][446/510] Data 1.894 (3.873) Batch 15.647 (28.292) Remain 04:30:39 loss: 0.1755 loss_seg: 0.0894 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:45:09,375 INFO misc.py line 117 726] Train: [19/20][447/510] Data 3.947 (3.873) Batch 30.373 (28.297) Remain 04:30:14 loss: 0.3150 loss_seg: 0.2125 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:45:36,609 INFO misc.py line 117 726] Train: [19/20][448/510] Data 2.857 (3.870) Batch 27.235 (28.295) Remain 04:29:44 loss: 0.1818 loss_seg: 0.0979 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:46:09,268 INFO misc.py line 117 726] Train: [19/20][449/510] Data 3.539 (3.870) Batch 32.659 (28.304) Remain 04:29:21 loss: 0.2185 loss_seg: 0.1313 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:46:31,621 INFO misc.py line 117 726] Train: [19/20][450/510] Data 2.964 (3.868) Batch 22.353 (28.291) Remain 04:28:45 loss: 0.4113 loss_seg: 0.2959 loss_superpoint_edge: 0.0460 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:46:31,622 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 21:46:59,858 INFO misc.py line 117 726] Train: [19/20][451/510] Data 3.148 (3.866) Batch 28.237 (28.291) Remain 04:28:17 loss: 0.2494 loss_seg: 0.1569 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:47:28,863 INFO misc.py line 117 726] Train: [19/20][452/510] Data 2.960 (3.864) Batch 29.005 (28.293) Remain 04:27:50 loss: 0.2003 loss_seg: 0.1111 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:47:48,202 INFO misc.py line 117 726] Train: [19/20][453/510] Data 2.589 (3.861) Batch 19.339 (28.273) Remain 04:27:10 loss: 0.1834 loss_seg: 0.0953 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:48:11,069 INFO misc.py line 117 726] Train: [19/20][454/510] Data 2.874 (3.859) Batch 22.867 (28.261) Remain 04:26:35 loss: 0.2243 loss_seg: 0.1309 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:48:39,479 INFO misc.py line 117 726] Train: [19/20][455/510] Data 3.359 (3.858) Batch 28.410 (28.261) Remain 04:26:07 loss: 0.2198 loss_seg: 0.1253 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:49:11,958 INFO misc.py line 117 726] Train: [19/20][456/510] Data 3.641 (3.857) Batch 32.479 (28.270) Remain 04:25:44 loss: 0.2214 loss_seg: 0.1265 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:49:37,448 INFO misc.py line 117 726] Train: [19/20][457/510] Data 2.250 (3.854) Batch 25.490 (28.264) Remain 04:25:12 loss: 0.1932 loss_seg: 0.1060 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:50:08,654 INFO misc.py line 117 726] Train: [19/20][458/510] Data 3.514 (3.853) Batch 31.206 (28.271) Remain 04:24:48 loss: 0.2288 loss_seg: 0.1369 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:50:38,719 INFO misc.py line 117 726] Train: [19/20][459/510] Data 4.314 (3.854) Batch 30.066 (28.275) Remain 04:24:22 loss: 0.2927 loss_seg: 0.2004 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:51:12,300 INFO misc.py line 117 726] Train: [19/20][460/510] Data 3.647 (3.854) Batch 33.580 (28.286) Remain 04:24:00 loss: 0.2315 loss_seg: 0.1362 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:51:36,701 INFO misc.py line 117 726] Train: [19/20][461/510] Data 3.078 (3.852) Batch 24.402 (28.278) Remain 04:23:27 loss: 0.1967 loss_seg: 0.1072 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:52:10,978 INFO misc.py line 117 726] Train: [19/20][462/510] Data 6.207 (3.857) Batch 34.277 (28.291) Remain 04:23:06 loss: 0.2846 loss_seg: 0.1875 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:52:40,459 INFO misc.py line 117 726] Train: [19/20][463/510] Data 5.531 (3.861) Batch 29.481 (28.293) Remain 04:22:39 loss: 0.4531 loss_seg: 0.3414 loss_superpoint_edge: 0.0444 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:53:10,511 INFO misc.py line 117 726] Train: [19/20][464/510] Data 3.293 (3.860) Batch 30.052 (28.297) Remain 04:22:13 loss: 0.2605 loss_seg: 0.1585 loss_superpoint_edge: 0.0351 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:53:31,940 INFO misc.py line 117 726] Train: [19/20][465/510] Data 2.126 (3.856) Batch 21.429 (28.282) Remain 04:21:36 loss: 0.2110 loss_seg: 0.1190 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:54:00,230 INFO misc.py line 117 726] Train: [19/20][466/510] Data 4.933 (3.858) Batch 28.291 (28.282) Remain 04:21:08 loss: 0.1787 loss_seg: 0.0943 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:54:36,287 INFO misc.py line 117 726] Train: [19/20][467/510] Data 7.054 (3.865) Batch 36.057 (28.299) Remain 04:20:49 loss: 0.2636 loss_seg: 0.1664 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:55:10,973 INFO misc.py line 117 726] Train: [19/20][468/510] Data 3.465 (3.864) Batch 34.686 (28.313) Remain 04:20:28 loss: 0.2017 loss_seg: 0.1147 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:55:41,414 INFO misc.py line 117 726] Train: [19/20][469/510] Data 3.459 (3.863) Batch 30.441 (28.317) Remain 04:20:02 loss: 0.1891 loss_seg: 0.1001 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:56:08,317 INFO misc.py line 117 726] Train: [19/20][470/510] Data 2.772 (3.861) Batch 26.903 (28.314) Remain 04:19:32 loss: 0.2909 loss_seg: 0.1919 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:56:30,931 INFO misc.py line 117 726] Train: [19/20][471/510] Data 2.952 (3.859) Batch 22.615 (28.302) Remain 04:18:57 loss: 0.2053 loss_seg: 0.1164 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:56:57,074 INFO misc.py line 117 726] Train: [19/20][472/510] Data 3.469 (3.858) Batch 26.143 (28.298) Remain 04:18:27 loss: 0.3991 loss_seg: 0.2873 loss_superpoint_edge: 0.0412 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:57:26,136 INFO misc.py line 117 726] Train: [19/20][473/510] Data 4.504 (3.860) Batch 29.062 (28.299) Remain 04:17:59 loss: 0.1636 loss_seg: 0.0761 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:57:56,717 INFO misc.py line 117 726] Train: [19/20][474/510] Data 5.996 (3.864) Batch 30.581 (28.304) Remain 04:17:34 loss: 0.2577 loss_seg: 0.1608 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:58:27,070 INFO misc.py line 117 726] Train: [19/20][475/510] Data 4.610 (3.866) Batch 30.353 (28.308) Remain 04:17:08 loss: 0.2278 loss_seg: 0.1359 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:58:46,097 INFO misc.py line 117 726] Train: [19/20][476/510] Data 3.243 (3.864) Batch 19.027 (28.289) Remain 04:16:29 loss: 0.2552 loss_seg: 0.1596 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0412 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:59:13,972 INFO misc.py line 117 726] Train: [19/20][477/510] Data 2.782 (3.862) Batch 27.875 (28.288) Remain 04:16:00 loss: 0.2168 loss_seg: 0.1266 loss_superpoint_edge: 0.0255 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 21:59:50,418 INFO misc.py line 117 726] Train: [19/20][478/510] Data 5.912 (3.866) Batch 36.446 (28.305) Remain 04:15:41 loss: 0.2449 loss_seg: 0.1511 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:00:18,251 INFO misc.py line 117 726] Train: [19/20][479/510] Data 3.047 (3.865) Batch 27.833 (28.304) Remain 04:15:12 loss: 0.2515 loss_seg: 0.1528 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:00:46,701 INFO misc.py line 117 726] Train: [19/20][480/510] Data 3.031 (3.863) Batch 28.450 (28.304) Remain 04:14:44 loss: 0.2124 loss_seg: 0.1208 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:01:12,905 INFO misc.py line 117 726] Train: [19/20][481/510] Data 3.533 (3.862) Batch 26.203 (28.300) Remain 04:14:13 loss: 0.1983 loss_seg: 0.1092 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:01:33,792 INFO misc.py line 117 726] Train: [19/20][482/510] Data 2.347 (3.859) Batch 20.888 (28.285) Remain 04:13:37 loss: 0.2269 loss_seg: 0.1344 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:02:07,754 INFO misc.py line 117 726] Train: [19/20][483/510] Data 4.942 (3.861) Batch 33.961 (28.296) Remain 04:13:15 loss: 0.2481 loss_seg: 0.1568 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:02:46,681 INFO misc.py line 117 726] Train: [19/20][484/510] Data 9.826 (3.874) Batch 38.927 (28.319) Remain 04:12:58 loss: 0.2003 loss_seg: 0.1051 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0451 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:03:09,242 INFO misc.py line 117 726] Train: [19/20][485/510] Data 2.804 (3.872) Batch 22.561 (28.307) Remain 04:12:24 loss: 0.2262 loss_seg: 0.1347 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:03:36,011 INFO misc.py line 117 726] Train: [19/20][486/510] Data 3.456 (3.871) Batch 26.769 (28.303) Remain 04:11:54 loss: 0.2559 loss_seg: 0.1616 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:04:05,886 INFO misc.py line 117 726] Train: [19/20][487/510] Data 4.378 (3.872) Batch 29.875 (28.307) Remain 04:11:27 loss: 0.2633 loss_seg: 0.1689 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:04:22,788 INFO misc.py line 117 726] Train: [19/20][488/510] Data 2.289 (3.868) Batch 16.902 (28.283) Remain 04:10:46 loss: 0.2444 loss_seg: 0.1484 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:04:50,992 INFO misc.py line 117 726] Train: [19/20][489/510] Data 2.648 (3.866) Batch 28.203 (28.283) Remain 04:10:18 loss: 0.2135 loss_seg: 0.1200 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:05:18,663 INFO misc.py line 117 726] Train: [19/20][490/510] Data 6.093 (3.871) Batch 27.671 (28.282) Remain 04:09:49 loss: 0.2713 loss_seg: 0.1777 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:05:38,421 INFO misc.py line 117 726] Train: [19/20][491/510] Data 2.382 (3.867) Batch 19.759 (28.264) Remain 04:09:11 loss: 0.4090 loss_seg: 0.2895 loss_superpoint_edge: 0.0516 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:06:02,089 INFO misc.py line 117 726] Train: [19/20][492/510] Data 3.138 (3.866) Batch 23.668 (28.255) Remain 04:08:38 loss: 0.3673 loss_seg: 0.2596 loss_superpoint_edge: 0.0401 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:06:28,092 INFO misc.py line 117 726] Train: [19/20][493/510] Data 4.021 (3.866) Batch 26.003 (28.250) Remain 04:08:07 loss: 0.2638 loss_seg: 0.1617 loss_superpoint_edge: 0.0349 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:07:03,373 INFO misc.py line 117 726] Train: [19/20][494/510] Data 3.847 (3.866) Batch 35.281 (28.265) Remain 04:07:47 loss: 0.2744 loss_seg: 0.1763 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:07:36,653 INFO misc.py line 117 726] Train: [19/20][495/510] Data 3.400 (3.865) Batch 33.280 (28.275) Remain 04:07:24 loss: 0.2385 loss_seg: 0.1412 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:08:00,782 INFO misc.py line 117 726] Train: [19/20][496/510] Data 4.045 (3.866) Batch 24.128 (28.266) Remain 04:06:51 loss: 0.2877 loss_seg: 0.1851 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:08:32,903 INFO misc.py line 117 726] Train: [19/20][497/510] Data 7.019 (3.872) Batch 32.121 (28.274) Remain 04:06:27 loss: 0.2517 loss_seg: 0.1559 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:09:03,621 INFO misc.py line 117 726] Train: [19/20][498/510] Data 3.875 (3.872) Batch 30.718 (28.279) Remain 04:06:01 loss: 0.2717 loss_seg: 0.1785 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:09:29,976 INFO misc.py line 117 726] Train: [19/20][499/510] Data 2.912 (3.870) Batch 26.355 (28.275) Remain 04:05:31 loss: 0.2647 loss_seg: 0.1635 loss_superpoint_edge: 0.0345 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:09:58,816 INFO misc.py line 117 726] Train: [19/20][500/510] Data 4.324 (3.871) Batch 28.840 (28.276) Remain 04:05:03 loss: 0.1750 loss_seg: 0.0873 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:09:58,817 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 22:10:26,452 INFO misc.py line 117 726] Train: [19/20][501/510] Data 4.649 (3.873) Batch 27.636 (28.275) Remain 04:04:34 loss: 0.2407 loss_seg: 0.1479 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:10:47,372 INFO misc.py line 117 726] Train: [19/20][502/510] Data 2.364 (3.870) Batch 20.920 (28.260) Remain 04:03:58 loss: 0.1764 loss_seg: 0.0894 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:11:16,581 INFO misc.py line 117 726] Train: [19/20][503/510] Data 3.481 (3.869) Batch 29.209 (28.262) Remain 04:03:31 loss: 0.2185 loss_seg: 0.1230 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0396 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:11:39,070 INFO misc.py line 117 726] Train: [19/20][504/510] Data 2.471 (3.866) Batch 22.489 (28.251) Remain 04:02:57 loss: 0.1810 loss_seg: 0.0932 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:12:01,070 INFO misc.py line 117 726] Train: [19/20][505/510] Data 2.697 (3.864) Batch 22.001 (28.238) Remain 04:02:22 loss: 0.2507 loss_seg: 0.1524 loss_superpoint_edge: 0.0315 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:12:29,282 INFO misc.py line 117 726] Train: [19/20][506/510] Data 3.073 (3.862) Batch 28.212 (28.238) Remain 04:01:54 loss: 0.2291 loss_seg: 0.1350 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:12:52,669 INFO misc.py line 117 726] Train: [19/20][507/510] Data 2.649 (3.860) Batch 23.387 (28.229) Remain 04:01:21 loss: 0.3825 loss_seg: 0.2663 loss_superpoint_edge: 0.0473 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:13:20,917 INFO misc.py line 117 726] Train: [19/20][508/510] Data 3.456 (3.859) Batch 28.248 (28.229) Remain 04:00:53 loss: 0.2284 loss_seg: 0.1316 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:13:43,736 INFO misc.py line 117 726] Train: [19/20][509/510] Data 2.626 (3.856) Batch 22.818 (28.218) Remain 04:00:19 loss: 0.1952 loss_seg: 0.1065 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:14:07,938 INFO misc.py line 117 726] Train: [19/20][510/510] Data 2.620 (3.854) Batch 24.203 (28.210) Remain 03:59:47 loss: 0.1782 loss_seg: 0.0955 loss_superpoint_edge: 0.0161 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:14:07,939 INFO misc.py line 147 726] Train result: loss: 0.2490 loss_seg: 0.1540 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 [2026-06-12 22:14:07,940 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-12 22:14:23,400 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6674 [2026-06-12 22:14:39,290 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.7151 [2026-06-12 22:15:53,337 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8492 [2026-06-12 22:16:33,391 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 1.0188 [2026-06-12 22:16:52,633 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9737 [2026-06-12 22:17:28,439 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.1663 [2026-06-12 22:18:14,934 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1412 [2026-06-12 22:18:30,409 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.3416 [2026-06-12 22:18:47,874 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 0.8250 [2026-06-12 22:19:06,393 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.4178 [2026-06-12 22:19:22,159 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5137 [2026-06-12 22:19:43,548 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7594 [2026-06-12 22:20:09,274 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8927 [2026-06-12 22:20:20,519 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.7107 [2026-06-12 22:20:51,760 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0696 [2026-06-12 22:21:17,632 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.3172 [2026-06-12 22:21:44,160 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.4363 [2026-06-12 22:22:26,905 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.2407 [2026-06-12 22:22:47,709 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3991 [2026-06-12 22:23:04,181 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.9779 [2026-06-12 22:23:35,022 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.9030 [2026-06-12 22:23:51,174 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.3553 [2026-06-12 22:24:13,129 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.3022 [2026-06-12 22:24:34,533 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8506 [2026-06-12 22:24:47,917 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6408 [2026-06-12 22:25:15,517 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5206 [2026-06-12 22:25:56,528 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.1476 [2026-06-12 22:26:13,644 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5190 [2026-06-12 22:26:32,031 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4577 [2026-06-12 22:26:48,669 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4109 [2026-06-12 22:27:13,550 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.2781 [2026-06-12 22:27:31,509 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.6664 [2026-06-12 22:27:48,879 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 1.1087 [2026-06-12 22:28:13,111 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.6981 [2026-06-12 22:28:13,133 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6708/0.7426/0.8966. [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9246/0.9583 [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9759/0.9881 [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8392/0.9695 [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0013/0.0094 [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3145/0.3808 [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6058/0.6295 [2026-06-12 22:28:13,133 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6039/0.6971 [2026-06-12 22:28:13,134 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7880/0.8964 [2026-06-12 22:28:13,134 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9149/0.9571 [2026-06-12 22:28:13,134 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6699/0.7418 [2026-06-12 22:28:13,134 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7628/0.8499 [2026-06-12 22:28:13,134 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7191/0.8696 [2026-06-12 22:28:13,134 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.6001/0.7067 [2026-06-12 22:28:13,134 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-12 22:28:13,135 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-12 22:28:13,135 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 22:28:39,278 INFO misc.py line 117 726] Train: [20/20][1/510] Data 2.667 (2.667) Batch 24.590 (24.590) Remain 03:28:36 loss: 0.2450 loss_seg: 0.1478 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:29:04,741 INFO misc.py line 117 726] Train: [20/20][2/510] Data 2.146 (2.146) Batch 25.463 (25.463) Remain 03:35:35 loss: 0.2139 loss_seg: 0.1210 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:29:31,273 INFO misc.py line 117 726] Train: [20/20][3/510] Data 2.258 (2.258) Batch 26.532 (26.532) Remain 03:44:11 loss: 0.2785 loss_seg: 0.1745 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:29:51,755 INFO misc.py line 117 726] Train: [20/20][4/510] Data 3.932 (3.932) Batch 20.482 (20.482) Remain 02:52:43 loss: 0.4289 loss_seg: 0.3214 loss_superpoint_edge: 0.0357 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:30:19,572 INFO misc.py line 117 726] Train: [20/20][5/510] Data 2.926 (3.429) Batch 27.817 (24.150) Remain 03:23:15 loss: 0.2844 loss_seg: 0.1908 loss_superpoint_edge: 0.0245 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:30:51,731 INFO misc.py line 117 726] Train: [20/20][6/510] Data 3.888 (3.582) Batch 32.159 (26.819) Remain 03:45:16 loss: 0.2730 loss_seg: 0.1779 loss_superpoint_edge: 0.0284 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:31:13,969 INFO misc.py line 117 726] Train: [20/20][7/510] Data 2.473 (3.305) Batch 22.238 (25.674) Remain 03:35:14 loss: 0.1851 loss_seg: 0.0997 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:31:44,298 INFO misc.py line 117 726] Train: [20/20][8/510] Data 4.774 (3.599) Batch 30.329 (26.605) Remain 03:42:35 loss: 0.2043 loss_seg: 0.1166 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:32:09,271 INFO misc.py line 117 726] Train: [20/20][9/510] Data 2.825 (3.470) Batch 24.974 (26.333) Remain 03:39:52 loss: 0.2649 loss_seg: 0.1635 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:32:42,215 INFO misc.py line 117 726] Train: [20/20][10/510] Data 3.568 (3.484) Batch 32.944 (27.277) Remain 03:47:18 loss: 0.2374 loss_seg: 0.1427 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:33:12,625 INFO misc.py line 117 726] Train: [20/20][11/510] Data 3.043 (3.429) Batch 30.410 (27.669) Remain 03:50:06 loss: 0.2293 loss_seg: 0.1327 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:33:36,773 INFO misc.py line 117 726] Train: [20/20][12/510] Data 2.428 (3.317) Batch 24.148 (27.278) Remain 03:46:24 loss: 0.2897 loss_seg: 0.1903 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:34:15,679 INFO misc.py line 117 726] Train: [20/20][13/510] Data 5.998 (3.586) Batch 38.907 (28.441) Remain 03:55:34 loss: 0.2143 loss_seg: 0.1233 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:34:47,634 INFO misc.py line 117 726] Train: [20/20][14/510] Data 8.343 (4.018) Batch 31.955 (28.760) Remain 03:57:45 loss: 0.2199 loss_seg: 0.1296 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:35:12,343 INFO misc.py line 117 726] Train: [20/20][15/510] Data 2.747 (3.912) Batch 24.709 (28.423) Remain 03:54:29 loss: 0.2019 loss_seg: 0.1139 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:35:29,210 INFO misc.py line 117 726] Train: [20/20][16/510] Data 2.016 (3.766) Batch 16.867 (27.534) Remain 03:46:41 loss: 0.2522 loss_seg: 0.1566 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:35:54,569 INFO misc.py line 117 726] Train: [20/20][17/510] Data 3.619 (3.756) Batch 25.359 (27.378) Remain 03:44:57 loss: 0.2439 loss_seg: 0.1522 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:36:15,372 INFO misc.py line 117 726] Train: [20/20][18/510] Data 2.534 (3.674) Batch 20.803 (26.940) Remain 03:40:54 loss: 0.2298 loss_seg: 0.1361 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:36:45,462 INFO misc.py line 117 726] Train: [20/20][19/510] Data 4.800 (3.745) Batch 30.090 (27.137) Remain 03:42:04 loss: 0.1998 loss_seg: 0.1124 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:37:19,007 INFO misc.py line 117 726] Train: [20/20][20/510] Data 4.031 (3.761) Batch 33.545 (27.514) Remain 03:44:41 loss: 0.1995 loss_seg: 0.1117 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:37:44,461 INFO misc.py line 117 726] Train: [20/20][21/510] Data 1.971 (3.662) Batch 25.453 (27.399) Remain 03:43:18 loss: 0.2044 loss_seg: 0.1166 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:38:17,819 INFO misc.py line 117 726] Train: [20/20][22/510] Data 6.922 (3.834) Batch 33.358 (27.713) Remain 03:45:23 loss: 0.2842 loss_seg: 0.1895 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:38:48,874 INFO misc.py line 117 726] Train: [20/20][23/510] Data 3.035 (3.794) Batch 31.055 (27.880) Remain 03:46:17 loss: 0.2301 loss_seg: 0.1390 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:39:06,976 INFO misc.py line 117 726] Train: [20/20][24/510] Data 2.628 (3.738) Batch 18.102 (27.414) Remain 03:42:03 loss: 0.2508 loss_seg: 0.1498 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:39:40,234 INFO misc.py line 117 726] Train: [20/20][25/510] Data 5.260 (3.807) Batch 33.257 (27.680) Remain 03:43:44 loss: 0.2512 loss_seg: 0.1535 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:40:12,473 INFO misc.py line 117 726] Train: [20/20][26/510] Data 3.310 (3.786) Batch 32.239 (27.878) Remain 03:44:53 loss: 0.2318 loss_seg: 0.1354 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:40:42,955 INFO misc.py line 117 726] Train: [20/20][27/510] Data 4.335 (3.809) Batch 30.482 (27.987) Remain 03:45:17 loss: 0.2873 loss_seg: 0.1925 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:41:08,501 INFO misc.py line 117 726] Train: [20/20][28/510] Data 2.844 (3.770) Batch 25.546 (27.889) Remain 03:44:02 loss: 0.2624 loss_seg: 0.1608 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:41:37,867 INFO misc.py line 117 726] Train: [20/20][29/510] Data 3.861 (3.773) Batch 29.365 (27.946) Remain 03:44:01 loss: 0.4146 loss_seg: 0.3018 loss_superpoint_edge: 0.0405 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:42:06,374 INFO misc.py line 117 726] Train: [20/20][30/510] Data 4.812 (3.812) Batch 28.508 (27.967) Remain 03:43:44 loss: 0.2196 loss_seg: 0.1292 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:42:35,450 INFO misc.py line 117 726] Train: [20/20][31/510] Data 3.712 (3.808) Batch 29.076 (28.006) Remain 03:43:35 loss: 0.2730 loss_seg: 0.1775 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:43:03,079 INFO misc.py line 117 726] Train: [20/20][32/510] Data 5.198 (3.856) Batch 27.629 (27.993) Remain 03:43:00 loss: 0.2798 loss_seg: 0.1832 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:43:23,817 INFO misc.py line 117 726] Train: [20/20][33/510] Data 1.996 (3.794) Batch 20.738 (27.751) Remain 03:40:37 loss: 0.2459 loss_seg: 0.1482 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:43:36,885 INFO misc.py line 117 726] Train: [20/20][34/510] Data 1.739 (3.728) Batch 13.068 (27.278) Remain 03:36:24 loss: 0.2753 loss_seg: 0.1795 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:43:55,185 INFO misc.py line 117 726] Train: [20/20][35/510] Data 2.519 (3.690) Batch 18.300 (26.997) Remain 03:33:43 loss: 0.2089 loss_seg: 0.1135 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:44:25,100 INFO misc.py line 117 726] Train: [20/20][36/510] Data 3.134 (3.673) Batch 29.916 (27.086) Remain 03:33:58 loss: 0.1870 loss_seg: 0.0998 loss_superpoint_edge: 0.0183 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:44:55,786 INFO misc.py line 117 726] Train: [20/20][37/510] Data 4.546 (3.699) Batch 30.686 (27.192) Remain 03:34:21 loss: 0.2347 loss_seg: 0.1379 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:45:24,419 INFO misc.py line 117 726] Train: [20/20][38/510] Data 2.349 (3.660) Batch 28.633 (27.233) Remain 03:34:13 loss: 0.2227 loss_seg: 0.1296 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:45:55,166 INFO misc.py line 117 726] Train: [20/20][39/510] Data 3.257 (3.649) Batch 30.748 (27.330) Remain 03:34:32 loss: 0.2143 loss_seg: 0.1209 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:46:30,075 INFO misc.py line 117 726] Train: [20/20][40/510] Data 8.373 (3.777) Batch 34.909 (27.535) Remain 03:35:41 loss: 0.2345 loss_seg: 0.1454 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:47:00,272 INFO misc.py line 117 726] Train: [20/20][41/510] Data 3.359 (3.766) Batch 30.197 (27.605) Remain 03:35:46 loss: 0.2364 loss_seg: 0.1396 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:47:24,725 INFO misc.py line 117 726] Train: [20/20][42/510] Data 3.324 (3.755) Batch 24.453 (27.524) Remain 03:34:41 loss: 0.3377 loss_seg: 0.2165 loss_superpoint_edge: 0.0506 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:47:45,449 INFO misc.py line 117 726] Train: [20/20][43/510] Data 3.155 (3.740) Batch 20.724 (27.354) Remain 03:32:54 loss: 0.2444 loss_seg: 0.1494 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:48:03,631 INFO misc.py line 117 726] Train: [20/20][44/510] Data 2.108 (3.700) Batch 18.182 (27.131) Remain 03:30:42 loss: 0.1708 loss_seg: 0.0834 loss_superpoint_edge: 0.0178 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:48:34,740 INFO misc.py line 117 726] Train: [20/20][45/510] Data 5.412 (3.741) Batch 31.110 (27.225) Remain 03:30:59 loss: 0.3253 loss_seg: 0.2243 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:49:03,392 INFO misc.py line 117 726] Train: [20/20][46/510] Data 3.163 (3.727) Batch 28.652 (27.259) Remain 03:30:47 loss: 0.2776 loss_seg: 0.1796 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:49:26,696 INFO misc.py line 117 726] Train: [20/20][47/510] Data 2.410 (3.697) Batch 23.304 (27.169) Remain 03:29:39 loss: 0.2565 loss_seg: 0.1591 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:49:46,224 INFO misc.py line 117 726] Train: [20/20][48/510] Data 2.783 (3.677) Batch 19.528 (26.999) Remain 03:27:53 loss: 0.2622 loss_seg: 0.1617 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:50:14,789 INFO misc.py line 117 726] Train: [20/20][49/510] Data 2.523 (3.652) Batch 28.565 (27.033) Remain 03:27:42 loss: 0.2162 loss_seg: 0.1243 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:50:47,685 INFO misc.py line 117 726] Train: [20/20][50/510] Data 3.295 (3.644) Batch 32.896 (27.158) Remain 03:28:12 loss: 0.3032 loss_seg: 0.2009 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:50:47,685 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 22:51:10,691 INFO misc.py line 117 726] Train: [20/20][51/510] Data 3.154 (3.634) Batch 23.006 (27.071) Remain 03:27:05 loss: 0.1967 loss_seg: 0.1052 loss_superpoint_edge: 0.0214 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:51:36,212 INFO misc.py line 117 726] Train: [20/20][52/510] Data 3.917 (3.640) Batch 25.522 (27.040) Remain 03:26:24 loss: 0.3337 loss_seg: 0.2211 loss_superpoint_edge: 0.0432 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0333 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:52:02,456 INFO misc.py line 117 726] Train: [20/20][53/510] Data 2.969 (3.626) Batch 26.243 (27.024) Remain 03:25:49 loss: 0.2230 loss_seg: 0.1259 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:52:22,188 INFO misc.py line 117 726] Train: [20/20][54/510] Data 2.417 (3.603) Batch 19.732 (26.881) Remain 03:24:17 loss: 0.2340 loss_seg: 0.1404 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:52:50,854 INFO misc.py line 117 726] Train: [20/20][55/510] Data 3.910 (3.609) Batch 28.666 (26.915) Remain 03:24:06 loss: 0.2270 loss_seg: 0.1348 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:53:28,641 INFO misc.py line 117 726] Train: [20/20][56/510] Data 5.790 (3.650) Batch 37.787 (27.120) Remain 03:25:12 loss: 0.2766 loss_seg: 0.1802 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:53:50,236 INFO misc.py line 117 726] Train: [20/20][57/510] Data 2.447 (3.627) Batch 21.595 (27.018) Remain 03:23:59 loss: 0.1523 loss_seg: 0.0728 loss_superpoint_edge: 0.0101 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:54:19,206 INFO misc.py line 117 726] Train: [20/20][58/510] Data 7.648 (3.701) Batch 28.970 (27.053) Remain 03:23:48 loss: 0.2145 loss_seg: 0.1202 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0432 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:54:47,809 INFO misc.py line 117 726] Train: [20/20][59/510] Data 2.721 (3.683) Batch 28.603 (27.081) Remain 03:23:33 loss: 0.2558 loss_seg: 0.1579 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:55:10,100 INFO misc.py line 117 726] Train: [20/20][60/510] Data 4.651 (3.700) Batch 22.291 (26.997) Remain 03:22:28 loss: 0.1999 loss_seg: 0.1136 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:55:26,866 INFO misc.py line 117 726] Train: [20/20][61/510] Data 1.727 (3.666) Batch 16.766 (26.821) Remain 03:20:42 loss: 0.2493 loss_seg: 0.1478 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:55:52,848 INFO misc.py line 117 726] Train: [20/20][62/510] Data 2.320 (3.643) Batch 25.981 (26.806) Remain 03:20:09 loss: 0.2604 loss_seg: 0.1567 loss_superpoint_edge: 0.0367 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:56:23,159 INFO misc.py line 117 726] Train: [20/20][63/510] Data 4.118 (3.651) Batch 30.311 (26.865) Remain 03:20:08 loss: 0.2386 loss_seg: 0.1444 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:56:45,950 INFO misc.py line 117 726] Train: [20/20][64/510] Data 2.587 (3.634) Batch 22.791 (26.798) Remain 03:19:11 loss: 0.2395 loss_seg: 0.1429 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:57:13,527 INFO misc.py line 117 726] Train: [20/20][65/510] Data 3.227 (3.627) Batch 27.577 (26.811) Remain 03:18:50 loss: 0.2466 loss_seg: 0.1473 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:57:35,193 INFO misc.py line 117 726] Train: [20/20][66/510] Data 2.565 (3.610) Batch 21.666 (26.729) Remain 03:17:47 loss: 0.2847 loss_seg: 0.1854 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:58:03,694 INFO misc.py line 117 726] Train: [20/20][67/510] Data 3.184 (3.604) Batch 28.502 (26.757) Remain 03:17:33 loss: 0.2046 loss_seg: 0.1180 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:58:36,515 INFO misc.py line 117 726] Train: [20/20][68/510] Data 6.170 (3.643) Batch 32.821 (26.850) Remain 03:17:47 loss: 0.2916 loss_seg: 0.1940 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:59:02,984 INFO misc.py line 117 726] Train: [20/20][69/510] Data 3.871 (3.647) Batch 26.469 (26.844) Remain 03:17:18 loss: 0.2517 loss_seg: 0.1530 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 22:59:29,480 INFO misc.py line 117 726] Train: [20/20][70/510] Data 3.012 (3.637) Batch 26.496 (26.839) Remain 03:16:49 loss: 0.2747 loss_seg: 0.1714 loss_superpoint_edge: 0.0379 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:00:00,149 INFO misc.py line 117 726] Train: [20/20][71/510] Data 2.814 (3.625) Batch 30.669 (26.895) Remain 03:16:47 loss: 0.1791 loss_seg: 0.0959 loss_superpoint_edge: 0.0158 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:00:26,184 INFO misc.py line 117 726] Train: [20/20][72/510] Data 2.897 (3.614) Batch 26.035 (26.883) Remain 03:16:14 loss: 0.1989 loss_seg: 0.1120 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:00:59,167 INFO misc.py line 117 726] Train: [20/20][73/510] Data 4.791 (3.631) Batch 32.984 (26.970) Remain 03:16:25 loss: 0.3430 loss_seg: 0.2426 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:01:22,463 INFO misc.py line 117 726] Train: [20/20][74/510] Data 2.078 (3.609) Batch 23.296 (26.918) Remain 03:15:36 loss: 0.2842 loss_seg: 0.1946 loss_superpoint_edge: 0.0228 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:01:41,993 INFO misc.py line 117 726] Train: [20/20][75/510] Data 2.181 (3.590) Batch 19.530 (26.816) Remain 03:14:24 loss: 0.2540 loss_seg: 0.1563 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:02:12,991 INFO misc.py line 117 726] Train: [20/20][76/510] Data 3.612 (3.590) Batch 30.998 (26.873) Remain 03:14:22 loss: 0.2791 loss_seg: 0.1790 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:02:48,522 INFO misc.py line 117 726] Train: [20/20][77/510] Data 6.108 (3.624) Batch 35.532 (26.990) Remain 03:14:46 loss: 0.2476 loss_seg: 0.1517 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:03:32,189 INFO misc.py line 117 726] Train: [20/20][78/510] Data 12.418 (3.741) Batch 43.666 (27.212) Remain 03:15:55 loss: 0.1989 loss_seg: 0.1079 loss_superpoint_edge: 0.0173 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:04:04,809 INFO misc.py line 117 726] Train: [20/20][79/510] Data 2.655 (3.727) Batch 32.620 (27.283) Remain 03:15:59 loss: 0.2816 loss_seg: 0.1765 loss_superpoint_edge: 0.0369 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:04:29,209 INFO misc.py line 117 726] Train: [20/20][80/510] Data 2.677 (3.713) Batch 24.400 (27.246) Remain 03:15:15 loss: 0.2495 loss_seg: 0.1574 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:05:04,800 INFO misc.py line 117 726] Train: [20/20][81/510] Data 3.638 (3.712) Batch 35.590 (27.353) Remain 03:15:34 loss: 0.2010 loss_seg: 0.1129 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:05:32,509 INFO misc.py line 117 726] Train: [20/20][82/510] Data 4.195 (3.718) Batch 27.710 (27.357) Remain 03:15:08 loss: 0.2145 loss_seg: 0.1276 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:05:55,945 INFO misc.py line 117 726] Train: [20/20][83/510] Data 3.792 (3.719) Batch 23.436 (27.308) Remain 03:14:20 loss: 0.2618 loss_seg: 0.1611 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:06:25,756 INFO misc.py line 117 726] Train: [20/20][84/510] Data 4.507 (3.729) Batch 29.811 (27.339) Remain 03:14:06 loss: 0.2432 loss_seg: 0.1485 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:06:58,646 INFO misc.py line 117 726] Train: [20/20][85/510] Data 4.964 (3.744) Batch 32.890 (27.407) Remain 03:14:07 loss: 0.1962 loss_seg: 0.1111 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:07:27,239 INFO misc.py line 117 726] Train: [20/20][86/510] Data 2.355 (3.727) Batch 28.593 (27.421) Remain 03:13:46 loss: 0.2374 loss_seg: 0.1414 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:07:52,792 INFO misc.py line 117 726] Train: [20/20][87/510] Data 2.664 (3.715) Batch 25.552 (27.399) Remain 03:13:09 loss: 0.1909 loss_seg: 0.1052 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:08:18,101 INFO misc.py line 117 726] Train: [20/20][88/510] Data 2.905 (3.705) Batch 25.310 (27.374) Remain 03:12:32 loss: 0.2024 loss_seg: 0.1115 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:08:59,358 INFO misc.py line 117 726] Train: [20/20][89/510] Data 13.625 (3.820) Batch 41.257 (27.536) Remain 03:13:12 loss: 0.1942 loss_seg: 0.1068 loss_superpoint_edge: 0.0166 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:09:31,833 INFO misc.py line 117 726] Train: [20/20][90/510] Data 4.279 (3.826) Batch 32.475 (27.593) Remain 03:13:08 loss: 0.2519 loss_seg: 0.1648 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:09:50,733 INFO misc.py line 117 726] Train: [20/20][91/510] Data 1.839 (3.803) Batch 18.900 (27.494) Remain 03:11:59 loss: 0.2626 loss_seg: 0.1575 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:10:12,075 INFO misc.py line 117 726] Train: [20/20][92/510] Data 2.192 (3.785) Batch 21.342 (27.425) Remain 03:11:03 loss: 0.2361 loss_seg: 0.1465 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:10:33,044 INFO misc.py line 117 726] Train: [20/20][93/510] Data 2.571 (3.772) Batch 20.968 (27.353) Remain 03:10:06 loss: 0.1919 loss_seg: 0.1060 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:10:53,026 INFO misc.py line 117 726] Train: [20/20][94/510] Data 2.019 (3.752) Batch 19.983 (27.272) Remain 03:09:05 loss: 0.1561 loss_seg: 0.0713 loss_superpoint_edge: 0.0154 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:11:24,863 INFO misc.py line 117 726] Train: [20/20][95/510] Data 3.100 (3.745) Batch 31.837 (27.322) Remain 03:08:58 loss: 0.2652 loss_seg: 0.1665 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:11:52,715 INFO misc.py line 117 726] Train: [20/20][96/510] Data 3.966 (3.748) Batch 27.852 (27.327) Remain 03:08:33 loss: 0.2472 loss_seg: 0.1559 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:12:20,009 INFO misc.py line 117 726] Train: [20/20][97/510] Data 3.480 (3.745) Batch 27.294 (27.327) Remain 03:08:06 loss: 0.2237 loss_seg: 0.1352 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:12:54,199 INFO misc.py line 117 726] Train: [20/20][98/510] Data 5.608 (3.764) Batch 34.191 (27.399) Remain 03:08:08 loss: 0.2146 loss_seg: 0.1236 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:13:17,007 INFO misc.py line 117 726] Train: [20/20][99/510] Data 2.074 (3.747) Batch 22.807 (27.351) Remain 03:07:21 loss: 0.2327 loss_seg: 0.1392 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:13:41,647 INFO misc.py line 117 726] Train: [20/20][100/510] Data 2.511 (3.734) Batch 24.640 (27.323) Remain 03:06:42 loss: 0.2022 loss_seg: 0.1140 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:13:41,648 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 23:14:00,453 INFO misc.py line 117 726] Train: [20/20][101/510] Data 2.922 (3.726) Batch 18.806 (27.237) Remain 03:05:39 loss: 0.3761 loss_seg: 0.2647 loss_superpoint_edge: 0.0439 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:14:24,965 INFO misc.py line 117 726] Train: [20/20][102/510] Data 2.766 (3.716) Batch 24.512 (27.209) Remain 03:05:01 loss: 0.2242 loss_seg: 0.1276 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:14:46,215 INFO misc.py line 117 726] Train: [20/20][103/510] Data 2.090 (3.700) Batch 21.250 (27.149) Remain 03:04:09 loss: 0.2324 loss_seg: 0.1348 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:15:15,875 INFO misc.py line 117 726] Train: [20/20][104/510] Data 3.271 (3.696) Batch 29.661 (27.174) Remain 03:03:52 loss: 0.2602 loss_seg: 0.1626 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:15:51,519 INFO misc.py line 117 726] Train: [20/20][105/510] Data 3.701 (3.696) Batch 35.644 (27.257) Remain 03:03:59 loss: 0.3038 loss_seg: 0.1953 loss_superpoint_edge: 0.0439 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:16:10,357 INFO misc.py line 117 726] Train: [20/20][106/510] Data 1.910 (3.678) Batch 18.838 (27.176) Remain 03:02:58 loss: 0.3345 loss_seg: 0.2338 loss_superpoint_edge: 0.0299 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:16:38,711 INFO misc.py line 117 726] Train: [20/20][107/510] Data 3.349 (3.675) Batch 28.354 (27.187) Remain 03:02:36 loss: 0.2640 loss_seg: 0.1614 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:17:15,489 INFO misc.py line 117 726] Train: [20/20][108/510] Data 9.699 (3.732) Batch 36.778 (27.278) Remain 03:02:45 loss: 0.2326 loss_seg: 0.1372 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:17:47,549 INFO misc.py line 117 726] Train: [20/20][109/510] Data 3.222 (3.728) Batch 32.060 (27.323) Remain 03:02:36 loss: 0.2730 loss_seg: 0.1704 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:18:19,024 INFO misc.py line 117 726] Train: [20/20][110/510] Data 5.636 (3.745) Batch 31.475 (27.362) Remain 03:02:24 loss: 0.2585 loss_seg: 0.1612 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:18:42,766 INFO misc.py line 117 726] Train: [20/20][111/510] Data 5.007 (3.757) Batch 23.743 (27.329) Remain 03:01:44 loss: 0.2368 loss_seg: 0.1502 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:19:06,597 INFO misc.py line 117 726] Train: [20/20][112/510] Data 2.203 (3.743) Batch 23.831 (27.297) Remain 03:01:04 loss: 0.1794 loss_seg: 0.0936 loss_superpoint_edge: 0.0197 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:19:30,047 INFO misc.py line 117 726] Train: [20/20][113/510] Data 1.759 (3.725) Batch 23.450 (27.262) Remain 03:00:22 loss: 0.3006 loss_seg: 0.1941 loss_superpoint_edge: 0.0414 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:19:59,391 INFO misc.py line 117 726] Train: [20/20][114/510] Data 3.208 (3.720) Batch 29.344 (27.280) Remain 03:00:03 loss: 0.2365 loss_seg: 0.1418 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:20:28,071 INFO misc.py line 117 726] Train: [20/20][115/510] Data 2.868 (3.713) Batch 28.680 (27.293) Remain 02:59:40 loss: 0.1984 loss_seg: 0.1100 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:20:48,625 INFO misc.py line 117 726] Train: [20/20][116/510] Data 2.634 (3.703) Batch 20.553 (27.233) Remain 02:58:49 loss: 0.2295 loss_seg: 0.1345 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:21:24,722 INFO misc.py line 117 726] Train: [20/20][117/510] Data 6.328 (3.726) Batch 36.098 (27.311) Remain 02:58:53 loss: 0.2170 loss_seg: 0.1346 loss_superpoint_edge: 0.0144 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:21:50,611 INFO misc.py line 117 726] Train: [20/20][118/510] Data 2.323 (3.714) Batch 25.889 (27.299) Remain 02:58:21 loss: 0.2400 loss_seg: 0.1450 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:22:20,502 INFO misc.py line 117 726] Train: [20/20][119/510] Data 2.266 (3.701) Batch 29.891 (27.321) Remain 02:58:02 loss: 0.2700 loss_seg: 0.1702 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:22:47,842 INFO misc.py line 117 726] Train: [20/20][120/510] Data 3.639 (3.701) Batch 27.340 (27.321) Remain 02:57:35 loss: 0.2559 loss_seg: 0.1580 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:23:18,996 INFO misc.py line 117 726] Train: [20/20][121/510] Data 3.894 (3.702) Batch 31.154 (27.354) Remain 02:57:20 loss: 0.2658 loss_seg: 0.1721 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:23:33,604 INFO misc.py line 117 726] Train: [20/20][122/510] Data 1.854 (3.687) Batch 14.608 (27.246) Remain 02:56:11 loss: 0.3277 loss_seg: 0.2206 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:23:59,155 INFO misc.py line 117 726] Train: [20/20][123/510] Data 3.969 (3.689) Batch 25.551 (27.232) Remain 02:55:38 loss: 0.2700 loss_seg: 0.1694 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:24:31,572 INFO misc.py line 117 726] Train: [20/20][124/510] Data 4.229 (3.694) Batch 32.417 (27.275) Remain 02:55:28 loss: 0.2192 loss_seg: 0.1271 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:25:04,073 INFO misc.py line 117 726] Train: [20/20][125/510] Data 3.090 (3.689) Batch 32.501 (27.318) Remain 02:55:17 loss: 0.2928 loss_seg: 0.1927 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:25:24,744 INFO misc.py line 117 726] Train: [20/20][126/510] Data 2.555 (3.680) Batch 20.671 (27.264) Remain 02:54:29 loss: 0.2220 loss_seg: 0.1275 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:26:02,434 INFO misc.py line 117 726] Train: [20/20][127/510] Data 4.087 (3.683) Batch 37.690 (27.348) Remain 02:54:34 loss: 0.2707 loss_seg: 0.1739 loss_superpoint_edge: 0.0297 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:26:18,755 INFO misc.py line 117 726] Train: [20/20][128/510] Data 1.856 (3.668) Batch 16.321 (27.260) Remain 02:53:33 loss: 0.2933 loss_seg: 0.1942 loss_superpoint_edge: 0.0318 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:26:47,865 INFO misc.py line 117 726] Train: [20/20][129/510] Data 5.227 (3.681) Batch 29.110 (27.275) Remain 02:53:11 loss: 0.2025 loss_seg: 0.1098 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:27:12,977 INFO misc.py line 117 726] Train: [20/20][130/510] Data 2.488 (3.671) Batch 25.112 (27.258) Remain 02:52:37 loss: 0.1808 loss_seg: 0.0941 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:27:37,456 INFO misc.py line 117 726] Train: [20/20][131/510] Data 3.241 (3.668) Batch 24.479 (27.236) Remain 02:52:02 loss: 0.3210 loss_seg: 0.2101 loss_superpoint_edge: 0.0423 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:28:01,827 INFO misc.py line 117 726] Train: [20/20][132/510] Data 2.096 (3.656) Batch 24.371 (27.214) Remain 02:51:26 loss: 0.2002 loss_seg: 0.1112 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:28:30,807 INFO misc.py line 117 726] Train: [20/20][133/510] Data 3.731 (3.656) Batch 28.979 (27.227) Remain 02:51:04 loss: 0.3071 loss_seg: 0.2055 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:28:57,569 INFO misc.py line 117 726] Train: [20/20][134/510] Data 3.581 (3.656) Batch 26.762 (27.224) Remain 02:50:36 loss: 0.1724 loss_seg: 0.0835 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0408 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:29:11,509 INFO misc.py line 117 726] Train: [20/20][135/510] Data 1.898 (3.642) Batch 13.940 (27.123) Remain 02:49:31 loss: 0.2434 loss_seg: 0.1477 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:29:30,127 INFO misc.py line 117 726] Train: [20/20][136/510] Data 2.435 (3.633) Batch 18.618 (27.059) Remain 02:48:40 loss: 0.2581 loss_seg: 0.1570 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:30:00,592 INFO misc.py line 117 726] Train: [20/20][137/510] Data 3.064 (3.629) Batch 30.466 (27.084) Remain 02:48:22 loss: 0.2322 loss_seg: 0.1389 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:30:33,032 INFO misc.py line 117 726] Train: [20/20][138/510] Data 4.062 (3.632) Batch 32.439 (27.124) Remain 02:48:10 loss: 0.2038 loss_seg: 0.1157 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:31:02,114 INFO misc.py line 117 726] Train: [20/20][139/510] Data 3.677 (3.633) Batch 29.082 (27.139) Remain 02:47:48 loss: 0.3326 loss_seg: 0.2353 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:31:32,036 INFO misc.py line 117 726] Train: [20/20][140/510] Data 3.786 (3.634) Batch 29.922 (27.159) Remain 02:47:28 loss: 0.2310 loss_seg: 0.1416 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:32:09,334 INFO misc.py line 117 726] Train: [20/20][141/510] Data 11.969 (3.694) Batch 37.298 (27.232) Remain 02:47:28 loss: 0.6042 loss_seg: 0.4952 loss_superpoint_edge: 0.0340 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:32:39,395 INFO misc.py line 117 726] Train: [20/20][142/510] Data 4.249 (3.698) Batch 30.061 (27.253) Remain 02:47:08 loss: 0.1798 loss_seg: 0.0933 loss_superpoint_edge: 0.0160 loss_superpoint_contrast: 0.0404 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:33:12,021 INFO misc.py line 117 726] Train: [20/20][143/510] Data 4.355 (3.703) Batch 32.626 (27.291) Remain 02:46:55 loss: 0.3744 loss_seg: 0.2725 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:33:39,228 INFO misc.py line 117 726] Train: [20/20][144/510] Data 3.729 (3.703) Batch 27.207 (27.290) Remain 02:46:28 loss: 0.2949 loss_seg: 0.1886 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:34:02,334 INFO misc.py line 117 726] Train: [20/20][145/510] Data 2.567 (3.695) Batch 23.106 (27.261) Remain 02:45:50 loss: 0.2174 loss_seg: 0.1256 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:34:19,064 INFO misc.py line 117 726] Train: [20/20][146/510] Data 1.781 (3.682) Batch 16.731 (27.187) Remain 02:44:56 loss: 0.1704 loss_seg: 0.0877 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:34:52,821 INFO misc.py line 117 726] Train: [20/20][147/510] Data 5.591 (3.695) Batch 33.756 (27.233) Remain 02:44:45 loss: 0.2053 loss_seg: 0.1118 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:35:15,248 INFO misc.py line 117 726] Train: [20/20][148/510] Data 1.814 (3.682) Batch 22.427 (27.200) Remain 02:44:06 loss: 0.2111 loss_seg: 0.1215 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:35:42,320 INFO misc.py line 117 726] Train: [20/20][149/510] Data 3.839 (3.683) Batch 27.072 (27.199) Remain 02:43:38 loss: 0.2648 loss_seg: 0.1644 loss_superpoint_edge: 0.0324 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:36:10,149 INFO misc.py line 117 726] Train: [20/20][150/510] Data 3.791 (3.684) Batch 27.829 (27.203) Remain 02:43:13 loss: 0.3090 loss_seg: 0.2005 loss_superpoint_edge: 0.0403 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:36:10,149 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-12 23:36:37,622 INFO misc.py line 117 726] Train: [20/20][151/510] Data 3.406 (3.682) Batch 27.474 (27.205) Remain 02:42:46 loss: 0.2323 loss_seg: 0.1492 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:37:03,594 INFO misc.py line 117 726] Train: [20/20][152/510] Data 2.657 (3.675) Batch 25.971 (27.197) Remain 02:42:16 loss: 0.2174 loss_seg: 0.1260 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:37:32,367 INFO misc.py line 117 726] Train: [20/20][153/510] Data 2.256 (3.665) Batch 28.774 (27.207) Remain 02:41:53 loss: 0.2786 loss_seg: 0.1778 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:38:05,061 INFO misc.py line 117 726] Train: [20/20][154/510] Data 3.626 (3.665) Batch 32.694 (27.244) Remain 02:41:38 loss: 0.3102 loss_seg: 0.2168 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:38:27,593 INFO misc.py line 117 726] Train: [20/20][155/510] Data 2.672 (3.659) Batch 22.532 (27.213) Remain 02:41:00 loss: 0.2691 loss_seg: 0.1684 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:39:05,713 INFO misc.py line 117 726] Train: [20/20][156/510] Data 9.200 (3.695) Batch 38.120 (27.284) Remain 02:40:58 loss: 0.2437 loss_seg: 0.1485 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:39:45,824 INFO misc.py line 117 726] Train: [20/20][157/510] Data 7.057 (3.717) Batch 40.111 (27.367) Remain 02:41:00 loss: 0.2346 loss_seg: 0.1402 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:40:13,826 INFO misc.py line 117 726] Train: [20/20][158/510] Data 4.221 (3.720) Batch 28.001 (27.371) Remain 02:40:34 loss: 0.1893 loss_seg: 0.0990 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:40:36,417 INFO misc.py line 117 726] Train: [20/20][159/510] Data 3.181 (3.717) Batch 22.591 (27.341) Remain 02:39:56 loss: 0.2934 loss_seg: 0.1863 loss_superpoint_edge: 0.0395 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:40:56,102 INFO misc.py line 117 726] Train: [20/20][160/510] Data 1.725 (3.704) Batch 19.685 (27.292) Remain 02:39:12 loss: 0.2734 loss_seg: 0.1711 loss_superpoint_edge: 0.0362 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:41:18,992 INFO misc.py line 117 726] Train: [20/20][161/510] Data 2.249 (3.695) Batch 22.890 (27.264) Remain 02:38:35 loss: 0.2274 loss_seg: 0.1343 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:41:52,809 INFO misc.py line 117 726] Train: [20/20][162/510] Data 3.432 (3.693) Batch 33.817 (27.305) Remain 02:38:22 loss: 0.2535 loss_seg: 0.1611 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:42:18,141 INFO misc.py line 117 726] Train: [20/20][163/510] Data 4.160 (3.696) Batch 25.331 (27.293) Remain 02:37:50 loss: 0.2595 loss_seg: 0.1658 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:42:53,211 INFO misc.py line 117 726] Train: [20/20][164/510] Data 6.518 (3.713) Batch 35.070 (27.341) Remain 02:37:40 loss: 0.1763 loss_seg: 0.0889 loss_superpoint_edge: 0.0185 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:43:25,500 INFO misc.py line 117 726] Train: [20/20][165/510] Data 3.522 (3.712) Batch 32.289 (27.372) Remain 02:37:23 loss: 0.2637 loss_seg: 0.1663 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:43:58,531 INFO misc.py line 117 726] Train: [20/20][166/510] Data 4.096 (3.715) Batch 33.032 (27.406) Remain 02:37:07 loss: 0.2395 loss_seg: 0.1459 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:44:38,646 INFO misc.py line 117 726] Train: [20/20][167/510] Data 8.269 (3.742) Batch 40.115 (27.484) Remain 02:37:07 loss: 0.3156 loss_seg: 0.2127 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:45:03,282 INFO misc.py line 117 726] Train: [20/20][168/510] Data 2.997 (3.738) Batch 24.636 (27.467) Remain 02:36:33 loss: 0.2759 loss_seg: 0.1747 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:45:21,345 INFO misc.py line 117 726] Train: [20/20][169/510] Data 2.084 (3.728) Batch 18.063 (27.410) Remain 02:35:46 loss: 0.2904 loss_seg: 0.1971 loss_superpoint_edge: 0.0266 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:45:47,117 INFO misc.py line 117 726] Train: [20/20][170/510] Data 2.344 (3.720) Batch 25.772 (27.400) Remain 02:35:16 loss: 0.2506 loss_seg: 0.1537 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:46:22,370 INFO misc.py line 117 726] Train: [20/20][171/510] Data 4.008 (3.721) Batch 35.253 (27.447) Remain 02:35:04 loss: 0.2240 loss_seg: 0.1311 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:46:46,853 INFO misc.py line 117 726] Train: [20/20][172/510] Data 3.312 (3.719) Batch 24.483 (27.429) Remain 02:34:31 loss: 0.2732 loss_seg: 0.1724 loss_superpoint_edge: 0.0332 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:47:23,139 INFO misc.py line 117 726] Train: [20/20][173/510] Data 5.303 (3.728) Batch 36.285 (27.482) Remain 02:34:21 loss: 0.2701 loss_seg: 0.1747 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:47:54,318 INFO misc.py line 117 726] Train: [20/20][174/510] Data 3.638 (3.728) Batch 31.180 (27.503) Remain 02:34:01 loss: 0.2192 loss_seg: 0.1283 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:48:24,034 INFO misc.py line 117 726] Train: [20/20][175/510] Data 2.719 (3.722) Batch 29.716 (27.516) Remain 02:33:37 loss: 0.2392 loss_seg: 0.1429 loss_superpoint_edge: 0.0316 loss_superpoint_contrast: 0.0327 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:49:09,276 INFO misc.py line 117 726] Train: [20/20][176/510] Data 11.571 (3.767) Batch 45.242 (27.619) Remain 02:33:44 loss: 0.2529 loss_seg: 0.1584 loss_superpoint_edge: 0.0277 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:49:44,165 INFO misc.py line 117 726] Train: [20/20][177/510] Data 6.887 (3.785) Batch 34.889 (27.660) Remain 02:33:30 loss: 0.2056 loss_seg: 0.1180 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:50:11,873 INFO misc.py line 117 726] Train: [20/20][178/510] Data 8.527 (3.812) Batch 27.709 (27.661) Remain 02:33:03 loss: 0.1806 loss_seg: 0.0934 loss_superpoint_edge: 0.0133 loss_superpoint_contrast: 0.0422 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:50:42,752 INFO misc.py line 117 726] Train: [20/20][179/510] Data 3.290 (3.809) Batch 30.877 (27.679) Remain 02:32:41 loss: 0.2295 loss_seg: 0.1357 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:51:11,328 INFO misc.py line 117 726] Train: [20/20][180/510] Data 2.639 (3.803) Batch 28.578 (27.684) Remain 02:32:15 loss: 0.1748 loss_seg: 0.0904 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:51:42,263 INFO misc.py line 117 726] Train: [20/20][181/510] Data 3.043 (3.798) Batch 30.935 (27.702) Remain 02:31:54 loss: 0.2092 loss_seg: 0.1209 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:52:02,117 INFO misc.py line 117 726] Train: [20/20][182/510] Data 2.618 (3.792) Batch 19.854 (27.658) Remain 02:31:11 loss: 0.2254 loss_seg: 0.1322 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:52:28,089 INFO misc.py line 117 726] Train: [20/20][183/510] Data 3.281 (3.789) Batch 25.972 (27.649) Remain 02:30:41 loss: 0.2682 loss_seg: 0.1683 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:52:53,860 INFO misc.py line 117 726] Train: [20/20][184/510] Data 3.068 (3.785) Batch 25.770 (27.639) Remain 02:30:10 loss: 0.1950 loss_seg: 0.1100 loss_superpoint_edge: 0.0165 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:53:29,819 INFO misc.py line 117 726] Train: [20/20][185/510] Data 5.021 (3.792) Batch 35.959 (27.684) Remain 02:29:57 loss: 0.1723 loss_seg: 0.0912 loss_superpoint_edge: 0.0164 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:53:56,166 INFO misc.py line 117 726] Train: [20/20][186/510] Data 2.497 (3.785) Batch 26.347 (27.677) Remain 02:29:27 loss: 0.1973 loss_seg: 0.1077 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:54:25,792 INFO misc.py line 117 726] Train: [20/20][187/510] Data 3.285 (3.782) Batch 29.627 (27.688) Remain 02:29:03 loss: 0.2201 loss_seg: 0.1261 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:54:49,885 INFO misc.py line 117 726] Train: [20/20][188/510] Data 3.924 (3.783) Batch 24.093 (27.668) Remain 02:28:29 loss: 0.2687 loss_seg: 0.1572 loss_superpoint_edge: 0.0432 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0331 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:55:15,940 INFO misc.py line 117 726] Train: [20/20][189/510] Data 3.081 (3.779) Batch 26.055 (27.659) Remain 02:27:58 loss: 0.2541 loss_seg: 0.1618 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:55:42,076 INFO misc.py line 117 726] Train: [20/20][190/510] Data 2.705 (3.773) Batch 26.136 (27.651) Remain 02:27:28 loss: 0.3010 loss_seg: 0.1970 loss_superpoint_edge: 0.0363 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:56:17,933 INFO misc.py line 117 726] Train: [20/20][191/510] Data 8.614 (3.799) Batch 35.857 (27.695) Remain 02:27:14 loss: 0.3192 loss_seg: 0.2219 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:56:44,631 INFO misc.py line 117 726] Train: [20/20][192/510] Data 2.941 (3.794) Batch 26.698 (27.690) Remain 02:26:45 loss: 0.2010 loss_seg: 0.1149 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:57:08,731 INFO misc.py line 117 726] Train: [20/20][193/510] Data 1.856 (3.784) Batch 24.100 (27.671) Remain 02:26:11 loss: 0.2441 loss_seg: 0.1482 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:57:41,073 INFO misc.py line 117 726] Train: [20/20][194/510] Data 3.638 (3.783) Batch 32.342 (27.695) Remain 02:25:51 loss: 0.2366 loss_seg: 0.1451 loss_superpoint_edge: 0.0242 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:58:20,003 INFO misc.py line 117 726] Train: [20/20][195/510] Data 7.729 (3.804) Batch 38.930 (27.754) Remain 02:25:42 loss: 0.3391 loss_seg: 0.2262 loss_superpoint_edge: 0.0455 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0334 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:58:42,900 INFO misc.py line 117 726] Train: [20/20][196/510] Data 2.254 (3.796) Batch 22.897 (27.729) Remain 02:25:06 loss: 0.2096 loss_seg: 0.1193 loss_superpoint_edge: 0.0240 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:59:06,459 INFO misc.py line 117 726] Train: [20/20][197/510] Data 3.075 (3.792) Batch 23.559 (27.707) Remain 02:24:32 loss: 0.2309 loss_seg: 0.1359 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:59:32,826 INFO misc.py line 117 726] Train: [20/20][198/510] Data 4.591 (3.796) Batch 26.367 (27.700) Remain 02:24:02 loss: 0.2609 loss_seg: 0.1618 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-12 23:59:58,504 INFO misc.py line 117 726] Train: [20/20][199/510] Data 3.494 (3.795) Batch 25.678 (27.690) Remain 02:23:31 loss: 0.1930 loss_seg: 0.1060 loss_superpoint_edge: 0.0224 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:00:29,670 INFO misc.py line 117 726] Train: [20/20][200/510] Data 3.929 (3.795) Batch 31.166 (27.708) Remain 02:23:09 loss: 0.2455 loss_seg: 0.1492 loss_superpoint_edge: 0.0305 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:00:29,671 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 00:01:05,426 INFO misc.py line 117 726] Train: [20/20][201/510] Data 4.656 (3.800) Batch 35.756 (27.748) Remain 02:22:54 loss: 0.2916 loss_seg: 0.1890 loss_superpoint_edge: 0.0368 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:01:25,017 INFO misc.py line 117 726] Train: [20/20][202/510] Data 2.624 (3.794) Batch 19.591 (27.707) Remain 02:22:13 loss: 0.3322 loss_seg: 0.2318 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0400 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:01:58,432 INFO misc.py line 117 726] Train: [20/20][203/510] Data 3.434 (3.792) Batch 33.415 (27.736) Remain 02:21:54 loss: 0.2511 loss_seg: 0.1568 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0322 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:02:32,561 INFO misc.py line 117 726] Train: [20/20][204/510] Data 3.292 (3.790) Batch 34.130 (27.768) Remain 02:21:36 loss: 0.2584 loss_seg: 0.1605 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0330 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:03:05,656 INFO misc.py line 117 726] Train: [20/20][205/510] Data 4.652 (3.794) Batch 33.095 (27.794) Remain 02:21:17 loss: 0.2807 loss_seg: 0.1865 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:03:37,261 INFO misc.py line 117 726] Train: [20/20][206/510] Data 6.019 (3.805) Batch 31.605 (27.813) Remain 02:20:55 loss: 0.2797 loss_seg: 0.1822 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:04:12,054 INFO misc.py line 117 726] Train: [20/20][207/510] Data 4.687 (3.809) Batch 34.792 (27.847) Remain 02:20:37 loss: 0.2533 loss_seg: 0.1491 loss_superpoint_edge: 0.0372 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:04:30,764 INFO misc.py line 117 726] Train: [20/20][208/510] Data 1.968 (3.800) Batch 18.710 (27.802) Remain 02:19:56 loss: 0.2287 loss_seg: 0.1342 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:04:55,175 INFO misc.py line 117 726] Train: [20/20][209/510] Data 2.799 (3.795) Batch 24.411 (27.786) Remain 02:19:23 loss: 0.2933 loss_seg: 0.1937 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:05:35,590 INFO misc.py line 117 726] Train: [20/20][210/510] Data 9.051 (3.821) Batch 40.415 (27.847) Remain 02:19:14 loss: 0.2384 loss_seg: 0.1378 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:05:52,442 INFO misc.py line 117 726] Train: [20/20][211/510] Data 2.145 (3.813) Batch 16.853 (27.794) Remain 02:18:30 loss: 0.2434 loss_seg: 0.1559 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:06:07,282 INFO misc.py line 117 726] Train: [20/20][212/510] Data 1.805 (3.803) Batch 14.839 (27.732) Remain 02:17:44 loss: 0.2060 loss_seg: 0.1129 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:06:35,656 INFO misc.py line 117 726] Train: [20/20][213/510] Data 4.574 (3.807) Batch 28.374 (27.735) Remain 02:17:17 loss: 0.2167 loss_seg: 0.1258 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:07:11,366 INFO misc.py line 117 726] Train: [20/20][214/510] Data 7.099 (3.822) Batch 35.711 (27.773) Remain 02:17:00 loss: 0.3118 loss_seg: 0.2166 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:07:39,031 INFO misc.py line 117 726] Train: [20/20][215/510] Data 5.472 (3.830) Batch 27.665 (27.772) Remain 02:16:32 loss: 0.2248 loss_seg: 0.1329 loss_superpoint_edge: 0.0237 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:08:02,525 INFO misc.py line 117 726] Train: [20/20][216/510] Data 2.874 (3.826) Batch 23.493 (27.752) Remain 02:15:59 loss: 0.3491 loss_seg: 0.2456 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:08:36,920 INFO misc.py line 117 726] Train: [20/20][217/510] Data 7.270 (3.842) Batch 34.396 (27.783) Remain 02:15:40 loss: 0.2484 loss_seg: 0.1520 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:08:55,888 INFO misc.py line 117 726] Train: [20/20][218/510] Data 2.370 (3.835) Batch 18.967 (27.742) Remain 02:15:00 loss: 0.2481 loss_seg: 0.1511 loss_superpoint_edge: 0.0300 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:09:13,137 INFO misc.py line 117 726] Train: [20/20][219/510] Data 2.219 (3.827) Batch 17.250 (27.694) Remain 02:14:18 loss: 0.3015 loss_seg: 0.2034 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:09:44,109 INFO misc.py line 117 726] Train: [20/20][220/510] Data 4.170 (3.829) Batch 30.972 (27.709) Remain 02:13:55 loss: 0.3168 loss_seg: 0.2152 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0330 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:10:09,966 INFO misc.py line 117 726] Train: [20/20][221/510] Data 3.104 (3.826) Batch 25.857 (27.700) Remain 02:13:25 loss: 0.2724 loss_seg: 0.1727 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:10:27,597 INFO misc.py line 117 726] Train: [20/20][222/510] Data 2.091 (3.818) Batch 17.631 (27.654) Remain 02:12:44 loss: 0.1755 loss_seg: 0.0875 loss_superpoint_edge: 0.0128 loss_superpoint_contrast: 0.0445 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:10:53,979 INFO misc.py line 117 726] Train: [20/20][223/510] Data 3.288 (3.815) Batch 26.381 (27.649) Remain 02:12:15 loss: 0.2631 loss_seg: 0.1675 loss_superpoint_edge: 0.0239 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:11:22,910 INFO misc.py line 117 726] Train: [20/20][224/510] Data 3.623 (3.814) Batch 28.931 (27.654) Remain 02:11:49 loss: 0.2400 loss_seg: 0.1480 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:11:48,064 INFO misc.py line 117 726] Train: [20/20][225/510] Data 3.029 (3.811) Batch 25.154 (27.643) Remain 02:11:18 loss: 0.2909 loss_seg: 0.1984 loss_superpoint_edge: 0.0231 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:12:19,850 INFO misc.py line 117 726] Train: [20/20][226/510] Data 3.053 (3.808) Batch 31.786 (27.662) Remain 02:10:55 loss: 0.3110 loss_seg: 0.2124 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:12:58,747 INFO misc.py line 117 726] Train: [20/20][227/510] Data 6.409 (3.819) Batch 38.897 (27.712) Remain 02:10:42 loss: 0.2666 loss_seg: 0.1705 loss_superpoint_edge: 0.0294 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:13:30,465 INFO misc.py line 117 726] Train: [20/20][228/510] Data 6.164 (3.830) Batch 31.718 (27.730) Remain 02:10:19 loss: 0.2760 loss_seg: 0.1869 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:13:55,808 INFO misc.py line 117 726] Train: [20/20][229/510] Data 2.457 (3.823) Batch 25.343 (27.719) Remain 02:09:49 loss: 0.2259 loss_seg: 0.1303 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:14:32,807 INFO misc.py line 117 726] Train: [20/20][230/510] Data 6.260 (3.834) Batch 36.999 (27.760) Remain 02:09:32 loss: 0.2610 loss_seg: 0.1580 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:15:03,830 INFO misc.py line 117 726] Train: [20/20][231/510] Data 4.081 (3.835) Batch 31.023 (27.774) Remain 02:09:09 loss: 0.4171 loss_seg: 0.3173 loss_superpoint_edge: 0.0320 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:15:25,259 INFO misc.py line 117 726] Train: [20/20][232/510] Data 2.670 (3.830) Batch 21.430 (27.747) Remain 02:08:33 loss: 0.1937 loss_seg: 0.1047 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:16:03,017 INFO misc.py line 117 726] Train: [20/20][233/510] Data 5.120 (3.836) Batch 37.757 (27.790) Remain 02:08:17 loss: 0.1868 loss_seg: 0.1020 loss_superpoint_edge: 0.0159 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:16:32,242 INFO misc.py line 117 726] Train: [20/20][234/510] Data 3.631 (3.835) Batch 29.226 (27.796) Remain 02:07:51 loss: 0.1965 loss_seg: 0.1026 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0406 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:17:07,509 INFO misc.py line 117 726] Train: [20/20][235/510] Data 3.294 (3.833) Batch 35.267 (27.829) Remain 02:07:32 loss: 0.2034 loss_seg: 0.1129 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:17:42,835 INFO misc.py line 117 726] Train: [20/20][236/510] Data 3.784 (3.832) Batch 35.325 (27.861) Remain 02:07:13 loss: 0.2738 loss_seg: 0.1772 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:18:12,077 INFO misc.py line 117 726] Train: [20/20][237/510] Data 3.006 (3.829) Batch 29.242 (27.867) Remain 02:06:47 loss: 0.2651 loss_seg: 0.1692 loss_superpoint_edge: 0.0286 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:18:29,998 INFO misc.py line 117 726] Train: [20/20][238/510] Data 2.540 (3.823) Batch 17.922 (27.824) Remain 02:06:08 loss: 0.2209 loss_seg: 0.1323 loss_superpoint_edge: 0.0217 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:19:00,708 INFO misc.py line 117 726] Train: [20/20][239/510] Data 3.735 (3.823) Batch 30.709 (27.837) Remain 02:05:43 loss: 0.3308 loss_seg: 0.2174 loss_superpoint_edge: 0.0458 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:19:30,113 INFO misc.py line 117 726] Train: [20/20][240/510] Data 2.443 (3.817) Batch 29.405 (27.843) Remain 02:05:17 loss: 0.1891 loss_seg: 0.1028 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:19:56,469 INFO misc.py line 117 726] Train: [20/20][241/510] Data 2.793 (3.813) Batch 26.356 (27.837) Remain 02:04:48 loss: 0.2115 loss_seg: 0.1229 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:20:28,167 INFO misc.py line 117 726] Train: [20/20][242/510] Data 5.902 (3.822) Batch 31.698 (27.853) Remain 02:04:24 loss: 0.4084 loss_seg: 0.3016 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:20:49,733 INFO misc.py line 117 726] Train: [20/20][243/510] Data 2.929 (3.818) Batch 21.565 (27.827) Remain 02:03:49 loss: 0.1945 loss_seg: 0.1093 loss_superpoint_edge: 0.0176 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:21:21,572 INFO misc.py line 117 726] Train: [20/20][244/510] Data 4.081 (3.819) Batch 31.840 (27.844) Remain 02:03:26 loss: 0.2521 loss_seg: 0.1538 loss_superpoint_edge: 0.0323 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:21:52,584 INFO misc.py line 117 726] Train: [20/20][245/510] Data 5.164 (3.825) Batch 31.012 (27.857) Remain 02:03:02 loss: 0.2010 loss_seg: 0.1128 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0298 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:22:23,890 INFO misc.py line 117 726] Train: [20/20][246/510] Data 4.788 (3.829) Batch 31.306 (27.871) Remain 02:02:37 loss: 0.1930 loss_seg: 0.1091 loss_superpoint_edge: 0.0177 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:22:57,517 INFO misc.py line 117 726] Train: [20/20][247/510] Data 3.545 (3.827) Batch 33.627 (27.894) Remain 02:02:16 loss: 0.2783 loss_seg: 0.1897 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:23:25,792 INFO misc.py line 117 726] Train: [20/20][248/510] Data 3.979 (3.828) Batch 28.275 (27.896) Remain 02:01:48 loss: 0.2113 loss_seg: 0.1228 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:23:51,621 INFO misc.py line 117 726] Train: [20/20][249/510] Data 3.091 (3.825) Batch 25.829 (27.888) Remain 02:01:18 loss: 0.2113 loss_seg: 0.1246 loss_superpoint_edge: 0.0208 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:24:10,159 INFO misc.py line 117 726] Train: [20/20][250/510] Data 2.270 (3.819) Batch 18.538 (27.850) Remain 02:00:40 loss: 0.3771 loss_seg: 0.2850 loss_superpoint_edge: 0.0236 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:24:10,160 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 00:24:35,362 INFO misc.py line 117 726] Train: [20/20][251/510] Data 3.925 (3.819) Batch 25.202 (27.839) Remain 02:00:10 loss: 0.1943 loss_seg: 0.1066 loss_superpoint_edge: 0.0203 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:24:54,870 INFO misc.py line 117 726] Train: [20/20][252/510] Data 2.463 (3.814) Batch 19.508 (27.806) Remain 01:59:33 loss: 0.3653 loss_seg: 0.2513 loss_superpoint_edge: 0.0454 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:25:26,391 INFO misc.py line 117 726] Train: [20/20][253/510] Data 2.635 (3.809) Batch 31.522 (27.820) Remain 01:59:09 loss: 0.1929 loss_seg: 0.1053 loss_superpoint_edge: 0.0211 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:25:54,177 INFO misc.py line 117 726] Train: [20/20][254/510] Data 2.546 (3.804) Batch 27.786 (27.820) Remain 01:58:42 loss: 0.2263 loss_seg: 0.1380 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:26:14,718 INFO misc.py line 117 726] Train: [20/20][255/510] Data 2.108 (3.797) Batch 20.541 (27.791) Remain 01:58:06 loss: 0.2472 loss_seg: 0.1514 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:26:41,064 INFO misc.py line 117 726] Train: [20/20][256/510] Data 2.805 (3.793) Batch 26.346 (27.786) Remain 01:57:37 loss: 0.2040 loss_seg: 0.1208 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:27:00,080 INFO misc.py line 117 726] Train: [20/20][257/510] Data 2.089 (3.787) Batch 19.016 (27.751) Remain 01:57:01 loss: 0.2296 loss_seg: 0.1321 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:27:35,861 INFO misc.py line 117 726] Train: [20/20][258/510] Data 3.543 (3.786) Batch 35.781 (27.783) Remain 01:56:41 loss: 0.2380 loss_seg: 0.1423 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:28:06,653 INFO misc.py line 117 726] Train: [20/20][259/510] Data 3.525 (3.785) Batch 30.792 (27.794) Remain 01:56:16 loss: 0.1852 loss_seg: 0.0979 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:28:37,980 INFO misc.py line 117 726] Train: [20/20][260/510] Data 3.731 (3.784) Batch 31.326 (27.808) Remain 01:55:52 loss: 0.2782 loss_seg: 0.1738 loss_superpoint_edge: 0.0385 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:29:11,990 INFO misc.py line 117 726] Train: [20/20][261/510] Data 4.806 (3.788) Batch 34.011 (27.832) Remain 01:55:30 loss: 0.2251 loss_seg: 0.1326 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:29:43,474 INFO misc.py line 117 726] Train: [20/20][262/510] Data 3.864 (3.789) Batch 31.484 (27.846) Remain 01:55:05 loss: 0.2781 loss_seg: 0.1833 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:30:10,495 INFO misc.py line 117 726] Train: [20/20][263/510] Data 2.906 (3.785) Batch 27.020 (27.843) Remain 01:54:37 loss: 0.2262 loss_seg: 0.1341 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:30:37,551 INFO misc.py line 117 726] Train: [20/20][264/510] Data 4.061 (3.786) Batch 27.057 (27.840) Remain 01:54:08 loss: 0.2789 loss_seg: 0.1776 loss_superpoint_edge: 0.0338 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:31:06,921 INFO misc.py line 117 726] Train: [20/20][265/510] Data 3.011 (3.783) Batch 29.370 (27.846) Remain 01:53:42 loss: 0.2540 loss_seg: 0.1596 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:31:36,934 INFO misc.py line 117 726] Train: [20/20][266/510] Data 3.542 (3.782) Batch 30.013 (27.854) Remain 01:53:16 loss: 0.1967 loss_seg: 0.1079 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:32:03,724 INFO misc.py line 117 726] Train: [20/20][267/510] Data 2.766 (3.779) Batch 26.791 (27.850) Remain 01:52:47 loss: 0.3042 loss_seg: 0.1933 loss_superpoint_edge: 0.0445 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:32:34,435 INFO misc.py line 117 726] Train: [20/20][268/510] Data 3.468 (3.777) Batch 30.711 (27.861) Remain 01:52:22 loss: 0.2340 loss_seg: 0.1391 loss_superpoint_edge: 0.0285 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:32:56,570 INFO misc.py line 117 726] Train: [20/20][269/510] Data 2.386 (3.772) Batch 22.134 (27.839) Remain 01:51:49 loss: 0.2184 loss_seg: 0.1267 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:33:26,417 INFO misc.py line 117 726] Train: [20/20][270/510] Data 2.764 (3.768) Batch 29.847 (27.847) Remain 01:51:23 loss: 0.2311 loss_seg: 0.1404 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:33:49,098 INFO misc.py line 117 726] Train: [20/20][271/510] Data 2.507 (3.764) Batch 22.682 (27.828) Remain 01:50:50 loss: 0.2236 loss_seg: 0.1329 loss_superpoint_edge: 0.0234 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:34:21,134 INFO misc.py line 117 726] Train: [20/20][272/510] Data 3.779 (3.764) Batch 32.035 (27.843) Remain 01:50:26 loss: 0.1974 loss_seg: 0.1077 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:34:52,457 INFO misc.py line 117 726] Train: [20/20][273/510] Data 5.831 (3.771) Batch 31.324 (27.856) Remain 01:50:01 loss: 0.3144 loss_seg: 0.2036 loss_superpoint_edge: 0.0411 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:35:19,517 INFO misc.py line 117 726] Train: [20/20][274/510] Data 2.650 (3.767) Batch 27.060 (27.853) Remain 01:49:33 loss: 0.2047 loss_seg: 0.1161 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:35:50,860 INFO misc.py line 117 726] Train: [20/20][275/510] Data 3.512 (3.766) Batch 31.343 (27.866) Remain 01:49:08 loss: 0.2780 loss_seg: 0.1725 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0391 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:36:12,346 INFO misc.py line 117 726] Train: [20/20][276/510] Data 2.672 (3.762) Batch 21.486 (27.843) Remain 01:48:35 loss: 0.2066 loss_seg: 0.1164 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0397 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:36:37,269 INFO misc.py line 117 726] Train: [20/20][277/510] Data 2.643 (3.758) Batch 24.922 (27.832) Remain 01:48:04 loss: 0.2322 loss_seg: 0.1422 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:37:04,277 INFO misc.py line 117 726] Train: [20/20][278/510] Data 3.239 (3.756) Batch 27.009 (27.829) Remain 01:47:36 loss: 0.2515 loss_seg: 0.1512 loss_superpoint_edge: 0.0314 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:37:43,628 INFO misc.py line 117 726] Train: [20/20][279/510] Data 6.418 (3.766) Batch 39.351 (27.871) Remain 01:47:18 loss: 0.2514 loss_seg: 0.1554 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:38:07,749 INFO misc.py line 117 726] Train: [20/20][280/510] Data 3.054 (3.763) Batch 24.120 (27.857) Remain 01:46:47 loss: 0.1793 loss_seg: 0.0961 loss_superpoint_edge: 0.0163 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:38:32,338 INFO misc.py line 117 726] Train: [20/20][281/510] Data 2.915 (3.760) Batch 24.589 (27.846) Remain 01:46:16 loss: 0.2220 loss_seg: 0.1229 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0414 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:38:55,277 INFO misc.py line 117 726] Train: [20/20][282/510] Data 2.331 (3.755) Batch 22.939 (27.828) Remain 01:45:44 loss: 0.2208 loss_seg: 0.1320 loss_superpoint_edge: 0.0209 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:39:26,635 INFO misc.py line 117 726] Train: [20/20][283/510] Data 4.635 (3.758) Batch 31.358 (27.841) Remain 01:45:19 loss: 0.1967 loss_seg: 0.1080 loss_superpoint_edge: 0.0218 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:40:09,224 INFO misc.py line 117 726] Train: [20/20][284/510] Data 13.512 (3.793) Batch 42.589 (27.893) Remain 01:45:03 loss: 0.1872 loss_seg: 0.0985 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0411 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:40:33,575 INFO misc.py line 117 726] Train: [20/20][285/510] Data 2.719 (3.789) Batch 24.351 (27.881) Remain 01:44:33 loss: 0.2682 loss_seg: 0.1702 loss_superpoint_edge: 0.0307 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:41:01,141 INFO misc.py line 117 726] Train: [20/20][286/510] Data 2.465 (3.785) Batch 27.566 (27.879) Remain 01:44:04 loss: 0.1918 loss_seg: 0.1045 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:41:27,676 INFO misc.py line 117 726] Train: [20/20][287/510] Data 2.454 (3.780) Batch 26.535 (27.875) Remain 01:43:36 loss: 0.2085 loss_seg: 0.1174 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:42:04,605 INFO misc.py line 117 726] Train: [20/20][288/510] Data 7.160 (3.792) Batch 36.929 (27.906) Remain 01:43:15 loss: 0.2743 loss_seg: 0.1809 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:42:28,837 INFO misc.py line 117 726] Train: [20/20][289/510] Data 3.988 (3.792) Batch 24.232 (27.894) Remain 01:42:44 loss: 0.2595 loss_seg: 0.1608 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:42:46,199 INFO misc.py line 117 726] Train: [20/20][290/510] Data 2.334 (3.787) Batch 17.362 (27.857) Remain 01:42:08 loss: 0.2299 loss_seg: 0.1325 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:43:17,460 INFO misc.py line 117 726] Train: [20/20][291/510] Data 3.443 (3.786) Batch 31.262 (27.869) Remain 01:41:43 loss: 0.2570 loss_seg: 0.1580 loss_superpoint_edge: 0.0312 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:43:41,018 INFO misc.py line 117 726] Train: [20/20][292/510] Data 2.231 (3.781) Batch 23.557 (27.854) Remain 01:41:12 loss: 0.2085 loss_seg: 0.1185 loss_superpoint_edge: 0.0253 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:44:11,259 INFO misc.py line 117 726] Train: [20/20][293/510] Data 3.812 (3.781) Batch 30.242 (27.862) Remain 01:40:46 loss: 0.2797 loss_seg: 0.1824 loss_superpoint_edge: 0.0306 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:44:36,476 INFO misc.py line 117 726] Train: [20/20][294/510] Data 1.897 (3.774) Batch 25.217 (27.853) Remain 01:40:16 loss: 0.3292 loss_seg: 0.2180 loss_superpoint_edge: 0.0433 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:45:06,188 INFO misc.py line 117 726] Train: [20/20][295/510] Data 5.122 (3.779) Batch 29.712 (27.859) Remain 01:39:49 loss: 0.2699 loss_seg: 0.1707 loss_superpoint_edge: 0.0326 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:45:41,445 INFO misc.py line 117 726] Train: [20/20][296/510] Data 5.175 (3.784) Batch 35.257 (27.885) Remain 01:39:27 loss: 0.2236 loss_seg: 0.1311 loss_superpoint_edge: 0.0265 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:46:08,820 INFO misc.py line 117 726] Train: [20/20][297/510] Data 4.517 (3.786) Batch 27.375 (27.883) Remain 01:38:59 loss: 0.2297 loss_seg: 0.1393 loss_superpoint_edge: 0.0250 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:46:39,074 INFO misc.py line 117 726] Train: [20/20][298/510] Data 5.628 (3.793) Batch 30.254 (27.891) Remain 01:38:32 loss: 0.2281 loss_seg: 0.1345 loss_superpoint_edge: 0.0269 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:47:10,118 INFO misc.py line 117 726] Train: [20/20][299/510] Data 5.218 (3.797) Batch 31.043 (27.901) Remain 01:38:07 loss: 0.1975 loss_seg: 0.1072 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:47:34,295 INFO misc.py line 117 726] Train: [20/20][300/510] Data 3.775 (3.797) Batch 24.177 (27.889) Remain 01:37:36 loss: 0.3405 loss_seg: 0.2390 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:47:34,295 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 00:48:04,753 INFO misc.py line 117 726] Train: [20/20][301/510] Data 4.105 (3.798) Batch 30.458 (27.898) Remain 01:37:10 loss: 0.3101 loss_seg: 0.1973 loss_superpoint_edge: 0.0466 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:48:37,062 INFO misc.py line 117 726] Train: [20/20][302/510] Data 3.542 (3.797) Batch 32.309 (27.912) Remain 01:36:45 loss: 0.2136 loss_seg: 0.1268 loss_superpoint_edge: 0.0212 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:49:04,980 INFO misc.py line 117 726] Train: [20/20][303/510] Data 3.171 (3.795) Batch 27.919 (27.912) Remain 01:36:17 loss: 0.2638 loss_seg: 0.1625 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:49:28,511 INFO misc.py line 117 726] Train: [20/20][304/510] Data 2.694 (3.792) Batch 23.530 (27.898) Remain 01:35:46 loss: 0.2271 loss_seg: 0.1356 loss_superpoint_edge: 0.0248 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:49:47,697 INFO misc.py line 117 726] Train: [20/20][305/510] Data 2.213 (3.786) Batch 19.186 (27.869) Remain 01:35:13 loss: 0.2434 loss_seg: 0.1476 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:50:19,279 INFO misc.py line 117 726] Train: [20/20][306/510] Data 4.815 (3.790) Batch 31.582 (27.881) Remain 01:34:47 loss: 0.2127 loss_seg: 0.1226 loss_superpoint_edge: 0.0194 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:50:46,381 INFO misc.py line 117 726] Train: [20/20][307/510] Data 3.302 (3.788) Batch 27.102 (27.879) Remain 01:34:19 loss: 0.2350 loss_seg: 0.1403 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:51:17,659 INFO misc.py line 117 726] Train: [20/20][308/510] Data 5.516 (3.794) Batch 31.278 (27.890) Remain 01:33:53 loss: 0.1889 loss_seg: 0.1065 loss_superpoint_edge: 0.0157 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:51:46,574 INFO misc.py line 117 726] Train: [20/20][309/510] Data 3.410 (3.793) Batch 28.915 (27.893) Remain 01:33:26 loss: 0.2615 loss_seg: 0.1664 loss_superpoint_edge: 0.0283 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:52:14,074 INFO misc.py line 117 726] Train: [20/20][310/510] Data 4.531 (3.795) Batch 27.500 (27.892) Remain 01:32:58 loss: 0.3063 loss_seg: 0.2038 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:52:50,449 INFO misc.py line 117 726] Train: [20/20][311/510] Data 5.064 (3.799) Batch 36.376 (27.919) Remain 01:32:35 loss: 0.2130 loss_seg: 0.1201 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:53:24,246 INFO misc.py line 117 726] Train: [20/20][312/510] Data 3.403 (3.798) Batch 33.797 (27.938) Remain 01:32:11 loss: 0.2410 loss_seg: 0.1472 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:53:48,915 INFO misc.py line 117 726] Train: [20/20][313/510] Data 3.217 (3.796) Batch 24.669 (27.928) Remain 01:31:41 loss: 0.3281 loss_seg: 0.2330 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:54:19,584 INFO misc.py line 117 726] Train: [20/20][314/510] Data 4.132 (3.797) Batch 30.669 (27.937) Remain 01:31:15 loss: 0.2126 loss_seg: 0.1227 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:54:50,987 INFO misc.py line 117 726] Train: [20/20][315/510] Data 3.508 (3.796) Batch 31.403 (27.948) Remain 01:30:49 loss: 0.2467 loss_seg: 0.1517 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0379 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:55:19,045 INFO misc.py line 117 726] Train: [20/20][316/510] Data 4.706 (3.799) Batch 28.057 (27.948) Remain 01:30:21 loss: 0.2595 loss_seg: 0.1653 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:55:41,992 INFO misc.py line 117 726] Train: [20/20][317/510] Data 2.748 (3.796) Batch 22.947 (27.932) Remain 01:29:50 loss: 0.2139 loss_seg: 0.1228 loss_superpoint_edge: 0.0272 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:56:10,228 INFO misc.py line 117 726] Train: [20/20][318/510] Data 2.684 (3.792) Batch 28.237 (27.933) Remain 01:29:23 loss: 0.2115 loss_seg: 0.1212 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:56:38,805 INFO misc.py line 117 726] Train: [20/20][319/510] Data 3.472 (3.791) Batch 28.577 (27.935) Remain 01:28:55 loss: 0.2615 loss_seg: 0.1671 loss_superpoint_edge: 0.0273 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:57:11,483 INFO misc.py line 117 726] Train: [20/20][320/510] Data 4.234 (3.793) Batch 32.678 (27.950) Remain 01:28:30 loss: 0.1957 loss_seg: 0.1139 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:57:35,663 INFO misc.py line 117 726] Train: [20/20][321/510] Data 2.729 (3.789) Batch 24.180 (27.938) Remain 01:28:00 loss: 0.2541 loss_seg: 0.1548 loss_superpoint_edge: 0.0313 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:58:01,225 INFO misc.py line 117 726] Train: [20/20][322/510] Data 2.987 (3.787) Batch 25.561 (27.931) Remain 01:27:31 loss: 0.2887 loss_seg: 0.1787 loss_superpoint_edge: 0.0420 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:58:29,242 INFO misc.py line 117 726] Train: [20/20][323/510] Data 3.179 (3.785) Batch 28.017 (27.931) Remain 01:27:03 loss: 0.2320 loss_seg: 0.1391 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:58:48,648 INFO misc.py line 117 726] Train: [20/20][324/510] Data 2.035 (3.779) Batch 19.406 (27.905) Remain 01:26:30 loss: 0.2761 loss_seg: 0.1768 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:59:22,069 INFO misc.py line 117 726] Train: [20/20][325/510] Data 8.890 (3.795) Batch 33.421 (27.922) Remain 01:26:05 loss: 0.2174 loss_seg: 0.1267 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 00:59:51,226 INFO misc.py line 117 726] Train: [20/20][326/510] Data 5.428 (3.800) Batch 29.157 (27.926) Remain 01:25:38 loss: 0.2205 loss_seg: 0.1301 loss_superpoint_edge: 0.0246 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:00:20,079 INFO misc.py line 117 726] Train: [20/20][327/510] Data 3.784 (3.800) Batch 28.853 (27.928) Remain 01:25:10 loss: 0.2780 loss_seg: 0.1785 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:00:44,065 INFO misc.py line 117 726] Train: [20/20][328/510] Data 3.009 (3.798) Batch 23.985 (27.916) Remain 01:24:40 loss: 0.2728 loss_seg: 0.1831 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:01:07,927 INFO misc.py line 117 726] Train: [20/20][329/510] Data 2.642 (3.794) Batch 23.863 (27.904) Remain 01:24:10 loss: 0.2561 loss_seg: 0.1558 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:01:47,317 INFO misc.py line 117 726] Train: [20/20][330/510] Data 5.044 (3.798) Batch 39.389 (27.939) Remain 01:23:49 loss: 0.3061 loss_seg: 0.2035 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:02:22,499 INFO misc.py line 117 726] Train: [20/20][331/510] Data 9.355 (3.815) Batch 35.182 (27.961) Remain 01:23:25 loss: 0.1830 loss_seg: 0.0957 loss_superpoint_edge: 0.0117 loss_superpoint_contrast: 0.0456 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:03:00,821 INFO misc.py line 117 726] Train: [20/20][332/510] Data 4.619 (3.817) Batch 38.322 (27.993) Remain 01:23:02 loss: 0.2067 loss_seg: 0.1187 loss_superpoint_edge: 0.0225 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:03:34,288 INFO misc.py line 117 726] Train: [20/20][333/510] Data 3.617 (3.817) Batch 33.467 (28.009) Remain 01:22:37 loss: 0.2543 loss_seg: 0.1567 loss_superpoint_edge: 0.0310 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:03:57,739 INFO misc.py line 117 726] Train: [20/20][334/510] Data 3.072 (3.815) Batch 23.451 (27.995) Remain 01:22:07 loss: 0.2140 loss_seg: 0.1219 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:04:26,518 INFO misc.py line 117 726] Train: [20/20][335/510] Data 2.894 (3.812) Batch 28.779 (27.998) Remain 01:21:39 loss: 0.2099 loss_seg: 0.1229 loss_superpoint_edge: 0.0188 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0300 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:05:02,520 INFO misc.py line 117 726] Train: [20/20][336/510] Data 4.389 (3.814) Batch 36.002 (28.022) Remain 01:21:15 loss: 0.2667 loss_seg: 0.1663 loss_superpoint_edge: 0.0337 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:05:21,947 INFO misc.py line 117 726] Train: [20/20][337/510] Data 2.828 (3.811) Batch 19.427 (27.996) Remain 01:20:43 loss: 0.1687 loss_seg: 0.0835 loss_superpoint_edge: 0.0167 loss_superpoint_contrast: 0.0377 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:05:51,120 INFO misc.py line 117 726] Train: [20/20][338/510] Data 4.569 (3.813) Batch 29.174 (28.000) Remain 01:20:15 loss: 0.3745 loss_seg: 0.2825 loss_superpoint_edge: 0.0252 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:06:21,058 INFO misc.py line 117 726] Train: [20/20][339/510] Data 4.091 (3.814) Batch 29.937 (28.005) Remain 01:19:48 loss: 0.2700 loss_seg: 0.1721 loss_superpoint_edge: 0.0336 loss_superpoint_contrast: 0.0329 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:06:56,239 INFO misc.py line 117 726] Train: [20/20][340/510] Data 10.020 (3.832) Batch 35.181 (28.027) Remain 01:19:24 loss: 0.2172 loss_seg: 0.1308 loss_superpoint_edge: 0.0181 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:07:24,740 INFO misc.py line 117 726] Train: [20/20][341/510] Data 3.209 (3.830) Batch 28.501 (28.028) Remain 01:18:56 loss: 0.2095 loss_seg: 0.1200 loss_superpoint_edge: 0.0244 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:07:54,261 INFO misc.py line 117 726] Train: [20/20][342/510] Data 4.166 (3.831) Batch 29.521 (28.032) Remain 01:18:29 loss: 0.2862 loss_seg: 0.1874 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0399 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:08:20,777 INFO misc.py line 117 726] Train: [20/20][343/510] Data 2.971 (3.829) Batch 26.516 (28.028) Remain 01:18:00 loss: 0.1827 loss_seg: 0.0962 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:08:32,794 INFO misc.py line 117 726] Train: [20/20][344/510] Data 1.481 (3.822) Batch 12.017 (27.981) Remain 01:17:24 loss: 0.3210 loss_seg: 0.2154 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:08:45,280 INFO misc.py line 117 726] Train: [20/20][345/510] Data 1.156 (3.814) Batch 12.486 (27.936) Remain 01:16:49 loss: 0.2056 loss_seg: 0.1151 loss_superpoint_edge: 0.0198 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:09:08,708 INFO misc.py line 117 726] Train: [20/20][346/510] Data 3.603 (3.813) Batch 23.427 (27.923) Remain 01:16:19 loss: 0.2968 loss_seg: 0.2004 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:09:38,966 INFO misc.py line 117 726] Train: [20/20][347/510] Data 3.406 (3.812) Batch 30.257 (27.929) Remain 01:15:52 loss: 0.2243 loss_seg: 0.1299 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:10:05,803 INFO misc.py line 117 726] Train: [20/20][348/510] Data 2.761 (3.809) Batch 26.838 (27.926) Remain 01:15:24 loss: 0.2891 loss_seg: 0.1901 loss_superpoint_edge: 0.0309 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:10:35,056 INFO misc.py line 117 726] Train: [20/20][349/510] Data 6.122 (3.816) Batch 29.253 (27.930) Remain 01:14:56 loss: 0.2331 loss_seg: 0.1419 loss_superpoint_edge: 0.0207 loss_superpoint_contrast: 0.0393 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:11:04,179 INFO misc.py line 117 726] Train: [20/20][350/510] Data 4.056 (3.817) Batch 29.123 (27.933) Remain 01:14:29 loss: 0.2145 loss_seg: 0.1255 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:11:04,180 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 01:11:40,180 INFO misc.py line 117 726] Train: [20/20][351/510] Data 5.531 (3.822) Batch 36.001 (27.957) Remain 01:14:05 loss: 0.2346 loss_seg: 0.1402 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:12:10,383 INFO misc.py line 117 726] Train: [20/20][352/510] Data 3.375 (3.820) Batch 30.203 (27.963) Remain 01:13:38 loss: 0.1869 loss_seg: 0.0992 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:12:39,637 INFO misc.py line 117 726] Train: [20/20][353/510] Data 3.908 (3.821) Batch 29.254 (27.967) Remain 01:13:10 loss: 0.2724 loss_seg: 0.1750 loss_superpoint_edge: 0.0308 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:13:00,412 INFO misc.py line 117 726] Train: [20/20][354/510] Data 2.158 (3.816) Batch 20.776 (27.946) Remain 01:12:39 loss: 0.2233 loss_seg: 0.1392 loss_superpoint_edge: 0.0162 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:13:25,387 INFO misc.py line 117 726] Train: [20/20][355/510] Data 3.125 (3.814) Batch 24.974 (27.938) Remain 01:12:10 loss: 0.2708 loss_seg: 0.1725 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:13:48,105 INFO misc.py line 117 726] Train: [20/20][356/510] Data 2.783 (3.811) Batch 22.718 (27.923) Remain 01:11:40 loss: 0.1909 loss_seg: 0.1032 loss_superpoint_edge: 0.0219 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:14:14,908 INFO misc.py line 117 726] Train: [20/20][357/510] Data 2.683 (3.808) Batch 26.803 (27.920) Remain 01:11:11 loss: 0.2551 loss_seg: 0.1552 loss_superpoint_edge: 0.0331 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:14:47,619 INFO misc.py line 117 726] Train: [20/20][358/510] Data 2.711 (3.805) Batch 32.711 (27.933) Remain 01:10:45 loss: 0.2924 loss_seg: 0.1938 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:15:17,675 INFO misc.py line 117 726] Train: [20/20][359/510] Data 2.375 (3.801) Batch 30.056 (27.939) Remain 01:10:18 loss: 0.2184 loss_seg: 0.1280 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:15:46,316 INFO misc.py line 117 726] Train: [20/20][360/510] Data 3.243 (3.799) Batch 28.641 (27.941) Remain 01:09:51 loss: 0.2630 loss_seg: 0.1642 loss_superpoint_edge: 0.0341 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:16:20,578 INFO misc.py line 117 726] Train: [20/20][361/510] Data 5.906 (3.805) Batch 34.262 (27.959) Remain 01:09:25 loss: 0.1966 loss_seg: 0.1106 loss_superpoint_edge: 0.0170 loss_superpoint_contrast: 0.0384 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:16:51,805 INFO misc.py line 117 726] Train: [20/20][362/510] Data 5.388 (3.809) Batch 31.226 (27.968) Remain 01:08:59 loss: 0.2132 loss_seg: 0.1237 loss_superpoint_edge: 0.0196 loss_superpoint_contrast: 0.0389 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:17:19,186 INFO misc.py line 117 726] Train: [20/20][363/510] Data 3.827 (3.809) Batch 27.382 (27.966) Remain 01:08:31 loss: 0.2041 loss_seg: 0.1189 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:17:40,011 INFO misc.py line 117 726] Train: [20/20][364/510] Data 1.842 (3.804) Batch 20.824 (27.947) Remain 01:08:00 loss: 0.2099 loss_seg: 0.1199 loss_superpoint_edge: 0.0233 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:18:06,674 INFO misc.py line 117 726] Train: [20/20][365/510] Data 4.808 (3.807) Batch 26.663 (27.943) Remain 01:07:31 loss: 0.2584 loss_seg: 0.1598 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:18:26,888 INFO misc.py line 117 726] Train: [20/20][366/510] Data 2.641 (3.804) Batch 20.214 (27.922) Remain 01:07:00 loss: 0.2840 loss_seg: 0.1842 loss_superpoint_edge: 0.0257 loss_superpoint_contrast: 0.0429 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:18:58,551 INFO misc.py line 117 726] Train: [20/20][367/510] Data 3.494 (3.803) Batch 31.663 (27.932) Remain 01:06:34 loss: 0.2735 loss_seg: 0.1729 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:19:25,435 INFO misc.py line 117 726] Train: [20/20][368/510] Data 4.063 (3.803) Batch 26.884 (27.929) Remain 01:06:05 loss: 0.2894 loss_seg: 0.1948 loss_superpoint_edge: 0.0251 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:19:54,214 INFO misc.py line 117 726] Train: [20/20][369/510] Data 3.221 (3.802) Batch 28.779 (27.932) Remain 01:05:38 loss: 0.1772 loss_seg: 0.0916 loss_superpoint_edge: 0.0193 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:20:20,912 INFO misc.py line 117 726] Train: [20/20][370/510] Data 3.351 (3.801) Batch 26.697 (27.928) Remain 01:05:09 loss: 0.1836 loss_seg: 0.0954 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:20:51,955 INFO misc.py line 117 726] Train: [20/20][371/510] Data 3.081 (3.799) Batch 31.043 (27.937) Remain 01:04:43 loss: 0.1884 loss_seg: 0.1029 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:21:18,455 INFO misc.py line 117 726] Train: [20/20][372/510] Data 2.953 (3.796) Batch 26.500 (27.933) Remain 01:04:14 loss: 0.2984 loss_seg: 0.1997 loss_superpoint_edge: 0.0335 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:21:48,689 INFO misc.py line 117 726] Train: [20/20][373/510] Data 4.071 (3.797) Batch 30.235 (27.939) Remain 01:03:47 loss: 0.3074 loss_seg: 0.2010 loss_superpoint_edge: 0.0393 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:22:06,401 INFO misc.py line 117 726] Train: [20/20][374/510] Data 2.132 (3.793) Batch 17.712 (27.911) Remain 01:03:15 loss: 0.3037 loss_seg: 0.2033 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0403 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:22:40,934 INFO misc.py line 117 726] Train: [20/20][375/510] Data 6.773 (3.801) Batch 34.533 (27.929) Remain 01:02:50 loss: 0.2722 loss_seg: 0.1748 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:23:05,896 INFO misc.py line 117 726] Train: [20/20][376/510] Data 2.599 (3.797) Batch 24.962 (27.921) Remain 01:02:21 loss: 0.3347 loss_seg: 0.2272 loss_superpoint_edge: 0.0410 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0332 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:23:36,438 INFO misc.py line 117 726] Train: [20/20][377/510] Data 2.639 (3.794) Batch 30.542 (27.928) Remain 01:01:54 loss: 0.2300 loss_seg: 0.1370 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:24:09,727 INFO misc.py line 117 726] Train: [20/20][378/510] Data 6.124 (3.800) Batch 33.289 (27.943) Remain 01:01:28 loss: 0.2827 loss_seg: 0.1841 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:24:46,487 INFO misc.py line 117 726] Train: [20/20][379/510] Data 5.907 (3.806) Batch 36.759 (27.966) Remain 01:01:03 loss: 0.3696 loss_seg: 0.2626 loss_superpoint_edge: 0.0381 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:25:16,584 INFO misc.py line 117 726] Train: [20/20][380/510] Data 3.686 (3.806) Batch 30.097 (27.972) Remain 01:00:36 loss: 0.3510 loss_seg: 0.2599 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0373 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:25:45,397 INFO misc.py line 117 726] Train: [20/20][381/510] Data 5.102 (3.809) Batch 28.814 (27.974) Remain 01:00:08 loss: 0.2284 loss_seg: 0.1363 loss_superpoint_edge: 0.0202 loss_superpoint_contrast: 0.0413 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:26:14,331 INFO misc.py line 117 726] Train: [20/20][382/510] Data 3.246 (3.808) Batch 28.934 (27.976) Remain 00:59:40 loss: 0.2721 loss_seg: 0.1712 loss_superpoint_edge: 0.0328 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:26:46,167 INFO misc.py line 117 726] Train: [20/20][383/510] Data 4.701 (3.810) Batch 31.835 (27.987) Remain 00:59:14 loss: 0.2771 loss_seg: 0.1793 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:27:13,973 INFO misc.py line 117 726] Train: [20/20][384/510] Data 2.641 (3.807) Batch 27.806 (27.986) Remain 00:58:46 loss: 0.2057 loss_seg: 0.1177 loss_superpoint_edge: 0.0221 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:27:41,599 INFO misc.py line 117 726] Train: [20/20][385/510] Data 3.665 (3.807) Batch 27.626 (27.985) Remain 00:58:18 loss: 0.2418 loss_seg: 0.1406 loss_superpoint_edge: 0.0334 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0321 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:28:01,402 INFO misc.py line 117 726] Train: [20/20][386/510] Data 1.827 (3.801) Batch 19.803 (27.964) Remain 00:57:47 loss: 0.2488 loss_seg: 0.1509 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:28:32,113 INFO misc.py line 117 726] Train: [20/20][387/510] Data 3.364 (3.800) Batch 30.710 (27.971) Remain 00:57:20 loss: 0.1828 loss_seg: 0.0941 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:29:10,754 INFO misc.py line 117 726] Train: [20/20][388/510] Data 8.914 (3.814) Batch 38.641 (27.999) Remain 00:56:55 loss: 0.2123 loss_seg: 0.1240 loss_superpoint_edge: 0.0220 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:29:25,275 INFO misc.py line 117 726] Train: [20/20][389/510] Data 2.148 (3.809) Batch 14.521 (27.964) Remain 00:56:23 loss: 0.2804 loss_seg: 0.1863 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:29:53,077 INFO misc.py line 117 726] Train: [20/20][390/510] Data 5.226 (3.813) Batch 27.802 (27.963) Remain 00:55:55 loss: 0.2455 loss_seg: 0.1463 loss_superpoint_edge: 0.0329 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:30:23,503 INFO misc.py line 117 726] Train: [20/20][391/510] Data 3.653 (3.813) Batch 30.426 (27.970) Remain 00:55:28 loss: 0.2079 loss_seg: 0.1224 loss_superpoint_edge: 0.0192 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:30:55,147 INFO misc.py line 117 726] Train: [20/20][392/510] Data 6.022 (3.818) Batch 31.644 (27.979) Remain 00:55:01 loss: 0.2207 loss_seg: 0.1333 loss_superpoint_edge: 0.0213 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:31:20,154 INFO misc.py line 117 726] Train: [20/20][393/510] Data 4.522 (3.820) Batch 25.007 (27.971) Remain 00:54:32 loss: 0.2923 loss_seg: 0.2000 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:31:49,403 INFO misc.py line 117 726] Train: [20/20][394/510] Data 4.010 (3.820) Batch 29.249 (27.975) Remain 00:54:05 loss: 0.2995 loss_seg: 0.2023 loss_superpoint_edge: 0.0291 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:32:05,473 INFO misc.py line 117 726] Train: [20/20][395/510] Data 2.158 (3.816) Batch 16.071 (27.944) Remain 00:53:33 loss: 0.2238 loss_seg: 0.1282 loss_superpoint_edge: 0.0260 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:32:38,526 INFO misc.py line 117 726] Train: [20/20][396/510] Data 2.603 (3.813) Batch 33.053 (27.957) Remain 00:53:07 loss: 0.2148 loss_seg: 0.1235 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0342 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:33:00,998 INFO misc.py line 117 726] Train: [20/20][397/510] Data 2.281 (3.809) Batch 22.472 (27.943) Remain 00:52:37 loss: 0.2711 loss_seg: 0.1703 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:33:34,687 INFO misc.py line 117 726] Train: [20/20][398/510] Data 6.248 (3.815) Batch 33.690 (27.958) Remain 00:52:11 loss: 0.1756 loss_seg: 0.0914 loss_superpoint_edge: 0.0156 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:34:00,913 INFO misc.py line 117 726] Train: [20/20][399/510] Data 3.522 (3.815) Batch 26.226 (27.954) Remain 00:51:42 loss: 0.2433 loss_seg: 0.1486 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:34:24,052 INFO misc.py line 117 726] Train: [20/20][400/510] Data 2.578 (3.812) Batch 23.139 (27.942) Remain 00:51:13 loss: 0.3250 loss_seg: 0.2147 loss_superpoint_edge: 0.0424 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:34:24,052 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 01:34:42,756 INFO misc.py line 117 726] Train: [20/20][401/510] Data 2.197 (3.808) Batch 18.704 (27.918) Remain 00:50:43 loss: 0.2725 loss_seg: 0.1857 loss_superpoint_edge: 0.0191 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:35:07,741 INFO misc.py line 117 726] Train: [20/20][402/510] Data 3.295 (3.806) Batch 24.985 (27.911) Remain 00:50:14 loss: 0.2209 loss_seg: 0.1325 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:35:36,915 INFO misc.py line 117 726] Train: [20/20][403/510] Data 2.645 (3.803) Batch 29.174 (27.914) Remain 00:49:46 loss: 0.2220 loss_seg: 0.1280 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:36:07,273 INFO misc.py line 117 726] Train: [20/20][404/510] Data 2.537 (3.800) Batch 30.357 (27.920) Remain 00:49:19 loss: 0.2598 loss_seg: 0.1566 loss_superpoint_edge: 0.0358 loss_superpoint_contrast: 0.0358 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:36:35,680 INFO misc.py line 117 726] Train: [20/20][405/510] Data 2.795 (3.798) Batch 28.408 (27.921) Remain 00:48:51 loss: 0.2853 loss_seg: 0.1875 loss_superpoint_edge: 0.0302 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:37:05,495 INFO misc.py line 117 726] Train: [20/20][406/510] Data 3.669 (3.797) Batch 29.815 (27.926) Remain 00:48:24 loss: 0.2193 loss_seg: 0.1339 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:37:28,659 INFO misc.py line 117 726] Train: [20/20][407/510] Data 5.022 (3.800) Batch 23.164 (27.914) Remain 00:47:55 loss: 0.3929 loss_seg: 0.2879 loss_superpoint_edge: 0.0327 loss_superpoint_contrast: 0.0407 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:37:56,037 INFO misc.py line 117 726] Train: [20/20][408/510] Data 3.101 (3.799) Batch 27.378 (27.913) Remain 00:47:27 loss: 0.2642 loss_seg: 0.1628 loss_superpoint_edge: 0.0346 loss_superpoint_contrast: 0.0350 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:38:16,249 INFO misc.py line 117 726] Train: [20/20][409/510] Data 2.763 (3.796) Batch 20.212 (27.894) Remain 00:46:57 loss: 0.2712 loss_seg: 0.1730 loss_superpoint_edge: 0.0278 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:38:44,532 INFO misc.py line 117 726] Train: [20/20][410/510] Data 3.061 (3.794) Batch 28.283 (27.895) Remain 00:46:29 loss: 0.2029 loss_seg: 0.1141 loss_superpoint_edge: 0.0232 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:39:15,427 INFO misc.py line 117 726] Train: [20/20][411/510] Data 2.525 (3.791) Batch 30.895 (27.902) Remain 00:46:02 loss: 0.2767 loss_seg: 0.1753 loss_superpoint_edge: 0.0356 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:39:38,611 INFO misc.py line 117 726] Train: [20/20][412/510] Data 1.860 (3.786) Batch 23.183 (27.891) Remain 00:45:33 loss: 0.2323 loss_seg: 0.1357 loss_superpoint_edge: 0.0304 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:40:05,932 INFO misc.py line 117 726] Train: [20/20][413/510] Data 4.282 (3.788) Batch 27.322 (27.889) Remain 00:45:05 loss: 0.2121 loss_seg: 0.1238 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:40:35,354 INFO misc.py line 117 726] Train: [20/20][414/510] Data 5.252 (3.791) Batch 29.422 (27.893) Remain 00:44:37 loss: 0.5022 loss_seg: 0.3805 loss_superpoint_edge: 0.0495 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0335 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:41:08,968 INFO misc.py line 117 726] Train: [20/20][415/510] Data 2.819 (3.789) Batch 33.614 (27.907) Remain 00:44:11 loss: 0.2910 loss_seg: 0.1889 loss_superpoint_edge: 0.0380 loss_superpoint_contrast: 0.0326 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:41:30,987 INFO misc.py line 117 726] Train: [20/20][416/510] Data 2.991 (3.787) Batch 22.019 (27.893) Remain 00:43:41 loss: 0.2805 loss_seg: 0.1716 loss_superpoint_edge: 0.0394 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0329 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:41:50,803 INFO misc.py line 117 726] Train: [20/20][417/510] Data 3.371 (3.786) Batch 19.817 (27.873) Remain 00:43:12 loss: 0.2667 loss_seg: 0.1650 loss_superpoint_edge: 0.0301 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0326 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:42:23,615 INFO misc.py line 117 726] Train: [20/20][418/510] Data 3.696 (3.786) Batch 32.811 (27.885) Remain 00:42:45 loss: 0.3027 loss_seg: 0.2106 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0335 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:42:45,280 INFO misc.py line 117 726] Train: [20/20][419/510] Data 2.321 (3.782) Batch 21.666 (27.870) Remain 00:42:16 loss: 0.2710 loss_seg: 0.1686 loss_superpoint_edge: 0.0325 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:43:13,489 INFO misc.py line 117 726] Train: [20/20][420/510] Data 3.321 (3.781) Batch 28.208 (27.871) Remain 00:41:48 loss: 0.2513 loss_seg: 0.1538 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:43:37,764 INFO misc.py line 117 726] Train: [20/20][421/510] Data 2.533 (3.778) Batch 24.276 (27.862) Remain 00:41:19 loss: 0.2640 loss_seg: 0.1676 loss_superpoint_edge: 0.0276 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:44:00,248 INFO misc.py line 117 726] Train: [20/20][422/510] Data 2.550 (3.775) Batch 22.484 (27.850) Remain 00:40:50 loss: 0.2278 loss_seg: 0.1317 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:44:32,941 INFO misc.py line 117 726] Train: [20/20][423/510] Data 4.347 (3.777) Batch 32.693 (27.861) Remain 00:40:23 loss: 0.2446 loss_seg: 0.1564 loss_superpoint_edge: 0.0210 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:44:58,440 INFO misc.py line 117 726] Train: [20/20][424/510] Data 2.644 (3.774) Batch 25.499 (27.856) Remain 00:39:55 loss: 0.2144 loss_seg: 0.1270 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:45:25,771 INFO misc.py line 117 726] Train: [20/20][425/510] Data 4.944 (3.777) Batch 27.331 (27.854) Remain 00:39:27 loss: 0.1978 loss_seg: 0.1112 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:45:58,390 INFO misc.py line 117 726] Train: [20/20][426/510] Data 5.179 (3.780) Batch 32.619 (27.866) Remain 00:39:00 loss: 0.1773 loss_seg: 0.0921 loss_superpoint_edge: 0.0130 loss_superpoint_contrast: 0.0402 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:46:29,257 INFO misc.py line 117 726] Train: [20/20][427/510] Data 4.311 (3.781) Batch 30.868 (27.873) Remain 00:38:33 loss: 0.2260 loss_seg: 0.1306 loss_superpoint_edge: 0.0296 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:47:05,760 INFO misc.py line 117 726] Train: [20/20][428/510] Data 4.746 (3.783) Batch 36.503 (27.893) Remain 00:38:07 loss: 0.2081 loss_seg: 0.1192 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:47:27,345 INFO misc.py line 117 726] Train: [20/20][429/510] Data 2.478 (3.780) Batch 21.584 (27.878) Remain 00:37:38 loss: 0.2382 loss_seg: 0.1408 loss_superpoint_edge: 0.0288 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:47:49,580 INFO misc.py line 117 726] Train: [20/20][430/510] Data 2.637 (3.778) Batch 22.235 (27.865) Remain 00:37:09 loss: 0.2483 loss_seg: 0.1531 loss_superpoint_edge: 0.0303 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:48:15,329 INFO misc.py line 117 726] Train: [20/20][431/510] Data 2.640 (3.775) Batch 25.750 (27.860) Remain 00:36:40 loss: 0.1927 loss_seg: 0.1072 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:48:45,975 INFO misc.py line 117 726] Train: [20/20][432/510] Data 3.121 (3.774) Batch 30.645 (27.866) Remain 00:36:13 loss: 0.2062 loss_seg: 0.1170 loss_superpoint_edge: 0.0256 loss_superpoint_contrast: 0.0333 loss_semantic_contrast: 0.0302 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:49:10,744 INFO misc.py line 117 726] Train: [20/20][433/510] Data 2.586 (3.771) Batch 24.770 (27.859) Remain 00:35:45 loss: 0.2238 loss_seg: 0.1339 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0328 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:49:48,643 INFO misc.py line 117 726] Train: [20/20][434/510] Data 5.074 (3.774) Batch 37.898 (27.883) Remain 00:35:19 loss: 0.2438 loss_seg: 0.1513 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0324 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:50:23,371 INFO misc.py line 117 726] Train: [20/20][435/510] Data 5.296 (3.777) Batch 34.729 (27.898) Remain 00:34:52 loss: 0.3115 loss_seg: 0.2056 loss_superpoint_edge: 0.0387 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:50:49,970 INFO misc.py line 117 726] Train: [20/20][436/510] Data 3.646 (3.777) Batch 26.599 (27.895) Remain 00:34:24 loss: 0.2364 loss_seg: 0.1457 loss_superpoint_edge: 0.0249 loss_superpoint_contrast: 0.0344 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:51:21,042 INFO misc.py line 117 726] Train: [20/20][437/510] Data 4.622 (3.779) Batch 31.072 (27.903) Remain 00:33:56 loss: 0.2139 loss_seg: 0.1215 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0349 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:51:56,822 INFO misc.py line 117 726] Train: [20/20][438/510] Data 10.531 (3.794) Batch 35.779 (27.921) Remain 00:33:30 loss: 0.4564 loss_seg: 0.3133 loss_superpoint_edge: 0.0743 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0327 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:52:24,771 INFO misc.py line 117 726] Train: [20/20][439/510] Data 3.828 (3.795) Batch 27.949 (27.921) Remain 00:33:02 loss: 0.2525 loss_seg: 0.1557 loss_superpoint_edge: 0.0287 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:52:46,918 INFO misc.py line 117 726] Train: [20/20][440/510] Data 2.528 (3.792) Batch 22.147 (27.908) Remain 00:32:33 loss: 0.1898 loss_seg: 0.1053 loss_superpoint_edge: 0.0150 loss_superpoint_contrast: 0.0395 loss_semantic_contrast: 0.0299 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:53:17,993 INFO misc.py line 117 726] Train: [20/20][441/510] Data 2.656 (3.789) Batch 31.075 (27.915) Remain 00:32:06 loss: 0.2474 loss_seg: 0.1513 loss_superpoint_edge: 0.0274 loss_superpoint_contrast: 0.0368 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:53:32,688 INFO misc.py line 117 726] Train: [20/20][442/510] Data 1.897 (3.785) Batch 14.695 (27.885) Remain 00:31:36 loss: 0.3778 loss_seg: 0.2704 loss_superpoint_edge: 0.0375 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:53:57,254 INFO misc.py line 117 726] Train: [20/20][443/510] Data 2.564 (3.782) Batch 24.566 (27.877) Remain 00:31:07 loss: 0.1881 loss_seg: 0.1041 loss_superpoint_edge: 0.0187 loss_superpoint_contrast: 0.0345 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:54:33,800 INFO misc.py line 117 726] Train: [20/20][444/510] Data 10.577 (3.797) Batch 36.545 (27.897) Remain 00:30:41 loss: 0.2085 loss_seg: 0.1148 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0401 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:55:01,184 INFO misc.py line 117 726] Train: [20/20][445/510] Data 3.133 (3.796) Batch 27.385 (27.896) Remain 00:30:13 loss: 0.1927 loss_seg: 0.1054 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:55:28,574 INFO misc.py line 117 726] Train: [20/20][446/510] Data 2.986 (3.794) Batch 27.390 (27.895) Remain 00:29:45 loss: 0.2189 loss_seg: 0.1288 loss_superpoint_edge: 0.0223 loss_superpoint_contrast: 0.0363 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:55:56,915 INFO misc.py line 117 726] Train: [20/20][447/510] Data 3.063 (3.792) Batch 28.341 (27.896) Remain 00:29:17 loss: 0.1918 loss_seg: 0.1026 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:56:21,145 INFO misc.py line 117 726] Train: [20/20][448/510] Data 2.868 (3.790) Batch 24.230 (27.887) Remain 00:28:49 loss: 0.2007 loss_seg: 0.1139 loss_superpoint_edge: 0.0201 loss_superpoint_contrast: 0.0357 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:56:52,744 INFO misc.py line 117 726] Train: [20/20][449/510] Data 4.467 (3.792) Batch 31.599 (27.896) Remain 00:28:21 loss: 0.2606 loss_seg: 0.1647 loss_superpoint_edge: 0.0230 loss_superpoint_contrast: 0.0410 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:57:21,567 INFO misc.py line 117 726] Train: [20/20][450/510] Data 4.277 (3.793) Batch 28.823 (27.898) Remain 00:27:53 loss: 0.2165 loss_seg: 0.1279 loss_superpoint_edge: 0.0204 loss_superpoint_contrast: 0.0369 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:57:21,568 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 01:57:49,186 INFO misc.py line 117 726] Train: [20/20][451/510] Data 4.018 (3.793) Batch 27.618 (27.897) Remain 00:27:25 loss: 0.2395 loss_seg: 0.1416 loss_superpoint_edge: 0.0292 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:58:16,578 INFO misc.py line 117 726] Train: [20/20][452/510] Data 4.560 (3.795) Batch 27.392 (27.896) Remain 00:26:57 loss: 0.1917 loss_seg: 0.1049 loss_superpoint_edge: 0.0189 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0304 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:58:46,281 INFO misc.py line 117 726] Train: [20/20][453/510] Data 3.513 (3.795) Batch 29.703 (27.900) Remain 00:26:30 loss: 0.1869 loss_seg: 0.1024 loss_superpoint_edge: 0.0186 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:59:12,228 INFO misc.py line 117 726] Train: [20/20][454/510] Data 2.518 (3.792) Batch 25.946 (27.896) Remain 00:26:02 loss: 0.2505 loss_seg: 0.1559 loss_superpoint_edge: 0.0281 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 01:59:52,711 INFO misc.py line 117 726] Train: [20/20][455/510] Data 9.360 (3.804) Batch 40.483 (27.924) Remain 00:25:35 loss: 0.2515 loss_seg: 0.1593 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0366 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:00:17,308 INFO misc.py line 117 726] Train: [20/20][456/510] Data 2.737 (3.802) Batch 24.597 (27.916) Remain 00:25:07 loss: 0.2697 loss_seg: 0.1676 loss_superpoint_edge: 0.0330 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:00:47,384 INFO misc.py line 117 726] Train: [20/20][457/510] Data 3.563 (3.801) Batch 30.076 (27.921) Remain 00:24:39 loss: 0.2550 loss_seg: 0.1576 loss_superpoint_edge: 0.0289 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:01:12,366 INFO misc.py line 117 726] Train: [20/20][458/510] Data 2.578 (3.798) Batch 24.982 (27.914) Remain 00:24:11 loss: 0.2169 loss_seg: 0.1237 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:01:47,512 INFO misc.py line 117 726] Train: [20/20][459/510] Data 4.160 (3.799) Batch 35.146 (27.930) Remain 00:23:44 loss: 0.2265 loss_seg: 0.1336 loss_superpoint_edge: 0.0259 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:02:15,018 INFO misc.py line 117 726] Train: [20/20][460/510] Data 2.927 (3.797) Batch 27.506 (27.929) Remain 00:23:16 loss: 0.2812 loss_seg: 0.1834 loss_superpoint_edge: 0.0282 loss_superpoint_contrast: 0.0376 loss_semantic_contrast: 0.0319 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:02:43,163 INFO misc.py line 117 726] Train: [20/20][461/510] Data 3.564 (3.797) Batch 28.145 (27.930) Remain 00:22:48 loss: 0.1861 loss_seg: 0.1012 loss_superpoint_edge: 0.0184 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:03:06,536 INFO misc.py line 117 726] Train: [20/20][462/510] Data 2.350 (3.794) Batch 23.373 (27.920) Remain 00:22:20 loss: 0.2387 loss_seg: 0.1460 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0355 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:03:33,040 INFO misc.py line 117 726] Train: [20/20][463/510] Data 3.648 (3.793) Batch 26.505 (27.917) Remain 00:21:52 loss: 0.1847 loss_seg: 0.1025 loss_superpoint_edge: 0.0138 loss_superpoint_contrast: 0.0381 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:04:13,993 INFO misc.py line 117 726] Train: [20/20][464/510] Data 7.908 (3.802) Batch 40.953 (27.945) Remain 00:21:25 loss: 0.2824 loss_seg: 0.1823 loss_superpoint_edge: 0.0333 loss_superpoint_contrast: 0.0347 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:04:36,454 INFO misc.py line 117 726] Train: [20/20][465/510] Data 2.595 (3.800) Batch 22.461 (27.933) Remain 00:20:56 loss: 0.2223 loss_seg: 0.1281 loss_superpoint_edge: 0.0247 loss_superpoint_contrast: 0.0390 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:04:54,227 INFO misc.py line 117 726] Train: [20/20][466/510] Data 2.188 (3.796) Batch 17.772 (27.911) Remain 00:20:28 loss: 0.2610 loss_seg: 0.1592 loss_superpoint_edge: 0.0322 loss_superpoint_contrast: 0.0380 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:05:21,865 INFO misc.py line 117 726] Train: [20/20][467/510] Data 3.259 (3.795) Batch 27.639 (27.911) Remain 00:20:00 loss: 0.1858 loss_seg: 0.0990 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0360 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:05:51,572 INFO misc.py line 117 726] Train: [20/20][468/510] Data 3.300 (3.794) Batch 29.706 (27.915) Remain 00:19:32 loss: 0.2474 loss_seg: 0.1519 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0367 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:06:23,807 INFO misc.py line 117 726] Train: [20/20][469/510] Data 3.751 (3.794) Batch 32.235 (27.924) Remain 00:19:04 loss: 0.3826 loss_seg: 0.2644 loss_superpoint_edge: 0.0496 loss_superpoint_contrast: 0.0361 loss_semantic_contrast: 0.0325 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:06:55,434 INFO misc.py line 117 726] Train: [20/20][470/510] Data 3.155 (3.793) Batch 31.626 (27.932) Remain 00:18:37 loss: 0.2625 loss_seg: 0.1570 loss_superpoint_edge: 0.0384 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:07:21,978 INFO misc.py line 117 726] Train: [20/20][471/510] Data 3.304 (3.791) Batch 26.545 (27.929) Remain 00:18:09 loss: 0.2858 loss_seg: 0.1834 loss_superpoint_edge: 0.0352 loss_superpoint_contrast: 0.0348 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:07:58,032 INFO misc.py line 117 726] Train: [20/20][472/510] Data 4.310 (3.793) Batch 36.054 (27.946) Remain 00:17:41 loss: 0.2805 loss_seg: 0.1786 loss_superpoint_edge: 0.0366 loss_superpoint_contrast: 0.0332 loss_semantic_contrast: 0.0322 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:08:35,890 INFO misc.py line 117 726] Train: [20/20][473/510] Data 5.962 (3.797) Batch 37.858 (27.967) Remain 00:17:14 loss: 0.2581 loss_seg: 0.1611 loss_superpoint_edge: 0.0295 loss_superpoint_contrast: 0.0359 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:09:00,530 INFO misc.py line 117 726] Train: [20/20][474/510] Data 2.792 (3.795) Batch 24.640 (27.960) Remain 00:16:46 loss: 0.2278 loss_seg: 0.1356 loss_superpoint_edge: 0.0279 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:09:24,498 INFO misc.py line 117 726] Train: [20/20][475/510] Data 2.021 (3.791) Batch 23.968 (27.952) Remain 00:16:18 loss: 0.2436 loss_seg: 0.1490 loss_superpoint_edge: 0.0264 loss_superpoint_contrast: 0.0374 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:09:58,619 INFO misc.py line 117 726] Train: [20/20][476/510] Data 4.427 (3.793) Batch 34.121 (27.965) Remain 00:15:50 loss: 0.2061 loss_seg: 0.1165 loss_superpoint_edge: 0.0205 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:10:27,465 INFO misc.py line 117 726] Train: [20/20][477/510] Data 3.963 (3.793) Batch 28.846 (27.967) Remain 00:15:22 loss: 0.1970 loss_seg: 0.1074 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0346 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:10:51,500 INFO misc.py line 117 726] Train: [20/20][478/510] Data 2.864 (3.791) Batch 24.034 (27.958) Remain 00:14:54 loss: 0.3765 loss_seg: 0.2785 loss_superpoint_edge: 0.0298 loss_superpoint_contrast: 0.0353 loss_semantic_contrast: 0.0328 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:11:23,066 INFO misc.py line 117 726] Train: [20/20][479/510] Data 4.195 (3.792) Batch 31.566 (27.966) Remain 00:14:26 loss: 0.2229 loss_seg: 0.1348 loss_superpoint_edge: 0.0229 loss_superpoint_contrast: 0.0337 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:11:50,436 INFO misc.py line 117 726] Train: [20/20][480/510] Data 2.993 (3.790) Batch 27.370 (27.965) Remain 00:13:58 loss: 0.2887 loss_seg: 0.1961 loss_superpoint_edge: 0.0258 loss_superpoint_contrast: 0.0356 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:12:10,354 INFO misc.py line 117 726] Train: [20/20][481/510] Data 3.169 (3.789) Batch 19.919 (27.948) Remain 00:13:30 loss: 0.2327 loss_seg: 0.1370 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:12:38,858 INFO misc.py line 117 726] Train: [20/20][482/510] Data 3.581 (3.788) Batch 28.503 (27.949) Remain 00:13:02 loss: 0.2505 loss_seg: 0.1570 loss_superpoint_edge: 0.0290 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0311 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:13:07,136 INFO misc.py line 117 726] Train: [20/20][483/510] Data 3.832 (3.789) Batch 28.278 (27.950) Remain 00:12:34 loss: 0.2626 loss_seg: 0.1607 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0378 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:13:43,441 INFO misc.py line 117 726] Train: [20/20][484/510] Data 10.872 (3.803) Batch 36.305 (27.967) Remain 00:12:07 loss: 0.2389 loss_seg: 0.1433 loss_superpoint_edge: 0.0271 loss_superpoint_contrast: 0.0382 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:14:08,170 INFO misc.py line 117 726] Train: [20/20][485/510] Data 2.412 (3.800) Batch 24.729 (27.960) Remain 00:11:39 loss: 0.2180 loss_seg: 0.1262 loss_superpoint_edge: 0.0263 loss_superpoint_contrast: 0.0352 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:14:35,031 INFO misc.py line 117 726] Train: [20/20][486/510] Data 4.652 (3.802) Batch 26.862 (27.958) Remain 00:11:10 loss: 0.2922 loss_seg: 0.2020 loss_superpoint_edge: 0.0199 loss_superpoint_contrast: 0.0394 loss_semantic_contrast: 0.0309 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:15:04,691 INFO misc.py line 117 726] Train: [20/20][487/510] Data 9.120 (3.813) Batch 29.660 (27.962) Remain 00:10:43 loss: 0.3075 loss_seg: 0.2104 loss_superpoint_edge: 0.0267 loss_superpoint_contrast: 0.0388 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:15:34,222 INFO misc.py line 117 726] Train: [20/20][488/510] Data 2.937 (3.811) Batch 29.531 (27.965) Remain 00:10:15 loss: 0.2353 loss_seg: 0.1474 loss_superpoint_edge: 0.0241 loss_superpoint_contrast: 0.0331 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:16:05,443 INFO misc.py line 117 726] Train: [20/20][489/510] Data 3.929 (3.812) Batch 31.221 (27.972) Remain 00:09:47 loss: 0.1933 loss_seg: 0.1091 loss_superpoint_edge: 0.0175 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:16:32,157 INFO misc.py line 117 726] Train: [20/20][490/510] Data 3.189 (3.810) Batch 26.714 (27.969) Remain 00:09:19 loss: 0.2149 loss_seg: 0.1274 loss_superpoint_edge: 0.0206 loss_superpoint_contrast: 0.0364 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:16:58,529 INFO misc.py line 117 726] Train: [20/20][491/510] Data 3.540 (3.810) Batch 26.372 (27.966) Remain 00:08:51 loss: 0.2928 loss_seg: 0.1881 loss_superpoint_edge: 0.0383 loss_superpoint_contrast: 0.0340 loss_semantic_contrast: 0.0324 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:17:16,732 INFO misc.py line 117 726] Train: [20/20][492/510] Data 1.756 (3.806) Batch 18.204 (27.946) Remain 00:08:23 loss: 0.3383 loss_seg: 0.2359 loss_superpoint_edge: 0.0321 loss_superpoint_contrast: 0.0386 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:17:48,571 INFO misc.py line 117 726] Train: [20/20][493/510] Data 4.190 (3.806) Batch 31.839 (27.954) Remain 00:07:55 loss: 0.2203 loss_seg: 0.1333 loss_superpoint_edge: 0.0226 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0310 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:18:24,489 INFO misc.py line 117 726] Train: [20/20][494/510] Data 5.204 (3.809) Batch 35.918 (27.970) Remain 00:07:27 loss: 0.1808 loss_seg: 0.1002 loss_superpoint_edge: 0.0168 loss_superpoint_contrast: 0.0338 loss_semantic_contrast: 0.0301 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:18:50,628 INFO misc.py line 117 726] Train: [20/20][495/510] Data 3.323 (3.808) Batch 26.138 (27.966) Remain 00:06:59 loss: 0.2209 loss_seg: 0.1279 loss_superpoint_edge: 0.0243 loss_superpoint_contrast: 0.0375 loss_semantic_contrast: 0.0312 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:19:08,683 INFO misc.py line 117 726] Train: [20/20][496/510] Data 1.392 (3.803) Batch 18.056 (27.946) Remain 00:06:31 loss: 0.2234 loss_seg: 0.1318 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0383 loss_semantic_contrast: 0.0306 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:19:39,824 INFO misc.py line 117 726] Train: [20/20][497/510] Data 3.732 (3.803) Batch 31.141 (27.953) Remain 00:06:03 loss: 0.3410 loss_seg: 0.2494 loss_superpoint_edge: 0.0235 loss_superpoint_contrast: 0.0365 loss_semantic_contrast: 0.0315 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:20:15,771 INFO misc.py line 117 726] Train: [20/20][498/510] Data 9.001 (3.814) Batch 35.948 (27.969) Remain 00:05:35 loss: 0.2509 loss_seg: 0.1631 loss_superpoint_edge: 0.0190 loss_superpoint_contrast: 0.0385 loss_semantic_contrast: 0.0303 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:20:53,396 INFO misc.py line 117 726] Train: [20/20][499/510] Data 4.014 (3.814) Batch 37.625 (27.988) Remain 00:05:07 loss: 0.2462 loss_seg: 0.1640 loss_superpoint_edge: 0.0180 loss_superpoint_contrast: 0.0336 loss_semantic_contrast: 0.0305 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:21:13,021 INFO misc.py line 117 726] Train: [20/20][500/510] Data 2.564 (3.812) Batch 19.625 (27.971) Remain 00:04:39 loss: 0.2590 loss_seg: 0.1676 loss_superpoint_edge: 0.0227 loss_superpoint_contrast: 0.0372 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:21:13,022 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth [2026-06-13 02:21:46,948 INFO misc.py line 117 726] Train: [20/20][501/510] Data 4.587 (3.813) Batch 33.926 (27.983) Remain 00:04:11 loss: 0.2554 loss_seg: 0.1584 loss_superpoint_edge: 0.0293 loss_superpoint_contrast: 0.0354 loss_semantic_contrast: 0.0323 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:22:12,221 INFO misc.py line 117 726] Train: [20/20][502/510] Data 2.473 (3.810) Batch 25.273 (27.978) Remain 00:03:43 loss: 0.2545 loss_seg: 0.1538 loss_superpoint_edge: 0.0319 loss_superpoint_contrast: 0.0371 loss_semantic_contrast: 0.0317 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:22:39,164 INFO misc.py line 117 726] Train: [20/20][503/510] Data 2.468 (3.808) Batch 26.943 (27.976) Remain 00:03:15 loss: 0.1845 loss_seg: 0.0966 loss_superpoint_edge: 0.0179 loss_superpoint_contrast: 0.0392 loss_semantic_contrast: 0.0308 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:23:04,122 INFO misc.py line 117 726] Train: [20/20][504/510] Data 2.554 (3.805) Batch 24.958 (27.970) Remain 00:02:47 loss: 0.2307 loss_seg: 0.1348 loss_superpoint_edge: 0.0311 loss_superpoint_contrast: 0.0334 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:23:21,971 INFO misc.py line 117 726] Train: [20/20][505/510] Data 2.080 (3.802) Batch 17.850 (27.950) Remain 00:02:19 loss: 0.2325 loss_seg: 0.1387 loss_superpoint_edge: 0.0261 loss_superpoint_contrast: 0.0370 loss_semantic_contrast: 0.0307 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:23:39,812 INFO misc.py line 117 726] Train: [20/20][506/510] Data 2.505 (3.799) Batch 17.841 (27.929) Remain 00:01:51 loss: 0.2652 loss_seg: 0.1674 loss_superpoint_edge: 0.0275 loss_superpoint_contrast: 0.0387 loss_semantic_contrast: 0.0316 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:24:18,162 INFO misc.py line 117 726] Train: [20/20][507/510] Data 5.517 (3.803) Batch 38.349 (27.950) Remain 00:01:23 loss: 0.2302 loss_seg: 0.1377 loss_superpoint_edge: 0.0254 loss_superpoint_contrast: 0.0351 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:24:41,290 INFO misc.py line 117 726] Train: [20/20][508/510] Data 2.236 (3.800) Batch 23.129 (27.941) Remain 00:00:55 loss: 0.1978 loss_seg: 0.1084 loss_superpoint_edge: 0.0238 loss_superpoint_contrast: 0.0343 loss_semantic_contrast: 0.0313 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:25:10,332 INFO misc.py line 117 726] Train: [20/20][509/510] Data 3.685 (3.799) Batch 29.042 (27.943) Remain 00:00:27 loss: 0.2380 loss_seg: 0.1452 loss_superpoint_edge: 0.0268 loss_superpoint_contrast: 0.0339 loss_semantic_contrast: 0.0320 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:25:33,969 INFO misc.py line 117 726] Train: [20/20][510/510] Data 2.855 (3.797) Batch 23.637 (27.934) Remain 00:00:00 loss: 0.2027 loss_seg: 0.1145 loss_superpoint_edge: 0.0222 loss_superpoint_contrast: 0.0341 loss_semantic_contrast: 0.0318 loss_semantic_rank_contrast: 0.0000 Lr: 0.00000 [2026-06-13 02:25:33,970 INFO misc.py line 147 726] Train result: loss: 0.2481 loss_seg: 0.1533 loss_superpoint_edge: 0.0270 loss_superpoint_contrast: 0.0362 loss_semantic_contrast: 0.0314 loss_semantic_rank_contrast: 0.0000 [2026-06-13 02:25:33,970 INFO evaluator.py line 137 726] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> [2026-06-13 02:25:49,371 INFO evaluator.py line 178 726] Interp. Test: [1/34] Loss 0.6777 [2026-06-13 02:26:05,482 INFO evaluator.py line 178 726] Interp. Test: [2/34] Loss 0.6991 [2026-06-13 02:27:20,268 INFO evaluator.py line 178 726] Interp. Test: [3/34] Loss 0.8934 [2026-06-13 02:28:00,128 INFO evaluator.py line 178 726] Interp. Test: [4/34] Loss 0.9166 [2026-06-13 02:28:19,330 INFO evaluator.py line 178 726] Interp. Test: [5/34] Loss 0.9547 [2026-06-13 02:28:55,022 INFO evaluator.py line 178 726] Interp. Test: [6/34] Loss 1.1683 [2026-06-13 02:29:41,537 INFO evaluator.py line 178 726] Interp. Test: [7/34] Loss 2.1551 [2026-06-13 02:29:56,890 INFO evaluator.py line 178 726] Interp. Test: [8/34] Loss 1.2064 [2026-06-13 02:30:14,731 INFO evaluator.py line 178 726] Interp. Test: [9/34] Loss 1.0198 [2026-06-13 02:30:33,324 INFO evaluator.py line 178 726] Interp. Test: [10/34] Loss 1.3775 [2026-06-13 02:30:49,075 INFO evaluator.py line 178 726] Interp. Test: [11/34] Loss 1.5784 [2026-06-13 02:31:10,524 INFO evaluator.py line 178 726] Interp. Test: [12/34] Loss 0.7942 [2026-06-13 02:31:36,312 INFO evaluator.py line 178 726] Interp. Test: [13/34] Loss 1.8889 [2026-06-13 02:31:47,565 INFO evaluator.py line 178 726] Interp. Test: [14/34] Loss 0.6165 [2026-06-13 02:32:19,516 INFO evaluator.py line 178 726] Interp. Test: [15/34] Loss 1.0447 [2026-06-13 02:32:45,603 INFO evaluator.py line 178 726] Interp. Test: [16/34] Loss 1.2690 [2026-06-13 02:33:12,435 INFO evaluator.py line 178 726] Interp. Test: [17/34] Loss 1.3018 [2026-06-13 02:33:55,088 INFO evaluator.py line 178 726] Interp. Test: [18/34] Loss 4.1768 [2026-06-13 02:34:16,221 INFO evaluator.py line 178 726] Interp. Test: [19/34] Loss 0.3963 [2026-06-13 02:34:32,625 INFO evaluator.py line 178 726] Interp. Test: [20/34] Loss 1.7662 [2026-06-13 02:35:03,501 INFO evaluator.py line 178 726] Interp. Test: [21/34] Loss 1.8354 [2026-06-13 02:35:19,636 INFO evaluator.py line 178 726] Interp. Test: [22/34] Loss 1.4125 [2026-06-13 02:35:41,410 INFO evaluator.py line 178 726] Interp. Test: [23/34] Loss 1.2428 [2026-06-13 02:36:02,992 INFO evaluator.py line 178 726] Interp. Test: [24/34] Loss 0.8220 [2026-06-13 02:36:16,298 INFO evaluator.py line 178 726] Interp. Test: [25/34] Loss 0.6068 [2026-06-13 02:36:43,855 INFO evaluator.py line 178 726] Interp. Test: [26/34] Loss 1.5700 [2026-06-13 02:37:25,227 INFO evaluator.py line 178 726] Interp. Test: [27/34] Loss 2.0560 [2026-06-13 02:37:42,663 INFO evaluator.py line 178 726] Interp. Test: [28/34] Loss 0.5244 [2026-06-13 02:38:01,128 INFO evaluator.py line 178 726] Interp. Test: [29/34] Loss 1.4683 [2026-06-13 02:38:17,830 INFO evaluator.py line 178 726] Interp. Test: [30/34] Loss 1.4724 [2026-06-13 02:38:42,624 INFO evaluator.py line 178 726] Interp. Test: [31/34] Loss 1.1448 [2026-06-13 02:39:00,727 INFO evaluator.py line 178 726] Interp. Test: [32/34] Loss 0.5595 [2026-06-13 02:39:18,171 INFO evaluator.py line 178 726] Interp. Test: [33/34] Loss 0.9801 [2026-06-13 02:39:42,448 INFO evaluator.py line 178 726] Interp. Test: [34/34] Loss 2.7377 [2026-06-13 02:39:42,464 INFO evaluator.py line 195 726] Val result: mIoU/mAcc/allAcc 0.6725/0.7448/0.8976. [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_0-ceiling Result: iou/accuracy 0.9249/0.9581 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_1-floor Result: iou/accuracy 0.9765/0.9882 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_2-wall Result: iou/accuracy 0.8433/0.9705 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_3-beam Result: iou/accuracy 0.0018/0.0152 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_4-column Result: iou/accuracy 0.3339/0.3963 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_5-window Result: iou/accuracy 0.6027/0.6297 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_6-door Result: iou/accuracy 0.6182/0.7136 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_7-table Result: iou/accuracy 0.7941/0.8961 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_8-chair Result: iou/accuracy 0.9079/0.9510 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_9-sofa Result: iou/accuracy 0.6729/0.7466 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_10-bookcase Result: iou/accuracy 0.7659/0.8509 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_11-board Result: iou/accuracy 0.7030/0.8580 [2026-06-13 02:39:42,464 INFO evaluator.py line 201 726] Class_12-clutter Result: iou/accuracy 0.5969/0.7080 [2026-06-13 02:39:42,465 INFO evaluator.py line 244 726] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< [2026-06-13 02:39:42,465 INFO misc.py line 218 726] Currently Best mIoU: 0.6740 [2026-06-13 02:39:42,465 INFO misc.py line 175 726] Saving checkpoint to: exp/s3dis/bidit_pycut_w1a1_weak_valfix_rare_protected_20260609/model/model_last.pth