pretrain-gs-v4-spunet-base/train.log

[2025-02-17 11:01:07,891 INFO train.py line 128 848561] => Loading config ...
[2025-02-17 11:01:07,891 INFO train.py line 130 848561] Save path: exp/scannet/pretrain-gs-v4-spunet-base-m3
[2025-02-17 11:01:08,361 INFO train.py line 131 848561] Config:
weight = None
resume = False
evaluate = False
test_only = False
seed = 59120461
save_path = 'exp/scannet/pretrain-gs-v4-spunet-base-m3'
num_worker = 64
batch_size = 32
batch_size_val = None
batch_size_test = None
epoch = 1200
eval_epoch = 100
clip_grad = None
sync_bn = False
enable_amp = True
empty_cache = False
empty_cache_per_epoch = True
find_unused_parameters = True
mix_prob = 0.0
param_dicts = None
hooks = [
    dict(type='CheckpointLoader'),
    dict(type='IterationTimer', warmup_iter=2),
    dict(type='CustomInformationWriter', interval=50, key=('loss', 'psnr')),
    dict(type='CheckpointSaver', save_freq=None)
]
train = dict(type='DefaultTrainer')
test = dict(type='SemSegTester', verbose=True)
use_semantic = True
model = dict(
    type='GSIndoor-v4',
    backbone_out_channels=96,
    backbone=dict(
        type='SpUNet-v1m1',
        in_channels=6,
        num_classes=0,
        channels=(32, 64, 128, 256, 256, 128, 96, 96),
        layers=(2, 3, 4, 6, 2, 2, 2, 2)),
    projection=dict(type='UNet3D-v1m2', in_channels=96, out_channels=128),
    regressor=dict(
        type='GSRegresser-v3',
        in_dim=128,
        hidden_size=256,
        scale_range=(0.02, 0.01),
        delta_range=0.1,
        feat_dim=29),
    loss_weights=dict(depth_loss=1.0, rgb_loss=10.0, feat_loss=2.0),
    grid_shape=(128, 128, 32),
    bg_color=0.0,
    opacity_thr=0.3,
    semantic=dict(type='radio', use_semantic=True, version='radio_v2.5-b'),
    use_depth=True)
optimizer = dict(type='AdamW', lr=0.002, weight_decay=0.05)
scheduler = dict(
    type='OneCycleLR',
    max_lr=0.002,
    pct_start=0.05,
    anneal_strategy='cos',
    div_factor=10.0,
    final_div_factor=10000.0)
num_cameras = 5
data = dict(
    train=dict(
        type='ScanNetRGBDDataset',
        split=['train', 'val', 'test'],
        data_root='data/scannet',
        rgb_root='data/scannet/rgbd',
        num_cameras=5,
        transform=[
            dict(type='ToTensor'),
            dict(type='CenterShift', apply_z=True, keys=['extrinsic']),
            dict(
                type='RandomDropout',
                dropout_ratio=0.3,
                dropout_application_ratio=1.0),
            dict(
                type='RandomRotate',
                angle=[-1, 1],
                axis='z',
                center=[0, 0, 0],
                p=1,
                keys=['extrinsic']),
            dict(
                type='RandomRotate',
                angle=[-0.015625, 0.015625],
                axis='x',
                p=1,
                keys=['extrinsic']),
            dict(
                type='RandomRotate',
                angle=[-0.015625, 0.015625],
                axis='y',
                p=1,
                keys=['extrinsic']),
            dict(type='RandomScale', scale=[0.9, 1.1], keys=['extrinsic']),
            dict(type='RandomFlip', p=0.5, keys=['extrinsic']),
            dict(
                type='GridSample',
                grid_size=0.02,
                hash_type='fnv',
                mode='train',
                return_grid_coord=True,
                keys=('coord', 'color', 'normal')),
            dict(type='CenterShift', apply_z=False, keys=['extrinsic']),
            dict(type='NormalizeColor'),
            dict(type='ShufflePoint'),
            dict(
                type='Collect',
                keys=('coord', 'grid_coord', 'depth_scale'),
                stack_keys=('intrinsic', 'extrinsic', 'rgb', 'depth'),
                feat_keys=('color', 'normal'))
        ],
        test_mode=False,
        loop=12))
num_worker_per_gpu = 8
batch_size_per_gpu = 4
batch_size_val_per_gpu = 1
batch_size_test_per_gpu = 1

[2025-02-17 11:01:08,361 INFO train.py line 132 848561] => Building model ...
[2025-02-17 11:01:12,346 INFO train.py line 225 848561] Num params: 42396555
[2025-02-17 11:01:12,701 INFO train.py line 134 848561] => Building writer ...
[2025-02-17 11:01:12,702 INFO train.py line 235 848561] Tensorboard writer logging dir: exp/scannet/pretrain-gs-v4-spunet-base-m3
[2025-02-17 11:01:12,702 INFO train.py line 136 848561] => Building train dataset & dataloader ...
[2025-02-17 11:01:12,705 INFO defaults.py line 68 848561] Totally 1613 x 12 samples in ['train', 'val', 'test'] set.
[2025-02-17 11:01:12,705 INFO train.py line 138 848561] => Building val dataset & dataloader ...
[2025-02-17 11:01:12,705 INFO train.py line 140 848561] => Building optimize, scheduler, scaler(amp) ...
[2025-02-17 11:01:12,706 INFO train.py line 144 848561] => Building hooks ...
[2025-02-17 11:01:12,706 INFO misc.py line 214 848561] => Loading checkpoint & weight ...
[2025-02-17 11:01:12,707 INFO misc.py line 250 848561] No weight found at: None
[2025-02-17 11:01:12,707 INFO train.py line 151 848561] >>>>>>>>>>>>>>>> Start Training >>>>>>>>>>>>>>>>
[2025-02-17 11:02:30,058 INFO hook.py line 109 848561] Train: [1/100][50/605] Data 0.003 (0.002) Batch 1.008 (0.998) Remain 16:45:07 loss: 3.7840 psnr: 12.7724 Lr: 2.00940e-04
[2025-02-17 11:03:19,507 INFO hook.py line 109 848561] Train: [1/100][100/605] Data 0.003 (0.002) Batch 0.988 (0.993) Remain 16:39:47 loss: 3.8086 psnr: 12.3325 Lr: 2.04288e-04
[2025-02-17 11:04:08,944 INFO hook.py line 109 848561] Train: [1/100][150/605] Data 0.002 (0.002) Batch 1.006 (0.992) Remain 16:37:26 loss: 3.3168 psnr: 14.5488 Lr: 2.10052e-04
[2025-02-17 11:04:58,838 INFO hook.py line 109 848561] Train: [1/100][200/605] Data 0.003 (0.002) Batch 0.970 (0.993) Remain 16:38:12 loss: 3.4426 psnr: 13.6478 Lr: 2.18217e-04
[2025-02-17 11:05:48,198 INFO hook.py line 109 848561] Train: [1/100][250/605] Data 0.003 (0.003) Batch 0.996 (0.992) Remain 16:36:09 loss: 3.2874 psnr: 14.5914 Lr: 2.28761e-04
[2025-02-17 11:06:37,294 INFO hook.py line 109 848561] Train: [1/100][300/605] Data 0.003 (0.003) Batch 0.992 (0.990) Remain 16:33:37 loss: 3.4963 psnr: 13.6071 Lr: 2.41655e-04
[2025-02-17 11:07:25,907 INFO hook.py line 109 848561] Train: [1/100][350/605] Data 0.002 (0.003) Batch 0.964 (0.988) Remain 16:30:10 loss: 3.3993 psnr: 14.2709 Lr: 2.56864e-04
[2025-02-17 11:08:14,067 INFO hook.py line 109 848561] Train: [1/100][400/605] Data 0.002 (0.003) Batch 0.973 (0.985) Remain 16:26:16 loss: 3.3951 psnr: 13.1890 Lr: 2.74348e-04
[2025-02-17 11:09:01,930 INFO hook.py line 109 848561] Train: [1/100][450/605] Data 0.004 (0.003) Batch 0.937 (0.982) Remain 16:22:23 loss: 3.0168 psnr: 15.2648 Lr: 2.94059e-04
[2025-02-17 11:09:49,416 INFO hook.py line 109 848561] Train: [1/100][500/605] Data 0.002 (0.003) Batch 0.938 (0.978) Remain 16:18:21 loss: 3.2358 psnr: 13.3323 Lr: 3.15944e-04
[2025-02-17 11:10:37,212 INFO hook.py line 109 848561] Train: [1/100][550/605] Data 0.003 (0.003) Batch 0.930 (0.976) Remain 16:15:29 loss: 3.4191 psnr: 12.2692 Lr: 3.39945e-04
[2025-02-17 11:11:24,523 INFO hook.py line 109 848561] Train: [1/100][600/605] Data 0.002 (0.003) Batch 0.856 (0.974) Remain 16:12:10 loss: 3.0530 psnr: 14.5304 Lr: 3.65995e-04
[2025-02-17 11:11:28,834 INFO misc.py line 135 848561] Train result: loss: 3.4455 rgb_loss: 1.5256 psnr: 13.7450 depth_loss: 0.1740 feat_loss: 1.7458 
[2025-02-17 11:11:28,834 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 11:12:19,398 INFO hook.py line 109 848561] Train: [2/100][50/605] Data 0.002 (0.003) Batch 0.931 (0.935) Remain 15:33:01 loss: 2.8886 psnr: 15.5798 Lr: 3.96935e-04
[2025-02-17 11:13:06,216 INFO hook.py line 109 848561] Train: [2/100][100/605] Data 0.002 (0.002) Batch 0.911 (0.936) Remain 15:32:42 loss: 2.7283 psnr: 16.8064 Lr: 4.27056e-04
[2025-02-17 11:13:53,264 INFO hook.py line 109 848561] Train: [2/100][150/605] Data 0.003 (0.002) Batch 0.923 (0.938) Remain 15:33:38 loss: 2.8874 psnr: 15.8881 Lr: 4.58993e-04
[2025-02-17 11:14:40,376 INFO hook.py line 109 848561] Train: [2/100][200/605] Data 0.002 (0.002) Batch 0.950 (0.939) Remain 15:34:01 loss: 2.8470 psnr: 16.0920 Lr: 4.92658e-04
[2025-02-17 11:15:27,509 INFO hook.py line 109 848561] Train: [2/100][250/605] Data 0.003 (0.002) Batch 0.935 (0.940) Remain 15:34:00 loss: 2.5605 psnr: 18.2193 Lr: 5.27963e-04
[2025-02-17 11:16:14,436 INFO hook.py line 109 848561] Train: [2/100][300/605] Data 0.003 (0.002) Batch 0.927 (0.939) Remain 15:33:03 loss: 2.6006 psnr: 17.7659 Lr: 5.64810e-04
[2025-02-17 11:17:01,189 INFO hook.py line 109 848561] Train: [2/100][350/605] Data 0.002 (0.002) Batch 0.965 (0.939) Remain 15:31:39 loss: 2.9905 psnr: 15.2314 Lr: 6.03101e-04
[2025-02-17 11:17:48,084 INFO hook.py line 109 848561] Train: [2/100][400/605] Data 0.003 (0.002) Batch 0.936 (0.939) Remain 15:30:45 loss: 2.8017 psnr: 16.6859 Lr: 6.42732e-04
[2025-02-17 11:18:35,157 INFO hook.py line 109 848561] Train: [2/100][450/605] Data 0.002 (0.002) Batch 0.919 (0.939) Remain 15:30:17 loss: 3.0204 psnr: 15.0204 Lr: 6.83597e-04
[2025-02-17 11:19:22,012 INFO hook.py line 109 848561] Train: [2/100][500/605] Data 0.002 (0.002) Batch 0.942 (0.939) Remain 15:29:19 loss: 2.8818 psnr: 16.4994 Lr: 7.25585e-04
[2025-02-17 11:20:08,830 INFO hook.py line 109 848561] Train: [2/100][550/605] Data 0.002 (0.002) Batch 0.941 (0.939) Remain 15:28:19 loss: 2.6743 psnr: 17.7980 Lr: 7.68584e-04
[2025-02-17 11:20:55,145 INFO hook.py line 109 848561] Train: [2/100][600/605] Data 0.002 (0.002) Batch 0.874 (0.938) Remain 15:26:31 loss: 2.8270 psnr: 16.0348 Lr: 8.12476e-04
[2025-02-17 11:20:59,481 INFO misc.py line 135 848561] Train result: loss: 2.8794 rgb_loss: 1.1209 psnr: 15.7550 depth_loss: 0.0934 feat_loss: 1.6651 
[2025-02-17 11:20:59,483 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 11:21:50,303 INFO hook.py line 109 848561] Train: [3/100][50/605] Data 0.003 (0.002) Batch 0.941 (0.937) Remain 15:25:05 loss: 2.8246 psnr: 15.9340 Lr: 8.61649e-04
[2025-02-17 11:22:37,086 INFO hook.py line 109 848561] Train: [3/100][100/605] Data 0.002 (0.002) Batch 0.923 (0.936) Remain 15:23:39 loss: 2.8759 psnr: 15.6927 Lr: 9.07030e-04
[2025-02-17 11:23:24,138 INFO hook.py line 109 848561] Train: [3/100][150/605] Data 0.003 (0.002) Batch 0.943 (0.938) Remain 15:24:27 loss: 2.6230 psnr: 17.2740 Lr: 9.52933e-04
[2025-02-17 11:24:10,763 INFO hook.py line 109 848561] Train: [3/100][200/605] Data 0.003 (0.002) Batch 0.942 (0.937) Remain 15:22:19 loss: 2.7531 psnr: 16.1178 Lr: 9.99232e-04
[2025-02-17 11:24:58,046 INFO hook.py line 109 848561] Train: [3/100][250/605] Data 0.002 (0.002) Batch 0.964 (0.938) Remain 15:23:21 loss: 2.8263 psnr: 16.0726 Lr: 1.04580e-03
[2025-02-17 11:25:45,281 INFO hook.py line 109 848561] Train: [3/100][300/605] Data 0.003 (0.002) Batch 0.936 (0.939) Remain 15:23:37 loss: 3.3178 psnr: 13.0652 Lr: 1.09252e-03
[2025-02-17 11:26:32,413 INFO hook.py line 109 848561] Train: [3/100][350/605] Data 0.002 (0.002) Batch 0.943 (0.940) Remain 15:23:18 loss: 2.9988 psnr: 14.4800 Lr: 1.13926e-03
[2025-02-17 11:27:19,841 INFO hook.py line 109 848561] Train: [3/100][400/605] Data 0.002 (0.002) Batch 0.934 (0.941) Remain 15:23:35 loss: 2.8524 psnr: 15.2351 Lr: 1.18589e-03
[2025-02-17 11:28:06,783 INFO hook.py line 109 848561] Train: [3/100][450/605] Data 0.003 (0.002) Batch 0.947 (0.941) Remain 15:22:33 loss: 2.9544 psnr: 14.6657 Lr: 1.23229e-03
[2025-02-17 11:28:54,164 INFO hook.py line 109 848561] Train: [3/100][500/605] Data 0.002 (0.002) Batch 0.928 (0.941) Remain 15:22:27 loss: 2.8738 psnr: 14.9197 Lr: 1.27833e-03
[2025-02-17 11:29:41,725 INFO hook.py line 109 848561] Train: [3/100][550/605] Data 0.002 (0.002) Batch 0.947 (0.942) Remain 15:22:32 loss: 2.6767 psnr: 17.0212 Lr: 1.32389e-03
[2025-02-17 11:30:28,123 INFO hook.py line 109 848561] Train: [3/100][600/605] Data 0.002 (0.002) Batch 0.878 (0.941) Remain 15:20:35 loss: 2.9617 psnr: 15.2215 Lr: 1.36885e-03
[2025-02-17 11:30:32,499 INFO misc.py line 135 848561] Train result: loss: 2.7873 rgb_loss: 1.0631 psnr: 16.0739 depth_loss: 0.0886 feat_loss: 1.6357 
[2025-02-17 11:30:32,500 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 11:31:23,604 INFO hook.py line 109 848561] Train: [4/100][50/605] Data 0.003 (0.002) Batch 0.939 (0.944) Remain 15:22:39 loss: 2.6148 psnr: 17.0336 Lr: 1.41746e-03
[2025-02-17 11:32:10,823 INFO hook.py line 109 848561] Train: [4/100][100/605] Data 0.002 (0.002) Batch 0.936 (0.944) Remain 15:21:59 loss: 2.4951 psnr: 17.7251 Lr: 1.46076e-03
[2025-02-17 11:32:58,219 INFO hook.py line 109 848561] Train: [4/100][150/605] Data 0.003 (0.002) Batch 0.923 (0.946) Remain 15:22:25 loss: 2.7099 psnr: 16.6368 Lr: 1.50308e-03
[2025-02-17 11:33:45,544 INFO hook.py line 109 848561] Train: [4/100][200/605] Data 0.003 (0.002) Batch 0.948 (0.946) Remain 15:21:52 loss: 2.7776 psnr: 15.3641 Lr: 1.54432e-03
[2025-02-17 11:34:33,200 INFO hook.py line 109 848561] Train: [4/100][250/605] Data 0.002 (0.002) Batch 0.976 (0.947) Remain 15:22:32 loss: 2.6428 psnr: 16.5070 Lr: 1.58436e-03
[2025-02-17 11:35:20,208 INFO hook.py line 109 848561] Train: [4/100][300/605] Data 0.002 (0.002) Batch 0.919 (0.946) Remain 15:20:35 loss: 2.7633 psnr: 16.6034 Lr: 1.62309e-03
[2025-02-17 11:36:07,327 INFO hook.py line 109 848561] Train: [4/100][350/605] Data 0.002 (0.002) Batch 0.955 (0.946) Remain 15:19:17 loss: 2.5175 psnr: 17.7316 Lr: 1.66041e-03
[2025-02-17 11:36:54,512 INFO hook.py line 109 848561] Train: [4/100][400/605] Data 0.002 (0.002) Batch 0.938 (0.945) Remain 15:18:16 loss: 2.5515 psnr: 17.4385 Lr: 1.69622e-03
[2025-02-17 11:37:41,829 INFO hook.py line 109 848561] Train: [4/100][450/605] Data 0.005 (0.002) Batch 0.962 (0.945) Remain 15:17:35 loss: 2.6806 psnr: 17.3247 Lr: 1.73042e-03
[2025-02-17 11:38:29,067 INFO hook.py line 109 848561] Train: [4/100][500/605] Data 0.003 (0.002) Batch 0.956 (0.945) Remain 15:16:44 loss: 2.5482 psnr: 18.0616 Lr: 1.76292e-03
[2025-02-17 11:39:16,146 INFO hook.py line 109 848561] Train: [4/100][550/605] Data 0.002 (0.002) Batch 0.939 (0.945) Remain 15:15:37 loss: 2.4841 psnr: 17.3203 Lr: 1.79363e-03
[2025-02-17 11:40:02,488 INFO hook.py line 109 848561] Train: [4/100][600/605] Data 0.002 (0.002) Batch 0.855 (0.943) Remain 15:13:22 loss: 2.7571 psnr: 15.8763 Lr: 1.82247e-03
[2025-02-17 11:40:06,885 INFO misc.py line 135 848561] Train result: loss: 2.7171 rgb_loss: 1.0258 psnr: 16.2700 depth_loss: 0.0838 feat_loss: 1.6075 
[2025-02-17 11:40:06,886 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 11:40:58,162 INFO hook.py line 109 848561] Train: [5/100][50/605] Data 0.002 (0.002) Batch 0.953 (0.941) Remain 15:09:52 loss: 2.5575 psnr: 16.6071 Lr: 1.85194e-03
[2025-02-17 11:41:45,162 INFO hook.py line 109 848561] Train: [5/100][100/605] Data 0.002 (0.002) Batch 0.904 (0.940) Remain 15:08:43 loss: 2.4995 psnr: 17.4052 Lr: 1.87660e-03
[2025-02-17 11:42:32,315 INFO hook.py line 109 848561] Train: [5/100][150/605] Data 0.002 (0.002) Batch 0.936 (0.941) Remain 15:08:48 loss: 2.4368 psnr: 18.3139 Lr: 1.89917e-03
[2025-02-17 11:43:19,551 INFO hook.py line 109 848561] Train: [5/100][200/605] Data 0.003 (0.002) Batch 0.952 (0.942) Remain 15:08:52 loss: 2.5328 psnr: 16.8256 Lr: 1.91958e-03
[2025-02-17 11:44:06,792 INFO hook.py line 109 848561] Train: [5/100][250/605] Data 0.003 (0.002) Batch 0.931 (0.943) Remain 15:08:36 loss: 2.6608 psnr: 15.6761 Lr: 1.93779e-03
[2025-02-17 11:44:54,275 INFO hook.py line 109 848561] Train: [5/100][300/605] Data 0.002 (0.002) Batch 0.948 (0.944) Remain 15:08:56 loss: 2.9822 psnr: 14.5835 Lr: 1.95373e-03
[2025-02-17 11:45:41,317 INFO hook.py line 109 848561] Train: [5/100][350/605] Data 0.003 (0.002) Batch 0.942 (0.943) Remain 15:07:44 loss: 2.9390 psnr: 15.2369 Lr: 1.96737e-03
[2025-02-17 11:46:28,591 INFO hook.py line 109 848561] Train: [5/100][400/605] Data 0.002 (0.002) Batch 0.976 (0.944) Remain 15:07:11 loss: 2.3802 psnr: 18.7799 Lr: 1.97867e-03
[2025-02-17 11:47:15,821 INFO hook.py line 109 848561] Train: [5/100][450/605] Data 0.003 (0.002) Batch 0.924 (0.944) Remain 15:06:30 loss: 2.6184 psnr: 15.9986 Lr: 1.98760e-03
[2025-02-17 11:48:02,783 INFO hook.py line 109 848561] Train: [5/100][500/605] Data 0.003 (0.002) Batch 0.965 (0.943) Remain 15:05:17 loss: 2.4938 psnr: 17.4030 Lr: 1.99413e-03
[2025-02-17 11:48:49,865 INFO hook.py line 109 848561] Train: [5/100][550/605] Data 0.002 (0.002) Batch 0.978 (0.943) Remain 15:04:21 loss: 2.6820 psnr: 16.2649 Lr: 1.99825e-03
[2025-02-17 11:49:36,151 INFO hook.py line 109 848561] Train: [5/100][600/605] Data 0.001 (0.002) Batch 0.896 (0.942) Remain 15:02:09 loss: 2.6825 psnr: 16.4821 Lr: 1.99995e-03
[2025-02-17 11:49:40,495 INFO misc.py line 135 848561] Train result: loss: 2.6728 rgb_loss: 1.0046 psnr: 16.3916 depth_loss: 0.0815 feat_loss: 1.5867 
[2025-02-17 11:49:40,497 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 11:50:31,964 INFO hook.py line 109 848561] Train: [6/100][50/605] Data 0.002 (0.002) Batch 0.980 (0.945) Remain 15:04:14 loss: 2.4691 psnr: 17.7570 Lr: 2.00000e-03
[2025-02-17 11:51:18,912 INFO hook.py line 109 848561] Train: [6/100][100/605] Data 0.002 (0.002) Batch 0.964 (0.942) Remain 15:00:34 loss: 2.5325 psnr: 18.0433 Lr: 1.99999e-03
[2025-02-17 11:52:05,851 INFO hook.py line 109 848561] Train: [6/100][150/605] Data 0.003 (0.002) Batch 0.920 (0.941) Remain 14:58:48 loss: 2.4980 psnr: 17.4759 Lr: 1.99997e-03
[2025-02-17 11:52:52,920 INFO hook.py line 109 848561] Train: [6/100][200/605] Data 0.002 (0.002) Batch 0.934 (0.941) Remain 14:58:10 loss: 2.7383 psnr: 15.6654 Lr: 1.99994e-03
[2025-02-17 11:53:40,151 INFO hook.py line 109 848561] Train: [6/100][250/605] Data 0.002 (0.002) Batch 0.928 (0.942) Remain 14:58:06 loss: 2.6321 psnr: 16.1401 Lr: 1.99991e-03
[2025-02-17 11:54:27,344 INFO hook.py line 109 848561] Train: [6/100][300/605] Data 0.002 (0.002) Batch 0.936 (0.942) Remain 14:57:40 loss: 2.4616 psnr: 18.4940 Lr: 1.99987e-03
[2025-02-17 11:55:14,660 INFO hook.py line 109 848561] Train: [6/100][350/605] Data 0.002 (0.002) Batch 0.971 (0.943) Remain 14:57:28 loss: 2.6666 psnr: 16.2619 Lr: 1.99982e-03
[2025-02-17 11:56:01,968 INFO hook.py line 109 848561] Train: [6/100][400/605] Data 0.003 (0.002) Batch 0.955 (0.943) Remain 14:57:07 loss: 2.3997 psnr: 18.2205 Lr: 1.99977e-03
[2025-02-17 11:56:49,066 INFO hook.py line 109 848561] Train: [6/100][450/605] Data 0.003 (0.002) Batch 0.952 (0.943) Remain 14:56:12 loss: 2.5529 psnr: 16.6689 Lr: 1.99970e-03
[2025-02-17 11:57:36,242 INFO hook.py line 109 848561] Train: [6/100][500/605] Data 0.002 (0.002) Batch 0.931 (0.943) Remain 14:55:28 loss: 2.6103 psnr: 16.4553 Lr: 1.99963e-03
[2025-02-17 11:58:23,573 INFO hook.py line 109 848561] Train: [6/100][550/605] Data 0.004 (0.002) Batch 0.891 (0.943) Remain 14:55:00 loss: 2.5874 psnr: 16.0956 Lr: 1.99956e-03
[2025-02-17 11:59:10,018 INFO hook.py line 109 848561] Train: [6/100][600/605] Data 0.002 (0.002) Batch 0.854 (0.942) Remain 14:53:04 loss: 2.7151 psnr: 15.4471 Lr: 1.99947e-03
[2025-02-17 11:59:14,346 INFO misc.py line 135 848561] Train result: loss: 2.6191 rgb_loss: 0.9760 psnr: 16.5803 depth_loss: 0.0802 feat_loss: 1.5629 
[2025-02-17 11:59:14,348 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:00:05,487 INFO hook.py line 109 848561] Train: [7/100][50/605] Data 0.002 (0.003) Batch 0.941 (0.944) Remain 14:53:39 loss: 2.5420 psnr: 16.7127 Lr: 1.99937e-03
[2025-02-17 12:00:52,616 INFO hook.py line 109 848561] Train: [7/100][100/605] Data 0.001 (0.002) Batch 0.913 (0.943) Remain 14:52:20 loss: 2.5008 psnr: 17.7575 Lr: 1.99927e-03
[2025-02-17 12:01:39,723 INFO hook.py line 109 848561] Train: [7/100][150/605] Data 0.003 (0.002) Batch 0.968 (0.943) Remain 14:51:14 loss: 2.5601 psnr: 16.9657 Lr: 1.99916e-03
[2025-02-17 12:02:26,821 INFO hook.py line 109 848561] Train: [7/100][200/605] Data 0.002 (0.002) Batch 0.918 (0.943) Remain 14:50:15 loss: 2.5992 psnr: 16.0468 Lr: 1.99904e-03
[2025-02-17 12:03:14,031 INFO hook.py line 109 848561] Train: [7/100][250/605] Data 0.003 (0.002) Batch 0.969 (0.943) Remain 14:49:47 loss: 2.3008 psnr: 17.8658 Lr: 1.99892e-03
[2025-02-17 12:04:01,198 INFO hook.py line 109 848561] Train: [7/100][300/605] Data 0.002 (0.002) Batch 0.936 (0.943) Remain 14:49:04 loss: 2.3034 psnr: 18.2050 Lr: 1.99879e-03
[2025-02-17 12:04:48,358 INFO hook.py line 109 848561] Train: [7/100][350/605] Data 0.002 (0.002) Batch 0.961 (0.943) Remain 14:48:18 loss: 2.5524 psnr: 16.2701 Lr: 1.99865e-03
[2025-02-17 12:05:35,491 INFO hook.py line 109 848561] Train: [7/100][400/605] Data 0.004 (0.002) Batch 0.945 (0.943) Remain 14:47:29 loss: 2.5531 psnr: 17.0058 Lr: 1.99851e-03
[2025-02-17 12:06:22,306 INFO hook.py line 109 848561] Train: [7/100][450/605] Data 0.003 (0.002) Batch 0.922 (0.942) Remain 14:45:59 loss: 2.3733 psnr: 17.8754 Lr: 1.99835e-03
[2025-02-17 12:07:09,430 INFO hook.py line 109 848561] Train: [7/100][500/605] Data 0.003 (0.002) Batch 0.945 (0.942) Remain 14:45:14 loss: 2.8636 psnr: 14.6618 Lr: 1.99819e-03
[2025-02-17 12:07:56,358 INFO hook.py line 109 848561] Train: [7/100][550/605] Data 0.002 (0.002) Batch 0.945 (0.942) Remain 14:44:08 loss: 2.4736 psnr: 17.9850 Lr: 1.99803e-03
[2025-02-17 12:08:42,488 INFO hook.py line 109 848561] Train: [7/100][600/605] Data 0.002 (0.002) Batch 0.871 (0.940) Remain 14:41:50 loss: 2.5021 psnr: 16.6085 Lr: 1.99785e-03
[2025-02-17 12:08:46,780 INFO misc.py line 135 848561] Train result: loss: 2.5876 rgb_loss: 0.9684 psnr: 16.5956 depth_loss: 0.0769 feat_loss: 1.5423 
[2025-02-17 12:08:46,780 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:09:37,705 INFO hook.py line 109 848561] Train: [8/100][50/605] Data 0.003 (0.002) Batch 0.923 (0.940) Remain 14:40:39 loss: 2.5529 psnr: 16.7459 Lr: 1.99765e-03
[2025-02-17 12:10:24,849 INFO hook.py line 109 848561] Train: [8/100][100/605] Data 0.003 (0.002) Batch 0.954 (0.941) Remain 14:41:17 loss: 2.5697 psnr: 16.4082 Lr: 1.99746e-03
[2025-02-17 12:11:11,960 INFO hook.py line 109 848561] Train: [8/100][150/605] Data 0.003 (0.002) Batch 0.917 (0.942) Remain 14:40:44 loss: 2.6078 psnr: 16.4209 Lr: 1.99726e-03
[2025-02-17 12:11:58,935 INFO hook.py line 109 848561] Train: [8/100][200/605] Data 0.002 (0.002) Batch 0.952 (0.941) Remain 14:39:25 loss: 2.5016 psnr: 16.9523 Lr: 1.99705e-03
[2025-02-17 12:12:45,904 INFO hook.py line 109 848561] Train: [8/100][250/605] Data 0.003 (0.002) Batch 0.929 (0.941) Remain 14:38:18 loss: 2.4457 psnr: 18.2990 Lr: 1.99684e-03
[2025-02-17 12:13:33,004 INFO hook.py line 109 848561] Train: [8/100][300/605] Data 0.003 (0.002) Batch 0.925 (0.941) Remain 14:37:42 loss: 2.3556 psnr: 17.2910 Lr: 1.99662e-03
[2025-02-17 12:14:19,929 INFO hook.py line 109 848561] Train: [8/100][350/605] Data 0.003 (0.002) Batch 0.937 (0.941) Remain 14:36:35 loss: 2.5682 psnr: 16.9743 Lr: 1.99639e-03
[2025-02-17 12:15:07,085 INFO hook.py line 109 848561] Train: [8/100][400/605] Data 0.002 (0.002) Batch 0.938 (0.941) Remain 14:36:06 loss: 2.5105 psnr: 17.1576 Lr: 1.99615e-03
[2025-02-17 12:15:54,327 INFO hook.py line 109 848561] Train: [8/100][450/605] Data 0.003 (0.002) Batch 0.956 (0.941) Remain 14:35:43 loss: 2.4654 psnr: 16.2475 Lr: 1.99592e-03
[2025-02-17 12:16:41,152 INFO hook.py line 109 848561] Train: [8/100][500/605] Data 0.002 (0.002) Batch 0.908 (0.941) Remain 14:34:28 loss: 2.4889 psnr: 17.2325 Lr: 1.99567e-03
[2025-02-17 12:17:28,409 INFO hook.py line 109 848561] Train: [8/100][550/605] Data 0.001 (0.002) Batch 0.940 (0.941) Remain 14:34:03 loss: 2.3771 psnr: 18.3742 Lr: 1.99541e-03
[2025-02-17 12:18:14,554 INFO hook.py line 109 848561] Train: [8/100][600/605] Data 0.002 (0.002) Batch 0.880 (0.940) Remain 14:31:50 loss: 2.4068 psnr: 17.6339 Lr: 1.99514e-03
[2025-02-17 12:18:18,891 INFO misc.py line 135 848561] Train result: loss: 2.5502 rgb_loss: 0.9465 psnr: 16.7533 depth_loss: 0.0769 feat_loss: 1.5268 
[2025-02-17 12:18:18,892 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:19:10,202 INFO hook.py line 109 848561] Train: [9/100][50/605] Data 0.003 (0.002) Batch 0.931 (0.941) Remain 14:32:21 loss: 2.6279 psnr: 15.5038 Lr: 1.99484e-03
[2025-02-17 12:19:56,925 INFO hook.py line 109 848561] Train: [9/100][100/605] Data 0.002 (0.002) Batch 0.959 (0.938) Remain 14:28:20 loss: 2.7021 psnr: 15.6951 Lr: 1.99456e-03
[2025-02-17 12:20:44,062 INFO hook.py line 109 848561] Train: [9/100][150/605] Data 0.002 (0.002) Batch 0.954 (0.939) Remain 14:29:07 loss: 2.4405 psnr: 17.9808 Lr: 1.99427e-03
[2025-02-17 12:21:31,049 INFO hook.py line 109 848561] Train: [9/100][200/605] Data 0.002 (0.002) Batch 0.931 (0.940) Remain 14:28:25 loss: 2.6372 psnr: 15.7317 Lr: 1.99398e-03
[2025-02-17 12:22:18,142 INFO hook.py line 109 848561] Train: [9/100][250/605] Data 0.003 (0.002) Batch 0.957 (0.940) Remain 14:28:04 loss: 2.3003 psnr: 18.1436 Lr: 1.99367e-03
[2025-02-17 12:23:05,234 INFO hook.py line 109 848561] Train: [9/100][300/605] Data 0.002 (0.002) Batch 0.944 (0.940) Remain 14:27:34 loss: 2.3537 psnr: 18.2469 Lr: 1.99336e-03
[2025-02-17 12:23:52,538 INFO hook.py line 109 848561] Train: [9/100][350/605] Data 0.002 (0.002) Batch 0.962 (0.941) Remain 14:27:33 loss: 2.5551 psnr: 17.2928 Lr: 1.99304e-03
[2025-02-17 12:24:39,925 INFO hook.py line 109 848561] Train: [9/100][400/605] Data 0.003 (0.002) Batch 0.942 (0.942) Remain 14:27:32 loss: 2.7148 psnr: 15.5718 Lr: 1.99272e-03
[2025-02-17 12:25:27,130 INFO hook.py line 109 848561] Train: [9/100][450/605] Data 0.002 (0.002) Batch 0.947 (0.942) Remain 14:26:59 loss: 2.3453 psnr: 18.2170 Lr: 1.99239e-03
[2025-02-17 12:26:14,186 INFO hook.py line 109 848561] Train: [9/100][500/605] Data 0.003 (0.002) Batch 0.953 (0.942) Remain 14:26:05 loss: 2.5270 psnr: 16.4890 Lr: 1.99205e-03
[2025-02-17 12:27:01,231 INFO hook.py line 109 848561] Train: [9/100][550/605] Data 0.002 (0.002) Batch 0.920 (0.942) Remain 14:25:12 loss: 2.3942 psnr: 16.8856 Lr: 1.99170e-03
[2025-02-17 12:27:47,598 INFO hook.py line 109 848561] Train: [9/100][600/605] Data 0.002 (0.002) Batch 0.896 (0.941) Remain 14:23:18 loss: 2.7558 psnr: 15.0101 Lr: 1.99134e-03
[2025-02-17 12:27:51,994 INFO misc.py line 135 848561] Train result: loss: 2.5402 rgb_loss: 0.9463 psnr: 16.7376 depth_loss: 0.0767 feat_loss: 1.5172 
[2025-02-17 12:27:51,994 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:28:43,033 INFO hook.py line 109 848561] Train: [10/100][50/605] Data 0.002 (0.002) Batch 0.944 (0.940) Remain 14:22:03 loss: 2.6428 psnr: 15.8867 Lr: 1.99094e-03
[2025-02-17 12:29:29,965 INFO hook.py line 109 848561] Train: [10/100][100/605] Data 0.002 (0.002) Batch 0.939 (0.939) Remain 14:20:27 loss: 2.6770 psnr: 16.3771 Lr: 1.99057e-03
[2025-02-17 12:30:16,906 INFO hook.py line 109 848561] Train: [10/100][150/605] Data 0.003 (0.002) Batch 0.939 (0.939) Remain 14:19:29 loss: 2.8124 psnr: 14.4121 Lr: 1.99020e-03
[2025-02-17 12:31:03,952 INFO hook.py line 109 848561] Train: [10/100][200/605] Data 0.004 (0.002) Batch 0.932 (0.940) Remain 14:19:05 loss: 2.2732 psnr: 18.0249 Lr: 1.98981e-03
[2025-02-17 12:31:50,851 INFO hook.py line 109 848561] Train: [10/100][250/605] Data 0.004 (0.002) Batch 0.946 (0.939) Remain 14:17:59 loss: 2.7040 psnr: 15.6134 Lr: 1.98942e-03
[2025-02-17 12:32:37,821 INFO hook.py line 109 848561] Train: [10/100][300/605] Data 0.002 (0.002) Batch 0.950 (0.939) Remain 14:17:13 loss: 2.5644 psnr: 16.7387 Lr: 1.98902e-03
[2025-02-17 12:33:24,651 INFO hook.py line 109 848561] Train: [10/100][350/605] Data 0.003 (0.002) Batch 0.947 (0.939) Remain 14:16:04 loss: 2.3578 psnr: 17.7833 Lr: 1.98861e-03
[2025-02-17 12:34:11,789 INFO hook.py line 109 848561] Train: [10/100][400/605] Data 0.002 (0.002) Batch 0.931 (0.939) Remain 14:15:44 loss: 2.3477 psnr: 17.8275 Lr: 1.98819e-03
[2025-02-17 12:34:58,824 INFO hook.py line 109 848561] Train: [10/100][450/605] Data 0.002 (0.002) Batch 0.968 (0.940) Remain 14:15:04 loss: 2.2407 psnr: 19.4265 Lr: 1.98777e-03
[2025-02-17 12:35:46,151 INFO hook.py line 109 848561] Train: [10/100][500/605] Data 0.002 (0.002) Batch 0.949 (0.940) Remain 14:14:56 loss: 2.3436 psnr: 18.1172 Lr: 1.98734e-03
[2025-02-17 12:36:33,612 INFO hook.py line 109 848561] Train: [10/100][550/605] Data 0.003 (0.002) Batch 0.957 (0.941) Remain 14:14:53 loss: 2.8773 psnr: 14.2382 Lr: 1.98690e-03
[2025-02-17 12:37:19,947 INFO hook.py line 109 848561] Train: [10/100][600/605] Data 0.002 (0.002) Batch 0.862 (0.940) Remain 14:13:01 loss: 2.5690 psnr: 16.9384 Lr: 1.98646e-03
[2025-02-17 12:37:24,278 INFO misc.py line 135 848561] Train result: loss: 2.5255 rgb_loss: 0.9427 psnr: 16.7499 depth_loss: 0.0747 feat_loss: 1.5081 
[2025-02-17 12:37:24,279 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:38:15,222 INFO hook.py line 109 848561] Train: [11/100][50/605] Data 0.003 (0.002) Batch 0.961 (0.938) Remain 14:10:36 loss: 2.4127 psnr: 17.0378 Lr: 1.98596e-03
[2025-02-17 12:39:02,289 INFO hook.py line 109 848561] Train: [11/100][100/605] Data 0.004 (0.003) Batch 0.926 (0.940) Remain 14:11:18 loss: 2.3444 psnr: 17.8288 Lr: 1.98550e-03
[2025-02-17 12:39:49,468 INFO hook.py line 109 848561] Train: [11/100][150/605] Data 0.002 (0.003) Batch 0.935 (0.941) Remain 14:11:41 loss: 2.7390 psnr: 15.5757 Lr: 1.98504e-03
[2025-02-17 12:40:36,409 INFO hook.py line 109 848561] Train: [11/100][200/605] Data 0.002 (0.002) Batch 0.938 (0.941) Remain 14:10:22 loss: 2.4599 psnr: 17.0304 Lr: 1.98456e-03
[2025-02-17 12:41:23,614 INFO hook.py line 109 848561] Train: [11/100][250/605] Data 0.001 (0.002) Batch 0.943 (0.941) Remain 14:10:15 loss: 2.4880 psnr: 16.8246 Lr: 1.98408e-03
[2025-02-17 12:42:10,565 INFO hook.py line 109 848561] Train: [11/100][300/605] Data 0.003 (0.002) Batch 0.940 (0.941) Remain 14:09:07 loss: 2.6278 psnr: 15.9012 Lr: 1.98359e-03
[2025-02-17 12:42:57,463 INFO hook.py line 109 848561] Train: [11/100][350/605] Data 0.003 (0.002) Batch 0.936 (0.940) Remain 14:07:58 loss: 2.4935 psnr: 16.5609 Lr: 1.98309e-03
[2025-02-17 12:43:44,464 INFO hook.py line 109 848561] Train: [11/100][400/605] Data 0.001 (0.002) Batch 0.963 (0.940) Remain 14:07:08 loss: 2.5687 psnr: 16.2100 Lr: 1.98259e-03
[2025-02-17 12:44:31,739 INFO hook.py line 109 848561] Train: [11/100][450/605] Data 0.004 (0.002) Batch 0.970 (0.941) Remain 14:06:52 loss: 2.8359 psnr: 14.3648 Lr: 1.98208e-03
[2025-02-17 12:45:18,612 INFO hook.py line 109 848561] Train: [11/100][500/605] Data 0.003 (0.002) Batch 0.938 (0.941) Remain 14:05:45 loss: 2.6919 psnr: 15.1511 Lr: 1.98156e-03
[2025-02-17 12:46:05,691 INFO hook.py line 109 848561] Train: [11/100][550/605] Data 0.002 (0.002) Batch 0.938 (0.941) Remain 14:05:03 loss: 2.6722 psnr: 16.0478 Lr: 1.98103e-03
[2025-02-17 12:46:51,969 INFO hook.py line 109 848561] Train: [11/100][600/605] Data 0.003 (0.002) Batch 0.876 (0.939) Remain 14:03:08 loss: 2.8000 psnr: 14.6965 Lr: 1.98050e-03
[2025-02-17 12:46:56,321 INFO misc.py line 135 848561] Train result: loss: 2.5086 rgb_loss: 0.9307 psnr: 16.8461 depth_loss: 0.0736 feat_loss: 1.5043 
[2025-02-17 12:46:56,322 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:47:48,161 INFO hook.py line 109 848561] Train: [12/100][50/605] Data 0.003 (0.002) Batch 0.951 (0.941) Remain 14:03:41 loss: 2.7873 psnr: 14.5741 Lr: 1.97990e-03
[2025-02-17 12:48:35,513 INFO hook.py line 109 848561] Train: [12/100][100/605] Data 0.002 (0.002) Batch 0.982 (0.944) Remain 14:05:41 loss: 2.4549 psnr: 16.9157 Lr: 1.97935e-03
[2025-02-17 12:49:22,645 INFO hook.py line 109 848561] Train: [12/100][150/605] Data 0.004 (0.002) Batch 0.935 (0.944) Remain 14:04:27 loss: 2.6409 psnr: 15.8987 Lr: 1.97880e-03
[2025-02-17 12:50:09,817 INFO hook.py line 109 848561] Train: [12/100][200/605] Data 0.003 (0.002) Batch 0.943 (0.944) Remain 14:03:37 loss: 2.4930 psnr: 16.3031 Lr: 1.97823e-03
[2025-02-17 12:50:57,100 INFO hook.py line 109 848561] Train: [12/100][250/605] Data 0.002 (0.002) Batch 0.931 (0.944) Remain 14:03:13 loss: 2.7429 psnr: 15.4696 Lr: 1.97766e-03
[2025-02-17 12:51:44,524 INFO hook.py line 109 848561] Train: [12/100][300/605] Data 0.002 (0.002) Batch 0.966 (0.945) Remain 14:03:06 loss: 2.4636 psnr: 17.4769 Lr: 1.97709e-03
[2025-02-17 12:52:31,452 INFO hook.py line 109 848561] Train: [12/100][350/605] Data 0.003 (0.002) Batch 0.958 (0.944) Remain 14:01:31 loss: 2.4994 psnr: 17.1525 Lr: 1.97650e-03
[2025-02-17 12:53:18,855 INFO hook.py line 109 848561] Train: [12/100][400/605] Data 0.002 (0.002) Batch 0.985 (0.944) Remain 14:01:12 loss: 2.7425 psnr: 15.6917 Lr: 1.97591e-03
[2025-02-17 12:54:05,493 INFO hook.py line 109 848561] Train: [12/100][450/605] Data 0.003 (0.002) Batch 0.951 (0.943) Remain 13:59:16 loss: 2.5266 psnr: 16.3411 Lr: 1.97531e-03
[2025-02-17 12:54:52,896 INFO hook.py line 109 848561] Train: [12/100][500/605] Data 0.002 (0.002) Batch 0.958 (0.944) Remain 13:58:55 loss: 2.5210 psnr: 16.2355 Lr: 1.97470e-03
[2025-02-17 12:55:39,939 INFO hook.py line 109 848561] Train: [12/100][550/605] Data 0.002 (0.002) Batch 0.936 (0.943) Remain 13:57:55 loss: 2.5451 psnr: 16.7097 Lr: 1.97409e-03
[2025-02-17 12:56:26,287 INFO hook.py line 109 848561] Train: [12/100][600/605] Data 0.001 (0.002) Batch 0.885 (0.942) Remain 13:55:54 loss: 2.6501 psnr: 16.1993 Lr: 1.97346e-03
[2025-02-17 12:56:30,633 INFO misc.py line 135 848561] Train result: loss: 2.5039 rgb_loss: 0.9330 psnr: 16.8037 depth_loss: 0.0738 feat_loss: 1.4972 
[2025-02-17 12:56:30,634 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 12:57:21,947 INFO hook.py line 109 848561] Train: [13/100][50/605] Data 0.001 (0.002) Batch 0.955 (0.940) Remain 13:53:08 loss: 2.6000 psnr: 16.2432 Lr: 1.97277e-03
[2025-02-17 12:58:08,633 INFO hook.py line 109 848561] Train: [13/100][100/605] Data 0.003 (0.002) Batch 0.938 (0.937) Remain 13:49:34 loss: 2.5575 psnr: 15.7107 Lr: 1.97214e-03
[2025-02-17 12:58:55,281 INFO hook.py line 109 848561] Train: [13/100][150/605] Data 0.003 (0.002) Batch 0.889 (0.935) Remain 13:47:40 loss: 2.2918 psnr: 18.7042 Lr: 1.97149e-03
[2025-02-17 12:59:42,350 INFO hook.py line 109 848561] Train: [13/100][200/605] Data 0.001 (0.003) Batch 0.909 (0.937) Remain 13:48:14 loss: 2.7487 psnr: 15.0532 Lr: 1.97084e-03
[2025-02-17 13:00:29,376 INFO hook.py line 109 848561] Train: [13/100][250/605] Data 0.003 (0.003) Batch 0.930 (0.938) Remain 13:48:05 loss: 2.3861 psnr: 17.0061 Lr: 1.97018e-03
[2025-02-17 13:01:16,226 INFO hook.py line 109 848561] Train: [13/100][300/605] Data 0.002 (0.003) Batch 0.930 (0.938) Remain 13:47:13 loss: 2.3682 psnr: 17.0120 Lr: 1.96951e-03
[2025-02-17 13:02:03,130 INFO hook.py line 109 848561] Train: [13/100][350/605] Data 0.003 (0.003) Batch 0.937 (0.938) Remain 13:46:30 loss: 2.4893 psnr: 17.0655 Lr: 1.96885e-03
[2025-02-17 13:02:49,696 INFO hook.py line 109 848561] Train: [13/100][400/605] Data 0.003 (0.002) Batch 0.957 (0.937) Remain 13:45:01 loss: 2.5873 psnr: 16.4413 Lr: 1.96817e-03
[2025-02-17 13:03:36,703 INFO hook.py line 109 848561] Train: [13/100][450/605] Data 0.003 (0.002) Batch 0.932 (0.937) Remain 13:44:34 loss: 2.3665 psnr: 18.0755 Lr: 1.96749e-03
[2025-02-17 13:04:24,143 INFO hook.py line 109 848561] Train: [13/100][500/605] Data 0.002 (0.002) Batch 0.957 (0.938) Remain 13:44:49 loss: 2.5486 psnr: 16.7718 Lr: 1.96679e-03
[2025-02-17 13:05:11,181 INFO hook.py line 109 848561] Train: [13/100][550/605] Data 0.003 (0.002) Batch 0.932 (0.939) Remain 13:44:13 loss: 2.5457 psnr: 16.2149 Lr: 1.96609e-03
[2025-02-17 13:05:57,225 INFO hook.py line 109 848561] Train: [13/100][600/605] Data 0.002 (0.002) Batch 0.850 (0.937) Remain 13:42:08 loss: 2.2326 psnr: 19.1520 Lr: 1.96538e-03
[2025-02-17 13:06:01,519 INFO misc.py line 135 848561] Train result: loss: 2.4795 rgb_loss: 0.9136 psnr: 16.9232 depth_loss: 0.0746 feat_loss: 1.4914 
[2025-02-17 13:06:01,521 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 13:06:52,543 INFO hook.py line 109 848561] Train: [14/100][50/605] Data 0.003 (0.002) Batch 0.922 (0.936) Remain 13:40:09 loss: 2.5034 psnr: 16.2732 Lr: 1.96459e-03
[2025-02-17 13:07:39,753 INFO hook.py line 109 848561] Train: [14/100][100/605] Data 0.002 (0.002) Batch 0.954 (0.940) Remain 13:43:10 loss: 2.5493 psnr: 16.0766 Lr: 1.96387e-03
[2025-02-17 13:08:26,684 INFO hook.py line 109 848561] Train: [14/100][150/605] Data 0.001 (0.002) Batch 0.919 (0.940) Remain 13:41:56 loss: 2.5506 psnr: 16.8517 Lr: 1.96314e-03
[2025-02-17 13:09:13,494 INFO hook.py line 109 848561] Train: [14/100][200/605] Data 0.002 (0.002) Batch 0.936 (0.939) Remain 13:40:23 loss: 2.4621 psnr: 16.5813 Lr: 1.96240e-03
[2025-02-17 13:10:00,767 INFO hook.py line 109 848561] Train: [14/100][250/605] Data 0.002 (0.002) Batch 0.937 (0.940) Remain 13:40:47 loss: 2.3526 psnr: 17.8460 Lr: 1.96165e-03
[2025-02-17 13:10:47,943 INFO hook.py line 109 848561] Train: [14/100][300/605] Data 0.002 (0.002) Batch 0.912 (0.941) Remain 13:40:30 loss: 2.3970 psnr: 17.0394 Lr: 1.96090e-03
[2025-02-17 13:11:34,928 INFO hook.py line 109 848561] Train: [14/100][350/605] Data 0.002 (0.002) Batch 0.945 (0.941) Remain 13:39:36 loss: 2.3113 psnr: 18.4417 Lr: 1.96014e-03
[2025-02-17 13:12:21,880 INFO hook.py line 109 848561] Train: [14/100][400/605] Data 0.002 (0.002) Batch 0.927 (0.940) Remain 13:38:39 loss: 2.4374 psnr: 16.5157 Lr: 1.95937e-03
[2025-02-17 13:13:08,622 INFO hook.py line 109 848561] Train: [14/100][450/605] Data 0.002 (0.002) Batch 0.932 (0.940) Remain 13:37:20 loss: 2.3347 psnr: 17.4615 Lr: 1.95860e-03
[2025-02-17 13:13:55,606 INFO hook.py line 109 848561] Train: [14/100][500/605] Data 0.002 (0.002) Batch 0.954 (0.940) Remain 13:36:32 loss: 2.5212 psnr: 16.1787 Lr: 1.95781e-03
[2025-02-17 13:14:42,735 INFO hook.py line 109 848561] Train: [14/100][550/605] Data 0.003 (0.002) Batch 0.931 (0.940) Remain 13:35:59 loss: 2.4045 psnr: 17.4633 Lr: 1.95702e-03
[2025-02-17 13:15:29,212 INFO hook.py line 109 848561] Train: [14/100][600/605] Data 0.002 (0.002) Batch 0.877 (0.939) Remain 13:34:26 loss: 2.5750 psnr: 16.1976 Lr: 1.95623e-03
[2025-02-17 13:15:33,537 INFO misc.py line 135 848561] Train result: loss: 2.4676 rgb_loss: 0.9067 psnr: 16.9926 depth_loss: 0.0746 feat_loss: 1.4863 
[2025-02-17 13:15:33,537 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 13:16:24,739 INFO hook.py line 109 848561] Train: [15/100][50/605] Data 0.002 (0.002) Batch 0.947 (0.940) Remain 13:34:22 loss: 2.4431 psnr: 18.0600 Lr: 1.95534e-03
[2025-02-17 13:17:11,760 INFO hook.py line 109 848561] Train: [15/100][100/605] Data 0.003 (0.002) Batch 0.947 (0.940) Remain 13:33:46 loss: 2.3641 psnr: 17.6142 Lr: 1.95453e-03
[2025-02-17 13:17:58,497 INFO hook.py line 109 848561] Train: [15/100][150/605] Data 0.002 (0.002) Batch 0.933 (0.938) Remain 13:31:22 loss: 2.5283 psnr: 16.4209 Lr: 1.95371e-03
[2025-02-17 13:18:45,545 INFO hook.py line 109 848561] Train: [15/100][200/605] Data 0.003 (0.002) Batch 0.908 (0.939) Remain 13:31:09 loss: 2.1292 psnr: 20.0237 Lr: 1.95289e-03
[2025-02-17 13:19:32,572 INFO hook.py line 109 848561] Train: [15/100][250/605] Data 0.002 (0.002) Batch 0.929 (0.939) Remain 13:30:38 loss: 2.4766 psnr: 16.2902 Lr: 1.95206e-03
[2025-02-17 13:20:19,794 INFO hook.py line 109 848561] Train: [15/100][300/605] Data 0.003 (0.002) Batch 0.933 (0.940) Remain 13:30:36 loss: 2.4930 psnr: 17.1393 Lr: 1.95122e-03
[2025-02-17 13:21:06,642 INFO hook.py line 109 848561] Train: [15/100][350/605] Data 0.003 (0.002) Batch 0.932 (0.940) Remain 13:29:24 loss: 2.3546 psnr: 17.3705 Lr: 1.95037e-03
[2025-02-17 13:21:53,558 INFO hook.py line 109 848561] Train: [15/100][400/605] Data 0.003 (0.002) Batch 0.935 (0.940) Remain 13:28:28 loss: 2.7370 psnr: 15.1512 Lr: 1.94952e-03
[2025-02-17 13:22:40,352 INFO hook.py line 109 848561] Train: [15/100][450/605] Data 0.002 (0.002) Batch 0.925 (0.939) Remain 13:27:20 loss: 2.6512 psnr: 15.4699 Lr: 1.94866e-03
[2025-02-17 13:23:27,449 INFO hook.py line 109 848561] Train: [15/100][500/605] Data 0.002 (0.002) Batch 0.938 (0.939) Remain 13:26:48 loss: 2.6822 psnr: 15.8103 Lr: 1.94779e-03
[2025-02-17 13:24:14,665 INFO hook.py line 109 848561] Train: [15/100][550/605] Data 0.003 (0.002) Batch 0.918 (0.940) Remain 13:26:24 loss: 2.4882 psnr: 16.9079 Lr: 1.94691e-03
[2025-02-17 13:25:00,862 INFO hook.py line 109 848561] Train: [15/100][600/605] Data 0.003 (0.002) Batch 0.878 (0.939) Remain 13:24:28 loss: 2.2484 psnr: 19.0932 Lr: 1.94603e-03
[2025-02-17 13:25:05,146 INFO misc.py line 135 848561] Train result: loss: 2.4632 rgb_loss: 0.9065 psnr: 16.9925 depth_loss: 0.0732 feat_loss: 1.4836 
[2025-02-17 13:25:05,148 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 13:25:56,186 INFO hook.py line 109 848561] Train: [16/100][50/605] Data 0.003 (0.002) Batch 0.925 (0.938) Remain 13:22:48 loss: 2.4141 psnr: 16.8192 Lr: 1.94505e-03
[2025-02-17 13:26:43,320 INFO hook.py line 109 848561] Train: [16/100][100/605] Data 0.002 (0.002) Batch 0.935 (0.940) Remain 13:24:16 loss: 2.3053 psnr: 17.8712 Lr: 1.94416e-03
[2025-02-17 13:27:30,226 INFO hook.py line 109 848561] Train: [16/100][150/605] Data 0.002 (0.002) Batch 0.932 (0.939) Remain 13:22:52 loss: 2.5609 psnr: 15.5329 Lr: 1.94325e-03
[2025-02-17 13:28:17,118 INFO hook.py line 109 848561] Train: [16/100][200/605] Data 0.001 (0.002) Batch 0.917 (0.939) Remain 13:21:44 loss: 2.2817 psnr: 19.2477 Lr: 1.94234e-03
[2025-02-17 13:29:04,017 INFO hook.py line 109 848561] Train: [16/100][250/605] Data 0.002 (0.002) Batch 0.945 (0.939) Remain 13:20:45 loss: 2.3975 psnr: 17.3408 Lr: 1.94142e-03
[2025-02-17 13:29:50,955 INFO hook.py line 109 848561] Train: [16/100][300/605] Data 0.002 (0.002) Batch 0.904 (0.939) Remain 13:19:58 loss: 2.2653 psnr: 17.9324 Lr: 1.94050e-03
[2025-02-17 13:30:37,907 INFO hook.py line 109 848561] Train: [16/100][350/605] Data 0.003 (0.002) Batch 0.928 (0.939) Remain 13:19:12 loss: 2.8759 psnr: 14.5353 Lr: 1.93956e-03
[2025-02-17 13:31:25,007 INFO hook.py line 109 848561] Train: [16/100][400/605] Data 0.003 (0.002) Batch 0.947 (0.939) Remain 13:18:45 loss: 2.2723 psnr: 18.3314 Lr: 1.93863e-03
[2025-02-17 13:32:11,899 INFO hook.py line 109 848561] Train: [16/100][450/605] Data 0.003 (0.002) Batch 0.914 (0.939) Remain 13:17:50 loss: 2.3205 psnr: 17.4880 Lr: 1.93768e-03
[2025-02-17 13:32:58,697 INFO hook.py line 109 848561] Train: [16/100][500/605] Data 0.003 (0.002) Batch 0.922 (0.939) Remain 13:16:47 loss: 2.7553 psnr: 14.9328 Lr: 1.93673e-03
[2025-02-17 13:33:45,605 INFO hook.py line 109 848561] Train: [16/100][550/605] Data 0.004 (0.002) Batch 0.899 (0.939) Remain 13:15:57 loss: 2.4663 psnr: 17.1095 Lr: 1.93577e-03
[2025-02-17 13:34:31,762 INFO hook.py line 109 848561] Train: [16/100][600/605] Data 0.002 (0.002) Batch 0.867 (0.937) Remain 13:14:04 loss: 2.3502 psnr: 17.4846 Lr: 1.93480e-03
[2025-02-17 13:34:36,027 INFO misc.py line 135 848561] Train result: loss: 2.4480 rgb_loss: 0.8951 psnr: 17.0810 depth_loss: 0.0724 feat_loss: 1.4806 
[2025-02-17 13:34:36,028 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 13:35:26,996 INFO hook.py line 109 848561] Train: [17/100][50/605] Data 0.002 (0.002) Batch 0.939 (0.940) Remain 13:15:27 loss: 2.4619 psnr: 16.0621 Lr: 1.93373e-03
[2025-02-17 13:36:14,082 INFO hook.py line 109 848561] Train: [17/100][100/605] Data 0.003 (0.002) Batch 0.958 (0.941) Remain 13:15:23 loss: 2.4400 psnr: 16.5370 Lr: 1.93274e-03
[2025-02-17 13:37:01,133 INFO hook.py line 109 848561] Train: [17/100][150/605] Data 0.003 (0.002) Batch 0.912 (0.941) Remain 13:14:38 loss: 2.5057 psnr: 16.3002 Lr: 1.93176e-03
[2025-02-17 13:37:48,052 INFO hook.py line 109 848561] Train: [17/100][200/605] Data 0.003 (0.002) Batch 0.960 (0.940) Remain 13:13:17 loss: 2.4487 psnr: 17.1138 Lr: 1.93076e-03
[2025-02-17 13:38:35,015 INFO hook.py line 109 848561] Train: [17/100][250/605] Data 0.003 (0.002) Batch 0.960 (0.940) Remain 13:12:20 loss: 2.4229 psnr: 16.8635 Lr: 1.92976e-03
[2025-02-17 13:39:21,857 INFO hook.py line 109 848561] Train: [17/100][300/605] Data 0.003 (0.002) Batch 0.935 (0.940) Remain 13:11:05 loss: 2.3208 psnr: 17.4372 Lr: 1.92875e-03
[2025-02-17 13:40:09,098 INFO hook.py line 109 848561] Train: [17/100][350/605] Data 0.003 (0.002) Batch 0.929 (0.940) Remain 13:10:56 loss: 2.4444 psnr: 16.6706 Lr: 1.92773e-03
[2025-02-17 13:40:55,925 INFO hook.py line 109 848561] Train: [17/100][400/605] Data 0.003 (0.002) Batch 0.977 (0.940) Remain 13:09:46 loss: 2.5310 psnr: 16.4193 Lr: 1.92671e-03
[2025-02-17 13:41:43,261 INFO hook.py line 109 848561] Train: [17/100][450/605] Data 0.003 (0.002) Batch 0.927 (0.941) Remain 13:09:37 loss: 2.5331 psnr: 16.0991 Lr: 1.92568e-03
[2025-02-17 13:42:30,268 INFO hook.py line 109 848561] Train: [17/100][500/605] Data 0.003 (0.002) Batch 0.965 (0.941) Remain 13:08:48 loss: 2.3888 psnr: 17.5485 Lr: 1.92464e-03
[2025-02-17 13:43:17,395 INFO hook.py line 109 848561] Train: [17/100][550/605] Data 0.001 (0.002) Batch 0.929 (0.941) Remain 13:08:10 loss: 2.2424 psnr: 18.3600 Lr: 1.92360e-03
[2025-02-17 13:44:03,961 INFO hook.py line 109 848561] Train: [17/100][600/605] Data 0.002 (0.002) Batch 0.844 (0.940) Remain 13:06:43 loss: 2.4467 psnr: 17.6100 Lr: 1.92256e-03
[2025-02-17 13:44:08,245 INFO misc.py line 135 848561] Train result: loss: 2.4465 rgb_loss: 0.8980 psnr: 17.0193 depth_loss: 0.0741 feat_loss: 1.4744 
[2025-02-17 13:44:08,246 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 13:44:59,023 INFO hook.py line 109 848561] Train: [18/100][50/605] Data 0.002 (0.002) Batch 0.919 (0.934) Remain 13:01:05 loss: 2.5458 psnr: 16.5004 Lr: 1.92140e-03
[2025-02-17 13:45:45,986 INFO hook.py line 109 848561] Train: [18/100][100/605] Data 0.002 (0.002) Batch 0.951 (0.937) Remain 13:02:28 loss: 2.6424 psnr: 15.2083 Lr: 1.92034e-03
[2025-02-17 13:46:33,039 INFO hook.py line 109 848561] Train: [18/100][150/605] Data 0.003 (0.003) Batch 0.955 (0.938) Remain 13:02:53 loss: 2.7005 psnr: 15.6546 Lr: 1.91926e-03
[2025-02-17 13:47:19,978 INFO hook.py line 109 848561] Train: [18/100][200/605] Data 0.003 (0.002) Batch 0.926 (0.938) Remain 13:02:13 loss: 2.3244 psnr: 17.9311 Lr: 1.91818e-03
[2025-02-17 13:48:07,071 INFO hook.py line 109 848561] Train: [18/100][250/605] Data 0.003 (0.002) Batch 0.974 (0.939) Remain 13:02:01 loss: 2.6224 psnr: 15.7139 Lr: 1.91710e-03
[2025-02-17 13:48:54,185 INFO hook.py line 109 848561] Train: [18/100][300/605] Data 0.003 (0.002) Batch 0.939 (0.940) Remain 13:01:41 loss: 2.4151 psnr: 16.7115 Lr: 1.91600e-03
[2025-02-17 13:49:41,270 INFO hook.py line 109 848561] Train: [18/100][350/605] Data 0.003 (0.002) Batch 0.937 (0.940) Remain 13:01:09 loss: 2.5536 psnr: 16.2931 Lr: 1.91490e-03
[2025-02-17 13:50:28,231 INFO hook.py line 109 848561] Train: [18/100][400/605] Data 0.003 (0.002) Batch 0.956 (0.940) Remain 13:00:17 loss: 2.3887 psnr: 17.2228 Lr: 1.91380e-03
[2025-02-17 13:51:15,264 INFO hook.py line 109 848561] Train: [18/100][450/605] Data 0.003 (0.002) Batch 0.938 (0.940) Remain 12:59:35 loss: 2.7330 psnr: 15.3083 Lr: 1.91268e-03
[2025-02-17 13:52:02,330 INFO hook.py line 109 848561] Train: [18/100][500/605] Data 0.002 (0.002) Batch 0.973 (0.940) Remain 12:58:55 loss: 2.3451 psnr: 17.8279 Lr: 1.91156e-03
[2025-02-17 13:52:49,303 INFO hook.py line 109 848561] Train: [18/100][550/605] Data 0.003 (0.002) Batch 0.988 (0.940) Remain 12:58:05 loss: 2.5587 psnr: 15.8392 Lr: 1.91044e-03
[2025-02-17 13:53:35,435 INFO hook.py line 109 848561] Train: [18/100][600/605] Data 0.002 (0.002) Batch 0.869 (0.939) Remain 12:56:06 loss: 2.3111 psnr: 17.3921 Lr: 1.90930e-03
[2025-02-17 13:53:39,802 INFO misc.py line 135 848561] Train result: loss: 2.4470 rgb_loss: 0.9011 psnr: 17.0091 depth_loss: 0.0725 feat_loss: 1.4734 
[2025-02-17 13:53:39,803 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 13:54:31,079 INFO hook.py line 109 848561] Train: [19/100][50/605] Data 0.002 (0.002) Batch 0.945 (0.944) Remain 12:59:58 loss: 2.3407 psnr: 18.4534 Lr: 1.90805e-03
[2025-02-17 13:55:18,303 INFO hook.py line 109 848561] Train: [19/100][100/605] Data 0.003 (0.002) Batch 0.959 (0.944) Remain 12:59:16 loss: 2.2511 psnr: 18.9827 Lr: 1.90690e-03
[2025-02-17 13:56:05,130 INFO hook.py line 109 848561] Train: [19/100][150/605] Data 0.002 (0.002) Batch 0.950 (0.942) Remain 12:56:17 loss: 2.4983 psnr: 17.1476 Lr: 1.90575e-03
[2025-02-17 13:56:51,996 INFO hook.py line 109 848561] Train: [19/100][200/605] Data 0.002 (0.002) Batch 0.937 (0.941) Remain 12:54:34 loss: 2.5079 psnr: 15.9583 Lr: 1.90458e-03
[2025-02-17 13:57:38,377 INFO hook.py line 109 848561] Train: [19/100][250/605] Data 0.002 (0.002) Batch 0.923 (0.938) Remain 12:51:38 loss: 2.2826 psnr: 18.6189 Lr: 1.90342e-03
[2025-02-17 13:58:25,409 INFO hook.py line 109 848561] Train: [19/100][300/605] Data 0.003 (0.002) Batch 0.957 (0.938) Remain 12:51:13 loss: 2.3456 psnr: 17.7765 Lr: 1.90224e-03
[2025-02-17 13:59:12,126 INFO hook.py line 109 848561] Train: [19/100][350/605] Data 0.003 (0.002) Batch 0.932 (0.938) Remain 12:49:57 loss: 2.2187 psnr: 18.2736 Lr: 1.90106e-03
[2025-02-17 13:59:59,157 INFO hook.py line 109 848561] Train: [19/100][400/605] Data 0.003 (0.002) Batch 0.964 (0.938) Remain 12:49:28 loss: 2.3736 psnr: 17.8518 Lr: 1.89987e-03
[2025-02-17 14:00:45,943 INFO hook.py line 109 848561] Train: [19/100][450/605] Data 0.002 (0.002) Batch 0.946 (0.938) Remain 12:48:27 loss: 2.1428 psnr: 20.0223 Lr: 1.89867e-03
[2025-02-17 14:01:33,001 INFO hook.py line 109 848561] Train: [19/100][500/605] Data 0.002 (0.002) Batch 1.014 (0.938) Remain 12:47:56 loss: 2.4413 psnr: 16.3953 Lr: 1.89747e-03
[2025-02-17 14:02:19,988 INFO hook.py line 109 848561] Train: [19/100][550/605] Data 0.002 (0.002) Batch 0.933 (0.938) Remain 12:47:16 loss: 2.6764 psnr: 15.3355 Lr: 1.89626e-03
[2025-02-17 14:03:06,005 INFO hook.py line 109 848561] Train: [19/100][600/605] Data 0.002 (0.002) Batch 0.865 (0.937) Remain 12:45:15 loss: 2.1704 psnr: 19.1579 Lr: 1.89505e-03
[2025-02-17 14:03:10,318 INFO misc.py line 135 848561] Train result: loss: 2.4296 rgb_loss: 0.8869 psnr: 17.1396 depth_loss: 0.0720 feat_loss: 1.4706 
[2025-02-17 14:03:10,318 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 14:04:01,678 INFO hook.py line 109 848561] Train: [20/100][50/605] Data 0.002 (0.002) Batch 0.928 (0.947) Remain 12:52:19 loss: 2.7122 psnr: 15.3661 Lr: 1.89370e-03
[2025-02-17 14:04:48,426 INFO hook.py line 109 848561] Train: [20/100][100/605] Data 0.002 (0.002) Batch 0.947 (0.941) Remain 12:46:39 loss: 2.6220 psnr: 16.1121 Lr: 1.89247e-03
[2025-02-17 14:05:35,045 INFO hook.py line 109 848561] Train: [20/100][150/605] Data 0.002 (0.002) Batch 0.932 (0.938) Remain 12:43:35 loss: 2.4383 psnr: 16.8803 Lr: 1.89124e-03
[2025-02-17 14:06:22,115 INFO hook.py line 109 848561] Train: [20/100][200/605] Data 0.004 (0.002) Batch 0.920 (0.939) Remain 12:43:33 loss: 2.3973 psnr: 17.8099 Lr: 1.88999e-03
[2025-02-17 14:07:09,278 INFO hook.py line 109 848561] Train: [20/100][250/605] Data 0.002 (0.002) Batch 0.925 (0.940) Remain 12:43:31 loss: 2.4993 psnr: 16.4911 Lr: 1.88874e-03
[2025-02-17 14:07:56,027 INFO hook.py line 109 848561] Train: [20/100][300/605] Data 0.003 (0.002) Batch 0.965 (0.939) Remain 12:42:06 loss: 2.3429 psnr: 17.5731 Lr: 1.88749e-03
[2025-02-17 14:08:43,038 INFO hook.py line 109 848561] Train: [20/100][350/605] Data 0.003 (0.002) Batch 0.956 (0.939) Remain 12:41:29 loss: 2.3452 psnr: 17.7214 Lr: 1.88623e-03
[2025-02-17 14:09:29,717 INFO hook.py line 109 848561] Train: [20/100][400/605] Data 0.003 (0.002) Batch 0.939 (0.938) Remain 12:40:08 loss: 2.5235 psnr: 16.4468 Lr: 1.88496e-03
[2025-02-17 14:10:16,647 INFO hook.py line 109 848561] Train: [20/100][450/605] Data 0.003 (0.002) Batch 0.925 (0.938) Remain 12:39:23 loss: 2.5310 psnr: 15.8698 Lr: 1.88368e-03
[2025-02-17 14:11:03,585 INFO hook.py line 109 848561] Train: [20/100][500/605] Data 0.003 (0.002) Batch 0.925 (0.938) Remain 12:38:38 loss: 2.7077 psnr: 15.1815 Lr: 1.88240e-03
[2025-02-17 14:11:50,508 INFO hook.py line 109 848561] Train: [20/100][550/605] Data 0.003 (0.002) Batch 0.950 (0.938) Remain 12:37:51 loss: 2.6817 psnr: 15.7377 Lr: 1.88111e-03
[2025-02-17 14:12:36,562 INFO hook.py line 109 848561] Train: [20/100][600/605] Data 0.002 (0.002) Batch 0.861 (0.937) Remain 12:35:54 loss: 2.2347 psnr: 18.6200 Lr: 1.87981e-03
[2025-02-17 14:12:40,883 INFO misc.py line 135 848561] Train result: loss: 2.4246 rgb_loss: 0.8848 psnr: 17.1327 depth_loss: 0.0714 feat_loss: 1.4684 
[2025-02-17 14:12:40,883 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 14:13:31,916 INFO hook.py line 109 848561] Train: [21/100][50/605] Data 0.001 (0.002) Batch 0.955 (0.939) Remain 12:36:31 loss: 2.4850 psnr: 17.0789 Lr: 1.87838e-03
[2025-02-17 14:14:18,834 INFO hook.py line 109 848561] Train: [21/100][100/605] Data 0.003 (0.002) Batch 0.964 (0.939) Remain 12:35:36 loss: 2.3326 psnr: 17.9041 Lr: 1.87707e-03
[2025-02-17 14:15:05,453 INFO hook.py line 109 848561] Train: [21/100][150/605] Data 0.002 (0.002) Batch 0.906 (0.937) Remain 12:33:06 loss: 2.1220 psnr: 19.6761 Lr: 1.87575e-03
[2025-02-17 14:15:52,334 INFO hook.py line 109 848561] Train: [21/100][200/605] Data 0.003 (0.002) Batch 0.964 (0.937) Remain 12:32:33 loss: 2.2796 psnr: 17.8455 Lr: 1.87443e-03
[2025-02-17 14:16:39,397 INFO hook.py line 109 848561] Train: [21/100][250/605] Data 0.002 (0.002) Batch 0.952 (0.938) Remain 12:32:29 loss: 2.2405 psnr: 18.0905 Lr: 1.87310e-03
[2025-02-17 14:17:25,986 INFO hook.py line 109 848561] Train: [21/100][300/605] Data 0.003 (0.002) Batch 0.927 (0.937) Remain 12:30:55 loss: 2.3041 psnr: 17.5174 Lr: 1.87177e-03
[2025-02-17 14:18:13,013 INFO hook.py line 109 848561] Train: [21/100][350/605] Data 0.002 (0.002) Batch 0.965 (0.937) Remain 12:30:34 loss: 2.4499 psnr: 17.0450 Lr: 1.87042e-03
[2025-02-17 14:18:59,856 INFO hook.py line 109 848561] Train: [21/100][400/605] Data 0.002 (0.002) Batch 0.957 (0.937) Remain 12:29:45 loss: 2.3746 psnr: 17.8069 Lr: 1.86908e-03
[2025-02-17 14:19:46,633 INFO hook.py line 109 848561] Train: [21/100][450/605] Data 0.003 (0.002) Batch 0.954 (0.937) Remain 12:28:49 loss: 2.5168 psnr: 16.2085 Lr: 1.86772e-03
[2025-02-17 14:20:33,579 INFO hook.py line 109 848561] Train: [21/100][500/605] Data 0.003 (0.002) Batch 0.941 (0.937) Remain 12:28:12 loss: 2.4580 psnr: 16.6628 Lr: 1.86636e-03
[2025-02-17 14:21:20,327 INFO hook.py line 109 848561] Train: [21/100][550/605] Data 0.002 (0.002) Batch 0.938 (0.937) Remain 12:27:15 loss: 2.3148 psnr: 18.2399 Lr: 1.86499e-03
[2025-02-17 14:22:06,519 INFO hook.py line 109 848561] Train: [21/100][600/605] Data 0.003 (0.002) Batch 0.867 (0.936) Remain 12:25:35 loss: 2.3681 psnr: 17.0436 Lr: 1.86362e-03
[2025-02-17 14:22:10,839 INFO misc.py line 135 848561] Train result: loss: 2.4155 rgb_loss: 0.8782 psnr: 17.1792 depth_loss: 0.0709 feat_loss: 1.4664 
[2025-02-17 14:22:10,841 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 14:23:01,897 INFO hook.py line 109 848561] Train: [22/100][50/605] Data 0.003 (0.002) Batch 0.945 (0.939) Remain 12:27:20 loss: 2.3151 psnr: 18.3041 Lr: 1.86210e-03
[2025-02-17 14:23:49,245 INFO hook.py line 109 848561] Train: [22/100][100/605] Data 0.002 (0.002) Batch 0.952 (0.943) Remain 12:29:45 loss: 2.3500 psnr: 17.6814 Lr: 1.86071e-03
[2025-02-17 14:24:36,054 INFO hook.py line 109 848561] Train: [22/100][150/605] Data 0.002 (0.002) Batch 0.918 (0.941) Remain 12:27:04 loss: 2.2559 psnr: 18.3813 Lr: 1.85931e-03
[2025-02-17 14:25:23,010 INFO hook.py line 109 848561] Train: [22/100][200/605] Data 0.003 (0.002) Batch 0.942 (0.940) Remain 12:25:56 loss: 2.4508 psnr: 16.8319 Lr: 1.85791e-03
[2025-02-17 14:26:09,560 INFO hook.py line 109 848561] Train: [22/100][250/605] Data 0.002 (0.002) Batch 0.918 (0.938) Remain 12:23:39 loss: 2.1136 psnr: 19.8183 Lr: 1.85651e-03
[2025-02-17 14:26:56,133 INFO hook.py line 109 848561] Train: [22/100][300/605] Data 0.002 (0.002) Batch 0.914 (0.937) Remain 12:21:56 loss: 2.4901 psnr: 16.2721 Lr: 1.85509e-03
[2025-02-17 14:27:42,793 INFO hook.py line 109 848561] Train: [22/100][350/605] Data 0.002 (0.002) Batch 0.953 (0.937) Remain 12:20:41 loss: 2.5284 psnr: 16.2705 Lr: 1.85367e-03
[2025-02-17 14:28:29,693 INFO hook.py line 109 848561] Train: [22/100][400/605] Data 0.002 (0.002) Batch 0.929 (0.937) Remain 12:20:02 loss: 2.4824 psnr: 16.7113 Lr: 1.85225e-03
[2025-02-17 14:29:16,383 INFO hook.py line 109 848561] Train: [22/100][450/605] Data 0.004 (0.002) Batch 0.933 (0.937) Remain 12:18:59 loss: 2.1822 psnr: 19.4739 Lr: 1.85081e-03
[2025-02-17 14:30:03,334 INFO hook.py line 109 848561] Train: [22/100][500/605] Data 0.003 (0.002) Batch 0.926 (0.937) Remain 12:18:24 loss: 2.3335 psnr: 18.2026 Lr: 1.84937e-03
[2025-02-17 14:30:50,367 INFO hook.py line 109 848561] Train: [22/100][550/605] Data 0.003 (0.002) Batch 0.958 (0.937) Remain 12:17:54 loss: 2.5832 psnr: 15.6711 Lr: 1.84793e-03
[2025-02-17 14:31:36,615 INFO hook.py line 109 848561] Train: [22/100][600/605] Data 0.002 (0.002) Batch 0.871 (0.936) Remain 12:16:19 loss: 2.3720 psnr: 17.1894 Lr: 1.84648e-03
[2025-02-17 14:31:40,956 INFO misc.py line 135 848561] Train result: loss: 2.4201 rgb_loss: 0.8829 psnr: 17.1385 depth_loss: 0.0715 feat_loss: 1.4657 
[2025-02-17 14:31:40,957 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 14:32:31,809 INFO hook.py line 109 848561] Train: [23/100][50/605] Data 0.003 (0.002) Batch 0.960 (0.934) Remain 12:14:07 loss: 2.4599 psnr: 16.6561 Lr: 1.84487e-03
[2025-02-17 14:33:18,915 INFO hook.py line 109 848561] Train: [23/100][100/605] Data 0.002 (0.003) Batch 0.907 (0.938) Remain 12:16:28 loss: 2.2358 psnr: 18.8328 Lr: 1.84341e-03
[2025-02-17 14:34:06,191 INFO hook.py line 109 848561] Train: [23/100][150/605] Data 0.002 (0.003) Batch 0.932 (0.941) Remain 12:17:35 loss: 2.3956 psnr: 17.4858 Lr: 1.84193e-03
[2025-02-17 14:34:53,022 INFO hook.py line 109 848561] Train: [23/100][200/605] Data 0.002 (0.002) Batch 0.916 (0.940) Remain 12:15:58 loss: 2.1861 psnr: 18.7844 Lr: 1.84046e-03
[2025-02-17 14:35:40,195 INFO hook.py line 109 848561] Train: [23/100][250/605] Data 0.002 (0.002) Batch 0.933 (0.940) Remain 12:15:46 loss: 2.5248 psnr: 16.3156 Lr: 1.83897e-03
[2025-02-17 14:36:26,663 INFO hook.py line 109 848561] Train: [23/100][300/605] Data 0.002 (0.002) Batch 0.993 (0.939) Remain 12:13:32 loss: 2.2740 psnr: 18.3970 Lr: 1.83748e-03
[2025-02-17 14:37:13,396 INFO hook.py line 109 848561] Train: [23/100][350/605] Data 0.002 (0.002) Batch 0.947 (0.938) Remain 12:12:18 loss: 2.0600 psnr: 20.5261 Lr: 1.83599e-03
[2025-02-17 14:38:00,337 INFO hook.py line 109 848561] Train: [23/100][400/605] Data 0.003 (0.002) Batch 0.912 (0.938) Remain 12:11:35 loss: 2.3817 psnr: 17.3407 Lr: 1.83448e-03
[2025-02-17 14:38:46,901 INFO hook.py line 109 848561] Train: [23/100][450/605] Data 0.002 (0.002) Batch 0.934 (0.937) Remain 12:10:13 loss: 2.3754 psnr: 17.4385 Lr: 1.83297e-03
[2025-02-17 14:39:34,048 INFO hook.py line 109 848561] Train: [23/100][500/605] Data 0.005 (0.002) Batch 0.930 (0.938) Remain 12:09:52 loss: 2.6986 psnr: 15.3922 Lr: 1.83146e-03
[2025-02-17 14:40:20,857 INFO hook.py line 109 848561] Train: [23/100][550/605] Data 0.005 (0.002) Batch 0.911 (0.938) Remain 12:08:57 loss: 2.3906 psnr: 16.6024 Lr: 1.82994e-03
[2025-02-17 14:41:06,984 INFO hook.py line 109 848561] Train: [23/100][600/605] Data 0.002 (0.002) Batch 0.874 (0.937) Remain 12:07:11 loss: 2.1642 psnr: 18.0647 Lr: 1.82841e-03
[2025-02-17 14:41:11,311 INFO misc.py line 135 848561] Train result: loss: 2.4015 rgb_loss: 0.8695 psnr: 17.2430 depth_loss: 0.0713 feat_loss: 1.4606 
[2025-02-17 14:41:11,312 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 14:42:02,034 INFO hook.py line 109 848561] Train: [24/100][50/605] Data 0.002 (0.002) Batch 0.951 (0.933) Remain 12:03:52 loss: 2.5083 psnr: 16.4349 Lr: 1.82672e-03
[2025-02-17 14:42:49,003 INFO hook.py line 109 848561] Train: [24/100][100/605] Data 0.002 (0.002) Batch 0.980 (0.936) Remain 12:05:31 loss: 2.2584 psnr: 17.4709 Lr: 1.82518e-03
[2025-02-17 14:43:36,213 INFO hook.py line 109 848561] Train: [24/100][150/605] Data 0.003 (0.002) Batch 0.908 (0.939) Remain 12:06:46 loss: 2.2362 psnr: 18.4977 Lr: 1.82363e-03
[2025-02-17 14:44:23,418 INFO hook.py line 109 848561] Train: [24/100][200/605] Data 0.003 (0.002) Batch 0.934 (0.940) Remain 12:06:58 loss: 2.3874 psnr: 17.1172 Lr: 1.82208e-03
[2025-02-17 14:45:10,354 INFO hook.py line 109 848561] Train: [24/100][250/605] Data 0.001 (0.002) Batch 0.948 (0.940) Remain 12:05:55 loss: 2.2216 psnr: 19.3344 Lr: 1.82052e-03
[2025-02-17 14:45:57,093 INFO hook.py line 109 848561] Train: [24/100][300/605] Data 0.004 (0.002) Batch 0.939 (0.939) Remain 12:04:28 loss: 2.4775 psnr: 15.5767 Lr: 1.81896e-03
[2025-02-17 14:46:44,087 INFO hook.py line 109 848561] Train: [24/100][350/605] Data 0.002 (0.002) Batch 0.937 (0.939) Remain 12:03:46 loss: 2.5564 psnr: 16.3253 Lr: 1.81738e-03
[2025-02-17 14:47:31,030 INFO hook.py line 109 848561] Train: [24/100][400/605] Data 0.003 (0.002) Batch 0.942 (0.939) Remain 12:02:56 loss: 2.3733 psnr: 17.8769 Lr: 1.81581e-03
[2025-02-17 14:48:17,917 INFO hook.py line 109 848561] Train: [24/100][450/605] Data 0.002 (0.002) Batch 0.951 (0.939) Remain 12:02:02 loss: 2.6411 psnr: 16.1954 Lr: 1.81422e-03
[2025-02-17 14:49:04,919 INFO hook.py line 109 848561] Train: [24/100][500/605] Data 0.004 (0.002) Batch 0.949 (0.939) Remain 12:01:20 loss: 2.5536 psnr: 15.9821 Lr: 1.81263e-03
[2025-02-17 14:49:51,586 INFO hook.py line 109 848561] Train: [24/100][550/605] Data 0.002 (0.002) Batch 0.918 (0.939) Remain 12:00:08 loss: 2.4686 psnr: 16.6354 Lr: 1.81104e-03
[2025-02-17 14:50:37,562 INFO hook.py line 109 848561] Train: [24/100][600/605] Data 0.002 (0.002) Batch 0.860 (0.937) Remain 11:58:08 loss: 2.6580 psnr: 15.4004 Lr: 1.80944e-03
[2025-02-17 14:50:41,901 INFO misc.py line 135 848561] Train result: loss: 2.4009 rgb_loss: 0.8708 psnr: 17.2601 depth_loss: 0.0707 feat_loss: 1.4595 
[2025-02-17 14:50:41,901 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 14:51:32,747 INFO hook.py line 109 848561] Train: [25/100][50/605] Data 0.002 (0.003) Batch 0.939 (0.933) Remain 11:54:21 loss: 2.4440 psnr: 16.8469 Lr: 1.80770e-03
[2025-02-17 14:52:19,753 INFO hook.py line 109 848561] Train: [25/100][100/605] Data 0.002 (0.002) Batch 0.935 (0.937) Remain 11:56:18 loss: 2.4764 psnr: 16.7725 Lr: 1.80609e-03
[2025-02-17 14:53:06,669 INFO hook.py line 109 848561] Train: [25/100][150/605] Data 0.002 (0.002) Batch 0.925 (0.937) Remain 11:55:56 loss: 2.3140 psnr: 17.3684 Lr: 1.80446e-03
[2025-02-17 14:53:54,036 INFO hook.py line 109 848561] Train: [25/100][200/605] Data 0.002 (0.002) Batch 0.910 (0.940) Remain 11:57:06 loss: 2.6964 psnr: 15.1023 Lr: 1.80284e-03
[2025-02-17 14:54:40,860 INFO hook.py line 109 848561] Train: [25/100][250/605] Data 0.002 (0.002) Batch 0.915 (0.939) Remain 11:55:47 loss: 2.3610 psnr: 17.3097 Lr: 1.80121e-03
[2025-02-17 14:55:27,736 INFO hook.py line 109 848561] Train: [25/100][300/605] Data 0.002 (0.002) Batch 0.929 (0.939) Remain 11:54:48 loss: 2.3246 psnr: 18.6509 Lr: 1.79957e-03
[2025-02-17 14:56:14,562 INFO hook.py line 109 848561] Train: [25/100][350/605] Data 0.003 (0.002) Batch 0.908 (0.939) Remain 11:53:45 loss: 2.3371 psnr: 17.5337 Lr: 1.79792e-03
[2025-02-17 14:57:01,385 INFO hook.py line 109 848561] Train: [25/100][400/605] Data 0.001 (0.002) Batch 0.916 (0.938) Remain 11:52:46 loss: 2.1290 psnr: 19.2497 Lr: 1.79627e-03
[2025-02-17 14:57:48,416 INFO hook.py line 109 848561] Train: [25/100][450/605] Data 0.002 (0.002) Batch 0.937 (0.939) Remain 11:52:11 loss: 2.3844 psnr: 17.0176 Lr: 1.79462e-03
[2025-02-17 14:58:35,200 INFO hook.py line 109 848561] Train: [25/100][500/605] Data 0.003 (0.002) Batch 0.951 (0.938) Remain 11:51:11 loss: 2.3497 psnr: 18.1763 Lr: 1.79295e-03
[2025-02-17 14:59:22,091 INFO hook.py line 109 848561] Train: [25/100][550/605] Data 0.002 (0.002) Batch 0.952 (0.938) Remain 11:50:23 loss: 2.6094 psnr: 15.4402 Lr: 1.79129e-03
[2025-02-17 15:00:07,969 INFO hook.py line 109 848561] Train: [25/100][600/605] Data 0.002 (0.002) Batch 0.859 (0.936) Remain 11:48:17 loss: 2.2924 psnr: 18.3075 Lr: 1.78961e-03
[2025-02-17 15:00:12,284 INFO misc.py line 135 848561] Train result: loss: 2.3874 rgb_loss: 0.8595 psnr: 17.3410 depth_loss: 0.0715 feat_loss: 1.4565 
[2025-02-17 15:00:12,286 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:01:03,182 INFO hook.py line 109 848561] Train: [26/100][50/605] Data 0.002 (0.002) Batch 0.942 (0.936) Remain 11:46:41 loss: 2.4879 psnr: 16.2748 Lr: 1.78776e-03
[2025-02-17 15:01:49,942 INFO hook.py line 109 848561] Train: [26/100][100/605] Data 0.002 (0.002) Batch 0.927 (0.935) Remain 11:45:47 loss: 2.2208 psnr: 18.5301 Lr: 1.78608e-03
[2025-02-17 15:02:36,800 INFO hook.py line 109 848561] Train: [26/100][150/605] Data 0.002 (0.002) Batch 0.955 (0.936) Remain 11:45:29 loss: 2.3859 psnr: 17.8578 Lr: 1.78439e-03
[2025-02-17 15:03:24,241 INFO hook.py line 109 848561] Train: [26/100][200/605] Data 0.002 (0.002) Batch 0.949 (0.939) Remain 11:47:09 loss: 2.4955 psnr: 16.9008 Lr: 1.78269e-03
[2025-02-17 15:04:10,853 INFO hook.py line 109 848561] Train: [26/100][250/605] Data 0.003 (0.002) Batch 0.924 (0.938) Remain 11:45:18 loss: 2.3683 psnr: 17.0837 Lr: 1.78098e-03
[2025-02-17 15:04:57,660 INFO hook.py line 109 848561] Train: [26/100][300/605] Data 0.003 (0.002) Batch 0.928 (0.938) Remain 11:44:19 loss: 2.3228 psnr: 18.9343 Lr: 1.77927e-03
[2025-02-17 15:05:44,270 INFO hook.py line 109 848561] Train: [26/100][350/605] Data 0.002 (0.002) Batch 0.949 (0.937) Remain 11:42:57 loss: 2.3149 psnr: 17.8220 Lr: 1.77756e-03
[2025-02-17 15:06:30,938 INFO hook.py line 109 848561] Train: [26/100][400/605] Data 0.002 (0.002) Batch 0.965 (0.936) Remain 11:41:51 loss: 2.0905 psnr: 20.9785 Lr: 1.77584e-03
[2025-02-17 15:07:17,646 INFO hook.py line 109 848561] Train: [26/100][450/605] Data 0.002 (0.002) Batch 0.927 (0.936) Remain 11:40:53 loss: 2.6775 psnr: 15.9745 Lr: 1.77411e-03
[2025-02-17 15:08:04,233 INFO hook.py line 109 848561] Train: [26/100][500/605] Data 0.004 (0.002) Batch 0.917 (0.936) Remain 11:39:47 loss: 2.3423 psnr: 18.1566 Lr: 1.77238e-03
[2025-02-17 15:08:51,122 INFO hook.py line 109 848561] Train: [26/100][550/605] Data 0.002 (0.002) Batch 0.941 (0.936) Remain 11:39:09 loss: 2.3884 psnr: 16.7118 Lr: 1.77064e-03
[2025-02-17 15:09:37,205 INFO hook.py line 109 848561] Train: [26/100][600/605] Data 0.002 (0.002) Batch 0.845 (0.935) Remain 11:37:29 loss: 2.2451 psnr: 19.1651 Lr: 1.76889e-03
[2025-02-17 15:09:41,510 INFO misc.py line 135 848561] Train result: loss: 2.3958 rgb_loss: 0.8698 psnr: 17.2328 depth_loss: 0.0711 feat_loss: 1.4549 
[2025-02-17 15:09:41,510 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:10:32,234 INFO hook.py line 109 848561] Train: [27/100][50/605] Data 0.003 (0.002) Batch 0.951 (0.938) Remain 11:38:53 loss: 2.6427 psnr: 16.2158 Lr: 1.76697e-03
[2025-02-17 15:11:18,993 INFO hook.py line 109 848561] Train: [27/100][100/605] Data 0.002 (0.002) Batch 0.939 (0.936) Remain 11:37:08 loss: 2.3091 psnr: 17.9911 Lr: 1.76521e-03
[2025-02-17 15:12:05,852 INFO hook.py line 109 848561] Train: [27/100][150/605] Data 0.003 (0.002) Batch 0.953 (0.937) Remain 11:36:33 loss: 2.4271 psnr: 17.1971 Lr: 1.76345e-03
[2025-02-17 15:12:52,465 INFO hook.py line 109 848561] Train: [27/100][200/605] Data 0.003 (0.002) Batch 0.928 (0.936) Remain 11:34:57 loss: 2.2019 psnr: 18.8957 Lr: 1.76168e-03
[2025-02-17 15:13:39,552 INFO hook.py line 109 848561] Train: [27/100][250/605] Data 0.002 (0.002) Batch 0.965 (0.937) Remain 11:35:06 loss: 2.4370 psnr: 16.2867 Lr: 1.75991e-03
[2025-02-17 15:14:26,384 INFO hook.py line 109 848561] Train: [27/100][300/605] Data 0.002 (0.002) Batch 0.911 (0.937) Remain 11:34:18 loss: 2.4761 psnr: 16.3930 Lr: 1.75813e-03
[2025-02-17 15:15:13,238 INFO hook.py line 109 848561] Train: [27/100][350/605] Data 0.002 (0.002) Batch 0.927 (0.937) Remain 11:33:33 loss: 2.4821 psnr: 16.1419 Lr: 1.75634e-03
[2025-02-17 15:16:00,196 INFO hook.py line 109 848561] Train: [27/100][400/605] Data 0.003 (0.002) Batch 0.934 (0.937) Remain 11:32:59 loss: 2.2636 psnr: 18.2357 Lr: 1.75455e-03
[2025-02-17 15:16:47,077 INFO hook.py line 109 848561] Train: [27/100][450/605] Data 0.003 (0.002) Batch 0.959 (0.937) Remain 11:32:15 loss: 2.3724 psnr: 17.6828 Lr: 1.75276e-03
[2025-02-17 15:17:33,859 INFO hook.py line 109 848561] Train: [27/100][500/605] Data 0.002 (0.002) Batch 0.903 (0.937) Remain 11:31:21 loss: 2.6219 psnr: 14.9765 Lr: 1.75095e-03
[2025-02-17 15:18:20,448 INFO hook.py line 109 848561] Train: [27/100][550/605] Data 0.003 (0.002) Batch 0.907 (0.937) Remain 11:30:13 loss: 2.4501 psnr: 16.6345 Lr: 1.74915e-03
[2025-02-17 15:19:06,291 INFO hook.py line 109 848561] Train: [27/100][600/605] Data 0.001 (0.002) Batch 0.864 (0.935) Remain 11:28:13 loss: 2.3085 psnr: 18.1112 Lr: 1.74733e-03
[2025-02-17 15:19:10,570 INFO misc.py line 135 848561] Train result: loss: 2.3871 rgb_loss: 0.8603 psnr: 17.3290 depth_loss: 0.0704 feat_loss: 1.4564 
[2025-02-17 15:19:10,571 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:20:01,147 INFO hook.py line 109 848561] Train: [28/100][50/605] Data 0.003 (0.002) Batch 0.976 (0.931) Remain 11:24:23 loss: 2.4335 psnr: 16.8374 Lr: 1.74533e-03
[2025-02-17 15:20:47,903 INFO hook.py line 109 848561] Train: [28/100][100/605] Data 0.002 (0.002) Batch 0.939 (0.933) Remain 11:25:14 loss: 2.4251 psnr: 17.3541 Lr: 1.74351e-03
[2025-02-17 15:21:34,518 INFO hook.py line 109 848561] Train: [28/100][150/605] Data 0.003 (0.002) Batch 0.942 (0.933) Remain 11:24:16 loss: 2.2454 psnr: 17.8082 Lr: 1.74168e-03
[2025-02-17 15:22:21,278 INFO hook.py line 109 848561] Train: [28/100][200/605] Data 0.003 (0.002) Batch 0.894 (0.933) Remain 11:23:56 loss: 2.4701 psnr: 16.7526 Lr: 1.73984e-03
[2025-02-17 15:23:08,157 INFO hook.py line 109 848561] Train: [28/100][250/605] Data 0.002 (0.002) Batch 1.022 (0.934) Remain 11:23:47 loss: 2.5180 psnr: 15.8346 Lr: 1.73800e-03
[2025-02-17 15:23:54,984 INFO hook.py line 109 848561] Train: [28/100][300/605] Data 0.003 (0.002) Batch 0.916 (0.935) Remain 11:23:17 loss: 2.5725 psnr: 15.7114 Lr: 1.73615e-03
[2025-02-17 15:24:41,989 INFO hook.py line 109 848561] Train: [28/100][350/605] Data 0.002 (0.002) Batch 0.947 (0.935) Remain 11:23:05 loss: 2.1005 psnr: 19.9507 Lr: 1.73430e-03
[2025-02-17 15:25:29,072 INFO hook.py line 109 848561] Train: [28/100][400/605] Data 0.003 (0.002) Batch 0.956 (0.936) Remain 11:22:52 loss: 2.3345 psnr: 17.6482 Lr: 1.73244e-03
[2025-02-17 15:26:15,867 INFO hook.py line 109 848561] Train: [28/100][450/605] Data 0.002 (0.002) Batch 0.943 (0.936) Remain 11:22:04 loss: 2.3755 psnr: 17.6599 Lr: 1.73058e-03
[2025-02-17 15:27:02,692 INFO hook.py line 109 848561] Train: [28/100][500/605] Data 0.003 (0.002) Batch 0.940 (0.936) Remain 11:21:19 loss: 2.4918 psnr: 15.8744 Lr: 1.72871e-03
[2025-02-17 15:27:49,627 INFO hook.py line 109 848561] Train: [28/100][550/605] Data 0.002 (0.002) Batch 0.921 (0.936) Remain 11:20:42 loss: 2.1496 psnr: 19.8845 Lr: 1.72687e-03
[2025-02-17 15:28:35,823 INFO hook.py line 109 848561] Train: [28/100][600/605] Data 0.002 (0.002) Batch 0.862 (0.935) Remain 11:19:09 loss: 2.6450 psnr: 15.4237 Lr: 1.72499e-03
[2025-02-17 15:28:40,162 INFO misc.py line 135 848561] Train result: loss: 2.3860 rgb_loss: 0.8627 psnr: 17.2999 depth_loss: 0.0695 feat_loss: 1.4538 
[2025-02-17 15:28:40,164 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:29:31,220 INFO hook.py line 109 848561] Train: [29/100][50/605] Data 0.003 (0.003) Batch 0.952 (0.939) Remain 11:21:04 loss: 2.3099 psnr: 17.8327 Lr: 1.72292e-03
[2025-02-17 15:30:18,044 INFO hook.py line 109 848561] Train: [29/100][100/605] Data 0.002 (0.002) Batch 0.960 (0.938) Remain 11:19:16 loss: 2.6121 psnr: 15.9275 Lr: 1.72103e-03
[2025-02-17 15:31:04,839 INFO hook.py line 109 848561] Train: [29/100][150/605] Data 0.003 (0.002) Batch 0.940 (0.937) Remain 11:18:01 loss: 2.3127 psnr: 18.5239 Lr: 1.71913e-03
[2025-02-17 15:31:51,777 INFO hook.py line 109 848561] Train: [29/100][200/605] Data 0.003 (0.002) Batch 0.913 (0.938) Remain 11:17:32 loss: 2.0637 psnr: 20.6068 Lr: 1.71723e-03
[2025-02-17 15:32:38,862 INFO hook.py line 109 848561] Train: [29/100][250/605] Data 0.002 (0.002) Batch 0.959 (0.938) Remain 11:17:21 loss: 2.3248 psnr: 17.7725 Lr: 1.71532e-03
[2025-02-17 15:33:25,857 INFO hook.py line 109 848561] Train: [29/100][300/605] Data 0.002 (0.002) Batch 0.954 (0.939) Remain 11:16:45 loss: 2.4256 psnr: 16.7715 Lr: 1.71341e-03
[2025-02-17 15:34:12,888 INFO hook.py line 109 848561] Train: [29/100][350/605] Data 0.002 (0.002) Batch 0.959 (0.939) Remain 11:16:11 loss: 2.7661 psnr: 14.9052 Lr: 1.71149e-03
[2025-02-17 15:34:59,904 INFO hook.py line 109 848561] Train: [29/100][400/605] Data 0.003 (0.002) Batch 0.967 (0.939) Remain 11:15:31 loss: 2.1972 psnr: 19.2603 Lr: 1.70957e-03
[2025-02-17 15:35:47,158 INFO hook.py line 109 848561] Train: [29/100][450/605] Data 0.003 (0.002) Batch 0.963 (0.940) Remain 11:15:13 loss: 2.6305 psnr: 15.6578 Lr: 1.70764e-03
[2025-02-17 15:36:33,950 INFO hook.py line 109 848561] Train: [29/100][500/605] Data 0.003 (0.002) Batch 0.955 (0.939) Remain 11:14:09 loss: 2.5817 psnr: 15.2326 Lr: 1.70571e-03
[2025-02-17 15:37:20,862 INFO hook.py line 109 848561] Train: [29/100][550/605] Data 0.002 (0.002) Batch 0.962 (0.939) Remain 11:13:18 loss: 2.6823 psnr: 15.5278 Lr: 1.70377e-03
[2025-02-17 15:38:06,830 INFO hook.py line 109 848561] Train: [29/100][600/605] Data 0.003 (0.002) Batch 0.874 (0.938) Remain 11:11:19 loss: 2.6014 psnr: 16.2565 Lr: 1.70182e-03
[2025-02-17 15:38:11,178 INFO misc.py line 135 848561] Train result: loss: 2.3729 rgb_loss: 0.8506 psnr: 17.4043 depth_loss: 0.0708 feat_loss: 1.4514 
[2025-02-17 15:38:11,179 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:39:02,140 INFO hook.py line 109 848561] Train: [30/100][50/605] Data 0.003 (0.002) Batch 0.902 (0.936) Remain 11:09:13 loss: 2.3853 psnr: 17.1932 Lr: 1.69968e-03
[2025-02-17 15:39:48,875 INFO hook.py line 109 848561] Train: [30/100][100/605] Data 0.002 (0.002) Batch 0.921 (0.935) Remain 11:08:00 loss: 2.4116 psnr: 16.7507 Lr: 1.69772e-03
[2025-02-17 15:40:35,590 INFO hook.py line 109 848561] Train: [30/100][150/605] Data 0.003 (0.002) Batch 0.917 (0.935) Remain 11:07:00 loss: 2.1927 psnr: 19.6992 Lr: 1.69576e-03
[2025-02-17 15:41:22,609 INFO hook.py line 109 848561] Train: [30/100][200/605] Data 0.002 (0.002) Batch 0.932 (0.936) Remain 11:07:12 loss: 2.3322 psnr: 17.5012 Lr: 1.69380e-03
[2025-02-17 15:42:08,982 INFO hook.py line 109 848561] Train: [30/100][250/605] Data 0.002 (0.002) Batch 0.927 (0.935) Remain 11:05:08 loss: 2.4565 psnr: 16.2643 Lr: 1.69183e-03
[2025-02-17 15:42:56,301 INFO hook.py line 109 848561] Train: [30/100][300/605] Data 0.003 (0.002) Batch 1.109 (0.937) Remain 11:05:47 loss: 2.3824 psnr: 17.9057 Lr: 1.68985e-03
[2025-02-17 15:43:43,107 INFO hook.py line 109 848561] Train: [30/100][350/605] Data 0.002 (0.002) Batch 0.917 (0.936) Remain 11:04:57 loss: 2.2876 psnr: 17.7131 Lr: 1.68787e-03
[2025-02-17 15:44:29,940 INFO hook.py line 109 848561] Train: [30/100][400/605] Data 0.002 (0.002) Batch 0.940 (0.936) Remain 11:04:12 loss: 2.2198 psnr: 18.4721 Lr: 1.68588e-03
[2025-02-17 15:45:16,899 INFO hook.py line 109 848561] Train: [30/100][450/605] Data 0.003 (0.002) Batch 0.961 (0.937) Remain 11:03:38 loss: 2.2287 psnr: 17.6231 Lr: 1.68389e-03
[2025-02-17 15:46:03,866 INFO hook.py line 109 848561] Train: [30/100][500/605] Data 0.003 (0.002) Batch 0.961 (0.937) Remain 11:03:02 loss: 2.1163 psnr: 19.6194 Lr: 1.68190e-03
[2025-02-17 15:46:50,509 INFO hook.py line 109 848561] Train: [30/100][550/605] Data 0.003 (0.002) Batch 0.945 (0.937) Remain 11:01:59 loss: 2.6256 psnr: 15.5941 Lr: 1.67989e-03
[2025-02-17 15:47:36,349 INFO hook.py line 109 848561] Train: [30/100][600/605] Data 0.002 (0.002) Batch 0.859 (0.935) Remain 11:00:01 loss: 2.2892 psnr: 18.3764 Lr: 1.67789e-03
[2025-02-17 15:47:40,624 INFO misc.py line 135 848561] Train result: loss: 2.3754 rgb_loss: 0.8573 psnr: 17.3241 depth_loss: 0.0692 feat_loss: 1.4489 
[2025-02-17 15:47:40,625 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:48:31,614 INFO hook.py line 109 848561] Train: [31/100][50/605] Data 0.002 (0.002) Batch 0.927 (0.937) Remain 11:00:38 loss: 2.3338 psnr: 17.3037 Lr: 1.67567e-03
[2025-02-17 15:49:18,217 INFO hook.py line 109 848561] Train: [31/100][100/605] Data 0.003 (0.002) Batch 0.938 (0.934) Remain 10:58:02 loss: 2.4428 psnr: 16.6011 Lr: 1.67366e-03
[2025-02-17 15:50:05,095 INFO hook.py line 109 848561] Train: [31/100][150/605] Data 0.004 (0.002) Batch 0.955 (0.936) Remain 10:57:59 loss: 2.5032 psnr: 16.6801 Lr: 1.67164e-03
[2025-02-17 15:50:52,072 INFO hook.py line 109 848561] Train: [31/100][200/605] Data 0.001 (0.002) Batch 0.982 (0.937) Remain 10:57:55 loss: 2.4301 psnr: 15.7865 Lr: 1.66961e-03
[2025-02-17 15:51:38,609 INFO hook.py line 109 848561] Train: [31/100][250/605] Data 0.002 (0.002) Batch 0.948 (0.935) Remain 10:56:19 loss: 2.3780 psnr: 16.8992 Lr: 1.66758e-03
[2025-02-17 15:52:25,774 INFO hook.py line 109 848561] Train: [31/100][300/605] Data 0.003 (0.002) Batch 0.933 (0.937) Remain 10:56:28 loss: 2.1870 psnr: 19.0137 Lr: 1.66554e-03
[2025-02-17 15:53:12,802 INFO hook.py line 109 848561] Train: [31/100][350/605] Data 0.002 (0.002) Batch 0.947 (0.937) Remain 10:56:05 loss: 2.6306 psnr: 15.6078 Lr: 1.66350e-03
[2025-02-17 15:53:59,622 INFO hook.py line 109 848561] Train: [31/100][400/605] Data 0.002 (0.002) Batch 0.919 (0.937) Remain 10:55:13 loss: 2.2610 psnr: 18.6688 Lr: 1.66145e-03
[2025-02-17 15:54:46,705 INFO hook.py line 109 848561] Train: [31/100][450/605] Data 0.002 (0.002) Batch 0.965 (0.938) Remain 10:54:47 loss: 2.4519 psnr: 16.5942 Lr: 1.65940e-03
[2025-02-17 15:55:33,602 INFO hook.py line 109 848561] Train: [31/100][500/605] Data 0.003 (0.002) Batch 0.908 (0.938) Remain 10:54:02 loss: 2.3644 psnr: 16.6614 Lr: 1.65734e-03
[2025-02-17 15:56:20,344 INFO hook.py line 109 848561] Train: [31/100][550/605] Data 0.002 (0.002) Batch 0.912 (0.937) Remain 10:53:04 loss: 2.4444 psnr: 16.6895 Lr: 1.65528e-03
[2025-02-17 15:57:06,218 INFO hook.py line 109 848561] Train: [31/100][600/605] Data 0.002 (0.002) Batch 0.886 (0.936) Remain 10:51:07 loss: 2.3923 psnr: 17.5372 Lr: 1.65321e-03
[2025-02-17 15:57:10,598 INFO misc.py line 135 848561] Train result: loss: 2.3741 rgb_loss: 0.8529 psnr: 17.3657 depth_loss: 0.0704 feat_loss: 1.4507 
[2025-02-17 15:57:10,600 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 15:58:01,413 INFO hook.py line 109 848561] Train: [32/100][50/605] Data 0.002 (0.003) Batch 0.915 (0.934) Remain 10:49:16 loss: 2.1599 psnr: 18.1461 Lr: 1.65093e-03
[2025-02-17 15:58:48,101 INFO hook.py line 109 848561] Train: [32/100][100/605] Data 0.002 (0.003) Batch 0.919 (0.934) Remain 10:48:17 loss: 2.1480 psnr: 19.5417 Lr: 1.64890e-03
[2025-02-17 15:59:34,948 INFO hook.py line 109 848561] Train: [32/100][150/605] Data 0.004 (0.003) Batch 0.946 (0.935) Remain 10:48:12 loss: 2.2337 psnr: 18.4162 Lr: 1.64681e-03
[2025-02-17 16:00:22,080 INFO hook.py line 109 848561] Train: [32/100][200/605] Data 0.002 (0.002) Batch 0.955 (0.937) Remain 10:48:45 loss: 2.5462 psnr: 16.6481 Lr: 1.64473e-03
[2025-02-17 16:01:08,920 INFO hook.py line 109 848561] Train: [32/100][250/605] Data 0.002 (0.002) Batch 0.951 (0.937) Remain 10:47:57 loss: 2.2128 psnr: 18.1306 Lr: 1.64264e-03
[2025-02-17 16:01:55,995 INFO hook.py line 109 848561] Train: [32/100][300/605] Data 0.002 (0.002) Batch 0.958 (0.938) Remain 10:47:42 loss: 2.3042 psnr: 17.3936 Lr: 1.64054e-03
[2025-02-17 16:02:42,934 INFO hook.py line 109 848561] Train: [32/100][350/605] Data 0.003 (0.002) Batch 0.968 (0.938) Remain 10:47:02 loss: 2.3068 psnr: 17.1913 Lr: 1.63844e-03
[2025-02-17 16:03:30,030 INFO hook.py line 109 848561] Train: [32/100][400/605] Data 0.003 (0.002) Batch 0.951 (0.938) Remain 10:46:36 loss: 2.3656 psnr: 17.5002 Lr: 1.63633e-03
[2025-02-17 16:04:16,656 INFO hook.py line 109 848561] Train: [32/100][450/605] Data 0.003 (0.002) Batch 0.948 (0.938) Remain 10:45:22 loss: 2.3091 psnr: 17.3286 Lr: 1.63422e-03
[2025-02-17 16:05:03,182 INFO hook.py line 109 848561] Train: [32/100][500/605] Data 0.003 (0.002) Batch 0.913 (0.937) Remain 10:44:05 loss: 2.5864 psnr: 16.0082 Lr: 1.63211e-03
[2025-02-17 16:05:50,142 INFO hook.py line 109 848561] Train: [32/100][550/605] Data 0.002 (0.002) Batch 0.955 (0.937) Remain 10:43:27 loss: 2.1223 psnr: 18.8689 Lr: 1.62999e-03
[2025-02-17 16:06:36,135 INFO hook.py line 109 848561] Train: [32/100][600/605] Data 0.001 (0.002) Batch 0.882 (0.936) Remain 10:41:40 loss: 2.3874 psnr: 16.8353 Lr: 1.62786e-03
[2025-02-17 16:06:40,444 INFO misc.py line 135 848561] Train result: loss: 2.3692 rgb_loss: 0.8497 psnr: 17.4039 depth_loss: 0.0698 feat_loss: 1.4497 
[2025-02-17 16:06:40,446 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 16:07:31,493 INFO hook.py line 109 848561] Train: [33/100][50/605] Data 0.003 (0.002) Batch 0.962 (0.937) Remain 10:41:57 loss: 2.4490 psnr: 17.1140 Lr: 1.62552e-03
[2025-02-17 16:08:18,492 INFO hook.py line 109 848561] Train: [33/100][100/605] Data 0.003 (0.002) Batch 0.949 (0.939) Remain 10:42:05 loss: 2.1598 psnr: 19.0446 Lr: 1.62338e-03
[2025-02-17 16:09:05,486 INFO hook.py line 109 848561] Train: [33/100][150/605] Data 0.002 (0.002) Batch 0.971 (0.939) Remain 10:41:34 loss: 2.4036 psnr: 16.8974 Lr: 1.62124e-03
[2025-02-17 16:09:52,469 INFO hook.py line 109 848561] Train: [33/100][200/605] Data 0.003 (0.002) Batch 0.913 (0.939) Remain 10:40:52 loss: 2.3510 psnr: 17.4630 Lr: 1.61910e-03
[2025-02-17 16:10:39,386 INFO hook.py line 109 848561] Train: [33/100][250/605] Data 0.002 (0.002) Batch 0.933 (0.939) Remain 10:39:58 loss: 2.4455 psnr: 17.0153 Lr: 1.61695e-03
[2025-02-17 16:11:26,005 INFO hook.py line 109 848561] Train: [33/100][300/605] Data 0.003 (0.002) Batch 0.929 (0.938) Remain 10:38:25 loss: 2.1921 psnr: 18.9794 Lr: 1.61480e-03
[2025-02-17 16:12:12,546 INFO hook.py line 109 848561] Train: [33/100][350/605] Data 0.001 (0.002) Batch 0.933 (0.937) Remain 10:36:56 loss: 2.2200 psnr: 18.2219 Lr: 1.61264e-03
[2025-02-17 16:12:59,705 INFO hook.py line 109 848561] Train: [33/100][400/605] Data 0.002 (0.002) Batch 0.917 (0.938) Remain 10:36:42 loss: 2.4878 psnr: 16.2293 Lr: 1.61048e-03
[2025-02-17 16:13:46,369 INFO hook.py line 109 848561] Train: [33/100][450/605] Data 0.002 (0.002) Batch 0.954 (0.937) Remain 10:35:35 loss: 2.1301 psnr: 18.7335 Lr: 1.60831e-03
[2025-02-17 16:14:33,278 INFO hook.py line 109 848561] Train: [33/100][500/605] Data 0.001 (0.002) Batch 0.947 (0.937) Remain 10:34:52 loss: 2.4021 psnr: 17.3623 Lr: 1.60614e-03
[2025-02-17 16:15:20,304 INFO hook.py line 109 848561] Train: [33/100][550/605] Data 0.002 (0.002) Batch 0.941 (0.938) Remain 10:34:17 loss: 2.3789 psnr: 17.2989 Lr: 1.60396e-03
[2025-02-17 16:16:06,525 INFO hook.py line 109 848561] Train: [33/100][600/605] Data 0.003 (0.002) Batch 0.857 (0.936) Remain 10:32:45 loss: 2.1508 psnr: 18.9607 Lr: 1.60178e-03
[2025-02-17 16:16:10,843 INFO misc.py line 135 848561] Train result: loss: 2.3619 rgb_loss: 0.8432 psnr: 17.4298 depth_loss: 0.0698 feat_loss: 1.4489 
[2025-02-17 16:16:10,844 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 16:17:01,597 INFO hook.py line 109 848561] Train: [34/100][50/605] Data 0.001 (0.002) Batch 0.949 (0.936) Remain 10:31:43 loss: 2.2954 psnr: 17.1451 Lr: 1.59938e-03
[2025-02-17 16:17:48,444 INFO hook.py line 109 848561] Train: [34/100][100/605] Data 0.003 (0.002) Batch 0.931 (0.937) Remain 10:31:11 loss: 2.4212 psnr: 16.0659 Lr: 1.59719e-03
[2025-02-17 16:18:35,246 INFO hook.py line 109 848561] Train: [34/100][150/605] Data 0.003 (0.002) Batch 0.938 (0.936) Remain 10:30:16 loss: 2.6555 psnr: 15.6672 Lr: 1.59500e-03
[2025-02-17 16:19:22,024 INFO hook.py line 109 848561] Train: [34/100][200/605] Data 0.003 (0.002) Batch 0.920 (0.936) Remain 10:29:21 loss: 2.1499 psnr: 19.0290 Lr: 1.59280e-03
[2025-02-17 16:20:08,756 INFO hook.py line 109 848561] Train: [34/100][250/605] Data 0.002 (0.002) Batch 0.967 (0.936) Remain 10:28:21 loss: 2.3443 psnr: 17.2736 Lr: 1.59059e-03
[2025-02-17 16:20:55,444 INFO hook.py line 109 848561] Train: [34/100][300/605] Data 0.003 (0.002) Batch 0.942 (0.936) Remain 10:27:20 loss: 2.4237 psnr: 17.2594 Lr: 1.58839e-03
[2025-02-17 16:21:42,486 INFO hook.py line 109 848561] Train: [34/100][350/605] Data 0.002 (0.002) Batch 0.948 (0.936) Remain 10:27:04 loss: 2.4708 psnr: 17.1744 Lr: 1.58617e-03
[2025-02-17 16:22:29,543 INFO hook.py line 109 848561] Train: [34/100][400/605] Data 0.002 (0.002) Batch 0.934 (0.937) Remain 10:26:42 loss: 2.3283 psnr: 17.5162 Lr: 1.58396e-03
[2025-02-17 16:23:16,549 INFO hook.py line 109 848561] Train: [34/100][450/605] Data 0.003 (0.002) Batch 0.918 (0.937) Remain 10:26:10 loss: 2.3188 psnr: 17.2751 Lr: 1.58174e-03
[2025-02-17 16:24:03,203 INFO hook.py line 109 848561] Train: [34/100][500/605] Data 0.003 (0.002) Batch 0.949 (0.937) Remain 10:25:06 loss: 2.5124 psnr: 16.7843 Lr: 1.57951e-03
[2025-02-17 16:24:50,037 INFO hook.py line 109 848561] Train: [34/100][550/605] Data 0.003 (0.002) Batch 0.955 (0.937) Remain 10:24:18 loss: 2.4147 psnr: 17.2945 Lr: 1.57728e-03
[2025-02-17 16:25:35,837 INFO hook.py line 109 848561] Train: [34/100][600/605] Data 0.002 (0.002) Batch 0.867 (0.935) Remain 10:22:22 loss: 2.2504 psnr: 18.8885 Lr: 1.57505e-03
[2025-02-17 16:25:40,258 INFO misc.py line 135 848561] Train result: loss: 2.3680 rgb_loss: 0.8523 psnr: 17.3818 depth_loss: 0.0696 feat_loss: 1.4461 
[2025-02-17 16:25:40,259 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 16:26:31,220 INFO hook.py line 109 848561] Train: [35/100][50/605] Data 0.003 (0.002) Batch 0.957 (0.937) Remain 10:22:34 loss: 2.1610 psnr: 19.3655 Lr: 1.57259e-03
[2025-02-17 16:27:18,264 INFO hook.py line 109 848561] Train: [35/100][100/605] Data 0.003 (0.002) Batch 0.960 (0.939) Remain 10:23:13 loss: 2.2292 psnr: 17.8836 Lr: 1.57034e-03
[2025-02-17 16:28:05,093 INFO hook.py line 109 848561] Train: [35/100][150/605] Data 0.002 (0.002) Batch 0.958 (0.938) Remain 10:21:56 loss: 2.2874 psnr: 18.1861 Lr: 1.56810e-03
[2025-02-17 16:28:51,898 INFO hook.py line 109 848561] Train: [35/100][200/605] Data 0.002 (0.002) Batch 0.977 (0.938) Remain 10:20:49 loss: 2.3813 psnr: 17.0185 Lr: 1.56585e-03
[2025-02-17 16:29:38,755 INFO hook.py line 109 848561] Train: [35/100][250/605] Data 0.003 (0.002) Batch 0.922 (0.937) Remain 10:19:59 loss: 2.4462 psnr: 17.6575 Lr: 1.56359e-03
[2025-02-17 16:30:25,322 INFO hook.py line 109 848561] Train: [35/100][300/605] Data 0.002 (0.002) Batch 0.932 (0.936) Remain 10:18:31 loss: 2.2949 psnr: 17.2468 Lr: 1.56133e-03
[2025-02-17 16:31:11,973 INFO hook.py line 109 848561] Train: [35/100][350/605] Data 0.003 (0.002) Batch 0.900 (0.936) Remain 10:17:24 loss: 2.4421 psnr: 16.6830 Lr: 1.55907e-03
[2025-02-17 16:31:59,025 INFO hook.py line 109 848561] Train: [35/100][400/605] Data 0.001 (0.002) Batch 0.941 (0.937) Remain 10:17:03 loss: 2.2254 psnr: 18.4974 Lr: 1.55680e-03
[2025-02-17 16:32:46,280 INFO hook.py line 109 848561] Train: [35/100][450/605] Data 0.002 (0.002) Batch 0.915 (0.938) Remain 10:16:54 loss: 1.8725 psnr: 22.5247 Lr: 1.55453e-03
[2025-02-17 16:33:33,342 INFO hook.py line 109 848561] Train: [35/100][500/605] Data 0.003 (0.002) Batch 0.908 (0.938) Remain 10:16:21 loss: 2.3826 psnr: 17.2508 Lr: 1.55225e-03
[2025-02-17 16:34:20,186 INFO hook.py line 109 848561] Train: [35/100][550/605] Data 0.003 (0.002) Batch 0.953 (0.938) Remain 10:15:31 loss: 2.4431 psnr: 16.3928 Lr: 1.54997e-03
[2025-02-17 16:35:05,899 INFO hook.py line 109 848561] Train: [35/100][600/605] Data 0.002 (0.002) Batch 0.876 (0.936) Remain 10:13:26 loss: 2.5568 psnr: 15.8601 Lr: 1.54768e-03
[2025-02-17 16:35:10,174 INFO misc.py line 135 848561] Train result: loss: 2.3615 rgb_loss: 0.8493 psnr: 17.3775 depth_loss: 0.0684 feat_loss: 1.4438 
[2025-02-17 16:35:10,175 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 16:36:00,803 INFO hook.py line 109 848561] Train: [36/100][50/605] Data 0.002 (0.002) Batch 0.925 (0.931) Remain 10:09:18 loss: 2.4579 psnr: 16.2383 Lr: 1.54517e-03
[2025-02-17 16:36:47,441 INFO hook.py line 109 848561] Train: [36/100][100/605] Data 0.003 (0.002) Batch 0.918 (0.932) Remain 10:09:10 loss: 2.3347 psnr: 17.6031 Lr: 1.54287e-03
[2025-02-17 16:37:34,310 INFO hook.py line 109 848561] Train: [36/100][150/605] Data 0.002 (0.002) Batch 0.950 (0.934) Remain 10:09:38 loss: 2.3764 psnr: 17.5210 Lr: 1.54058e-03
[2025-02-17 16:38:20,734 INFO hook.py line 109 848561] Train: [36/100][200/605] Data 0.002 (0.002) Batch 0.956 (0.932) Remain 10:07:59 loss: 2.5242 psnr: 16.4361 Lr: 1.53828e-03
[2025-02-17 16:39:07,558 INFO hook.py line 109 848561] Train: [36/100][250/605] Data 0.002 (0.002) Batch 0.948 (0.933) Remain 10:07:45 loss: 2.6466 psnr: 14.7725 Lr: 1.53597e-03
[2025-02-17 16:39:54,329 INFO hook.py line 109 848561] Train: [36/100][300/605] Data 0.002 (0.002) Batch 0.887 (0.934) Remain 10:07:13 loss: 2.3119 psnr: 16.8986 Lr: 1.53366e-03
[2025-02-17 16:40:41,122 INFO hook.py line 109 848561] Train: [36/100][350/605] Data 0.002 (0.002) Batch 0.927 (0.934) Remain 10:06:39 loss: 2.1913 psnr: 18.6768 Lr: 1.53135e-03
[2025-02-17 16:41:28,019 INFO hook.py line 109 848561] Train: [36/100][400/605] Data 0.002 (0.002) Batch 0.959 (0.934) Remain 10:06:12 loss: 2.4028 psnr: 16.9925 Lr: 1.52903e-03
[2025-02-17 16:42:15,171 INFO hook.py line 109 848561] Train: [36/100][450/605] Data 0.003 (0.002) Batch 0.963 (0.935) Remain 10:06:02 loss: 2.3931 psnr: 17.1609 Lr: 1.52671e-03
[2025-02-17 16:43:01,979 INFO hook.py line 109 848561] Train: [36/100][500/605] Data 0.003 (0.002) Batch 0.927 (0.935) Remain 10:05:19 loss: 2.4364 psnr: 17.2725 Lr: 1.52438e-03
[2025-02-17 16:43:49,138 INFO hook.py line 109 848561] Train: [36/100][550/605] Data 0.003 (0.002) Batch 0.945 (0.936) Remain 10:04:59 loss: 2.5452 psnr: 16.4036 Lr: 1.52205e-03
[2025-02-17 16:44:35,720 INFO hook.py line 109 848561] Train: [36/100][600/605] Data 0.002 (0.002) Batch 0.871 (0.936) Remain 10:03:58 loss: 2.3914 psnr: 16.9374 Lr: 1.51972e-03
[2025-02-17 16:44:40,008 INFO misc.py line 135 848561] Train result: loss: 2.3543 rgb_loss: 0.8428 psnr: 17.4577 depth_loss: 0.0699 feat_loss: 1.4416 
[2025-02-17 16:44:40,010 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 16:45:30,794 INFO hook.py line 109 848561] Train: [37/100][50/605] Data 0.002 (0.002) Batch 0.963 (0.936) Remain 10:03:16 loss: 2.0923 psnr: 19.1331 Lr: 1.51715e-03
[2025-02-17 16:46:17,633 INFO hook.py line 109 848561] Train: [37/100][100/605] Data 0.002 (0.002) Batch 0.944 (0.936) Remain 10:02:44 loss: 2.2622 psnr: 17.5525 Lr: 1.51481e-03
[2025-02-17 16:47:04,419 INFO hook.py line 109 848561] Train: [37/100][150/605] Data 0.002 (0.002) Batch 0.951 (0.936) Remain 10:01:48 loss: 2.2372 psnr: 18.4952 Lr: 1.51247e-03
[2025-02-17 16:47:51,241 INFO hook.py line 109 848561] Train: [37/100][200/605] Data 0.001 (0.002) Batch 0.931 (0.936) Remain 10:01:03 loss: 2.2617 psnr: 17.9379 Lr: 1.51012e-03
[2025-02-17 16:48:37,921 INFO hook.py line 109 848561] Train: [37/100][250/605] Data 0.002 (0.002) Batch 0.921 (0.936) Remain 09:59:56 loss: 2.3127 psnr: 17.5220 Lr: 1.50776e-03
[2025-02-17 16:49:24,888 INFO hook.py line 109 848561] Train: [37/100][300/605] Data 0.002 (0.002) Batch 0.934 (0.936) Remain 09:59:33 loss: 2.3964 psnr: 17.0870 Lr: 1.50541e-03
[2025-02-17 16:50:11,719 INFO hook.py line 109 848561] Train: [37/100][350/605] Data 0.003 (0.002) Batch 0.947 (0.936) Remain 09:58:48 loss: 2.2295 psnr: 18.4881 Lr: 1.50305e-03
[2025-02-17 16:50:58,683 INFO hook.py line 109 848561] Train: [37/100][400/605] Data 0.001 (0.002) Batch 0.931 (0.937) Remain 09:58:15 loss: 2.3020 psnr: 17.8638 Lr: 1.50068e-03
[2025-02-17 16:51:45,636 INFO hook.py line 109 848561] Train: [37/100][450/605] Data 0.003 (0.002) Batch 0.952 (0.937) Remain 09:57:38 loss: 2.4828 psnr: 16.3180 Lr: 1.49832e-03
[2025-02-17 16:52:32,558 INFO hook.py line 109 848561] Train: [37/100][500/605] Data 0.002 (0.002) Batch 0.911 (0.937) Remain 09:56:57 loss: 2.3159 psnr: 18.2629 Lr: 1.49594e-03
[2025-02-17 16:53:19,427 INFO hook.py line 109 848561] Train: [37/100][550/605] Data 0.003 (0.002) Batch 0.903 (0.937) Remain 09:56:11 loss: 2.4019 psnr: 17.2983 Lr: 1.49357e-03
[2025-02-17 16:54:05,587 INFO hook.py line 109 848561] Train: [37/100][600/605] Data 0.002 (0.002) Batch 0.865 (0.936) Remain 09:54:39 loss: 2.5544 psnr: 15.8604 Lr: 1.49119e-03
[2025-02-17 16:54:09,908 INFO misc.py line 135 848561] Train result: loss: 2.3545 rgb_loss: 0.8443 psnr: 17.4173 depth_loss: 0.0691 feat_loss: 1.4411 
[2025-02-17 16:54:09,909 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 16:55:00,660 INFO hook.py line 109 848561] Train: [38/100][50/605] Data 0.003 (0.002) Batch 0.969 (0.932) Remain 09:51:24 loss: 2.3526 psnr: 17.0906 Lr: 1.48857e-03
[2025-02-17 16:55:47,791 INFO hook.py line 109 848561] Train: [38/100][100/605] Data 0.004 (0.002) Batch 0.923 (0.938) Remain 09:54:02 loss: 2.1650 psnr: 18.2395 Lr: 1.48618e-03
[2025-02-17 16:56:34,597 INFO hook.py line 109 848561] Train: [38/100][150/605] Data 0.003 (0.002) Batch 0.977 (0.937) Remain 09:52:56 loss: 2.2749 psnr: 18.3115 Lr: 1.48379e-03
[2025-02-17 16:57:21,272 INFO hook.py line 109 848561] Train: [38/100][200/605] Data 0.002 (0.002) Batch 0.932 (0.936) Remain 09:51:35 loss: 2.3681 psnr: 16.7569 Lr: 1.48140e-03
[2025-02-17 16:58:08,414 INFO hook.py line 109 848561] Train: [38/100][250/605] Data 0.003 (0.002) Batch 0.956 (0.938) Remain 09:51:39 loss: 2.5860 psnr: 15.5899 Lr: 1.47900e-03
[2025-02-17 16:58:55,054 INFO hook.py line 109 848561] Train: [38/100][300/605] Data 0.002 (0.002) Batch 0.940 (0.937) Remain 09:50:22 loss: 2.1694 psnr: 19.3256 Lr: 1.47660e-03
[2025-02-17 16:59:41,929 INFO hook.py line 109 848561] Train: [38/100][350/605] Data 0.002 (0.002) Batch 0.931 (0.937) Remain 09:49:39 loss: 2.3337 psnr: 17.7101 Lr: 1.47420e-03
[2025-02-17 17:00:29,029 INFO hook.py line 109 848561] Train: [38/100][400/605] Data 0.004 (0.002) Batch 0.940 (0.937) Remain 09:49:17 loss: 2.2017 psnr: 18.4007 Lr: 1.47179e-03
[2025-02-17 17:01:15,592 INFO hook.py line 109 848561] Train: [38/100][450/605] Data 0.002 (0.002) Batch 0.944 (0.937) Remain 09:48:04 loss: 2.5251 psnr: 15.9084 Lr: 1.46938e-03
[2025-02-17 17:02:02,557 INFO hook.py line 109 848561] Train: [38/100][500/605] Data 0.003 (0.002) Batch 0.951 (0.937) Remain 09:47:26 loss: 2.3089 psnr: 17.4903 Lr: 1.46696e-03
[2025-02-17 17:02:49,915 INFO hook.py line 109 848561] Train: [38/100][550/605] Data 0.003 (0.002) Batch 0.932 (0.938) Remain 09:47:14 loss: 2.2821 psnr: 17.5957 Lr: 1.46454e-03
[2025-02-17 17:03:36,128 INFO hook.py line 109 848561] Train: [38/100][600/605] Data 0.002 (0.002) Batch 0.870 (0.937) Remain 09:45:44 loss: 2.3227 psnr: 18.2016 Lr: 1.46212e-03
[2025-02-17 17:03:40,520 INFO misc.py line 135 848561] Train result: loss: 2.3529 rgb_loss: 0.8435 psnr: 17.4339 depth_loss: 0.0684 feat_loss: 1.4410 
[2025-02-17 17:03:40,522 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 17:04:30,967 INFO hook.py line 109 848561] Train: [39/100][50/605] Data 0.002 (0.002) Batch 0.941 (0.933) Remain 09:42:27 loss: 2.2425 psnr: 18.7313 Lr: 1.45945e-03
[2025-02-17 17:05:17,627 INFO hook.py line 109 848561] Train: [39/100][100/605] Data 0.003 (0.002) Batch 0.966 (0.933) Remain 09:41:46 loss: 2.5896 psnr: 15.7330 Lr: 1.45703e-03
[2025-02-17 17:06:04,256 INFO hook.py line 109 848561] Train: [39/100][150/605] Data 0.003 (0.002) Batch 0.952 (0.933) Remain 09:40:53 loss: 2.3028 psnr: 18.1682 Lr: 1.45459e-03
[2025-02-17 17:06:51,115 INFO hook.py line 109 848561] Train: [39/100][200/605] Data 0.002 (0.002) Batch 0.955 (0.934) Remain 09:40:47 loss: 2.0769 psnr: 19.4870 Lr: 1.45216e-03
[2025-02-17 17:07:37,941 INFO hook.py line 109 848561] Train: [39/100][250/605] Data 0.003 (0.002) Batch 0.938 (0.935) Remain 09:40:19 loss: 2.2133 psnr: 18.7971 Lr: 1.44972e-03
[2025-02-17 17:08:24,994 INFO hook.py line 109 848561] Train: [39/100][300/605] Data 0.002 (0.002) Batch 0.961 (0.936) Remain 09:40:13 loss: 2.5198 psnr: 16.1878 Lr: 1.44727e-03
[2025-02-17 17:09:11,877 INFO hook.py line 109 848561] Train: [39/100][350/605] Data 0.003 (0.002) Batch 0.943 (0.936) Remain 09:39:38 loss: 2.3127 psnr: 17.0888 Lr: 1.44483e-03
[2025-02-17 17:09:58,852 INFO hook.py line 109 848561] Train: [39/100][400/605] Data 0.003 (0.002) Batch 0.969 (0.936) Remain 09:39:08 loss: 2.3171 psnr: 17.8349 Lr: 1.44238e-03
[2025-02-17 17:10:46,020 INFO hook.py line 109 848561] Train: [39/100][450/605] Data 0.002 (0.002) Batch 0.902 (0.937) Remain 09:38:50 loss: 2.4794 psnr: 17.0631 Lr: 1.43993e-03
[2025-02-17 17:11:33,130 INFO hook.py line 109 848561] Train: [39/100][500/605] Data 0.003 (0.002) Batch 0.967 (0.938) Remain 09:38:22 loss: 2.3617 psnr: 17.0684 Lr: 1.43747e-03
[2025-02-17 17:12:20,484 INFO hook.py line 109 848561] Train: [39/100][550/605] Data 0.002 (0.002) Batch 0.958 (0.939) Remain 09:38:07 loss: 2.4052 psnr: 16.4517 Lr: 1.43501e-03
[2025-02-17 17:13:06,673 INFO hook.py line 109 848561] Train: [39/100][600/605] Data 0.002 (0.002) Batch 0.833 (0.937) Remain 09:36:34 loss: 2.3087 psnr: 17.2478 Lr: 1.43255e-03
[2025-02-17 17:13:10,995 INFO misc.py line 135 848561] Train result: loss: 2.3457 rgb_loss: 0.8354 psnr: 17.4982 depth_loss: 0.0685 feat_loss: 1.4419 
[2025-02-17 17:13:10,995 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 17:14:02,026 INFO hook.py line 109 848561] Train: [40/100][50/605] Data 0.003 (0.002) Batch 0.935 (0.937) Remain 09:35:33 loss: 2.3137 psnr: 17.9471 Lr: 1.42984e-03
[2025-02-17 17:14:49,037 INFO hook.py line 109 848561] Train: [40/100][100/605] Data 0.002 (0.002) Batch 0.958 (0.939) Remain 09:35:47 loss: 2.2440 psnr: 17.6680 Lr: 1.42737e-03
[2025-02-17 17:15:35,672 INFO hook.py line 109 848561] Train: [40/100][150/605] Data 0.003 (0.003) Batch 0.906 (0.937) Remain 09:33:46 loss: 2.3740 psnr: 17.6378 Lr: 1.42489e-03
[2025-02-17 17:16:22,635 INFO hook.py line 109 848561] Train: [40/100][200/605] Data 0.003 (0.002) Batch 0.949 (0.937) Remain 09:33:23 loss: 2.6224 psnr: 16.0547 Lr: 1.42242e-03
[2025-02-17 17:17:09,516 INFO hook.py line 109 848561] Train: [40/100][250/605] Data 0.002 (0.002) Batch 0.947 (0.937) Remain 09:32:39 loss: 2.5466 psnr: 16.0749 Lr: 1.41994e-03
[2025-02-17 17:17:56,023 INFO hook.py line 109 848561] Train: [40/100][300/605] Data 0.002 (0.002) Batch 0.934 (0.936) Remain 09:31:07 loss: 2.4214 psnr: 17.6802 Lr: 1.41746e-03
[2025-02-17 17:18:42,766 INFO hook.py line 109 848561] Train: [40/100][350/605] Data 0.002 (0.002) Batch 0.939 (0.936) Remain 09:30:14 loss: 2.0720 psnr: 20.7062 Lr: 1.41497e-03
[2025-02-17 17:19:29,900 INFO hook.py line 109 848561] Train: [40/100][400/605] Data 0.003 (0.002) Batch 0.918 (0.937) Remain 09:29:58 loss: 2.6390 psnr: 15.9921 Lr: 1.41254e-03
[2025-02-17 17:20:16,862 INFO hook.py line 109 848561] Train: [40/100][450/605] Data 0.002 (0.002) Batch 0.911 (0.937) Remain 09:29:21 loss: 2.4539 psnr: 17.0985 Lr: 1.41004e-03
[2025-02-17 17:21:03,847 INFO hook.py line 109 848561] Train: [40/100][500/605] Data 0.002 (0.002) Batch 0.969 (0.937) Remain 09:28:44 loss: 2.4303 psnr: 16.8639 Lr: 1.40755e-03
[2025-02-17 17:21:50,919 INFO hook.py line 109 848561] Train: [40/100][550/605] Data 0.002 (0.002) Batch 0.925 (0.938) Remain 09:28:10 loss: 2.0212 psnr: 21.7158 Lr: 1.40505e-03
[2025-02-17 17:22:37,335 INFO hook.py line 109 848561] Train: [40/100][600/605] Data 0.003 (0.002) Batch 0.861 (0.937) Remain 09:26:55 loss: 2.3623 psnr: 17.4341 Lr: 1.40255e-03
[2025-02-17 17:22:41,640 INFO misc.py line 135 848561] Train result: loss: 2.3475 rgb_loss: 0.8376 psnr: 17.4878 depth_loss: 0.0686 feat_loss: 1.4413 
[2025-02-17 17:22:41,641 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 17:23:32,702 INFO hook.py line 109 848561] Train: [41/100][50/605] Data 0.002 (0.002) Batch 0.943 (0.936) Remain 09:25:39 loss: 2.1412 psnr: 18.9578 Lr: 1.39980e-03
[2025-02-17 17:24:19,455 INFO hook.py line 109 848561] Train: [41/100][100/605] Data 0.002 (0.002) Batch 0.947 (0.936) Remain 09:24:30 loss: 2.3714 psnr: 16.7783 Lr: 1.39729e-03
[2025-02-17 17:25:06,305 INFO hook.py line 109 848561] Train: [41/100][150/605] Data 0.002 (0.002) Batch 0.912 (0.936) Remain 09:24:00 loss: 2.2324 psnr: 17.9684 Lr: 1.39478e-03
[2025-02-17 17:25:53,270 INFO hook.py line 109 848561] Train: [41/100][200/605] Data 0.003 (0.002) Batch 0.939 (0.937) Remain 09:23:42 loss: 2.2036 psnr: 19.7757 Lr: 1.39232e-03
[2025-02-17 17:26:40,337 INFO hook.py line 109 848561] Train: [41/100][250/605] Data 0.003 (0.002) Batch 0.918 (0.938) Remain 09:23:28 loss: 2.1896 psnr: 18.4676 Lr: 1.38980e-03
[2025-02-17 17:27:27,120 INFO hook.py line 109 848561] Train: [41/100][300/605] Data 0.002 (0.002) Batch 0.927 (0.937) Remain 09:22:27 loss: 2.2046 psnr: 18.7107 Lr: 1.38729e-03
[2025-02-17 17:28:13,769 INFO hook.py line 109 848561] Train: [41/100][350/605] Data 0.002 (0.002) Batch 0.940 (0.937) Remain 09:21:18 loss: 2.6040 psnr: 16.2414 Lr: 1.38477e-03
[2025-02-17 17:29:00,611 INFO hook.py line 109 848561] Train: [41/100][400/605] Data 0.003 (0.002) Batch 0.952 (0.937) Remain 09:20:31 loss: 2.5015 psnr: 16.1824 Lr: 1.38224e-03
[2025-02-17 17:29:47,566 INFO hook.py line 109 848561] Train: [41/100][450/605] Data 0.002 (0.002) Batch 0.937 (0.937) Remain 09:19:53 loss: 2.3292 psnr: 17.5260 Lr: 1.37971e-03
[2025-02-17 17:30:34,314 INFO hook.py line 109 848561] Train: [41/100][500/605] Data 0.003 (0.002) Batch 0.933 (0.937) Remain 09:18:59 loss: 2.4067 psnr: 17.4708 Lr: 1.37718e-03
[2025-02-17 17:31:21,344 INFO hook.py line 109 848561] Train: [41/100][550/605] Data 0.003 (0.002) Batch 0.954 (0.937) Remain 09:18:24 loss: 2.2690 psnr: 18.8451 Lr: 1.37465e-03
[2025-02-17 17:32:07,754 INFO hook.py line 109 848561] Train: [41/100][600/605] Data 0.002 (0.002) Batch 0.874 (0.936) Remain 09:17:10 loss: 2.3371 psnr: 17.1889 Lr: 1.37212e-03
[2025-02-17 17:32:12,045 INFO misc.py line 135 848561] Train result: loss: 2.3398 rgb_loss: 0.8339 psnr: 17.4990 depth_loss: 0.0682 feat_loss: 1.4377 
[2025-02-17 17:32:12,045 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 17:33:02,931 INFO hook.py line 109 848561] Train: [42/100][50/605] Data 0.003 (0.002) Batch 0.930 (0.934) Remain 09:14:38 loss: 2.1180 psnr: 19.1705 Lr: 1.36932e-03
[2025-02-17 17:33:49,810 INFO hook.py line 109 848561] Train: [42/100][100/605] Data 0.002 (0.002) Batch 0.910 (0.936) Remain 09:15:04 loss: 2.2125 psnr: 18.6426 Lr: 1.36678e-03
[2025-02-17 17:34:36,478 INFO hook.py line 109 848561] Train: [42/100][150/605] Data 0.003 (0.002) Batch 0.960 (0.935) Remain 09:13:49 loss: 2.2052 psnr: 18.0473 Lr: 1.36424e-03
[2025-02-17 17:35:23,422 INFO hook.py line 109 848561] Train: [42/100][200/605] Data 0.003 (0.002) Batch 0.936 (0.936) Remain 09:13:39 loss: 2.1314 psnr: 18.9308 Lr: 1.36169e-03
[2025-02-17 17:36:10,198 INFO hook.py line 109 848561] Train: [42/100][250/605] Data 0.003 (0.002) Batch 0.919 (0.936) Remain 09:12:49 loss: 2.1613 psnr: 18.9118 Lr: 1.35914e-03
[2025-02-17 17:36:57,220 INFO hook.py line 109 848561] Train: [42/100][300/605] Data 0.001 (0.002) Batch 0.945 (0.937) Remain 09:12:30 loss: 2.2623 psnr: 18.2745 Lr: 1.35659e-03
[2025-02-17 17:37:44,273 INFO hook.py line 109 848561] Train: [42/100][350/605] Data 0.002 (0.002) Batch 0.931 (0.937) Remain 09:12:06 loss: 2.3710 psnr: 17.7139 Lr: 1.35404e-03
[2025-02-17 17:38:31,123 INFO hook.py line 109 848561] Train: [42/100][400/605] Data 0.003 (0.002) Batch 0.934 (0.937) Remain 09:11:18 loss: 2.1401 psnr: 18.9669 Lr: 1.35148e-03
[2025-02-17 17:39:18,152 INFO hook.py line 109 848561] Train: [42/100][450/605] Data 0.003 (0.002) Batch 0.934 (0.938) Remain 09:10:45 loss: 2.2166 psnr: 17.9492 Lr: 1.34892e-03
[2025-02-17 17:40:05,269 INFO hook.py line 109 848561] Train: [42/100][500/605] Data 0.003 (0.002) Batch 0.922 (0.938) Remain 09:10:15 loss: 2.5033 psnr: 16.4614 Lr: 1.34636e-03
[2025-02-17 17:40:52,301 INFO hook.py line 109 848561] Train: [42/100][550/605] Data 0.003 (0.002) Batch 0.923 (0.938) Remain 09:09:36 loss: 2.2036 psnr: 17.7038 Lr: 1.34379e-03
[2025-02-17 17:41:38,773 INFO hook.py line 109 848561] Train: [42/100][600/605] Data 0.003 (0.002) Batch 0.922 (0.938) Remain 09:08:23 loss: 2.1249 psnr: 18.6452 Lr: 1.34122e-03
[2025-02-17 17:41:43,231 INFO misc.py line 135 848561] Train result: loss: 2.3231 rgb_loss: 0.8197 psnr: 17.6061 depth_loss: 0.0673 feat_loss: 1.4361 
[2025-02-17 17:41:43,233 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 17:42:34,453 INFO hook.py line 109 848561] Train: [43/100][50/605] Data 0.003 (0.002) Batch 0.943 (0.946) Remain 09:12:17 loss: 2.1094 psnr: 19.0500 Lr: 1.33840e-03
[2025-02-17 17:43:21,569 INFO hook.py line 109 848561] Train: [43/100][100/605] Data 0.003 (0.002) Batch 0.951 (0.944) Remain 09:10:29 loss: 2.3575 psnr: 17.2511 Lr: 1.33582e-03
[2025-02-17 17:44:08,402 INFO hook.py line 109 848561] Train: [43/100][150/605] Data 0.003 (0.002) Batch 0.937 (0.941) Remain 09:08:15 loss: 2.4716 psnr: 16.8521 Lr: 1.33325e-03
[2025-02-17 17:44:55,387 INFO hook.py line 109 848561] Train: [43/100][200/605] Data 0.003 (0.002) Batch 0.941 (0.941) Remain 09:07:12 loss: 2.1746 psnr: 18.3471 Lr: 1.33067e-03
[2025-02-17 17:45:42,328 INFO hook.py line 109 848561] Train: [43/100][250/605] Data 0.002 (0.002) Batch 0.933 (0.941) Remain 09:06:09 loss: 2.3984 psnr: 17.1325 Lr: 1.32809e-03
[2025-02-17 17:46:29,170 INFO hook.py line 109 848561] Train: [43/100][300/605] Data 0.003 (0.002) Batch 0.941 (0.940) Remain 09:05:00 loss: 2.3239 psnr: 17.4594 Lr: 1.32551e-03
[2025-02-17 17:47:15,894 INFO hook.py line 109 848561] Train: [43/100][350/605] Data 0.003 (0.002) Batch 0.948 (0.939) Remain 09:03:46 loss: 2.4263 psnr: 17.2680 Lr: 1.32292e-03
[2025-02-17 17:48:02,681 INFO hook.py line 109 848561] Train: [43/100][400/605] Data 0.002 (0.002) Batch 0.953 (0.939) Remain 09:02:44 loss: 2.2908 psnr: 17.9245 Lr: 1.32033e-03
[2025-02-17 17:48:49,220 INFO hook.py line 109 848561] Train: [43/100][450/605] Data 0.002 (0.002) Batch 0.986 (0.938) Remain 09:01:26 loss: 2.3807 psnr: 17.5612 Lr: 1.31774e-03
[2025-02-17 17:49:36,182 INFO hook.py line 109 848561] Train: [43/100][500/605] Data 0.002 (0.002) Batch 0.952 (0.938) Remain 09:00:44 loss: 2.4953 psnr: 15.9958 Lr: 1.31515e-03
[2025-02-17 17:50:23,021 INFO hook.py line 109 848561] Train: [43/100][550/605] Data 0.002 (0.002) Batch 0.951 (0.938) Remain 08:59:54 loss: 2.1822 psnr: 18.1093 Lr: 1.31256e-03
[2025-02-17 17:51:09,000 INFO hook.py line 109 848561] Train: [43/100][600/605] Data 0.002 (0.002) Batch 0.854 (0.936) Remain 08:58:14 loss: 2.2346 psnr: 19.0920 Lr: 1.30996e-03
[2025-02-17 17:51:13,323 INFO misc.py line 135 848561] Train result: loss: 2.3410 rgb_loss: 0.8356 psnr: 17.5013 depth_loss: 0.0690 feat_loss: 1.4364 
[2025-02-17 17:51:13,324 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 17:52:04,961 INFO hook.py line 109 848561] Train: [44/100][50/605] Data 0.003 (0.002) Batch 0.934 (0.946) Remain 09:02:53 loss: 2.2666 psnr: 18.1325 Lr: 1.30710e-03
[2025-02-17 17:52:51,856 INFO hook.py line 109 848561] Train: [44/100][100/605] Data 0.003 (0.002) Batch 0.956 (0.942) Remain 08:59:43 loss: 2.2653 psnr: 17.7963 Lr: 1.30450e-03
[2025-02-17 17:53:38,956 INFO hook.py line 109 848561] Train: [44/100][150/605] Data 0.002 (0.002) Batch 0.902 (0.942) Remain 08:58:59 loss: 2.3068 psnr: 17.6583 Lr: 1.30189e-03
[2025-02-17 17:54:25,687 INFO hook.py line 109 848561] Train: [44/100][200/605] Data 0.003 (0.002) Batch 0.923 (0.940) Remain 08:57:08 loss: 2.4355 psnr: 16.3488 Lr: 1.29929e-03
[2025-02-17 17:55:12,662 INFO hook.py line 109 848561] Train: [44/100][250/605] Data 0.002 (0.002) Batch 0.964 (0.940) Remain 08:56:18 loss: 2.0009 psnr: 20.9923 Lr: 1.29668e-03
[2025-02-17 17:55:59,234 INFO hook.py line 109 848561] Train: [44/100][300/605] Data 0.002 (0.002) Batch 0.944 (0.938) Remain 08:54:42 loss: 2.1172 psnr: 19.5802 Lr: 1.29407e-03
[2025-02-17 17:56:46,378 INFO hook.py line 109 848561] Train: [44/100][350/605] Data 0.002 (0.002) Batch 0.972 (0.939) Remain 08:54:17 loss: 2.3091 psnr: 17.9253 Lr: 1.29145e-03
[2025-02-17 17:57:33,235 INFO hook.py line 109 848561] Train: [44/100][400/605] Data 0.003 (0.002) Batch 0.913 (0.939) Remain 08:53:21 loss: 2.3204 psnr: 17.8881 Lr: 1.28884e-03
[2025-02-17 17:58:20,081 INFO hook.py line 109 848561] Train: [44/100][450/605] Data 0.003 (0.002) Batch 0.953 (0.939) Remain 08:52:27 loss: 2.4335 psnr: 16.6549 Lr: 1.28622e-03
[2025-02-17 17:59:06,920 INFO hook.py line 109 848561] Train: [44/100][500/605] Data 0.003 (0.002) Batch 0.930 (0.938) Remain 08:51:33 loss: 2.2368 psnr: 17.8486 Lr: 1.28360e-03
[2025-02-17 17:59:54,010 INFO hook.py line 109 848561] Train: [44/100][550/605] Data 0.002 (0.002) Batch 0.975 (0.939) Remain 08:50:57 loss: 2.1726 psnr: 18.9600 Lr: 1.28098e-03
[2025-02-17 18:00:40,049 INFO hook.py line 109 848561] Train: [44/100][600/605] Data 0.002 (0.002) Batch 0.855 (0.937) Remain 08:49:19 loss: 2.2629 psnr: 17.8447 Lr: 1.27836e-03
[2025-02-17 18:00:44,326 INFO misc.py line 135 848561] Train result: loss: 2.3204 rgb_loss: 0.8187 psnr: 17.6408 depth_loss: 0.0681 feat_loss: 1.4336 
[2025-02-17 18:00:44,328 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:01:35,540 INFO hook.py line 109 848561] Train: [45/100][50/605] Data 0.003 (0.002) Batch 0.945 (0.944) Remain 08:52:10 loss: 2.2124 psnr: 18.2452 Lr: 1.27547e-03
[2025-02-17 18:02:22,381 INFO hook.py line 109 848561] Train: [45/100][100/605] Data 0.003 (0.003) Batch 0.937 (0.940) Remain 08:49:21 loss: 2.1500 psnr: 19.4949 Lr: 1.27284e-03
[2025-02-17 18:03:09,434 INFO hook.py line 109 848561] Train: [45/100][150/605] Data 0.003 (0.003) Batch 0.970 (0.941) Remain 08:48:43 loss: 2.2679 psnr: 17.3858 Lr: 1.27021e-03
[2025-02-17 18:03:56,232 INFO hook.py line 109 848561] Train: [45/100][200/605] Data 0.002 (0.002) Batch 0.939 (0.939) Remain 08:47:17 loss: 2.3924 psnr: 17.3778 Lr: 1.26758e-03
[2025-02-17 18:04:43,349 INFO hook.py line 109 848561] Train: [45/100][250/605] Data 0.002 (0.002) Batch 0.963 (0.940) Remain 08:46:50 loss: 2.2317 psnr: 18.5073 Lr: 1.26494e-03
[2025-02-17 18:05:30,028 INFO hook.py line 109 848561] Train: [45/100][300/605] Data 0.002 (0.002) Batch 0.936 (0.939) Remain 08:45:27 loss: 2.2728 psnr: 18.3532 Lr: 1.26236e-03
[2025-02-17 18:06:16,696 INFO hook.py line 109 848561] Train: [45/100][350/605] Data 0.003 (0.002) Batch 0.926 (0.938) Remain 08:44:14 loss: 2.1067 psnr: 18.4838 Lr: 1.25972e-03
[2025-02-17 18:07:03,561 INFO hook.py line 109 848561] Train: [45/100][400/605] Data 0.002 (0.002) Batch 0.923 (0.938) Remain 08:43:23 loss: 2.0150 psnr: 20.9950 Lr: 1.25708e-03
[2025-02-17 18:07:50,964 INFO hook.py line 109 848561] Train: [45/100][450/605] Data 0.002 (0.002) Batch 0.921 (0.939) Remain 08:43:14 loss: 2.4517 psnr: 16.5385 Lr: 1.25444e-03
[2025-02-17 18:08:37,692 INFO hook.py line 109 848561] Train: [45/100][500/605] Data 0.003 (0.002) Batch 0.937 (0.939) Remain 08:42:12 loss: 2.1587 psnr: 19.2230 Lr: 1.25179e-03
[2025-02-17 18:09:24,730 INFO hook.py line 109 848561] Train: [45/100][550/605] Data 0.002 (0.002) Batch 0.933 (0.939) Remain 08:41:31 loss: 2.2222 psnr: 18.4199 Lr: 1.24915e-03
[2025-02-17 18:10:11,094 INFO hook.py line 109 848561] Train: [45/100][600/605] Data 0.002 (0.002) Batch 0.863 (0.938) Remain 08:40:12 loss: 2.3554 psnr: 17.6223 Lr: 1.24650e-03
[2025-02-17 18:10:15,477 INFO misc.py line 135 848561] Train result: loss: 2.3215 rgb_loss: 0.8187 psnr: 17.6462 depth_loss: 0.0685 feat_loss: 1.4343 
[2025-02-17 18:10:15,479 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:11:06,635 INFO hook.py line 109 848561] Train: [46/100][50/605] Data 0.003 (0.002) Batch 0.940 (0.938) Remain 08:39:24 loss: 2.2167 psnr: 18.7375 Lr: 1.24359e-03
[2025-02-17 18:11:53,861 INFO hook.py line 109 848561] Train: [46/100][100/605] Data 0.002 (0.002) Batch 0.933 (0.941) Remain 08:40:29 loss: 2.2803 psnr: 18.2694 Lr: 1.24093e-03
[2025-02-17 18:12:41,015 INFO hook.py line 109 848561] Train: [46/100][150/605] Data 0.002 (0.002) Batch 0.950 (0.942) Remain 08:40:01 loss: 2.4865 psnr: 17.1687 Lr: 1.23828e-03
[2025-02-17 18:13:27,920 INFO hook.py line 109 848561] Train: [46/100][200/605] Data 0.002 (0.002) Batch 0.975 (0.941) Remain 08:38:42 loss: 2.5370 psnr: 15.2530 Lr: 1.23562e-03
[2025-02-17 18:14:14,740 INFO hook.py line 109 848561] Train: [46/100][250/605] Data 0.003 (0.002) Batch 0.893 (0.940) Remain 08:37:24 loss: 2.3201 psnr: 17.1922 Lr: 1.23297e-03
[2025-02-17 18:15:01,651 INFO hook.py line 109 848561] Train: [46/100][300/605] Data 0.002 (0.002) Batch 0.963 (0.940) Remain 08:36:27 loss: 2.3702 psnr: 16.7171 Lr: 1.23031e-03
[2025-02-17 18:15:48,159 INFO hook.py line 109 848561] Train: [46/100][350/605] Data 0.003 (0.002) Batch 0.963 (0.938) Remain 08:34:55 loss: 2.2859 psnr: 17.3633 Lr: 1.22765e-03
[2025-02-17 18:16:35,143 INFO hook.py line 109 848561] Train: [46/100][400/605] Data 0.002 (0.002) Batch 0.964 (0.939) Remain 08:34:13 loss: 2.2487 psnr: 17.9582 Lr: 1.22499e-03
[2025-02-17 18:17:22,254 INFO hook.py line 109 848561] Train: [46/100][450/605] Data 0.002 (0.002) Batch 0.931 (0.939) Remain 08:33:40 loss: 2.2829 psnr: 16.9280 Lr: 1.22232e-03
[2025-02-17 18:18:09,012 INFO hook.py line 109 848561] Train: [46/100][500/605] Data 0.003 (0.002) Batch 0.948 (0.939) Remain 08:32:41 loss: 2.5017 psnr: 16.0564 Lr: 1.21966e-03
[2025-02-17 18:18:55,917 INFO hook.py line 109 848561] Train: [46/100][550/605] Data 0.002 (0.002) Batch 0.948 (0.939) Remain 08:31:52 loss: 2.1229 psnr: 18.9907 Lr: 1.21699e-03
[2025-02-17 18:19:42,013 INFO hook.py line 109 848561] Train: [46/100][600/605] Data 0.002 (0.002) Batch 0.847 (0.937) Remain 08:30:20 loss: 2.4139 psnr: 16.6082 Lr: 1.21432e-03
[2025-02-17 18:19:46,329 INFO misc.py line 135 848561] Train result: loss: 2.3204 rgb_loss: 0.8171 psnr: 17.6329 depth_loss: 0.0685 feat_loss: 1.4348 
[2025-02-17 18:19:46,329 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:20:37,566 INFO hook.py line 109 848561] Train: [47/100][50/605] Data 0.002 (0.002) Batch 0.904 (0.943) Remain 08:32:54 loss: 2.1285 psnr: 18.9992 Lr: 1.21138e-03
[2025-02-17 18:21:24,561 INFO hook.py line 109 848561] Train: [47/100][100/605] Data 0.002 (0.002) Batch 0.943 (0.942) Remain 08:31:07 loss: 2.5230 psnr: 16.4940 Lr: 1.20871e-03
[2025-02-17 18:22:11,486 INFO hook.py line 109 848561] Train: [47/100][150/605] Data 0.003 (0.002) Batch 0.914 (0.941) Remain 08:29:46 loss: 2.2734 psnr: 17.5320 Lr: 1.20604e-03
[2025-02-17 18:22:58,331 INFO hook.py line 109 848561] Train: [47/100][200/605] Data 0.003 (0.002) Batch 0.904 (0.940) Remain 08:28:29 loss: 2.1692 psnr: 18.8704 Lr: 1.20336e-03
[2025-02-17 18:23:45,077 INFO hook.py line 109 848561] Train: [47/100][250/605] Data 0.002 (0.002) Batch 0.931 (0.939) Remain 08:27:11 loss: 2.5562 psnr: 15.8979 Lr: 1.20069e-03
[2025-02-17 18:24:32,240 INFO hook.py line 109 848561] Train: [47/100][300/605] Data 0.002 (0.002) Batch 0.938 (0.939) Remain 08:26:49 loss: 2.3489 psnr: 17.1191 Lr: 1.19801e-03
[2025-02-17 18:25:19,198 INFO hook.py line 109 848561] Train: [47/100][350/605] Data 0.002 (0.002) Batch 0.956 (0.939) Remain 08:26:01 loss: 2.2297 psnr: 18.5121 Lr: 1.19533e-03
[2025-02-17 18:26:06,014 INFO hook.py line 109 848561] Train: [47/100][400/605] Data 0.002 (0.002) Batch 0.944 (0.939) Remain 08:25:01 loss: 2.2381 psnr: 18.3719 Lr: 1.19265e-03
[2025-02-17 18:26:52,820 INFO hook.py line 109 848561] Train: [47/100][450/605] Data 0.003 (0.002) Batch 0.944 (0.939) Remain 08:24:04 loss: 2.0718 psnr: 20.0336 Lr: 1.18997e-03
[2025-02-17 18:27:39,595 INFO hook.py line 109 848561] Train: [47/100][500/605] Data 0.003 (0.002) Batch 0.954 (0.938) Remain 08:23:07 loss: 2.3481 psnr: 17.1607 Lr: 1.18728e-03
[2025-02-17 18:28:26,719 INFO hook.py line 109 848561] Train: [47/100][550/605] Data 0.003 (0.002) Batch 0.919 (0.939) Remain 08:22:32 loss: 2.3349 psnr: 17.9479 Lr: 1.18460e-03
[2025-02-17 18:29:12,387 INFO hook.py line 109 848561] Train: [47/100][600/605] Data 0.002 (0.002) Batch 0.828 (0.937) Remain 08:20:37 loss: 2.2211 psnr: 19.0392 Lr: 1.18191e-03
[2025-02-17 18:29:16,629 INFO misc.py line 135 848561] Train result: loss: 2.3217 rgb_loss: 0.8217 psnr: 17.5811 depth_loss: 0.0678 feat_loss: 1.4322 
[2025-02-17 18:29:16,630 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:30:07,625 INFO hook.py line 109 848561] Train: [48/100][50/605] Data 0.003 (0.002) Batch 0.919 (0.939) Remain 08:21:10 loss: 2.0989 psnr: 20.3750 Lr: 1.17895e-03
[2025-02-17 18:30:54,401 INFO hook.py line 109 848561] Train: [48/100][100/605] Data 0.003 (0.002) Batch 0.951 (0.937) Remain 08:19:21 loss: 2.5163 psnr: 17.0898 Lr: 1.17626e-03
[2025-02-17 18:31:41,829 INFO hook.py line 109 848561] Train: [48/100][150/605] Data 0.002 (0.002) Batch 0.938 (0.941) Remain 08:20:36 loss: 2.2668 psnr: 17.7531 Lr: 1.17357e-03
[2025-02-17 18:32:28,763 INFO hook.py line 109 848561] Train: [48/100][200/605] Data 0.002 (0.002) Batch 0.939 (0.941) Remain 08:19:29 loss: 2.2318 psnr: 18.8810 Lr: 1.17088e-03
[2025-02-17 18:33:15,864 INFO hook.py line 109 848561] Train: [48/100][250/605] Data 0.002 (0.002) Batch 0.925 (0.941) Remain 08:18:52 loss: 2.4155 psnr: 16.5939 Lr: 1.16819e-03
[2025-02-17 18:34:02,749 INFO hook.py line 109 848561] Train: [48/100][300/605] Data 0.003 (0.002) Batch 0.945 (0.940) Remain 08:17:48 loss: 2.3618 psnr: 17.3277 Lr: 1.16549e-03
[2025-02-17 18:34:49,767 INFO hook.py line 109 848561] Train: [48/100][350/605] Data 0.002 (0.002) Batch 0.937 (0.940) Remain 08:17:01 loss: 2.4912 psnr: 17.2035 Lr: 1.16280e-03
[2025-02-17 18:35:36,447 INFO hook.py line 109 848561] Train: [48/100][400/605] Data 0.003 (0.002) Batch 0.908 (0.939) Remain 08:15:48 loss: 2.2582 psnr: 18.0410 Lr: 1.16010e-03
[2025-02-17 18:36:23,595 INFO hook.py line 109 848561] Train: [48/100][450/605] Data 0.003 (0.002) Batch 0.955 (0.940) Remain 08:15:13 loss: 2.4530 psnr: 16.6444 Lr: 1.15740e-03
[2025-02-17 18:37:10,611 INFO hook.py line 109 848561] Train: [48/100][500/605] Data 0.002 (0.002) Batch 0.942 (0.940) Remain 08:14:27 loss: 2.3155 psnr: 17.3266 Lr: 1.15470e-03
[2025-02-17 18:37:57,668 INFO hook.py line 109 848561] Train: [48/100][550/605] Data 0.002 (0.002) Batch 0.963 (0.940) Remain 08:13:44 loss: 1.8784 psnr: 22.4989 Lr: 1.15200e-03
[2025-02-17 18:38:43,571 INFO hook.py line 109 848561] Train: [48/100][600/605] Data 0.002 (0.002) Batch 0.850 (0.938) Remain 08:11:59 loss: 2.2062 psnr: 18.8458 Lr: 1.14930e-03
[2025-02-17 18:38:47,811 INFO misc.py line 135 848561] Train result: loss: 2.3113 rgb_loss: 0.8108 psnr: 17.6950 depth_loss: 0.0675 feat_loss: 1.4329 
[2025-02-17 18:38:47,812 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:39:39,162 INFO hook.py line 109 848561] Train: [49/100][50/605] Data 0.003 (0.002) Batch 0.969 (0.942) Remain 08:12:54 loss: 2.0290 psnr: 19.6320 Lr: 1.14633e-03
[2025-02-17 18:40:26,091 INFO hook.py line 109 848561] Train: [49/100][100/605] Data 0.003 (0.002) Batch 0.940 (0.940) Remain 08:11:19 loss: 2.2484 psnr: 17.6233 Lr: 1.14362e-03
[2025-02-17 18:41:12,894 INFO hook.py line 109 848561] Train: [49/100][150/605] Data 0.002 (0.002) Batch 1.044 (0.939) Remain 08:09:50 loss: 2.3066 psnr: 17.8017 Lr: 1.14092e-03
[2025-02-17 18:41:59,917 INFO hook.py line 109 848561] Train: [49/100][200/605] Data 0.002 (0.002) Batch 0.901 (0.939) Remain 08:09:17 loss: 2.2991 psnr: 17.9354 Lr: 1.13821e-03
[2025-02-17 18:42:46,985 INFO hook.py line 109 848561] Train: [49/100][250/605] Data 0.002 (0.002) Batch 0.929 (0.940) Remain 08:08:44 loss: 2.4142 psnr: 16.6562 Lr: 1.13550e-03
[2025-02-17 18:43:34,155 INFO hook.py line 109 848561] Train: [49/100][300/605] Data 0.003 (0.002) Batch 0.934 (0.940) Remain 08:08:17 loss: 2.1937 psnr: 18.2724 Lr: 1.13279e-03
[2025-02-17 18:44:21,307 INFO hook.py line 109 848561] Train: [49/100][350/605] Data 0.003 (0.002) Batch 0.937 (0.941) Remain 08:07:42 loss: 2.4067 psnr: 16.6157 Lr: 1.13009e-03
[2025-02-17 18:45:08,172 INFO hook.py line 109 848561] Train: [49/100][400/605] Data 0.002 (0.002) Batch 0.944 (0.940) Remain 08:06:42 loss: 2.3610 psnr: 17.5806 Lr: 1.12738e-03
[2025-02-17 18:45:55,410 INFO hook.py line 109 848561] Train: [49/100][450/605] Data 0.002 (0.002) Batch 0.955 (0.941) Remain 08:06:11 loss: 2.2101 psnr: 18.3274 Lr: 1.12466e-03
[2025-02-17 18:46:42,454 INFO hook.py line 109 848561] Train: [49/100][500/605] Data 0.002 (0.002) Batch 0.924 (0.941) Remain 08:05:25 loss: 2.2943 psnr: 17.6682 Lr: 1.12195e-03
[2025-02-17 18:47:29,380 INFO hook.py line 109 848561] Train: [49/100][550/605] Data 0.002 (0.002) Batch 0.947 (0.941) Remain 08:04:31 loss: 2.1354 psnr: 19.8515 Lr: 1.11924e-03
[2025-02-17 18:48:15,828 INFO hook.py line 109 848561] Train: [49/100][600/605] Data 0.002 (0.002) Batch 0.877 (0.940) Remain 08:03:14 loss: 2.3742 psnr: 17.6620 Lr: 1.11653e-03
[2025-02-17 18:48:20,113 INFO misc.py line 135 848561] Train result: loss: 2.3269 rgb_loss: 0.8267 psnr: 17.5595 depth_loss: 0.0675 feat_loss: 1.4327 
[2025-02-17 18:48:20,114 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:49:10,819 INFO hook.py line 109 848561] Train: [50/100][50/605] Data 0.003 (0.002) Batch 0.944 (0.936) Remain 08:00:18 loss: 2.0795 psnr: 19.3658 Lr: 1.11354e-03
[2025-02-17 18:49:57,673 INFO hook.py line 109 848561] Train: [50/100][100/605] Data 0.002 (0.002) Batch 0.946 (0.936) Remain 07:59:56 loss: 2.5218 psnr: 16.4295 Lr: 1.11082e-03
[2025-02-17 18:50:44,685 INFO hook.py line 109 848561] Train: [50/100][150/605] Data 0.003 (0.002) Batch 0.965 (0.938) Remain 07:59:50 loss: 2.0673 psnr: 19.1857 Lr: 1.10811e-03
[2025-02-17 18:51:32,217 INFO hook.py line 109 848561] Train: [50/100][200/605] Data 0.002 (0.002) Batch 0.936 (0.941) Remain 08:00:44 loss: 2.1672 psnr: 19.1400 Lr: 1.10539e-03
[2025-02-17 18:52:19,192 INFO hook.py line 109 848561] Train: [50/100][250/605] Data 0.002 (0.002) Batch 0.939 (0.941) Remain 07:59:48 loss: 2.1011 psnr: 19.6871 Lr: 1.10267e-03
[2025-02-17 18:53:06,153 INFO hook.py line 109 848561] Train: [50/100][300/605] Data 0.003 (0.002) Batch 0.924 (0.940) Remain 07:58:54 loss: 2.3872 psnr: 16.8114 Lr: 1.09995e-03
[2025-02-17 18:53:53,211 INFO hook.py line 109 848561] Train: [50/100][350/605] Data 0.003 (0.002) Batch 0.997 (0.941) Remain 07:58:10 loss: 2.1959 psnr: 17.9901 Lr: 1.09723e-03
[2025-02-17 18:54:39,969 INFO hook.py line 109 848561] Train: [50/100][400/605] Data 0.002 (0.002) Batch 0.939 (0.940) Remain 07:57:03 loss: 2.1321 psnr: 19.3533 Lr: 1.09451e-03
[2025-02-17 18:55:26,702 INFO hook.py line 109 848561] Train: [50/100][450/605] Data 0.002 (0.002) Batch 0.939 (0.939) Remain 07:55:58 loss: 2.2449 psnr: 18.0026 Lr: 1.09179e-03
[2025-02-17 18:56:13,457 INFO hook.py line 109 848561] Train: [50/100][500/605] Data 0.002 (0.002) Batch 0.917 (0.939) Remain 07:54:58 loss: 2.3711 psnr: 16.8912 Lr: 1.08907e-03
[2025-02-17 18:57:00,162 INFO hook.py line 109 848561] Train: [50/100][550/605] Data 0.003 (0.002) Batch 0.943 (0.938) Remain 07:53:58 loss: 2.2629 psnr: 18.3399 Lr: 1.08635e-03
[2025-02-17 18:57:46,109 INFO hook.py line 109 848561] Train: [50/100][600/605] Data 0.002 (0.002) Batch 0.846 (0.937) Remain 07:52:22 loss: 2.1909 psnr: 18.2751 Lr: 1.08362e-03
[2025-02-17 18:57:50,394 INFO misc.py line 135 848561] Train result: loss: 2.3185 rgb_loss: 0.8187 psnr: 17.6447 depth_loss: 0.0680 feat_loss: 1.4318 
[2025-02-17 18:57:50,395 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 18:58:41,465 INFO hook.py line 109 848561] Train: [51/100][50/605] Data 0.002 (0.002) Batch 0.934 (0.937) Remain 07:51:27 loss: 2.4862 psnr: 16.3439 Lr: 1.08063e-03
[2025-02-17 18:59:28,048 INFO hook.py line 109 848561] Train: [51/100][100/605] Data 0.003 (0.002) Batch 0.935 (0.934) Remain 07:49:22 loss: 2.2758 psnr: 17.5126 Lr: 1.07790e-03
[2025-02-17 19:00:15,129 INFO hook.py line 109 848561] Train: [51/100][150/605] Data 0.003 (0.002) Batch 0.970 (0.937) Remain 07:49:53 loss: 2.3284 psnr: 18.0364 Lr: 1.07518e-03
[2025-02-17 19:01:02,034 INFO hook.py line 109 848561] Train: [51/100][200/605] Data 0.002 (0.002) Batch 0.974 (0.937) Remain 07:49:17 loss: 2.1922 psnr: 18.2012 Lr: 1.07245e-03
[2025-02-17 19:01:49,167 INFO hook.py line 109 848561] Train: [51/100][250/605] Data 0.002 (0.002) Batch 0.905 (0.938) Remain 07:49:04 loss: 2.5138 psnr: 16.7077 Lr: 1.06973e-03
[2025-02-17 19:02:35,935 INFO hook.py line 109 848561] Train: [51/100][300/605] Data 0.002 (0.002) Batch 0.922 (0.938) Remain 07:48:03 loss: 2.3608 psnr: 17.4676 Lr: 1.06700e-03
[2025-02-17 19:03:22,933 INFO hook.py line 109 848561] Train: [51/100][350/605] Data 0.002 (0.002) Batch 0.973 (0.938) Remain 07:47:26 loss: 2.2856 psnr: 17.2294 Lr: 1.06427e-03
[2025-02-17 19:04:09,762 INFO hook.py line 109 848561] Train: [51/100][400/605] Data 0.001 (0.002) Batch 0.918 (0.938) Remain 07:46:34 loss: 2.6553 psnr: 15.5022 Lr: 1.06155e-03
[2025-02-17 19:04:56,835 INFO hook.py line 109 848561] Train: [51/100][450/605] Data 0.003 (0.002) Batch 0.928 (0.938) Remain 07:45:59 loss: 2.1006 psnr: 18.7973 Lr: 1.05882e-03
[2025-02-17 19:05:43,750 INFO hook.py line 109 848561] Train: [51/100][500/605] Data 0.002 (0.002) Batch 0.940 (0.938) Remain 07:45:12 loss: 2.1743 psnr: 18.2544 Lr: 1.05609e-03
[2025-02-17 19:06:30,756 INFO hook.py line 109 848561] Train: [51/100][550/605] Data 0.002 (0.002) Batch 0.954 (0.938) Remain 07:44:30 loss: 2.4586 psnr: 16.9448 Lr: 1.05336e-03
[2025-02-17 19:07:16,929 INFO hook.py line 109 848561] Train: [51/100][600/605] Data 0.003 (0.002) Batch 0.886 (0.937) Remain 07:43:06 loss: 2.2630 psnr: 17.1547 Lr: 1.05063e-03
[2025-02-17 19:07:21,306 INFO misc.py line 135 848561] Train result: loss: 2.3127 rgb_loss: 0.8170 psnr: 17.6098 depth_loss: 0.0675 feat_loss: 1.4281 
[2025-02-17 19:07:21,307 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 19:08:12,161 INFO hook.py line 109 848561] Train: [52/100][50/605] Data 0.002 (0.002) Batch 0.951 (0.936) Remain 07:41:53 loss: 2.2422 psnr: 17.7536 Lr: 1.04763e-03
[2025-02-17 19:08:58,858 INFO hook.py line 109 848561] Train: [52/100][100/605] Data 0.002 (0.002) Batch 0.940 (0.935) Remain 07:40:28 loss: 2.3012 psnr: 17.6133 Lr: 1.04490e-03
[2025-02-17 19:09:45,840 INFO hook.py line 109 848561] Train: [52/100][150/605] Data 0.003 (0.002) Batch 0.944 (0.937) Remain 07:40:27 loss: 2.4185 psnr: 16.9554 Lr: 1.04222e-03
[2025-02-17 19:10:32,570 INFO hook.py line 109 848561] Train: [52/100][200/605] Data 0.002 (0.002) Batch 0.917 (0.936) Remain 07:39:24 loss: 2.4025 psnr: 16.8261 Lr: 1.03949e-03
[2025-02-17 19:11:19,925 INFO hook.py line 109 848561] Train: [52/100][250/605] Data 0.003 (0.002) Batch 0.933 (0.938) Remain 07:39:43 loss: 2.4880 psnr: 16.4685 Lr: 1.03676e-03
[2025-02-17 19:12:06,738 INFO hook.py line 109 848561] Train: [52/100][300/605] Data 0.002 (0.002) Batch 0.928 (0.938) Remain 07:38:45 loss: 2.0761 psnr: 19.5431 Lr: 1.03403e-03
[2025-02-17 19:12:53,757 INFO hook.py line 109 848561] Train: [52/100][350/605] Data 0.002 (0.002) Batch 0.945 (0.938) Remain 07:38:08 loss: 2.2269 psnr: 17.7023 Lr: 1.03130e-03
[2025-02-17 19:13:40,610 INFO hook.py line 109 848561] Train: [52/100][400/605] Data 0.002 (0.002) Batch 0.937 (0.938) Remain 07:37:17 loss: 2.4795 psnr: 16.4842 Lr: 1.02857e-03
[2025-02-17 19:14:27,558 INFO hook.py line 109 848561] Train: [52/100][450/605] Data 0.003 (0.002) Batch 0.916 (0.938) Remain 07:36:32 loss: 2.4207 psnr: 15.6003 Lr: 1.02583e-03
[2025-02-17 19:15:14,458 INFO hook.py line 109 848561] Train: [52/100][500/605] Data 0.003 (0.002) Batch 0.919 (0.938) Remain 07:35:45 loss: 2.0939 psnr: 18.9886 Lr: 1.02310e-03
[2025-02-17 19:16:01,232 INFO hook.py line 109 848561] Train: [52/100][550/605] Data 0.003 (0.002) Batch 0.924 (0.938) Remain 07:34:50 loss: 2.3616 psnr: 17.2509 Lr: 1.02037e-03
[2025-02-17 19:16:47,583 INFO hook.py line 109 848561] Train: [52/100][600/605] Data 0.001 (0.002) Batch 0.875 (0.937) Remain 07:33:37 loss: 2.3055 psnr: 18.0173 Lr: 1.01764e-03
[2025-02-17 19:16:51,945 INFO misc.py line 135 848561] Train result: loss: 2.2997 rgb_loss: 0.8028 psnr: 17.7396 depth_loss: 0.0674 feat_loss: 1.4295 
[2025-02-17 19:16:51,946 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 19:17:42,828 INFO hook.py line 109 848561] Train: [53/100][50/605] Data 0.002 (0.002) Batch 0.940 (0.937) Remain 07:32:53 loss: 2.3181 psnr: 17.3371 Lr: 1.01463e-03
[2025-02-17 19:18:29,750 INFO hook.py line 109 848561] Train: [53/100][100/605] Data 0.002 (0.002) Batch 0.955 (0.938) Remain 07:32:23 loss: 2.2975 psnr: 17.5845 Lr: 1.01190e-03
[2025-02-17 19:19:16,400 INFO hook.py line 109 848561] Train: [53/100][150/605] Data 0.002 (0.002) Batch 0.941 (0.936) Remain 07:30:47 loss: 2.5338 psnr: 16.3541 Lr: 1.00922e-03
[2025-02-17 19:20:03,056 INFO hook.py line 109 848561] Train: [53/100][200/605] Data 0.003 (0.002) Batch 0.913 (0.935) Remain 07:29:38 loss: 2.3598 psnr: 17.0740 Lr: 1.00649e-03
[2025-02-17 19:20:49,826 INFO hook.py line 109 848561] Train: [53/100][250/605] Data 0.002 (0.002) Batch 0.930 (0.935) Remain 07:28:51 loss: 2.2047 psnr: 17.9853 Lr: 1.00375e-03
[2025-02-17 19:21:37,353 INFO hook.py line 109 848561] Train: [53/100][300/605] Data 0.002 (0.002) Batch 0.910 (0.938) Remain 07:29:17 loss: 2.5963 psnr: 16.2268 Lr: 1.00102e-03
[2025-02-17 19:22:24,418 INFO hook.py line 109 848561] Train: [53/100][350/605] Data 0.003 (0.002) Batch 0.929 (0.938) Remain 07:28:44 loss: 2.3753 psnr: 17.2971 Lr: 9.98288e-04
[2025-02-17 19:23:11,468 INFO hook.py line 109 848561] Train: [53/100][400/605] Data 0.003 (0.002) Batch 0.947 (0.939) Remain 07:28:06 loss: 2.4334 psnr: 17.1014 Lr: 9.95555e-04
[2025-02-17 19:23:58,517 INFO hook.py line 109 848561] Train: [53/100][450/605] Data 0.001 (0.002) Batch 0.977 (0.939) Remain 07:27:26 loss: 2.1590 psnr: 18.6610 Lr: 9.92822e-04
[2025-02-17 19:24:45,555 INFO hook.py line 109 848561] Train: [53/100][500/605] Data 0.001 (0.002) Batch 0.922 (0.939) Remain 07:26:44 loss: 2.0963 psnr: 19.6139 Lr: 9.90089e-04
[2025-02-17 19:25:32,575 INFO hook.py line 109 848561] Train: [53/100][550/605] Data 0.002 (0.002) Batch 0.937 (0.939) Remain 07:26:00 loss: 1.9105 psnr: 21.3460 Lr: 9.87357e-04
[2025-02-17 19:26:18,719 INFO hook.py line 109 848561] Train: [53/100][600/605] Data 0.002 (0.002) Batch 0.861 (0.938) Remain 07:24:34 loss: 2.1979 psnr: 18.9009 Lr: 9.84624e-04
[2025-02-17 19:26:22,964 INFO misc.py line 135 848561] Train result: loss: 2.3068 rgb_loss: 0.8113 psnr: 17.6891 depth_loss: 0.0684 feat_loss: 1.4272 
[2025-02-17 19:26:22,965 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 19:27:13,797 INFO hook.py line 109 848561] Train: [54/100][50/605] Data 0.002 (0.002) Batch 0.906 (0.936) Remain 07:23:02 loss: 2.1051 psnr: 19.2626 Lr: 9.81618e-04
[2025-02-17 19:28:00,983 INFO hook.py line 109 848561] Train: [54/100][100/605] Data 0.002 (0.002) Batch 0.930 (0.940) Remain 07:24:01 loss: 2.3241 psnr: 17.4046 Lr: 9.78886e-04
[2025-02-17 19:28:48,045 INFO hook.py line 109 848561] Train: [54/100][150/605] Data 0.003 (0.002) Batch 0.909 (0.941) Remain 07:23:23 loss: 2.2337 psnr: 18.7716 Lr: 9.76153e-04
[2025-02-17 19:29:35,051 INFO hook.py line 109 848561] Train: [54/100][200/605] Data 0.002 (0.002) Batch 0.936 (0.940) Remain 07:22:33 loss: 2.1508 psnr: 18.5223 Lr: 9.73421e-04
[2025-02-17 19:30:21,858 INFO hook.py line 109 848561] Train: [54/100][250/605] Data 0.004 (0.002) Batch 0.933 (0.940) Remain 07:21:21 loss: 2.3054 psnr: 17.7330 Lr: 9.70689e-04
[2025-02-17 19:31:08,770 INFO hook.py line 109 848561] Train: [54/100][300/605] Data 0.002 (0.002) Batch 0.980 (0.939) Remain 07:20:28 loss: 2.4830 psnr: 16.5982 Lr: 9.67958e-04
[2025-02-17 19:31:55,756 INFO hook.py line 109 848561] Train: [54/100][350/605] Data 0.002 (0.002) Batch 0.971 (0.939) Remain 07:19:43 loss: 2.1926 psnr: 18.3070 Lr: 9.65226e-04
[2025-02-17 19:32:42,747 INFO hook.py line 109 848561] Train: [54/100][400/605] Data 0.002 (0.002) Batch 0.958 (0.939) Remain 07:18:57 loss: 2.2061 psnr: 18.9135 Lr: 9.62495e-04
[2025-02-17 19:33:29,845 INFO hook.py line 109 848561] Train: [54/100][450/605] Data 0.003 (0.002) Batch 0.948 (0.940) Remain 07:18:18 loss: 2.2681 psnr: 18.2066 Lr: 9.59764e-04
[2025-02-17 19:34:16,408 INFO hook.py line 109 848561] Train: [54/100][500/605] Data 0.002 (0.002) Batch 0.929 (0.939) Remain 07:17:07 loss: 2.1818 psnr: 18.9193 Lr: 9.57033e-04
[2025-02-17 19:35:03,307 INFO hook.py line 109 848561] Train: [54/100][550/605] Data 0.002 (0.002) Batch 0.936 (0.939) Remain 07:16:18 loss: 2.1169 psnr: 19.3739 Lr: 9.54358e-04
[2025-02-17 19:35:49,452 INFO hook.py line 109 848561] Train: [54/100][600/605] Data 0.002 (0.002) Batch 0.875 (0.937) Remain 07:14:54 loss: 2.2494 psnr: 16.6636 Lr: 9.51628e-04
[2025-02-17 19:35:53,745 INFO misc.py line 135 848561] Train result: loss: 2.3127 rgb_loss: 0.8177 psnr: 17.6219 depth_loss: 0.0672 feat_loss: 1.4278 
[2025-02-17 19:35:53,746 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 19:36:44,658 INFO hook.py line 109 848561] Train: [55/100][50/605] Data 0.003 (0.002) Batch 0.946 (0.942) Remain 07:15:59 loss: 2.5177 psnr: 15.9399 Lr: 9.48625e-04
[2025-02-17 19:37:31,564 INFO hook.py line 109 848561] Train: [55/100][100/605] Data 0.001 (0.002) Batch 0.922 (0.940) Remain 07:14:21 loss: 2.1267 psnr: 18.9245 Lr: 9.45896e-04
[2025-02-17 19:38:18,649 INFO hook.py line 109 848561] Train: [55/100][150/605] Data 0.002 (0.002) Batch 0.931 (0.940) Remain 07:13:52 loss: 2.0826 psnr: 20.0322 Lr: 9.43167e-04
[2025-02-17 19:39:05,356 INFO hook.py line 109 848561] Train: [55/100][200/605] Data 0.002 (0.002) Batch 0.935 (0.939) Remain 07:12:20 loss: 2.2415 psnr: 17.7801 Lr: 9.40439e-04
[2025-02-17 19:39:52,325 INFO hook.py line 109 848561] Train: [55/100][250/605] Data 0.002 (0.002) Batch 0.923 (0.939) Remain 07:11:36 loss: 2.1782 psnr: 19.4587 Lr: 9.37711e-04
[2025-02-17 19:40:39,089 INFO hook.py line 109 848561] Train: [55/100][300/605] Data 0.002 (0.002) Batch 0.919 (0.938) Remain 07:10:32 loss: 2.3472 psnr: 17.6328 Lr: 9.34984e-04
[2025-02-17 19:41:26,243 INFO hook.py line 109 848561] Train: [55/100][350/605] Data 0.002 (0.002) Batch 0.961 (0.939) Remain 07:10:04 loss: 2.6158 psnr: 15.5943 Lr: 9.32257e-04
[2025-02-17 19:42:13,020 INFO hook.py line 109 848561] Train: [55/100][400/605] Data 0.002 (0.002) Batch 0.940 (0.939) Remain 07:09:05 loss: 2.3378 psnr: 18.2394 Lr: 9.29530e-04
[2025-02-17 19:43:00,023 INFO hook.py line 109 848561] Train: [55/100][450/605] Data 0.003 (0.002) Batch 0.960 (0.939) Remain 07:08:23 loss: 2.2856 psnr: 17.2236 Lr: 9.26804e-04
[2025-02-17 19:43:46,827 INFO hook.py line 109 848561] Train: [55/100][500/605] Data 0.003 (0.002) Batch 0.930 (0.938) Remain 07:07:28 loss: 2.4678 psnr: 16.0846 Lr: 9.24079e-04
[2025-02-17 19:44:33,905 INFO hook.py line 109 848561] Train: [55/100][550/605] Data 0.002 (0.002) Batch 0.959 (0.939) Remain 07:06:49 loss: 2.4612 psnr: 16.8468 Lr: 9.21354e-04
[2025-02-17 19:45:20,094 INFO hook.py line 109 848561] Train: [55/100][600/605] Data 0.002 (0.002) Batch 0.870 (0.938) Remain 07:05:28 loss: 2.0487 psnr: 19.1274 Lr: 9.18630e-04
[2025-02-17 19:45:24,458 INFO misc.py line 135 848561] Train result: loss: 2.3040 rgb_loss: 0.8101 psnr: 17.6679 depth_loss: 0.0675 feat_loss: 1.4263 
[2025-02-17 19:45:24,459 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 19:46:15,332 INFO hook.py line 109 848561] Train: [56/100][50/605] Data 0.002 (0.002) Batch 0.973 (0.940) Remain 07:05:55 loss: 2.4080 psnr: 16.6683 Lr: 9.15634e-04
[2025-02-17 19:47:02,091 INFO hook.py line 109 848561] Train: [56/100][100/605] Data 0.002 (0.002) Batch 0.938 (0.938) Remain 07:03:55 loss: 2.0934 psnr: 19.5725 Lr: 9.12911e-04
[2025-02-17 19:47:48,839 INFO hook.py line 109 848561] Train: [56/100][150/605] Data 0.002 (0.002) Batch 0.953 (0.937) Remain 07:02:43 loss: 2.4586 psnr: 15.6722 Lr: 9.10189e-04
[2025-02-17 19:48:35,720 INFO hook.py line 109 848561] Train: [56/100][200/605] Data 0.003 (0.002) Batch 0.950 (0.937) Remain 07:02:02 loss: 2.1095 psnr: 18.5719 Lr: 9.07467e-04
[2025-02-17 19:49:22,652 INFO hook.py line 109 848561] Train: [56/100][250/605] Data 0.003 (0.002) Batch 0.933 (0.937) Remain 07:01:24 loss: 2.2832 psnr: 17.6872 Lr: 9.04746e-04
[2025-02-17 19:50:09,243 INFO hook.py line 109 848561] Train: [56/100][300/605] Data 0.002 (0.002) Batch 0.943 (0.936) Remain 07:00:12 loss: 2.3942 psnr: 17.4120 Lr: 9.02026e-04
[2025-02-17 19:50:56,570 INFO hook.py line 109 848561] Train: [56/100][350/605] Data 0.003 (0.002) Batch 0.935 (0.938) Remain 07:00:04 loss: 2.3900 psnr: 17.0057 Lr: 8.99307e-04
[2025-02-17 19:51:43,471 INFO hook.py line 109 848561] Train: [56/100][400/605] Data 0.003 (0.002) Batch 0.939 (0.938) Remain 06:59:18 loss: 2.3180 psnr: 17.6775 Lr: 8.96588e-04
[2025-02-17 19:52:30,192 INFO hook.py line 109 848561] Train: [56/100][450/605] Data 0.002 (0.002) Batch 0.939 (0.937) Remain 06:58:21 loss: 2.2707 psnr: 17.3520 Lr: 8.93870e-04
[2025-02-17 19:53:17,138 INFO hook.py line 109 848561] Train: [56/100][500/605] Data 0.002 (0.002) Batch 0.968 (0.938) Remain 06:57:38 loss: 2.5094 psnr: 17.4798 Lr: 8.91153e-04
[2025-02-17 19:54:04,201 INFO hook.py line 109 848561] Train: [56/100][550/605] Data 0.002 (0.002) Batch 0.926 (0.938) Remain 06:57:00 loss: 2.3635 psnr: 16.7598 Lr: 8.88437e-04
[2025-02-17 19:54:50,438 INFO hook.py line 109 848561] Train: [56/100][600/605] Data 0.003 (0.002) Batch 0.875 (0.937) Remain 06:55:43 loss: 2.3082 psnr: 17.9856 Lr: 8.85721e-04
[2025-02-17 19:54:54,729 INFO misc.py line 135 848561] Train result: loss: 2.3056 rgb_loss: 0.8145 psnr: 17.6324 depth_loss: 0.0662 feat_loss: 1.4249 
[2025-02-17 19:54:54,730 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 19:55:45,836 INFO hook.py line 109 848561] Train: [57/100][50/605] Data 0.002 (0.003) Batch 0.936 (0.934) Remain 06:53:36 loss: 2.0776 psnr: 20.0937 Lr: 8.82735e-04
[2025-02-17 19:56:32,484 INFO hook.py line 109 848561] Train: [57/100][100/605] Data 0.003 (0.002) Batch 0.939 (0.933) Remain 06:52:35 loss: 2.1972 psnr: 18.4511 Lr: 8.80021e-04
[2025-02-17 19:57:19,448 INFO hook.py line 109 848561] Train: [57/100][150/605] Data 0.003 (0.002) Batch 0.930 (0.935) Remain 06:52:41 loss: 2.2959 psnr: 17.5076 Lr: 8.77309e-04
[2025-02-17 19:58:06,454 INFO hook.py line 109 848561] Train: [57/100][200/605] Data 0.003 (0.002) Batch 0.943 (0.937) Remain 06:52:25 loss: 2.4214 psnr: 17.1446 Lr: 8.74597e-04
[2025-02-17 19:58:53,287 INFO hook.py line 109 848561] Train: [57/100][250/605] Data 0.002 (0.002) Batch 0.951 (0.937) Remain 06:51:38 loss: 2.3757 psnr: 17.1407 Lr: 8.71886e-04
[2025-02-17 19:59:40,337 INFO hook.py line 109 848561] Train: [57/100][300/605] Data 0.003 (0.002) Batch 0.926 (0.937) Remain 06:51:11 loss: 2.3756 psnr: 17.1908 Lr: 8.69176e-04
[2025-02-17 20:00:27,342 INFO hook.py line 109 848561] Train: [57/100][350/605] Data 0.002 (0.002) Batch 0.947 (0.938) Remain 06:50:34 loss: 2.3630 psnr: 17.3933 Lr: 8.66467e-04
[2025-02-17 20:01:14,520 INFO hook.py line 109 848561] Train: [57/100][400/605] Data 0.003 (0.002) Batch 0.957 (0.938) Remain 06:50:07 loss: 2.1586 psnr: 18.7844 Lr: 8.63759e-04
[2025-02-17 20:02:01,495 INFO hook.py line 109 848561] Train: [57/100][450/605] Data 0.003 (0.002) Batch 0.949 (0.939) Remain 06:49:23 loss: 2.2155 psnr: 18.5982 Lr: 8.61052e-04
[2025-02-17 20:02:48,367 INFO hook.py line 109 848561] Train: [57/100][500/605] Data 0.002 (0.002) Batch 0.954 (0.938) Remain 06:48:33 loss: 2.1703 psnr: 18.5359 Lr: 8.58346e-04
[2025-02-17 20:03:35,482 INFO hook.py line 109 848561] Train: [57/100][550/605] Data 0.003 (0.002) Batch 0.960 (0.939) Remain 06:47:55 loss: 2.1629 psnr: 18.7523 Lr: 8.55641e-04
[2025-02-17 20:04:21,506 INFO hook.py line 109 848561] Train: [57/100][600/605] Data 0.002 (0.002) Batch 0.853 (0.937) Remain 06:46:28 loss: 2.1943 psnr: 17.9024 Lr: 8.52937e-04
[2025-02-17 20:04:25,833 INFO misc.py line 135 848561] Train result: loss: 2.2933 rgb_loss: 0.8000 psnr: 17.7752 depth_loss: 0.0665 feat_loss: 1.4268 
[2025-02-17 20:04:25,835 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 20:05:16,785 INFO hook.py line 109 848561] Train: [58/100][50/605] Data 0.002 (0.003) Batch 0.958 (0.937) Remain 06:45:38 loss: 2.1327 psnr: 18.9895 Lr: 8.49964e-04
[2025-02-17 20:06:03,736 INFO hook.py line 109 848561] Train: [58/100][100/605] Data 0.002 (0.003) Batch 0.986 (0.938) Remain 06:45:13 loss: 2.1562 psnr: 17.8090 Lr: 8.47263e-04
[2025-02-17 20:06:50,656 INFO hook.py line 109 848561] Train: [58/100][150/605] Data 0.003 (0.003) Batch 0.940 (0.938) Remain 06:44:28 loss: 2.2872 psnr: 17.3861 Lr: 8.44562e-04
[2025-02-17 20:07:37,685 INFO hook.py line 109 848561] Train: [58/100][200/605] Data 0.002 (0.002) Batch 0.925 (0.939) Remain 06:43:56 loss: 2.6094 psnr: 15.7239 Lr: 8.41863e-04
[2025-02-17 20:08:24,324 INFO hook.py line 109 848561] Train: [58/100][250/605] Data 0.002 (0.002) Batch 0.914 (0.938) Remain 06:42:38 loss: 2.1487 psnr: 18.8484 Lr: 8.39165e-04
[2025-02-17 20:09:11,246 INFO hook.py line 109 848561] Train: [58/100][300/605] Data 0.003 (0.002) Batch 0.920 (0.938) Remain 06:41:54 loss: 2.1498 psnr: 18.5011 Lr: 8.36468e-04
[2025-02-17 20:09:58,312 INFO hook.py line 109 848561] Train: [58/100][350/605] Data 0.003 (0.002) Batch 0.979 (0.938) Remain 06:41:20 loss: 2.1340 psnr: 19.1858 Lr: 8.33773e-04
[2025-02-17 20:10:45,477 INFO hook.py line 109 848561] Train: [58/100][400/605] Data 0.002 (0.002) Batch 0.948 (0.939) Remain 06:40:50 loss: 2.2415 psnr: 17.4481 Lr: 8.31079e-04
[2025-02-17 20:11:32,373 INFO hook.py line 109 848561] Train: [58/100][450/605] Data 0.002 (0.002) Batch 0.941 (0.939) Remain 06:40:00 loss: 2.4329 psnr: 17.0060 Lr: 8.28386e-04
[2025-02-17 20:12:19,213 INFO hook.py line 109 848561] Train: [58/100][500/605] Data 0.003 (0.002) Batch 0.950 (0.939) Remain 06:39:08 loss: 2.3782 psnr: 17.5531 Lr: 8.25694e-04
[2025-02-17 20:13:06,278 INFO hook.py line 109 848561] Train: [58/100][550/605] Data 0.003 (0.002) Batch 0.952 (0.939) Remain 06:38:27 loss: 2.4080 psnr: 16.1527 Lr: 8.23003e-04
[2025-02-17 20:13:52,406 INFO hook.py line 109 848561] Train: [58/100][600/605] Data 0.002 (0.002) Batch 0.856 (0.937) Remain 06:37:06 loss: 2.2972 psnr: 17.7042 Lr: 8.20314e-04
[2025-02-17 20:13:56,672 INFO misc.py line 135 848561] Train result: loss: 2.2876 rgb_loss: 0.7991 psnr: 17.7574 depth_loss: 0.0660 feat_loss: 1.4225 
[2025-02-17 20:13:56,673 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 20:14:47,468 INFO hook.py line 109 848561] Train: [59/100][50/605] Data 0.002 (0.002) Batch 0.954 (0.934) Remain 06:34:34 loss: 2.4522 psnr: 16.7277 Lr: 8.17358e-04
[2025-02-17 20:15:34,200 INFO hook.py line 109 848561] Train: [59/100][100/605] Data 0.003 (0.002) Batch 0.931 (0.934) Remain 06:34:02 loss: 2.1823 psnr: 19.1737 Lr: 8.14671e-04
[2025-02-17 20:16:21,189 INFO hook.py line 109 848561] Train: [59/100][150/605] Data 0.004 (0.002) Batch 0.947 (0.936) Remain 06:34:04 loss: 2.2217 psnr: 18.2636 Lr: 8.11986e-04
[2025-02-17 20:17:08,380 INFO hook.py line 109 848561] Train: [59/100][200/605] Data 0.002 (0.002) Batch 0.948 (0.938) Remain 06:34:07 loss: 2.2095 psnr: 17.9804 Lr: 8.09303e-04
[2025-02-17 20:17:55,187 INFO hook.py line 109 848561] Train: [59/100][250/605] Data 0.002 (0.002) Batch 0.931 (0.938) Remain 06:33:10 loss: 2.3480 psnr: 17.5026 Lr: 8.06621e-04
[2025-02-17 20:18:42,310 INFO hook.py line 109 848561] Train: [59/100][300/605] Data 0.002 (0.002) Batch 0.948 (0.938) Remain 06:32:44 loss: 2.3669 psnr: 16.9762 Lr: 8.03940e-04
[2025-02-17 20:19:28,950 INFO hook.py line 109 848561] Train: [59/100][350/605] Data 0.002 (0.002) Batch 0.914 (0.938) Remain 06:31:37 loss: 2.5126 psnr: 16.1863 Lr: 8.01261e-04
[2025-02-17 20:20:16,004 INFO hook.py line 109 848561] Train: [59/100][400/605] Data 0.003 (0.002) Batch 0.934 (0.938) Remain 06:31:01 loss: 2.2639 psnr: 18.0096 Lr: 7.98583e-04
[2025-02-17 20:21:03,219 INFO hook.py line 109 848561] Train: [59/100][450/605] Data 0.003 (0.002) Batch 0.938 (0.939) Remain 06:30:31 loss: 2.1157 psnr: 19.0656 Lr: 7.95907e-04
[2025-02-17 20:21:50,444 INFO hook.py line 109 848561] Train: [59/100][500/605] Data 0.002 (0.002) Batch 0.931 (0.939) Remain 06:29:58 loss: 2.0535 psnr: 18.8782 Lr: 7.93232e-04
[2025-02-17 20:22:37,164 INFO hook.py line 109 848561] Train: [59/100][550/605] Data 0.002 (0.002) Batch 0.930 (0.939) Remain 06:29:00 loss: 2.0536 psnr: 19.4582 Lr: 7.90559e-04
[2025-02-17 20:23:23,411 INFO hook.py line 109 848561] Train: [59/100][600/605] Data 0.003 (0.002) Batch 0.856 (0.938) Remain 06:27:44 loss: 2.5581 psnr: 15.8503 Lr: 7.87887e-04
[2025-02-17 20:23:27,759 INFO misc.py line 135 848561] Train result: loss: 2.2818 rgb_loss: 0.7934 psnr: 17.8119 depth_loss: 0.0666 feat_loss: 1.4217 
[2025-02-17 20:23:27,761 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 20:24:18,472 INFO hook.py line 109 848561] Train: [60/100][50/605] Data 0.002 (0.002) Batch 0.916 (0.932) Remain 06:24:29 loss: 2.4653 psnr: 16.4953 Lr: 7.84951e-04
[2025-02-17 20:25:05,039 INFO hook.py line 109 848561] Train: [60/100][100/605] Data 0.002 (0.002) Batch 0.905 (0.932) Remain 06:23:35 loss: 2.2556 psnr: 18.2960 Lr: 7.82282e-04
[2025-02-17 20:25:52,264 INFO hook.py line 109 848561] Train: [60/100][150/605] Data 0.003 (0.002) Batch 0.946 (0.936) Remain 06:24:37 loss: 2.1270 psnr: 19.4030 Lr: 7.79616e-04
[2025-02-17 20:26:39,232 INFO hook.py line 109 848561] Train: [60/100][200/605] Data 0.002 (0.002) Batch 0.944 (0.937) Remain 06:24:11 loss: 2.3696 psnr: 17.1574 Lr: 7.76951e-04
[2025-02-17 20:27:26,299 INFO hook.py line 109 848561] Train: [60/100][250/605] Data 0.002 (0.002) Batch 0.941 (0.938) Remain 06:23:46 loss: 2.2746 psnr: 17.5125 Lr: 7.74288e-04
[2025-02-17 20:28:13,080 INFO hook.py line 109 848561] Train: [60/100][300/605] Data 0.002 (0.002) Batch 0.946 (0.937) Remain 06:22:50 loss: 2.0540 psnr: 19.6002 Lr: 7.71626e-04
[2025-02-17 20:29:00,123 INFO hook.py line 109 848561] Train: [60/100][350/605] Data 0.003 (0.002) Batch 0.944 (0.938) Remain 06:22:16 loss: 2.2612 psnr: 17.8819 Lr: 7.68966e-04
[2025-02-17 20:29:47,139 INFO hook.py line 109 848561] Train: [60/100][400/605] Data 0.003 (0.002) Batch 0.934 (0.938) Remain 06:21:36 loss: 2.4552 psnr: 16.3992 Lr: 7.66308e-04
[2025-02-17 20:30:34,361 INFO hook.py line 109 848561] Train: [60/100][450/605] Data 0.002 (0.002) Batch 0.925 (0.939) Remain 06:21:06 loss: 2.4272 psnr: 16.8360 Lr: 7.63651e-04
[2025-02-17 20:31:21,541 INFO hook.py line 109 848561] Train: [60/100][500/605] Data 0.003 (0.002) Batch 0.928 (0.939) Remain 06:20:31 loss: 2.3383 psnr: 17.6759 Lr: 7.60997e-04
[2025-02-17 20:32:08,492 INFO hook.py line 109 848561] Train: [60/100][550/605] Data 0.003 (0.002) Batch 0.953 (0.939) Remain 06:19:43 loss: 2.2889 psnr: 18.0691 Lr: 7.58344e-04
[2025-02-17 20:32:54,857 INFO hook.py line 109 848561] Train: [60/100][600/605] Data 0.001 (0.002) Batch 0.859 (0.938) Remain 06:18:32 loss: 2.2811 psnr: 17.8894 Lr: 7.55693e-04
[2025-02-17 20:32:59,230 INFO misc.py line 135 848561] Train result: loss: 2.2816 rgb_loss: 0.7926 psnr: 17.8262 depth_loss: 0.0667 feat_loss: 1.4223 
[2025-02-17 20:32:59,231 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 20:33:50,044 INFO hook.py line 109 848561] Train: [61/100][50/605] Data 0.002 (0.002) Batch 0.941 (0.938) Remain 06:17:41 loss: 2.2255 psnr: 17.8541 Lr: 7.52779e-04
[2025-02-17 20:34:36,973 INFO hook.py line 109 848561] Train: [61/100][100/605] Data 0.002 (0.002) Batch 0.930 (0.938) Remain 06:16:56 loss: 2.3579 psnr: 17.1361 Lr: 7.50132e-04
[2025-02-17 20:35:24,017 INFO hook.py line 109 848561] Train: [61/100][150/605] Data 0.004 (0.002) Batch 0.946 (0.939) Remain 06:16:29 loss: 2.2553 psnr: 18.6147 Lr: 7.47486e-04
[2025-02-17 20:36:11,176 INFO hook.py line 109 848561] Train: [61/100][200/605] Data 0.002 (0.002) Batch 0.928 (0.940) Remain 06:16:06 loss: 2.6267 psnr: 15.8520 Lr: 7.44843e-04
[2025-02-17 20:36:58,362 INFO hook.py line 109 848561] Train: [61/100][250/605] Data 0.002 (0.002) Batch 0.926 (0.941) Remain 06:15:36 loss: 2.1499 psnr: 18.5591 Lr: 7.42201e-04
[2025-02-17 20:37:45,339 INFO hook.py line 109 848561] Train: [61/100][300/605] Data 0.002 (0.002) Batch 0.930 (0.941) Remain 06:14:43 loss: 2.3506 psnr: 17.5134 Lr: 7.39562e-04
[2025-02-17 20:38:32,261 INFO hook.py line 109 848561] Train: [61/100][350/605] Data 0.004 (0.002) Batch 0.930 (0.940) Remain 06:13:48 loss: 2.2100 psnr: 18.3656 Lr: 7.36924e-04
[2025-02-17 20:39:19,498 INFO hook.py line 109 848561] Train: [61/100][400/605] Data 0.002 (0.002) Batch 0.927 (0.941) Remain 06:13:14 loss: 2.2756 psnr: 18.1604 Lr: 7.34288e-04
[2025-02-17 20:40:06,333 INFO hook.py line 109 848561] Train: [61/100][450/605] Data 0.002 (0.002) Batch 0.951 (0.940) Remain 06:12:16 loss: 2.3116 psnr: 17.1501 Lr: 7.31654e-04
[2025-02-17 20:40:53,528 INFO hook.py line 109 848561] Train: [61/100][500/605] Data 0.003 (0.002) Batch 0.919 (0.941) Remain 06:11:37 loss: 2.3701 psnr: 16.7943 Lr: 7.29023e-04
[2025-02-17 20:41:40,937 INFO hook.py line 109 848561] Train: [61/100][550/605] Data 0.001 (0.002) Batch 0.941 (0.941) Remain 06:11:06 loss: 2.5461 psnr: 16.3786 Lr: 7.26393e-04
[2025-02-17 20:42:27,125 INFO hook.py line 109 848561] Train: [61/100][600/605] Data 0.002 (0.002) Batch 0.866 (0.940) Remain 06:09:44 loss: 2.3484 psnr: 16.9795 Lr: 7.23765e-04
[2025-02-17 20:42:31,478 INFO misc.py line 135 848561] Train result: loss: 2.2901 rgb_loss: 0.8027 psnr: 17.7182 depth_loss: 0.0657 feat_loss: 1.4217 
[2025-02-17 20:42:31,479 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 20:43:22,498 INFO hook.py line 109 848561] Train: [62/100][50/605] Data 0.003 (0.002) Batch 0.948 (0.937) Remain 06:07:34 loss: 2.2162 psnr: 18.7450 Lr: 7.20877e-04
[2025-02-17 20:44:09,350 INFO hook.py line 109 848561] Train: [62/100][100/605] Data 0.005 (0.002) Batch 0.925 (0.937) Remain 06:06:51 loss: 2.2112 psnr: 18.4178 Lr: 7.18254e-04
[2025-02-17 20:44:56,230 INFO hook.py line 109 848561] Train: [62/100][150/605] Data 0.002 (0.002) Batch 0.922 (0.937) Remain 06:06:10 loss: 2.2125 psnr: 18.2887 Lr: 7.15633e-04
[2025-02-17 20:45:42,986 INFO hook.py line 109 848561] Train: [62/100][200/605] Data 0.002 (0.002) Batch 0.896 (0.937) Remain 06:05:12 loss: 2.3802 psnr: 17.1602 Lr: 7.13014e-04
[2025-02-17 20:46:29,837 INFO hook.py line 109 848561] Train: [62/100][250/605] Data 0.002 (0.002) Batch 0.959 (0.937) Remain 06:04:27 loss: 2.2469 psnr: 17.4046 Lr: 7.10397e-04
[2025-02-17 20:47:16,855 INFO hook.py line 109 848561] Train: [62/100][300/605] Data 0.002 (0.002) Batch 0.926 (0.937) Remain 06:03:54 loss: 2.1520 psnr: 18.5614 Lr: 7.07782e-04
[2025-02-17 20:48:03,890 INFO hook.py line 109 848561] Train: [62/100][350/605] Data 0.002 (0.002) Batch 0.969 (0.938) Remain 06:03:19 loss: 2.1670 psnr: 19.1276 Lr: 7.05169e-04
[2025-02-17 20:48:51,029 INFO hook.py line 109 848561] Train: [62/100][400/605] Data 0.002 (0.002) Batch 0.937 (0.938) Remain 06:02:46 loss: 2.0731 psnr: 19.9078 Lr: 7.02559e-04
[2025-02-17 20:49:38,071 INFO hook.py line 109 848561] Train: [62/100][450/605] Data 0.003 (0.002) Batch 0.932 (0.939) Remain 06:02:06 loss: 2.1429 psnr: 18.7630 Lr: 6.99951e-04
[2025-02-17 20:50:25,493 INFO hook.py line 109 848561] Train: [62/100][500/605] Data 0.003 (0.002) Batch 0.948 (0.940) Remain 06:01:41 loss: 2.5650 psnr: 15.7523 Lr: 6.97345e-04
[2025-02-17 20:51:12,505 INFO hook.py line 109 848561] Train: [62/100][550/605] Data 0.004 (0.002) Batch 0.904 (0.940) Remain 06:00:56 loss: 2.2093 psnr: 18.2406 Lr: 6.94741e-04
[2025-02-17 20:51:58,786 INFO hook.py line 109 848561] Train: [62/100][600/605] Data 0.001 (0.002) Batch 0.867 (0.939) Remain 05:59:41 loss: 2.3239 psnr: 17.7181 Lr: 6.92140e-04
[2025-02-17 20:52:03,135 INFO misc.py line 135 848561] Train result: loss: 2.2729 rgb_loss: 0.7881 psnr: 17.8649 depth_loss: 0.0649 feat_loss: 1.4199 
[2025-02-17 20:52:03,137 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 20:52:54,441 INFO hook.py line 109 848561] Train: [63/100][50/605] Data 0.004 (0.003) Batch 0.943 (0.941) Remain 05:59:55 loss: 2.3620 psnr: 17.2630 Lr: 6.89281e-04
[2025-02-17 20:53:41,461 INFO hook.py line 109 848561] Train: [63/100][100/605] Data 0.002 (0.002) Batch 0.926 (0.941) Remain 05:58:56 loss: 2.1793 psnr: 18.5424 Lr: 6.86685e-04
[2025-02-17 20:54:28,408 INFO hook.py line 109 848561] Train: [63/100][150/605] Data 0.002 (0.002) Batch 0.945 (0.940) Remain 05:57:54 loss: 2.5127 psnr: 16.4162 Lr: 6.84090e-04
[2025-02-17 20:55:15,478 INFO hook.py line 109 848561] Train: [63/100][200/605] Data 0.002 (0.002) Batch 0.932 (0.941) Remain 05:57:14 loss: 1.9713 psnr: 20.5902 Lr: 6.81499e-04
[2025-02-17 20:56:02,120 INFO hook.py line 109 848561] Train: [63/100][250/605] Data 0.002 (0.002) Batch 0.964 (0.939) Remain 05:55:52 loss: 2.2535 psnr: 17.8797 Lr: 6.78909e-04
[2025-02-17 20:56:49,277 INFO hook.py line 109 848561] Train: [63/100][300/605] Data 0.003 (0.002) Batch 0.928 (0.940) Remain 05:55:21 loss: 2.2689 psnr: 18.0128 Lr: 6.76322e-04
[2025-02-17 20:57:36,250 INFO hook.py line 109 848561] Train: [63/100][350/605] Data 0.002 (0.002) Batch 0.923 (0.940) Remain 05:54:33 loss: 2.3260 psnr: 19.0960 Lr: 6.73737e-04
[2025-02-17 20:58:22,965 INFO hook.py line 109 848561] Train: [63/100][400/605] Data 0.002 (0.002) Batch 0.925 (0.939) Remain 05:53:31 loss: 2.5043 psnr: 15.8252 Lr: 6.71155e-04
[2025-02-17 20:59:09,730 INFO hook.py line 109 848561] Train: [63/100][450/605] Data 0.002 (0.002) Batch 0.926 (0.939) Remain 05:52:35 loss: 2.0683 psnr: 19.5473 Lr: 6.68576e-04
[2025-02-17 20:59:56,773 INFO hook.py line 109 848561] Train: [63/100][500/605] Data 0.002 (0.002) Batch 0.944 (0.939) Remain 05:51:53 loss: 2.2591 psnr: 17.4842 Lr: 6.65998e-04
[2025-02-17 21:00:43,950 INFO hook.py line 109 848561] Train: [63/100][550/605] Data 0.001 (0.002) Batch 0.914 (0.939) Remain 05:51:16 loss: 1.9242 psnr: 21.2307 Lr: 6.63423e-04
[2025-02-17 21:01:29,907 INFO hook.py line 109 848561] Train: [63/100][600/605] Data 0.002 (0.002) Batch 0.890 (0.938) Remain 05:49:51 loss: 2.2807 psnr: 17.3756 Lr: 6.60851e-04
[2025-02-17 21:01:34,292 INFO misc.py line 135 848561] Train result: loss: 2.2733 rgb_loss: 0.7870 psnr: 17.8511 depth_loss: 0.0664 feat_loss: 1.4199 
[2025-02-17 21:01:34,294 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:02:25,532 INFO hook.py line 109 848561] Train: [64/100][50/605] Data 0.003 (0.002) Batch 0.937 (0.941) Remain 05:50:26 loss: 2.0202 psnr: 19.4205 Lr: 6.58025e-04
[2025-02-17 21:03:12,330 INFO hook.py line 109 848561] Train: [64/100][100/605] Data 0.002 (0.002) Batch 0.961 (0.939) Remain 05:48:36 loss: 2.2957 psnr: 17.6412 Lr: 6.55458e-04
[2025-02-17 21:03:59,210 INFO hook.py line 109 848561] Train: [64/100][150/605] Data 0.002 (0.002) Batch 0.962 (0.938) Remain 05:47:42 loss: 2.3134 psnr: 17.6490 Lr: 6.52893e-04
[2025-02-17 21:04:46,205 INFO hook.py line 109 848561] Train: [64/100][200/605] Data 0.002 (0.002) Batch 0.940 (0.939) Remain 05:47:04 loss: 2.4725 psnr: 16.2959 Lr: 6.50332e-04
[2025-02-17 21:05:33,401 INFO hook.py line 109 848561] Train: [64/100][250/605] Data 0.001 (0.002) Batch 0.921 (0.940) Remain 05:46:41 loss: 2.2839 psnr: 17.9305 Lr: 6.47773e-04
[2025-02-17 21:06:20,637 INFO hook.py line 109 848561] Train: [64/100][300/605] Data 0.002 (0.002) Batch 0.955 (0.941) Remain 05:46:12 loss: 2.2624 psnr: 17.2950 Lr: 6.45216e-04
[2025-02-17 21:07:07,723 INFO hook.py line 109 848561] Train: [64/100][350/605] Data 0.003 (0.002) Batch 0.957 (0.941) Remain 05:45:29 loss: 2.3690 psnr: 17.0539 Lr: 6.42662e-04
[2025-02-17 21:07:54,604 INFO hook.py line 109 848561] Train: [64/100][400/605] Data 0.002 (0.002) Batch 0.925 (0.940) Remain 05:44:33 loss: 2.3151 psnr: 18.5009 Lr: 6.40111e-04
[2025-02-17 21:08:41,684 INFO hook.py line 109 848561] Train: [64/100][450/605] Data 0.003 (0.002) Batch 0.934 (0.940) Remain 05:43:49 loss: 2.3825 psnr: 16.4965 Lr: 6.37562e-04
[2025-02-17 21:09:28,598 INFO hook.py line 109 848561] Train: [64/100][500/605] Data 0.002 (0.002) Batch 0.923 (0.940) Remain 05:42:57 loss: 2.0468 psnr: 20.1632 Lr: 6.35017e-04
[2025-02-17 21:10:15,724 INFO hook.py line 109 848561] Train: [64/100][550/605] Data 0.003 (0.002) Batch 0.948 (0.940) Remain 05:42:15 loss: 2.0239 psnr: 20.6943 Lr: 6.32474e-04
[2025-02-17 21:11:01,948 INFO hook.py line 109 848561] Train: [64/100][600/605] Data 0.002 (0.002) Batch 0.856 (0.939) Remain 05:40:59 loss: 2.4704 psnr: 16.6624 Lr: 6.29984e-04
[2025-02-17 21:11:06,239 INFO misc.py line 135 848561] Train result: loss: 2.2733 rgb_loss: 0.7871 psnr: 17.8563 depth_loss: 0.0661 feat_loss: 1.4201 
[2025-02-17 21:11:06,240 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:11:57,262 INFO hook.py line 109 848561] Train: [65/100][50/605] Data 0.002 (0.002) Batch 0.939 (0.936) Remain 05:39:06 loss: 2.1888 psnr: 17.6772 Lr: 6.27193e-04
[2025-02-17 21:12:44,412 INFO hook.py line 109 848561] Train: [65/100][100/605] Data 0.002 (0.002) Batch 0.953 (0.940) Remain 05:39:34 loss: 2.2294 psnr: 17.9765 Lr: 6.24658e-04
[2025-02-17 21:13:31,292 INFO hook.py line 109 848561] Train: [65/100][150/605] Data 0.003 (0.002) Batch 0.943 (0.939) Remain 05:38:31 loss: 2.1034 psnr: 19.9573 Lr: 6.22127e-04
[2025-02-17 21:14:18,208 INFO hook.py line 109 848561] Train: [65/100][200/605] Data 0.003 (0.002) Batch 0.946 (0.939) Remain 05:37:40 loss: 2.2549 psnr: 17.6494 Lr: 6.19598e-04
[2025-02-17 21:15:05,089 INFO hook.py line 109 848561] Train: [65/100][250/605] Data 0.002 (0.002) Batch 0.926 (0.939) Remain 05:36:48 loss: 2.4205 psnr: 16.3012 Lr: 6.17072e-04
[2025-02-17 21:15:52,139 INFO hook.py line 109 848561] Train: [65/100][300/605] Data 0.004 (0.002) Batch 0.956 (0.939) Remain 05:36:09 loss: 2.2572 psnr: 18.3032 Lr: 6.14548e-04
[2025-02-17 21:16:39,085 INFO hook.py line 109 848561] Train: [65/100][350/605] Data 0.003 (0.002) Batch 0.940 (0.939) Remain 05:35:22 loss: 2.2153 psnr: 17.4761 Lr: 6.12028e-04
[2025-02-17 21:17:26,019 INFO hook.py line 109 848561] Train: [65/100][400/605] Data 0.002 (0.002) Batch 0.938 (0.939) Remain 05:34:34 loss: 2.2965 psnr: 17.5738 Lr: 6.09511e-04
[2025-02-17 21:18:12,891 INFO hook.py line 109 848561] Train: [65/100][450/605] Data 0.002 (0.002) Batch 0.943 (0.939) Remain 05:33:44 loss: 2.0970 psnr: 19.4326 Lr: 6.06996e-04
[2025-02-17 21:18:59,734 INFO hook.py line 109 848561] Train: [65/100][500/605] Data 0.003 (0.002) Batch 0.976 (0.939) Remain 05:32:53 loss: 2.1598 psnr: 17.9345 Lr: 6.04484e-04
[2025-02-17 21:19:46,741 INFO hook.py line 109 848561] Train: [65/100][550/605] Data 0.003 (0.002) Batch 0.923 (0.939) Remain 05:32:09 loss: 2.3865 psnr: 17.2301 Lr: 6.01976e-04
[2025-02-17 21:20:33,056 INFO hook.py line 109 848561] Train: [65/100][600/605] Data 0.002 (0.002) Batch 0.857 (0.938) Remain 05:31:00 loss: 2.2187 psnr: 18.2251 Lr: 5.99470e-04
[2025-02-17 21:20:37,410 INFO misc.py line 135 848561] Train result: loss: 2.2811 rgb_loss: 0.7938 psnr: 17.8287 depth_loss: 0.0669 feat_loss: 1.4204 
[2025-02-17 21:20:37,411 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:21:28,771 INFO hook.py line 109 848561] Train: [66/100][50/605] Data 0.003 (0.002) Batch 0.948 (0.944) Remain 05:32:31 loss: 2.1166 psnr: 18.9044 Lr: 5.96717e-04
[2025-02-17 21:22:15,909 INFO hook.py line 109 848561] Train: [66/100][100/605] Data 0.002 (0.002) Batch 0.922 (0.944) Remain 05:31:26 loss: 2.1402 psnr: 18.9197 Lr: 5.94218e-04
[2025-02-17 21:23:02,968 INFO hook.py line 109 848561] Train: [66/100][150/605] Data 0.001 (0.002) Batch 0.930 (0.943) Remain 05:30:21 loss: 1.9977 psnr: 20.5212 Lr: 5.91722e-04
[2025-02-17 21:23:49,970 INFO hook.py line 109 848561] Train: [66/100][200/605] Data 0.002 (0.002) Batch 0.940 (0.942) Remain 05:29:19 loss: 2.2188 psnr: 18.5136 Lr: 5.89228e-04
[2025-02-17 21:24:36,737 INFO hook.py line 109 848561] Train: [66/100][250/605] Data 0.003 (0.002) Batch 0.924 (0.941) Remain 05:28:04 loss: 1.9792 psnr: 20.9201 Lr: 5.86738e-04
[2025-02-17 21:25:23,721 INFO hook.py line 109 848561] Train: [66/100][300/605] Data 0.003 (0.002) Batch 0.948 (0.941) Remain 05:27:13 loss: 1.9893 psnr: 20.3135 Lr: 5.84251e-04
[2025-02-17 21:26:10,863 INFO hook.py line 109 848561] Train: [66/100][350/605] Data 0.002 (0.002) Batch 0.967 (0.941) Remain 05:26:33 loss: 2.3255 psnr: 17.9297 Lr: 5.81767e-04
[2025-02-17 21:26:57,858 INFO hook.py line 109 848561] Train: [66/100][400/605] Data 0.002 (0.002) Batch 0.942 (0.941) Remain 05:25:44 loss: 2.1738 psnr: 18.6230 Lr: 5.79286e-04
[2025-02-17 21:27:44,697 INFO hook.py line 109 848561] Train: [66/100][450/605] Data 0.003 (0.002) Batch 0.965 (0.940) Remain 05:24:47 loss: 2.3516 psnr: 17.7462 Lr: 5.76808e-04
[2025-02-17 21:28:31,814 INFO hook.py line 109 848561] Train: [66/100][500/605] Data 0.002 (0.002) Batch 0.962 (0.941) Remain 05:24:04 loss: 2.3563 psnr: 16.3841 Lr: 5.74334e-04
[2025-02-17 21:29:19,089 INFO hook.py line 109 848561] Train: [66/100][550/605] Data 0.002 (0.002) Batch 0.944 (0.941) Remain 05:23:27 loss: 1.9675 psnr: 20.5550 Lr: 5.71862e-04
[2025-02-17 21:30:05,713 INFO hook.py line 109 848561] Train: [66/100][600/605] Data 0.002 (0.002) Batch 0.913 (0.940) Remain 05:22:25 loss: 2.1789 psnr: 18.5745 Lr: 5.69394e-04
[2025-02-17 21:30:10,070 INFO misc.py line 135 848561] Train result: loss: 2.2746 rgb_loss: 0.7895 psnr: 17.8517 depth_loss: 0.0665 feat_loss: 1.4186 
[2025-02-17 21:30:10,070 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:31:00,966 INFO hook.py line 109 848561] Train: [67/100][50/605] Data 0.002 (0.002) Batch 0.920 (0.939) Remain 05:21:03 loss: 2.3165 psnr: 17.4134 Lr: 5.66683e-04
[2025-02-17 21:31:47,772 INFO hook.py line 109 848561] Train: [67/100][100/605] Data 0.002 (0.002) Batch 0.950 (0.937) Remain 05:19:48 loss: 2.1832 psnr: 17.8795 Lr: 5.64222e-04
[2025-02-17 21:32:34,615 INFO hook.py line 109 848561] Train: [67/100][150/605] Data 0.002 (0.002) Batch 0.925 (0.937) Remain 05:18:57 loss: 2.5878 psnr: 15.4945 Lr: 5.61763e-04
[2025-02-17 21:33:21,464 INFO hook.py line 109 848561] Train: [67/100][200/605] Data 0.003 (0.002) Batch 0.958 (0.937) Remain 05:18:09 loss: 2.2965 psnr: 17.7177 Lr: 5.59308e-04
[2025-02-17 21:34:08,565 INFO hook.py line 109 848561] Train: [67/100][250/605] Data 0.002 (0.002) Batch 0.932 (0.938) Remain 05:17:42 loss: 2.2178 psnr: 18.2144 Lr: 5.56857e-04
[2025-02-17 21:34:55,766 INFO hook.py line 109 848561] Train: [67/100][300/605] Data 0.004 (0.002) Batch 0.912 (0.939) Remain 05:17:16 loss: 2.3586 psnr: 17.1035 Lr: 5.54409e-04
[2025-02-17 21:35:42,894 INFO hook.py line 109 848561] Train: [67/100][350/605] Data 0.002 (0.002) Batch 0.914 (0.940) Remain 05:16:39 loss: 2.6027 psnr: 15.4393 Lr: 5.51964e-04
[2025-02-17 21:36:30,034 INFO hook.py line 109 848561] Train: [67/100][400/605] Data 0.002 (0.002) Batch 0.967 (0.940) Remain 05:16:00 loss: 2.3155 psnr: 17.4018 Lr: 5.49522e-04
[2025-02-17 21:37:17,031 INFO hook.py line 109 848561] Train: [67/100][450/605] Data 0.002 (0.002) Batch 0.936 (0.940) Remain 05:15:13 loss: 2.3301 psnr: 16.7710 Lr: 5.47084e-04
[2025-02-17 21:38:04,280 INFO hook.py line 109 848561] Train: [67/100][500/605] Data 0.002 (0.002) Batch 0.965 (0.941) Remain 05:14:36 loss: 2.2402 psnr: 17.9008 Lr: 5.44649e-04
[2025-02-17 21:38:51,281 INFO hook.py line 109 848561] Train: [67/100][550/605] Data 0.002 (0.002) Batch 0.931 (0.940) Remain 05:13:48 loss: 2.1852 psnr: 18.7178 Lr: 5.42217e-04
[2025-02-17 21:39:37,342 INFO hook.py line 109 848561] Train: [67/100][600/605] Data 0.002 (0.002) Batch 0.846 (0.939) Remain 05:12:28 loss: 2.1902 psnr: 18.3385 Lr: 5.39789e-04
[2025-02-17 21:39:41,707 INFO misc.py line 135 848561] Train result: loss: 2.2665 rgb_loss: 0.7857 psnr: 17.8656 depth_loss: 0.0643 feat_loss: 1.4165 
[2025-02-17 21:39:41,708 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:40:32,904 INFO hook.py line 109 848561] Train: [68/100][50/605] Data 0.002 (0.002) Batch 0.935 (0.941) Remain 05:12:12 loss: 2.2405 psnr: 17.7888 Lr: 5.37171e-04
[2025-02-17 21:41:19,841 INFO hook.py line 109 848561] Train: [68/100][100/605] Data 0.003 (0.002) Batch 0.934 (0.940) Remain 05:11:05 loss: 2.2936 psnr: 17.9290 Lr: 5.34750e-04
[2025-02-17 21:42:07,086 INFO hook.py line 109 848561] Train: [68/100][150/605] Data 0.003 (0.002) Batch 0.939 (0.941) Remain 05:10:54 loss: 2.3943 psnr: 16.7330 Lr: 5.32332e-04
[2025-02-17 21:42:54,183 INFO hook.py line 109 848561] Train: [68/100][200/605] Data 0.002 (0.002) Batch 0.929 (0.942) Remain 05:10:09 loss: 2.1162 psnr: 20.1559 Lr: 5.29919e-04
[2025-02-17 21:43:41,108 INFO hook.py line 109 848561] Train: [68/100][250/605] Data 0.003 (0.002) Batch 0.922 (0.941) Remain 05:09:10 loss: 2.0785 psnr: 18.8455 Lr: 5.27508e-04
[2025-02-17 21:44:28,261 INFO hook.py line 109 848561] Train: [68/100][300/605] Data 0.005 (0.002) Batch 0.925 (0.941) Remain 05:08:30 loss: 2.2336 psnr: 18.1251 Lr: 5.25101e-04
[2025-02-17 21:45:15,075 INFO hook.py line 109 848561] Train: [68/100][350/605] Data 0.003 (0.002) Batch 0.924 (0.941) Remain 05:07:29 loss: 2.3646 psnr: 16.7744 Lr: 5.22698e-04
[2025-02-17 21:46:02,182 INFO hook.py line 109 848561] Train: [68/100][400/605] Data 0.001 (0.002) Batch 0.950 (0.941) Remain 05:06:46 loss: 2.1189 psnr: 18.2852 Lr: 5.20298e-04
[2025-02-17 21:46:48,914 INFO hook.py line 109 848561] Train: [68/100][450/605] Data 0.002 (0.002) Batch 0.944 (0.940) Remain 05:05:45 loss: 2.1355 psnr: 18.3502 Lr: 5.17902e-04
[2025-02-17 21:47:35,817 INFO hook.py line 109 848561] Train: [68/100][500/605] Data 0.002 (0.002) Batch 0.934 (0.940) Remain 05:04:54 loss: 2.4207 psnr: 17.3198 Lr: 5.15509e-04
[2025-02-17 21:48:22,805 INFO hook.py line 109 848561] Train: [68/100][550/605] Data 0.003 (0.002) Batch 0.939 (0.940) Remain 05:04:07 loss: 2.2249 psnr: 18.3122 Lr: 5.13120e-04
[2025-02-17 21:49:08,841 INFO hook.py line 109 848561] Train: [68/100][600/605] Data 0.002 (0.002) Batch 0.837 (0.938) Remain 05:02:49 loss: 2.1267 psnr: 19.0551 Lr: 5.10735e-04
[2025-02-17 21:49:13,132 INFO misc.py line 135 848561] Train result: loss: 2.2517 rgb_loss: 0.7735 psnr: 17.9828 depth_loss: 0.0647 feat_loss: 1.4134 
[2025-02-17 21:49:13,133 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:50:04,790 INFO hook.py line 109 848561] Train: [69/100][50/605] Data 0.002 (0.002) Batch 0.937 (0.950) Remain 05:05:53 loss: 2.0767 psnr: 18.9947 Lr: 5.08115e-04
[2025-02-17 21:50:52,164 INFO hook.py line 109 848561] Train: [69/100][100/605] Data 0.003 (0.002) Batch 0.938 (0.949) Remain 05:04:36 loss: 2.7948 psnr: 14.4508 Lr: 5.05738e-04
[2025-02-17 21:51:39,306 INFO hook.py line 109 848561] Train: [69/100][150/605] Data 0.003 (0.003) Batch 0.949 (0.947) Remain 05:03:09 loss: 2.1431 psnr: 19.1169 Lr: 5.03364e-04
[2025-02-17 21:52:26,238 INFO hook.py line 109 848561] Train: [69/100][200/605] Data 0.003 (0.003) Batch 0.936 (0.945) Remain 05:01:41 loss: 2.3320 psnr: 17.7045 Lr: 5.00994e-04
[2025-02-17 21:53:13,341 INFO hook.py line 109 848561] Train: [69/100][250/605] Data 0.002 (0.003) Batch 0.960 (0.944) Remain 05:00:44 loss: 2.2805 psnr: 17.9251 Lr: 4.98627e-04
[2025-02-17 21:54:00,321 INFO hook.py line 109 848561] Train: [69/100][300/605] Data 0.002 (0.003) Batch 0.925 (0.943) Remain 04:59:42 loss: 2.3044 psnr: 18.1067 Lr: 4.96264e-04
[2025-02-17 21:54:47,335 INFO hook.py line 109 848561] Train: [69/100][350/605] Data 0.002 (0.002) Batch 0.947 (0.943) Remain 04:58:46 loss: 2.4757 psnr: 16.2752 Lr: 4.93905e-04
[2025-02-17 21:55:34,280 INFO hook.py line 109 848561] Train: [69/100][400/605] Data 0.003 (0.002) Batch 0.964 (0.942) Remain 04:57:49 loss: 2.3646 psnr: 16.5348 Lr: 4.91550e-04
[2025-02-17 21:56:21,456 INFO hook.py line 109 848561] Train: [69/100][450/605] Data 0.003 (0.002) Batch 0.940 (0.943) Remain 04:57:04 loss: 2.2812 psnr: 18.0503 Lr: 4.89199e-04
[2025-02-17 21:57:08,276 INFO hook.py line 109 848561] Train: [69/100][500/605] Data 0.002 (0.002) Batch 0.934 (0.942) Remain 04:56:05 loss: 2.4950 psnr: 16.0954 Lr: 4.86851e-04
[2025-02-17 21:57:55,039 INFO hook.py line 109 848561] Train: [69/100][550/605] Data 0.002 (0.002) Batch 0.945 (0.941) Remain 04:55:06 loss: 2.1289 psnr: 19.1173 Lr: 4.84507e-04
[2025-02-17 21:58:41,423 INFO hook.py line 109 848561] Train: [69/100][600/605] Data 0.002 (0.002) Batch 0.853 (0.940) Remain 04:53:58 loss: 2.2007 psnr: 17.8161 Lr: 4.82167e-04
[2025-02-17 21:58:45,763 INFO misc.py line 135 848561] Train result: loss: 2.2644 rgb_loss: 0.7819 psnr: 17.9101 depth_loss: 0.0651 feat_loss: 1.4174 
[2025-02-17 21:58:45,764 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 21:59:37,223 INFO hook.py line 109 848561] Train: [70/100][50/605] Data 0.003 (0.002) Batch 0.941 (0.946) Remain 04:54:55 loss: 2.3643 psnr: 16.3525 Lr: 4.79598e-04
[2025-02-17 22:00:24,181 INFO hook.py line 109 848561] Train: [70/100][100/605] Data 0.003 (0.002) Batch 0.910 (0.943) Remain 04:53:02 loss: 2.1663 psnr: 18.0850 Lr: 4.77266e-04
[2025-02-17 22:01:11,155 INFO hook.py line 109 848561] Train: [70/100][150/605] Data 0.003 (0.002) Batch 0.950 (0.941) Remain 04:51:56 loss: 2.1258 psnr: 17.9501 Lr: 4.74938e-04
[2025-02-17 22:01:58,096 INFO hook.py line 109 848561] Train: [70/100][200/605] Data 0.002 (0.002) Batch 0.976 (0.941) Remain 04:50:56 loss: 2.2365 psnr: 18.8781 Lr: 4.72614e-04
[2025-02-17 22:02:45,257 INFO hook.py line 109 848561] Train: [70/100][250/605] Data 0.002 (0.002) Batch 0.936 (0.941) Remain 04:50:18 loss: 2.2233 psnr: 17.3613 Lr: 4.70294e-04
[2025-02-17 22:03:32,163 INFO hook.py line 109 848561] Train: [70/100][300/605] Data 0.002 (0.002) Batch 0.950 (0.941) Remain 04:49:21 loss: 2.0914 psnr: 19.2123 Lr: 4.67978e-04
[2025-02-17 22:04:18,973 INFO hook.py line 109 848561] Train: [70/100][350/605] Data 0.003 (0.002) Batch 0.950 (0.940) Remain 04:48:22 loss: 2.3783 psnr: 16.4443 Lr: 4.65666e-04
[2025-02-17 22:05:06,104 INFO hook.py line 109 848561] Train: [70/100][400/605] Data 0.002 (0.002) Batch 0.927 (0.940) Remain 04:47:41 loss: 2.1799 psnr: 18.7041 Lr: 4.63358e-04
[2025-02-17 22:05:53,175 INFO hook.py line 109 848561] Train: [70/100][450/605] Data 0.002 (0.002) Batch 0.911 (0.941) Remain 04:46:56 loss: 2.1845 psnr: 18.8433 Lr: 4.61054e-04
[2025-02-17 22:06:40,266 INFO hook.py line 109 848561] Train: [70/100][500/605] Data 0.002 (0.002) Batch 0.951 (0.941) Remain 04:46:11 loss: 2.1576 psnr: 18.4506 Lr: 4.58754e-04
[2025-02-17 22:07:27,273 INFO hook.py line 109 848561] Train: [70/100][550/605] Data 0.003 (0.002) Batch 0.947 (0.941) Remain 04:45:23 loss: 2.2183 psnr: 17.4316 Lr: 4.56458e-04
[2025-02-17 22:08:13,301 INFO hook.py line 109 848561] Train: [70/100][600/605] Data 0.002 (0.002) Batch 0.859 (0.939) Remain 04:44:06 loss: 2.1868 psnr: 18.2713 Lr: 4.54166e-04
[2025-02-17 22:08:17,625 INFO misc.py line 135 848561] Train result: loss: 2.2611 rgb_loss: 0.7797 psnr: 17.9297 depth_loss: 0.0650 feat_loss: 1.4164 
[2025-02-17 22:08:17,626 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 22:09:08,765 INFO hook.py line 109 848561] Train: [71/100][50/605] Data 0.002 (0.002) Batch 0.955 (0.939) Remain 04:43:22 loss: 2.1114 psnr: 18.4602 Lr: 4.51650e-04
[2025-02-17 22:09:55,915 INFO hook.py line 109 848561] Train: [71/100][100/605] Data 0.002 (0.002) Batch 0.973 (0.941) Remain 04:43:09 loss: 2.2080 psnr: 18.2497 Lr: 4.49366e-04
[2025-02-17 22:10:42,847 INFO hook.py line 109 848561] Train: [71/100][150/605] Data 0.002 (0.002) Batch 0.919 (0.940) Remain 04:42:06 loss: 2.1652 psnr: 17.8992 Lr: 4.47087e-04
[2025-02-17 22:11:29,662 INFO hook.py line 109 848561] Train: [71/100][200/605] Data 0.002 (0.002) Batch 0.927 (0.939) Remain 04:41:00 loss: 2.2039 psnr: 18.6649 Lr: 4.44812e-04
[2025-02-17 22:12:16,688 INFO hook.py line 109 848561] Train: [71/100][250/605] Data 0.003 (0.002) Batch 0.939 (0.940) Remain 04:40:18 loss: 2.2697 psnr: 17.7340 Lr: 4.42541e-04
[2025-02-17 22:13:03,415 INFO hook.py line 109 848561] Train: [71/100][300/605] Data 0.003 (0.002) Batch 0.950 (0.939) Remain 04:39:16 loss: 1.9879 psnr: 20.0738 Lr: 4.40274e-04
[2025-02-17 22:13:50,569 INFO hook.py line 109 848561] Train: [71/100][350/605] Data 0.002 (0.002) Batch 0.927 (0.939) Remain 04:38:40 loss: 2.4580 psnr: 16.1786 Lr: 4.38011e-04
[2025-02-17 22:14:37,613 INFO hook.py line 109 848561] Train: [71/100][400/605] Data 0.003 (0.002) Batch 0.950 (0.940) Remain 04:37:56 loss: 2.0536 psnr: 19.9911 Lr: 4.35753e-04
[2025-02-17 22:15:24,725 INFO hook.py line 109 848561] Train: [71/100][450/605] Data 0.003 (0.002) Batch 0.930 (0.940) Remain 04:37:15 loss: 2.4182 psnr: 16.6164 Lr: 4.33499e-04
[2025-02-17 22:16:11,619 INFO hook.py line 109 848561] Train: [71/100][500/605] Data 0.003 (0.002) Batch 0.945 (0.940) Remain 04:36:24 loss: 2.1647 psnr: 18.7583 Lr: 4.31249e-04
[2025-02-17 22:16:58,469 INFO hook.py line 109 848561] Train: [71/100][550/605] Data 0.003 (0.002) Batch 0.967 (0.939) Remain 04:35:33 loss: 2.0997 psnr: 19.3002 Lr: 4.29003e-04
[2025-02-17 22:17:44,674 INFO hook.py line 109 848561] Train: [71/100][600/605] Data 0.002 (0.002) Batch 0.865 (0.938) Remain 04:34:23 loss: 2.2679 psnr: 17.0691 Lr: 4.26761e-04
[2025-02-17 22:17:48,994 INFO misc.py line 135 848561] Train result: loss: 2.2492 rgb_loss: 0.7691 psnr: 17.9970 depth_loss: 0.0649 feat_loss: 1.4152 
[2025-02-17 22:17:48,995 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 22:18:40,170 INFO hook.py line 109 848561] Train: [72/100][50/605] Data 0.003 (0.002) Batch 0.943 (0.941) Remain 04:34:31 loss: 2.2824 psnr: 17.0308 Lr: 4.24301e-04
[2025-02-17 22:19:27,028 INFO hook.py line 109 848561] Train: [72/100][100/605] Data 0.003 (0.002) Batch 0.933 (0.939) Remain 04:33:05 loss: 2.2792 psnr: 17.6994 Lr: 4.22068e-04
[2025-02-17 22:20:14,199 INFO hook.py line 109 848561] Train: [72/100][150/605] Data 0.002 (0.002) Batch 0.940 (0.941) Remain 04:32:43 loss: 2.3294 psnr: 17.7019 Lr: 4.19840e-04
[2025-02-17 22:21:01,235 INFO hook.py line 109 848561] Train: [72/100][200/605] Data 0.001 (0.002) Batch 0.915 (0.941) Remain 04:31:56 loss: 2.2689 psnr: 17.4768 Lr: 4.17616e-04
[2025-02-17 22:21:48,178 INFO hook.py line 109 848561] Train: [72/100][250/605] Data 0.002 (0.002) Batch 0.937 (0.940) Remain 04:31:02 loss: 2.1901 psnr: 17.7238 Lr: 4.15397e-04
[2025-02-17 22:22:34,989 INFO hook.py line 109 848561] Train: [72/100][300/605] Data 0.002 (0.002) Batch 0.925 (0.940) Remain 04:30:03 loss: 2.2260 psnr: 19.0754 Lr: 4.13182e-04
[2025-02-17 22:23:22,236 INFO hook.py line 109 848561] Train: [72/100][350/605] Data 0.002 (0.002) Batch 0.940 (0.940) Remain 04:29:30 loss: 2.1521 psnr: 18.5107 Lr: 4.10971e-04
[2025-02-17 22:24:09,392 INFO hook.py line 109 848561] Train: [72/100][400/605] Data 0.003 (0.002) Batch 0.969 (0.941) Remain 04:28:48 loss: 2.0960 psnr: 18.7101 Lr: 4.08765e-04
[2025-02-17 22:24:56,401 INFO hook.py line 109 848561] Train: [72/100][450/605] Data 0.003 (0.002) Batch 0.926 (0.941) Remain 04:28:00 loss: 2.2607 psnr: 18.1178 Lr: 4.06563e-04
[2025-02-17 22:25:43,364 INFO hook.py line 109 848561] Train: [72/100][500/605] Data 0.003 (0.002) Batch 0.953 (0.941) Remain 04:27:11 loss: 2.0080 psnr: 20.2115 Lr: 4.04365e-04
[2025-02-17 22:26:30,300 INFO hook.py line 109 848561] Train: [72/100][550/605] Data 0.003 (0.002) Batch 0.938 (0.940) Remain 04:26:21 loss: 2.1619 psnr: 18.4419 Lr: 4.02172e-04
[2025-02-17 22:27:16,365 INFO hook.py line 109 848561] Train: [72/100][600/605] Data 0.002 (0.002) Batch 0.883 (0.939) Remain 04:25:07 loss: 2.2844 psnr: 17.8584 Lr: 3.99984e-04
[2025-02-17 22:27:20,667 INFO misc.py line 135 848561] Train result: loss: 2.2569 rgb_loss: 0.7784 psnr: 17.9138 depth_loss: 0.0649 feat_loss: 1.4135 
[2025-02-17 22:27:20,668 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 22:28:11,843 INFO hook.py line 109 848561] Train: [73/100][50/605] Data 0.003 (0.003) Batch 0.961 (0.938) Remain 04:23:58 loss: 2.3498 psnr: 17.3236 Lr: 3.97582e-04
[2025-02-17 22:28:58,799 INFO hook.py line 109 848561] Train: [73/100][100/605] Data 0.003 (0.003) Batch 0.951 (0.938) Remain 04:23:23 loss: 1.9570 psnr: 21.1390 Lr: 3.95402e-04
[2025-02-17 22:29:46,260 INFO hook.py line 109 848561] Train: [73/100][150/605] Data 0.002 (0.002) Batch 0.965 (0.942) Remain 04:23:38 loss: 2.2613 psnr: 18.0066 Lr: 3.93228e-04
[2025-02-17 22:30:33,180 INFO hook.py line 109 848561] Train: [73/100][200/605] Data 0.002 (0.002) Batch 0.983 (0.941) Remain 04:22:35 loss: 2.3067 psnr: 17.7996 Lr: 3.91058e-04
[2025-02-17 22:31:20,044 INFO hook.py line 109 848561] Train: [73/100][250/605] Data 0.002 (0.002) Batch 0.922 (0.940) Remain 04:21:35 loss: 2.1762 psnr: 18.0683 Lr: 3.88892e-04
[2025-02-17 22:32:07,227 INFO hook.py line 109 848561] Train: [73/100][300/605] Data 0.003 (0.002) Batch 0.944 (0.941) Remain 04:20:57 loss: 2.1623 psnr: 18.1852 Lr: 3.86731e-04
[2025-02-17 22:32:54,323 INFO hook.py line 109 848561] Train: [73/100][350/605] Data 0.002 (0.002) Batch 0.917 (0.941) Remain 04:20:12 loss: 2.2861 psnr: 17.9072 Lr: 3.84575e-04
[2025-02-17 22:33:41,377 INFO hook.py line 109 848561] Train: [73/100][400/605] Data 0.003 (0.002) Batch 0.925 (0.941) Remain 04:19:25 loss: 2.1009 psnr: 19.3351 Lr: 3.82423e-04
[2025-02-17 22:34:28,506 INFO hook.py line 109 848561] Train: [73/100][450/605] Data 0.003 (0.002) Batch 0.951 (0.941) Remain 04:18:41 loss: 2.4128 psnr: 17.1248 Lr: 3.80276e-04
[2025-02-17 22:35:15,396 INFO hook.py line 109 848561] Train: [73/100][500/605] Data 0.002 (0.002) Batch 0.924 (0.941) Remain 04:17:48 loss: 2.4402 psnr: 17.7696 Lr: 3.78133e-04
[2025-02-17 22:36:02,761 INFO hook.py line 109 848561] Train: [73/100][550/605] Data 0.002 (0.002) Batch 0.955 (0.941) Remain 04:17:10 loss: 2.1392 psnr: 18.7059 Lr: 3.75995e-04
[2025-02-17 22:36:48,929 INFO hook.py line 109 848561] Train: [73/100][600/605] Data 0.002 (0.002) Batch 0.866 (0.940) Remain 04:15:59 loss: 2.3457 psnr: 16.6653 Lr: 3.73862e-04
[2025-02-17 22:36:53,270 INFO misc.py line 135 848561] Train result: loss: 2.2452 rgb_loss: 0.7671 psnr: 18.0221 depth_loss: 0.0648 feat_loss: 1.4132 
[2025-02-17 22:36:53,271 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 22:37:44,301 INFO hook.py line 109 848561] Train: [74/100][50/605] Data 0.003 (0.002) Batch 0.922 (0.938) Remain 04:14:30 loss: 2.4497 psnr: 17.2454 Lr: 3.71521e-04
[2025-02-17 22:38:31,401 INFO hook.py line 109 848561] Train: [74/100][100/605] Data 0.003 (0.002) Batch 0.944 (0.940) Remain 04:14:19 loss: 2.3974 psnr: 16.7911 Lr: 3.69398e-04
[2025-02-17 22:39:18,223 INFO hook.py line 109 848561] Train: [74/100][150/605] Data 0.003 (0.002) Batch 0.928 (0.939) Remain 04:13:13 loss: 2.1987 psnr: 18.5764 Lr: 3.67279e-04
[2025-02-17 22:40:05,460 INFO hook.py line 109 848561] Train: [74/100][200/605] Data 0.002 (0.002) Batch 0.935 (0.940) Remain 04:12:50 loss: 2.1869 psnr: 19.0987 Lr: 3.65165e-04
[2025-02-17 22:40:52,345 INFO hook.py line 109 848561] Train: [74/100][250/605] Data 0.002 (0.002) Batch 0.959 (0.940) Remain 04:11:55 loss: 2.6816 psnr: 15.2509 Lr: 3.63056e-04
[2025-02-17 22:41:39,206 INFO hook.py line 109 848561] Train: [74/100][300/605] Data 0.003 (0.002) Batch 0.931 (0.939) Remain 04:11:01 loss: 2.0809 psnr: 18.9332 Lr: 3.60951e-04
[2025-02-17 22:42:26,208 INFO hook.py line 109 848561] Train: [74/100][350/605] Data 0.003 (0.002) Batch 0.953 (0.939) Remain 04:10:16 loss: 2.0858 psnr: 19.3373 Lr: 3.58852e-04
[2025-02-17 22:43:13,496 INFO hook.py line 109 848561] Train: [74/100][400/605] Data 0.003 (0.002) Batch 0.933 (0.940) Remain 04:09:42 loss: 2.3062 psnr: 17.8005 Lr: 3.56757e-04
[2025-02-17 22:44:00,483 INFO hook.py line 109 848561] Train: [74/100][450/605] Data 0.003 (0.002) Batch 0.936 (0.940) Remain 04:08:54 loss: 2.2998 psnr: 17.1673 Lr: 3.54667e-04
[2025-02-17 22:44:47,628 INFO hook.py line 109 848561] Train: [74/100][500/605] Data 0.002 (0.002) Batch 0.954 (0.940) Remain 04:08:11 loss: 2.2363 psnr: 18.5820 Lr: 3.52581e-04
[2025-02-17 22:45:34,936 INFO hook.py line 109 848561] Train: [74/100][550/605] Data 0.002 (0.002) Batch 0.954 (0.941) Remain 04:07:33 loss: 2.2429 psnr: 18.5391 Lr: 3.50501e-04
[2025-02-17 22:46:20,779 INFO hook.py line 109 848561] Train: [74/100][600/605] Data 0.002 (0.002) Batch 0.864 (0.939) Remain 04:06:14 loss: 2.3057 psnr: 17.6444 Lr: 3.48425e-04
[2025-02-17 22:46:25,088 INFO misc.py line 135 848561] Train result: loss: 2.2463 rgb_loss: 0.7694 psnr: 18.0015 depth_loss: 0.0644 feat_loss: 1.4126 
[2025-02-17 22:46:25,089 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 22:47:16,343 INFO hook.py line 109 848561] Train: [75/100][50/605] Data 0.002 (0.002) Batch 0.948 (0.942) Remain 04:06:11 loss: 2.1777 psnr: 17.9639 Lr: 3.46148e-04
[2025-02-17 22:48:03,440 INFO hook.py line 109 848561] Train: [75/100][100/605] Data 0.002 (0.002) Batch 0.953 (0.942) Remain 04:05:23 loss: 2.3032 psnr: 16.9787 Lr: 3.44082e-04
[2025-02-17 22:48:50,366 INFO hook.py line 109 848561] Train: [75/100][150/605] Data 0.002 (0.002) Batch 0.943 (0.941) Remain 04:04:17 loss: 2.0577 psnr: 19.7959 Lr: 3.42022e-04
[2025-02-17 22:49:37,814 INFO hook.py line 109 848561] Train: [75/100][200/605] Data 0.003 (0.002) Batch 0.949 (0.943) Remain 04:04:02 loss: 2.2806 psnr: 18.3682 Lr: 3.39966e-04
[2025-02-17 22:50:24,730 INFO hook.py line 109 848561] Train: [75/100][250/605] Data 0.002 (0.002) Batch 0.924 (0.942) Remain 04:03:01 loss: 2.0575 psnr: 19.8856 Lr: 3.37957e-04
[2025-02-17 22:51:12,003 INFO hook.py line 109 848561] Train: [75/100][300/605] Data 0.003 (0.002) Batch 0.953 (0.943) Remain 04:02:23 loss: 2.2041 psnr: 17.5709 Lr: 3.35911e-04
[2025-02-17 22:51:59,027 INFO hook.py line 109 848561] Train: [75/100][350/605] Data 0.002 (0.002) Batch 0.934 (0.942) Remain 04:01:31 loss: 2.2377 psnr: 18.2522 Lr: 3.33870e-04
[2025-02-17 22:52:45,818 INFO hook.py line 109 848561] Train: [75/100][400/605] Data 0.003 (0.002) Batch 0.964 (0.941) Remain 04:00:32 loss: 2.2304 psnr: 17.4568 Lr: 3.31834e-04
[2025-02-17 22:53:32,796 INFO hook.py line 109 848561] Train: [75/100][450/605] Data 0.002 (0.002) Batch 0.929 (0.941) Remain 03:59:41 loss: 2.2536 psnr: 17.8673 Lr: 3.29804e-04
[2025-02-17 22:54:19,665 INFO hook.py line 109 848561] Train: [75/100][500/605] Data 0.002 (0.002) Batch 0.956 (0.941) Remain 03:58:48 loss: 1.9408 psnr: 21.1745 Lr: 3.27778e-04
[2025-02-17 22:55:06,542 INFO hook.py line 109 848561] Train: [75/100][550/605] Data 0.003 (0.002) Batch 0.949 (0.941) Remain 03:57:57 loss: 2.0707 psnr: 19.2456 Lr: 3.25757e-04
[2025-02-17 22:55:52,752 INFO hook.py line 109 848561] Train: [75/100][600/605] Data 0.002 (0.002) Batch 0.874 (0.939) Remain 03:56:49 loss: 2.0472 psnr: 20.8087 Lr: 3.23741e-04
[2025-02-17 22:55:57,098 INFO misc.py line 135 848561] Train result: loss: 2.2415 rgb_loss: 0.7631 psnr: 18.0451 depth_loss: 0.0653 feat_loss: 1.4131 
[2025-02-17 22:55:57,099 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 22:56:47,932 INFO hook.py line 109 848561] Train: [76/100][50/605] Data 0.003 (0.002) Batch 0.908 (0.932) Remain 03:54:13 loss: 2.4155 psnr: 16.5406 Lr: 3.21530e-04
[2025-02-17 22:57:34,703 INFO hook.py line 109 848561] Train: [76/100][100/605] Data 0.002 (0.002) Batch 0.943 (0.934) Remain 03:53:51 loss: 2.1525 psnr: 18.0746 Lr: 3.19525e-04
[2025-02-17 22:58:21,601 INFO hook.py line 109 848561] Train: [76/100][150/605] Data 0.002 (0.002) Batch 0.938 (0.935) Remain 03:53:25 loss: 2.2116 psnr: 17.7895 Lr: 3.17524e-04
[2025-02-17 22:59:08,496 INFO hook.py line 109 848561] Train: [76/100][200/605] Data 0.003 (0.002) Batch 0.936 (0.936) Remain 03:52:48 loss: 2.1512 psnr: 18.7110 Lr: 3.15530e-04
[2025-02-17 22:59:55,353 INFO hook.py line 109 848561] Train: [76/100][250/605] Data 0.003 (0.002) Batch 0.920 (0.936) Remain 03:52:05 loss: 2.3074 psnr: 18.1637 Lr: 3.13540e-04
[2025-02-17 23:00:42,284 INFO hook.py line 109 848561] Train: [76/100][300/605] Data 0.003 (0.002) Batch 0.933 (0.937) Remain 03:51:24 loss: 2.2565 psnr: 17.5030 Lr: 3.11555e-04
[2025-02-17 23:01:29,383 INFO hook.py line 109 848561] Train: [76/100][350/605] Data 0.002 (0.002) Batch 0.949 (0.937) Remain 03:50:49 loss: 2.3967 psnr: 16.6820 Lr: 3.09575e-04
[2025-02-17 23:02:16,531 INFO hook.py line 109 848561] Train: [76/100][400/605] Data 0.002 (0.002) Batch 0.925 (0.938) Remain 03:50:13 loss: 2.3148 psnr: 18.2177 Lr: 3.07601e-04
[2025-02-17 23:03:03,442 INFO hook.py line 109 848561] Train: [76/100][450/605] Data 0.002 (0.002) Batch 0.978 (0.938) Remain 03:49:26 loss: 2.2444 psnr: 17.7433 Lr: 3.05632e-04
[2025-02-17 23:03:50,642 INFO hook.py line 109 848561] Train: [76/100][500/605] Data 0.002 (0.002) Batch 0.963 (0.939) Remain 03:48:48 loss: 2.2628 psnr: 17.7450 Lr: 3.03668e-04
[2025-02-17 23:04:37,687 INFO hook.py line 109 848561] Train: [76/100][550/605] Data 0.002 (0.002) Batch 0.944 (0.939) Remain 03:48:04 loss: 2.1716 psnr: 18.1004 Lr: 3.01709e-04
[2025-02-17 23:05:23,891 INFO hook.py line 109 848561] Train: [76/100][600/605] Data 0.002 (0.002) Batch 0.883 (0.938) Remain 03:46:59 loss: 2.2602 psnr: 17.4551 Lr: 2.99755e-04
[2025-02-17 23:05:28,286 INFO misc.py line 135 848561] Train result: loss: 2.2404 rgb_loss: 0.7665 psnr: 18.0012 depth_loss: 0.0637 feat_loss: 1.4101 
[2025-02-17 23:05:28,288 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 23:06:19,359 INFO hook.py line 109 848561] Train: [77/100][50/605] Data 0.002 (0.002) Batch 0.975 (0.938) Remain 03:46:16 loss: 2.2313 psnr: 18.9646 Lr: 2.97612e-04
[2025-02-17 23:07:06,263 INFO hook.py line 109 848561] Train: [77/100][100/605] Data 0.003 (0.002) Batch 0.916 (0.938) Remain 03:45:28 loss: 2.3508 psnr: 17.5259 Lr: 2.95669e-04
[2025-02-17 23:07:53,220 INFO hook.py line 109 848561] Train: [77/100][150/605] Data 0.002 (0.002) Batch 0.934 (0.939) Remain 03:44:46 loss: 2.3742 psnr: 16.4617 Lr: 2.93732e-04
[2025-02-17 23:08:40,210 INFO hook.py line 109 848561] Train: [77/100][200/605] Data 0.002 (0.002) Batch 0.911 (0.939) Remain 03:44:04 loss: 2.0782 psnr: 19.1216 Lr: 2.91800e-04
[2025-02-17 23:09:27,639 INFO hook.py line 109 848561] Train: [77/100][250/605] Data 0.003 (0.002) Batch 0.927 (0.941) Remain 03:43:45 loss: 2.3406 psnr: 16.8399 Lr: 2.89873e-04
[2025-02-17 23:10:14,722 INFO hook.py line 109 848561] Train: [77/100][300/605] Data 0.003 (0.002) Batch 0.945 (0.941) Remain 03:43:00 loss: 2.3172 psnr: 18.0818 Lr: 2.87952e-04
[2025-02-17 23:11:01,578 INFO hook.py line 109 848561] Train: [77/100][350/605] Data 0.003 (0.002) Batch 0.931 (0.940) Remain 03:42:05 loss: 2.5611 psnr: 15.5892 Lr: 2.86035e-04
[2025-02-17 23:11:48,498 INFO hook.py line 109 848561] Train: [77/100][400/605] Data 0.003 (0.002) Batch 0.921 (0.940) Remain 03:41:14 loss: 2.3162 psnr: 17.5832 Lr: 2.84125e-04
[2025-02-17 23:12:35,170 INFO hook.py line 109 848561] Train: [77/100][450/605] Data 0.003 (0.002) Batch 0.933 (0.939) Remain 03:40:17 loss: 2.1379 psnr: 18.0539 Lr: 2.82219e-04
[2025-02-17 23:13:22,246 INFO hook.py line 109 848561] Train: [77/100][500/605] Data 0.003 (0.002) Batch 0.942 (0.940) Remain 03:39:33 loss: 2.4707 psnr: 15.8924 Lr: 2.80319e-04
[2025-02-17 23:14:09,096 INFO hook.py line 109 848561] Train: [77/100][550/605] Data 0.003 (0.002) Batch 0.925 (0.939) Remain 03:38:43 loss: 2.1250 psnr: 18.9283 Lr: 2.78424e-04
[2025-02-17 23:14:55,349 INFO hook.py line 109 848561] Train: [77/100][600/605] Data 0.002 (0.002) Batch 0.853 (0.938) Remain 03:37:39 loss: 2.1963 psnr: 18.0518 Lr: 2.76535e-04
[2025-02-17 23:14:59,745 INFO misc.py line 135 848561] Train result: loss: 2.2443 rgb_loss: 0.7668 psnr: 18.0008 depth_loss: 0.0652 feat_loss: 1.4123 
[2025-02-17 23:14:59,745 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 23:15:50,922 INFO hook.py line 109 848561] Train: [78/100][50/605] Data 0.003 (0.002) Batch 0.915 (0.943) Remain 03:37:59 loss: 2.2122 psnr: 18.5522 Lr: 2.74463e-04
[2025-02-17 23:16:37,699 INFO hook.py line 109 848561] Train: [78/100][100/605] Data 0.002 (0.002) Batch 0.916 (0.939) Remain 03:36:16 loss: 2.2762 psnr: 17.9701 Lr: 2.72585e-04
[2025-02-17 23:17:24,570 INFO hook.py line 109 848561] Train: [78/100][150/605] Data 0.002 (0.002) Batch 0.937 (0.939) Remain 03:35:20 loss: 2.3425 psnr: 16.9921 Lr: 2.70712e-04
[2025-02-17 23:18:11,486 INFO hook.py line 109 848561] Train: [78/100][200/605] Data 0.002 (0.002) Batch 0.912 (0.939) Remain 03:34:32 loss: 2.3132 psnr: 17.5697 Lr: 2.68845e-04
[2025-02-17 23:18:58,828 INFO hook.py line 109 848561] Train: [78/100][250/605] Data 0.002 (0.002) Batch 0.985 (0.940) Remain 03:34:08 loss: 2.6522 psnr: 15.4327 Lr: 2.66983e-04
[2025-02-17 23:19:46,087 INFO hook.py line 109 848561] Train: [78/100][300/605] Data 0.003 (0.002) Batch 0.961 (0.941) Remain 03:33:32 loss: 2.2525 psnr: 17.8913 Lr: 2.65127e-04
[2025-02-17 23:20:33,364 INFO hook.py line 109 848561] Train: [78/100][350/605] Data 0.003 (0.002) Batch 0.968 (0.942) Remain 03:32:54 loss: 2.5021 psnr: 16.0099 Lr: 2.63276e-04
[2025-02-17 23:21:20,614 INFO hook.py line 109 848561] Train: [78/100][400/605] Data 0.002 (0.002) Batch 0.943 (0.942) Remain 03:32:12 loss: 2.2010 psnr: 18.1463 Lr: 2.61431e-04
[2025-02-17 23:22:07,776 INFO hook.py line 109 848561] Train: [78/100][450/605] Data 0.002 (0.002) Batch 0.901 (0.942) Remain 03:31:27 loss: 2.3324 psnr: 17.8719 Lr: 2.59591e-04
[2025-02-17 23:22:55,171 INFO hook.py line 109 848561] Train: [78/100][500/605] Data 0.002 (0.002) Batch 0.956 (0.943) Remain 03:30:48 loss: 2.2970 psnr: 17.5279 Lr: 2.57757e-04
[2025-02-17 23:23:42,268 INFO hook.py line 109 848561] Train: [78/100][550/605] Data 0.002 (0.002) Batch 0.955 (0.943) Remain 03:29:59 loss: 2.2947 psnr: 17.3232 Lr: 2.55929e-04
[2025-02-17 23:24:28,588 INFO hook.py line 109 848561] Train: [78/100][600/605] Data 0.002 (0.002) Batch 0.876 (0.941) Remain 03:28:54 loss: 2.2282 psnr: 18.3348 Lr: 2.54105e-04
[2025-02-17 23:24:32,901 INFO misc.py line 135 848561] Train result: loss: 2.2434 rgb_loss: 0.7688 psnr: 17.9874 depth_loss: 0.0640 feat_loss: 1.4106 
[2025-02-17 23:24:32,902 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 23:25:23,967 INFO hook.py line 109 848561] Train: [79/100][50/605] Data 0.002 (0.003) Batch 0.951 (0.943) Remain 03:28:21 loss: 2.0166 psnr: 19.3675 Lr: 2.52106e-04
[2025-02-17 23:26:10,846 INFO hook.py line 109 848561] Train: [79/100][100/605] Data 0.002 (0.003) Batch 0.941 (0.940) Remain 03:26:58 loss: 2.3327 psnr: 16.8976 Lr: 2.50295e-04
[2025-02-17 23:26:57,936 INFO hook.py line 109 848561] Train: [79/100][150/605] Data 0.002 (0.002) Batch 0.924 (0.941) Remain 03:26:19 loss: 2.1571 psnr: 18.7098 Lr: 2.48489e-04
[2025-02-17 23:27:44,714 INFO hook.py line 109 848561] Train: [79/100][200/605] Data 0.002 (0.002) Batch 0.940 (0.939) Remain 03:25:15 loss: 2.3263 psnr: 17.1519 Lr: 2.46689e-04
[2025-02-17 23:28:31,794 INFO hook.py line 109 848561] Train: [79/100][250/605] Data 0.003 (0.002) Batch 0.906 (0.940) Remain 03:24:34 loss: 2.0601 psnr: 18.9556 Lr: 2.44895e-04
[2025-02-17 23:29:19,170 INFO hook.py line 109 848561] Train: [79/100][300/605] Data 0.003 (0.002) Batch 0.935 (0.941) Remain 03:24:04 loss: 2.0625 psnr: 20.0603 Lr: 2.43106e-04
[2025-02-17 23:30:05,909 INFO hook.py line 109 848561] Train: [79/100][350/605] Data 0.003 (0.002) Batch 0.925 (0.940) Remain 03:23:05 loss: 2.1480 psnr: 18.0815 Lr: 2.41323e-04
[2025-02-17 23:30:52,840 INFO hook.py line 109 848561] Train: [79/100][400/605] Data 0.002 (0.002) Batch 0.953 (0.940) Remain 03:22:15 loss: 2.1437 psnr: 19.1910 Lr: 2.39545e-04
[2025-02-17 23:31:40,198 INFO hook.py line 109 848561] Train: [79/100][450/605] Data 0.002 (0.002) Batch 0.972 (0.941) Remain 03:21:38 loss: 2.3203 psnr: 17.3367 Lr: 2.37773e-04
[2025-02-17 23:32:27,188 INFO hook.py line 109 848561] Train: [79/100][500/605] Data 0.003 (0.002) Batch 0.932 (0.941) Remain 03:20:50 loss: 1.9504 psnr: 20.2257 Lr: 2.36042e-04
[2025-02-17 23:33:14,397 INFO hook.py line 109 848561] Train: [79/100][550/605] Data 0.002 (0.002) Batch 0.947 (0.941) Remain 03:20:07 loss: 2.1941 psnr: 18.0296 Lr: 2.34282e-04
[2025-02-17 23:34:00,835 INFO hook.py line 109 848561] Train: [79/100][600/605] Data 0.002 (0.002) Batch 0.868 (0.940) Remain 03:19:07 loss: 2.1241 psnr: 18.2597 Lr: 2.32527e-04
[2025-02-17 23:34:05,202 INFO misc.py line 135 848561] Train result: loss: 2.2304 rgb_loss: 0.7580 psnr: 18.0897 depth_loss: 0.0638 feat_loss: 1.4086 
[2025-02-17 23:34:05,202 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 23:34:56,280 INFO hook.py line 109 848561] Train: [80/100][50/605] Data 0.003 (0.002) Batch 0.928 (0.940) Remain 03:18:15 loss: 2.1350 psnr: 18.9215 Lr: 2.30603e-04
[2025-02-17 23:35:43,184 INFO hook.py line 109 848561] Train: [80/100][100/605] Data 0.003 (0.002) Batch 0.958 (0.939) Remain 03:17:16 loss: 2.2814 psnr: 18.6626 Lr: 2.28860e-04
[2025-02-17 23:36:29,994 INFO hook.py line 109 848561] Train: [80/100][150/605] Data 0.002 (0.002) Batch 0.938 (0.938) Remain 03:16:17 loss: 2.3926 psnr: 16.7447 Lr: 2.27123e-04
[2025-02-17 23:37:16,640 INFO hook.py line 109 848561] Train: [80/100][200/605] Data 0.002 (0.002) Batch 0.955 (0.937) Remain 03:15:13 loss: 2.0924 psnr: 18.6058 Lr: 2.25392e-04
[2025-02-17 23:38:03,653 INFO hook.py line 109 848561] Train: [80/100][250/605] Data 0.003 (0.002) Batch 0.920 (0.937) Remain 03:14:36 loss: 2.0348 psnr: 19.3202 Lr: 2.23666e-04
[2025-02-17 23:38:50,923 INFO hook.py line 109 848561] Train: [80/100][300/605] Data 0.002 (0.002) Batch 1.142 (0.939) Remain 03:14:05 loss: 2.1665 psnr: 19.1973 Lr: 2.21947e-04
[2025-02-17 23:39:38,292 INFO hook.py line 109 848561] Train: [80/100][350/605] Data 0.004 (0.002) Batch 0.950 (0.940) Remain 03:13:34 loss: 2.4643 psnr: 16.2454 Lr: 2.20233e-04
[2025-02-17 23:40:25,439 INFO hook.py line 109 848561] Train: [80/100][400/605] Data 0.002 (0.002) Batch 0.941 (0.940) Remain 03:12:51 loss: 2.1126 psnr: 19.2057 Lr: 2.18525e-04
[2025-02-17 23:41:12,397 INFO hook.py line 109 848561] Train: [80/100][450/605] Data 0.002 (0.002) Batch 0.925 (0.940) Remain 03:12:02 loss: 2.1410 psnr: 19.1450 Lr: 2.16823e-04
[2025-02-17 23:41:59,419 INFO hook.py line 109 848561] Train: [80/100][500/605] Data 0.002 (0.002) Batch 0.916 (0.940) Remain 03:11:16 loss: 2.0729 psnr: 19.0484 Lr: 2.15126e-04
[2025-02-17 23:42:46,267 INFO hook.py line 109 848561] Train: [80/100][550/605] Data 0.003 (0.002) Batch 0.927 (0.940) Remain 03:10:25 loss: 2.1458 psnr: 18.7909 Lr: 2.13436e-04
[2025-02-17 23:43:32,373 INFO hook.py line 109 848561] Train: [80/100][600/605] Data 0.003 (0.002) Batch 0.883 (0.938) Remain 03:09:20 loss: 2.1671 psnr: 19.4910 Lr: 2.11751e-04
[2025-02-17 23:43:36,749 INFO misc.py line 135 848561] Train result: loss: 2.2444 rgb_loss: 0.7685 psnr: 17.9951 depth_loss: 0.0637 feat_loss: 1.4122 
[2025-02-17 23:43:36,749 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 23:44:27,736 INFO hook.py line 109 848561] Train: [81/100][50/605] Data 0.002 (0.002) Batch 0.943 (0.942) Remain 03:09:06 loss: 2.4292 psnr: 16.9021 Lr: 2.09905e-04
[2025-02-17 23:45:14,715 INFO hook.py line 109 848561] Train: [81/100][100/605] Data 0.002 (0.002) Batch 0.923 (0.941) Remain 03:08:06 loss: 2.2475 psnr: 18.0388 Lr: 2.08233e-04
[2025-02-17 23:46:01,714 INFO hook.py line 109 848561] Train: [81/100][150/605] Data 0.002 (0.002) Batch 0.932 (0.940) Remain 03:07:17 loss: 1.9808 psnr: 20.4579 Lr: 2.06566e-04
[2025-02-17 23:46:48,515 INFO hook.py line 109 848561] Train: [81/100][200/605] Data 0.002 (0.002) Batch 0.940 (0.939) Remain 03:06:17 loss: 2.1759 psnr: 18.0202 Lr: 2.04906e-04
[2025-02-17 23:47:35,304 INFO hook.py line 109 848561] Train: [81/100][250/605] Data 0.003 (0.002) Batch 0.938 (0.939) Remain 03:05:21 loss: 2.1277 psnr: 18.9485 Lr: 2.03251e-04
[2025-02-17 23:48:22,492 INFO hook.py line 109 848561] Train: [81/100][300/605] Data 0.003 (0.002) Batch 0.948 (0.939) Remain 03:04:45 loss: 2.3502 psnr: 17.1054 Lr: 2.01603e-04
[2025-02-17 23:49:09,769 INFO hook.py line 109 848561] Train: [81/100][350/605] Data 0.002 (0.002) Batch 0.914 (0.940) Remain 03:04:08 loss: 2.4134 psnr: 16.9919 Lr: 1.99960e-04
[2025-02-17 23:49:56,886 INFO hook.py line 109 848561] Train: [81/100][400/605] Data 0.002 (0.002) Batch 0.935 (0.941) Remain 03:03:24 loss: 2.4351 psnr: 16.3403 Lr: 1.98324e-04
[2025-02-17 23:50:43,755 INFO hook.py line 109 848561] Train: [81/100][450/605] Data 0.002 (0.002) Batch 0.924 (0.940) Remain 03:02:33 loss: 2.1017 psnr: 19.8166 Lr: 1.96693e-04
[2025-02-17 23:51:30,577 INFO hook.py line 109 848561] Train: [81/100][500/605] Data 0.002 (0.002) Batch 0.945 (0.940) Remain 03:01:41 loss: 2.0397 psnr: 20.3015 Lr: 1.95068e-04
[2025-02-17 23:52:17,527 INFO hook.py line 109 848561] Train: [81/100][550/605] Data 0.003 (0.002) Batch 0.921 (0.940) Remain 03:00:54 loss: 2.2542 psnr: 17.6589 Lr: 1.93450e-04
[2025-02-17 23:53:03,571 INFO hook.py line 109 848561] Train: [81/100][600/605] Data 0.002 (0.002) Batch 0.883 (0.938) Remain 02:59:48 loss: 2.3275 psnr: 17.6298 Lr: 1.91837e-04
[2025-02-17 23:53:07,866 INFO misc.py line 135 848561] Train result: loss: 2.2348 rgb_loss: 0.7612 psnr: 18.0503 depth_loss: 0.0635 feat_loss: 1.4102 
[2025-02-17 23:53:07,867 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-17 23:53:58,959 INFO hook.py line 109 848561] Train: [82/100][50/605] Data 0.003 (0.002) Batch 0.939 (0.939) Remain 02:59:01 loss: 2.2174 psnr: 17.7667 Lr: 1.90070e-04
[2025-02-17 23:54:45,981 INFO hook.py line 109 848561] Train: [82/100][100/605] Data 0.003 (0.002) Batch 0.930 (0.940) Remain 02:58:25 loss: 2.1896 psnr: 19.1125 Lr: 1.88471e-04
[2025-02-17 23:55:33,159 INFO hook.py line 109 848561] Train: [82/100][150/605] Data 0.004 (0.002) Batch 0.931 (0.941) Remain 02:57:54 loss: 2.2939 psnr: 17.1930 Lr: 1.86877e-04
[2025-02-17 23:56:20,141 INFO hook.py line 109 848561] Train: [82/100][200/605] Data 0.002 (0.002) Batch 0.932 (0.941) Remain 02:57:03 loss: 2.1256 psnr: 18.8690 Lr: 1.85289e-04
[2025-02-17 23:57:07,087 INFO hook.py line 109 848561] Train: [82/100][250/605] Data 0.002 (0.002) Batch 0.926 (0.940) Remain 02:56:12 loss: 2.1982 psnr: 17.9634 Lr: 1.83707e-04
[2025-02-17 23:57:53,963 INFO hook.py line 109 848561] Train: [82/100][300/605] Data 0.003 (0.002) Batch 0.953 (0.940) Remain 02:55:20 loss: 2.2250 psnr: 18.0681 Lr: 1.82132e-04
[2025-02-17 23:58:40,935 INFO hook.py line 109 848561] Train: [82/100][350/605] Data 0.002 (0.002) Batch 0.942 (0.940) Remain 02:54:33 loss: 2.2236 psnr: 17.9596 Lr: 1.80562e-04
[2025-02-17 23:59:28,326 INFO hook.py line 109 848561] Train: [82/100][400/605] Data 0.002 (0.002) Batch 0.920 (0.941) Remain 02:53:57 loss: 2.4201 psnr: 16.4787 Lr: 1.78999e-04
[2025-02-18 00:00:15,087 INFO hook.py line 109 848561] Train: [82/100][450/605] Data 0.003 (0.002) Batch 0.906 (0.940) Remain 02:53:03 loss: 2.2147 psnr: 17.9518 Lr: 1.77442e-04
[2025-02-18 00:01:02,053 INFO hook.py line 109 848561] Train: [82/100][500/605] Data 0.002 (0.002) Batch 0.979 (0.940) Remain 02:52:15 loss: 2.4418 psnr: 16.3606 Lr: 1.75891e-04
[2025-02-18 00:01:48,888 INFO hook.py line 109 848561] Train: [82/100][550/605] Data 0.002 (0.002) Batch 0.946 (0.940) Remain 02:51:25 loss: 2.3405 psnr: 17.0315 Lr: 1.74346e-04
[2025-02-18 00:02:35,316 INFO hook.py line 109 848561] Train: [82/100][600/605] Data 0.003 (0.002) Batch 0.854 (0.939) Remain 02:50:28 loss: 2.2393 psnr: 18.0836 Lr: 1.72807e-04
[2025-02-18 00:02:39,677 INFO misc.py line 135 848561] Train result: loss: 2.2432 rgb_loss: 0.7686 psnr: 17.9753 depth_loss: 0.0642 feat_loss: 1.4103 
[2025-02-18 00:02:39,677 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 00:03:30,654 INFO hook.py line 109 848561] Train: [83/100][50/605] Data 0.002 (0.002) Batch 0.927 (0.938) Remain 02:49:31 loss: 2.5289 psnr: 16.0519 Lr: 1.71122e-04
[2025-02-18 00:04:17,373 INFO hook.py line 109 848561] Train: [83/100][100/605] Data 0.003 (0.002) Batch 0.930 (0.936) Remain 02:48:22 loss: 2.3768 psnr: 16.8317 Lr: 1.69596e-04
[2025-02-18 00:05:04,406 INFO hook.py line 109 848561] Train: [83/100][150/605] Data 0.002 (0.002) Batch 0.964 (0.938) Remain 02:47:51 loss: 2.3805 psnr: 16.5470 Lr: 1.68076e-04
[2025-02-18 00:05:51,556 INFO hook.py line 109 848561] Train: [83/100][200/605] Data 0.002 (0.002) Batch 0.923 (0.939) Remain 02:47:19 loss: 2.2762 psnr: 18.4542 Lr: 1.66563e-04
[2025-02-18 00:06:38,542 INFO hook.py line 109 848561] Train: [83/100][250/605] Data 0.003 (0.002) Batch 0.939 (0.939) Remain 02:46:33 loss: 2.4639 psnr: 16.3906 Lr: 1.65056e-04
[2025-02-18 00:07:25,672 INFO hook.py line 109 848561] Train: [83/100][300/605] Data 0.003 (0.002) Batch 0.948 (0.940) Remain 02:45:52 loss: 2.0408 psnr: 18.6956 Lr: 1.63555e-04
[2025-02-18 00:08:12,395 INFO hook.py line 109 848561] Train: [83/100][350/605] Data 0.002 (0.002) Batch 0.935 (0.939) Remain 02:44:57 loss: 2.3338 psnr: 17.3419 Lr: 1.62061e-04
[2025-02-18 00:08:59,703 INFO hook.py line 109 848561] Train: [83/100][400/605] Data 0.002 (0.002) Batch 0.950 (0.940) Remain 02:44:19 loss: 2.0653 psnr: 19.9009 Lr: 1.60572e-04
[2025-02-18 00:09:46,721 INFO hook.py line 109 848561] Train: [83/100][450/605] Data 0.002 (0.002) Batch 0.924 (0.940) Remain 02:43:33 loss: 2.4087 psnr: 17.0424 Lr: 1.59090e-04
[2025-02-18 00:10:33,616 INFO hook.py line 109 848561] Train: [83/100][500/605] Data 0.002 (0.002) Batch 0.933 (0.940) Remain 02:42:44 loss: 2.0057 psnr: 19.8557 Lr: 1.57614e-04
[2025-02-18 00:11:20,493 INFO hook.py line 109 848561] Train: [83/100][550/605] Data 0.003 (0.002) Batch 0.925 (0.940) Remain 02:41:55 loss: 2.1828 psnr: 18.1021 Lr: 1.56145e-04
[2025-02-18 00:12:06,913 INFO hook.py line 109 848561] Train: [83/100][600/605] Data 0.002 (0.002) Batch 0.871 (0.939) Remain 02:40:58 loss: 2.1050 psnr: 18.2779 Lr: 1.54682e-04
[2025-02-18 00:12:11,231 INFO misc.py line 135 848561] Train result: loss: 2.2237 rgb_loss: 0.7508 psnr: 18.1249 depth_loss: 0.0639 feat_loss: 1.4089 
[2025-02-18 00:12:11,232 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 00:13:02,170 INFO hook.py line 109 848561] Train: [84/100][50/605] Data 0.002 (0.002) Batch 0.919 (0.938) Remain 02:39:56 loss: 2.1923 psnr: 17.8680 Lr: 1.53079e-04
[2025-02-18 00:13:49,086 INFO hook.py line 109 848561] Train: [84/100][100/605] Data 0.003 (0.002) Batch 0.951 (0.938) Remain 02:39:13 loss: 2.0817 psnr: 19.7524 Lr: 1.51629e-04
[2025-02-18 00:14:36,218 INFO hook.py line 109 848561] Train: [84/100][150/605] Data 0.003 (0.002) Batch 0.969 (0.940) Remain 02:38:42 loss: 2.3571 psnr: 16.3353 Lr: 1.50186e-04
[2025-02-18 00:15:23,331 INFO hook.py line 109 848561] Train: [84/100][200/605] Data 0.002 (0.002) Batch 0.936 (0.940) Remain 02:38:02 loss: 2.1574 psnr: 18.3915 Lr: 1.48749e-04
[2025-02-18 00:16:10,254 INFO hook.py line 109 848561] Train: [84/100][250/605] Data 0.001 (0.002) Batch 0.936 (0.940) Remain 02:37:11 loss: 2.2885 psnr: 17.7328 Lr: 1.47318e-04
[2025-02-18 00:16:57,292 INFO hook.py line 109 848561] Train: [84/100][300/605] Data 0.003 (0.002) Batch 0.933 (0.940) Remain 02:36:26 loss: 2.3241 psnr: 17.2027 Lr: 1.45893e-04
[2025-02-18 00:17:43,806 INFO hook.py line 109 848561] Train: [84/100][350/605] Data 0.003 (0.002) Batch 0.910 (0.939) Remain 02:35:25 loss: 2.3343 psnr: 16.8271 Lr: 1.44475e-04
[2025-02-18 00:18:30,829 INFO hook.py line 109 848561] Train: [84/100][400/605] Data 0.003 (0.002) Batch 0.916 (0.939) Remain 02:34:40 loss: 2.2531 psnr: 18.4997 Lr: 1.43063e-04
[2025-02-18 00:19:18,229 INFO hook.py line 109 848561] Train: [84/100][450/605] Data 0.003 (0.002) Batch 0.943 (0.940) Remain 02:34:03 loss: 2.1635 psnr: 18.1259 Lr: 1.41658e-04
[2025-02-18 00:20:05,517 INFO hook.py line 109 848561] Train: [84/100][500/605] Data 0.003 (0.002) Batch 0.947 (0.940) Remain 02:33:22 loss: 2.3186 psnr: 17.8152 Lr: 1.40259e-04
[2025-02-18 00:20:52,491 INFO hook.py line 109 848561] Train: [84/100][550/605] Data 0.002 (0.002) Batch 0.954 (0.940) Remain 02:32:34 loss: 2.4302 psnr: 16.4385 Lr: 1.38866e-04
[2025-02-18 00:21:38,619 INFO hook.py line 109 848561] Train: [84/100][600/605] Data 0.001 (0.002) Batch 0.838 (0.939) Remain 02:31:33 loss: 2.1730 psnr: 18.7290 Lr: 1.37480e-04
[2025-02-18 00:21:42,932 INFO misc.py line 135 848561] Train result: loss: 2.2304 rgb_loss: 0.7588 psnr: 18.0663 depth_loss: 0.0629 feat_loss: 1.4088 
[2025-02-18 00:21:42,934 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 00:22:34,219 INFO hook.py line 109 848561] Train: [85/100][50/605] Data 0.002 (0.002) Batch 0.970 (0.941) Remain 02:31:03 loss: 2.4234 psnr: 17.5622 Lr: 1.35963e-04
[2025-02-18 00:23:21,263 INFO hook.py line 109 848561] Train: [85/100][100/605] Data 0.003 (0.002) Batch 0.937 (0.941) Remain 02:30:15 loss: 2.1089 psnr: 18.3298 Lr: 1.34591e-04
[2025-02-18 00:24:08,568 INFO hook.py line 109 848561] Train: [85/100][150/605] Data 0.002 (0.002) Batch 0.930 (0.943) Remain 02:29:44 loss: 2.6579 psnr: 15.5311 Lr: 1.33224e-04
[2025-02-18 00:24:55,365 INFO hook.py line 109 848561] Train: [85/100][200/605] Data 0.001 (0.002) Batch 0.924 (0.941) Remain 02:28:40 loss: 2.2349 psnr: 18.2864 Lr: 1.31865e-04
[2025-02-18 00:25:42,388 INFO hook.py line 109 848561] Train: [85/100][250/605] Data 0.001 (0.002) Batch 0.923 (0.941) Remain 02:27:52 loss: 1.9409 psnr: 21.0899 Lr: 1.30512e-04
[2025-02-18 00:26:29,620 INFO hook.py line 109 848561] Train: [85/100][300/605] Data 0.003 (0.002) Batch 0.917 (0.942) Remain 02:27:11 loss: 2.2858 psnr: 17.7526 Lr: 1.29165e-04
[2025-02-18 00:27:16,457 INFO hook.py line 109 848561] Train: [85/100][350/605] Data 0.001 (0.002) Batch 0.976 (0.941) Remain 02:26:18 loss: 2.1823 psnr: 18.5269 Lr: 1.27825e-04
[2025-02-18 00:28:03,627 INFO hook.py line 109 848561] Train: [85/100][400/605] Data 0.002 (0.002) Batch 0.941 (0.941) Remain 02:25:34 loss: 1.9824 psnr: 20.8734 Lr: 1.26491e-04
[2025-02-18 00:28:51,061 INFO hook.py line 109 848561] Train: [85/100][450/605] Data 0.003 (0.002) Batch 1.007 (0.942) Remain 02:24:54 loss: 2.0816 psnr: 19.1265 Lr: 1.25164e-04
[2025-02-18 00:29:37,943 INFO hook.py line 109 848561] Train: [85/100][500/605] Data 0.002 (0.002) Batch 0.914 (0.942) Remain 02:24:03 loss: 2.1173 psnr: 18.9554 Lr: 1.23844e-04
[2025-02-18 00:30:24,914 INFO hook.py line 109 848561] Train: [85/100][550/605] Data 0.002 (0.002) Batch 0.940 (0.941) Remain 02:23:14 loss: 2.3711 psnr: 17.5542 Lr: 1.22530e-04
[2025-02-18 00:31:11,341 INFO hook.py line 109 848561] Train: [85/100][600/605] Data 0.002 (0.002) Batch 0.863 (0.940) Remain 02:22:17 loss: 2.5090 psnr: 16.1991 Lr: 1.21222e-04
[2025-02-18 00:31:15,662 INFO misc.py line 135 848561] Train result: loss: 2.2221 rgb_loss: 0.7504 psnr: 18.1305 depth_loss: 0.0638 feat_loss: 1.4079 
[2025-02-18 00:31:15,664 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 00:32:06,687 INFO hook.py line 109 848561] Train: [86/100][50/605] Data 0.003 (0.002) Batch 0.921 (0.942) Remain 02:21:41 loss: 2.1214 psnr: 18.8819 Lr: 1.19792e-04
[2025-02-18 00:32:53,536 INFO hook.py line 109 848561] Train: [86/100][100/605] Data 0.002 (0.002) Batch 0.940 (0.939) Remain 02:20:31 loss: 2.2316 psnr: 18.0418 Lr: 1.18498e-04
[2025-02-18 00:33:40,384 INFO hook.py line 109 848561] Train: [86/100][150/605] Data 0.002 (0.002) Batch 0.960 (0.939) Remain 02:19:36 loss: 2.2366 psnr: 17.8993 Lr: 1.17211e-04
[2025-02-18 00:34:27,247 INFO hook.py line 109 848561] Train: [86/100][200/605] Data 0.002 (0.002) Batch 0.924 (0.938) Remain 02:18:46 loss: 2.0559 psnr: 19.7032 Lr: 1.15931e-04
[2025-02-18 00:35:14,306 INFO hook.py line 109 848561] Train: [86/100][250/605] Data 0.002 (0.002) Batch 0.940 (0.939) Remain 02:18:05 loss: 2.0782 psnr: 19.1766 Lr: 1.14657e-04
[2025-02-18 00:36:01,499 INFO hook.py line 109 848561] Train: [86/100][300/605] Data 0.003 (0.002) Batch 0.950 (0.940) Remain 02:17:25 loss: 2.0856 psnr: 19.3356 Lr: 1.13389e-04
[2025-02-18 00:36:48,620 INFO hook.py line 109 848561] Train: [86/100][350/605] Data 0.002 (0.002) Batch 0.957 (0.940) Remain 02:16:42 loss: 2.2805 psnr: 17.3261 Lr: 1.12129e-04
[2025-02-18 00:37:35,747 INFO hook.py line 109 848561] Train: [86/100][400/605] Data 0.002 (0.002) Batch 0.932 (0.940) Remain 02:15:57 loss: 2.3545 psnr: 17.7147 Lr: 1.10900e-04
[2025-02-18 00:38:22,732 INFO hook.py line 109 848561] Train: [86/100][450/605] Data 0.003 (0.002) Batch 0.927 (0.940) Remain 02:15:10 loss: 2.3811 psnr: 16.9698 Lr: 1.09652e-04
[2025-02-18 00:39:09,963 INFO hook.py line 109 848561] Train: [86/100][500/605] Data 0.003 (0.002) Batch 0.937 (0.941) Remain 02:14:26 loss: 2.1180 psnr: 18.8119 Lr: 1.08411e-04
[2025-02-18 00:39:57,103 INFO hook.py line 109 848561] Train: [86/100][550/605] Data 0.003 (0.002) Batch 0.947 (0.941) Remain 02:13:41 loss: 2.2844 psnr: 17.7759 Lr: 1.07177e-04
[2025-02-18 00:40:43,457 INFO hook.py line 109 848561] Train: [86/100][600/605] Data 0.003 (0.002) Batch 0.896 (0.940) Remain 02:12:44 loss: 2.1215 psnr: 18.9898 Lr: 1.05950e-04
[2025-02-18 00:40:47,790 INFO misc.py line 135 848561] Train result: loss: 2.2258 rgb_loss: 0.7547 psnr: 18.0641 depth_loss: 0.0626 feat_loss: 1.4086 
[2025-02-18 00:40:47,791 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 00:41:39,083 INFO hook.py line 109 848561] Train: [87/100][50/605] Data 0.002 (0.002) Batch 0.941 (0.939) Remain 02:11:45 loss: 2.1075 psnr: 19.4741 Lr: 1.04607e-04
[2025-02-18 00:42:26,311 INFO hook.py line 109 848561] Train: [87/100][100/605] Data 0.003 (0.002) Batch 0.924 (0.942) Remain 02:11:23 loss: 2.2576 psnr: 17.7067 Lr: 1.03394e-04
[2025-02-18 00:43:13,173 INFO hook.py line 109 848561] Train: [87/100][150/605] Data 0.003 (0.002) Batch 0.937 (0.940) Remain 02:10:22 loss: 2.2927 psnr: 17.1542 Lr: 1.02187e-04
[2025-02-18 00:43:59,995 INFO hook.py line 109 848561] Train: [87/100][200/605] Data 0.003 (0.002) Batch 0.984 (0.939) Remain 02:09:27 loss: 2.0829 psnr: 19.0176 Lr: 1.00987e-04
[2025-02-18 00:44:46,914 INFO hook.py line 109 848561] Train: [87/100][250/605] Data 0.003 (0.002) Batch 0.915 (0.939) Remain 02:08:39 loss: 2.1636 psnr: 17.8974 Lr: 9.97934e-05
[2025-02-18 00:45:33,854 INFO hook.py line 109 848561] Train: [87/100][300/605] Data 0.002 (0.002) Batch 0.943 (0.939) Remain 02:07:52 loss: 2.0512 psnr: 19.9492 Lr: 9.86068e-05
[2025-02-18 00:46:21,104 INFO hook.py line 109 848561] Train: [87/100][350/605] Data 0.004 (0.002) Batch 0.947 (0.940) Remain 02:07:12 loss: 2.1564 psnr: 18.4466 Lr: 9.74269e-05
[2025-02-18 00:47:07,869 INFO hook.py line 109 848561] Train: [87/100][400/605] Data 0.003 (0.002) Batch 0.903 (0.939) Remain 02:06:20 loss: 2.3163 psnr: 17.4233 Lr: 9.62537e-05
[2025-02-18 00:47:54,869 INFO hook.py line 109 848561] Train: [87/100][450/605] Data 0.003 (0.002) Batch 0.953 (0.939) Remain 02:05:34 loss: 2.1442 psnr: 18.0192 Lr: 9.50873e-05
[2025-02-18 00:48:42,407 INFO hook.py line 109 848561] Train: [87/100][500/605] Data 0.003 (0.002) Batch 0.929 (0.941) Remain 02:04:56 loss: 2.1052 psnr: 18.6601 Lr: 9.39276e-05
[2025-02-18 00:49:29,424 INFO hook.py line 109 848561] Train: [87/100][550/605] Data 0.003 (0.002) Batch 0.918 (0.941) Remain 02:04:08 loss: 2.3631 psnr: 17.4366 Lr: 9.27747e-05
[2025-02-18 00:50:15,822 INFO hook.py line 109 848561] Train: [87/100][600/605] Data 0.002 (0.002) Batch 0.863 (0.939) Remain 02:03:13 loss: 2.2082 psnr: 18.1134 Lr: 9.16286e-05
[2025-02-18 00:50:20,198 INFO misc.py line 135 848561] Train result: loss: 2.2213 rgb_loss: 0.7511 psnr: 18.1529 depth_loss: 0.0634 feat_loss: 1.4068 
[2025-02-18 00:50:20,198 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 00:51:11,316 INFO hook.py line 109 848561] Train: [88/100][50/605] Data 0.002 (0.002) Batch 0.949 (0.939) Remain 02:02:19 loss: 2.0300 psnr: 20.4763 Lr: 9.03757e-05
[2025-02-18 00:51:58,446 INFO hook.py line 109 848561] Train: [88/100][100/605] Data 0.003 (0.003) Batch 0.959 (0.941) Remain 02:01:46 loss: 2.0809 psnr: 18.8175 Lr: 8.92439e-05
[2025-02-18 00:52:45,210 INFO hook.py line 109 848561] Train: [88/100][150/605] Data 0.003 (0.003) Batch 0.926 (0.939) Remain 02:00:44 loss: 2.2205 psnr: 17.5295 Lr: 8.81188e-05
[2025-02-18 00:53:32,091 INFO hook.py line 109 848561] Train: [88/100][200/605] Data 0.002 (0.003) Batch 0.931 (0.939) Remain 01:59:54 loss: 2.2201 psnr: 18.1939 Lr: 8.70006e-05
[2025-02-18 00:54:19,089 INFO hook.py line 109 848561] Train: [88/100][250/605] Data 0.003 (0.003) Batch 0.937 (0.939) Remain 01:59:09 loss: 2.2843 psnr: 17.7703 Lr: 8.58892e-05
[2025-02-18 00:55:05,914 INFO hook.py line 109 848561] Train: [88/100][300/605] Data 0.003 (0.003) Batch 0.930 (0.939) Remain 01:58:19 loss: 2.4427 psnr: 16.7291 Lr: 8.47846e-05
[2025-02-18 00:55:52,739 INFO hook.py line 109 848561] Train: [88/100][350/605] Data 0.003 (0.003) Batch 0.924 (0.938) Remain 01:57:30 loss: 2.2696 psnr: 17.5611 Lr: 8.36868e-05
[2025-02-18 00:56:39,956 INFO hook.py line 109 848561] Train: [88/100][400/605] Data 0.002 (0.002) Batch 0.950 (0.939) Remain 01:56:49 loss: 2.3230 psnr: 17.4571 Lr: 8.25959e-05
[2025-02-18 00:57:27,143 INFO hook.py line 109 848561] Train: [88/100][450/605] Data 0.003 (0.002) Batch 0.926 (0.940) Remain 01:56:06 loss: 2.0383 psnr: 19.3265 Lr: 8.15119e-05
[2025-02-18 00:58:14,495 INFO hook.py line 109 848561] Train: [88/100][500/605] Data 0.002 (0.002) Batch 0.946 (0.940) Remain 01:55:25 loss: 2.4219 psnr: 16.3022 Lr: 8.04347e-05
[2025-02-18 00:59:02,008 INFO hook.py line 109 848561] Train: [88/100][550/605] Data 0.004 (0.002) Batch 0.926 (0.941) Remain 01:54:44 loss: 2.3126 psnr: 16.8158 Lr: 7.93643e-05
[2025-02-18 00:59:48,416 INFO hook.py line 109 848561] Train: [88/100][600/605] Data 0.002 (0.002) Batch 0.865 (0.940) Remain 01:53:49 loss: 2.3850 psnr: 16.4477 Lr: 7.83009e-05
[2025-02-18 00:59:52,756 INFO misc.py line 135 848561] Train result: loss: 2.2298 rgb_loss: 0.7588 psnr: 18.0559 depth_loss: 0.0637 feat_loss: 1.4073 
[2025-02-18 00:59:52,756 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:00:43,805 INFO hook.py line 109 848561] Train: [89/100][50/605] Data 0.002 (0.002) Batch 0.915 (0.935) Remain 01:52:19 loss: 2.1744 psnr: 18.5032 Lr: 7.71390e-05
[2025-02-18 01:01:30,901 INFO hook.py line 109 848561] Train: [89/100][100/605] Data 0.002 (0.002) Batch 0.965 (0.938) Remain 01:51:59 loss: 2.2720 psnr: 18.0278 Lr: 7.60900e-05
[2025-02-18 01:02:17,674 INFO hook.py line 109 848561] Train: [89/100][150/605] Data 0.003 (0.002) Batch 0.905 (0.937) Remain 01:51:05 loss: 2.1617 psnr: 18.4803 Lr: 7.50479e-05
[2025-02-18 01:03:04,529 INFO hook.py line 109 848561] Train: [89/100][200/605] Data 0.005 (0.002) Batch 0.926 (0.937) Remain 01:50:17 loss: 2.1895 psnr: 18.9583 Lr: 7.40128e-05
[2025-02-18 01:03:51,733 INFO hook.py line 109 848561] Train: [89/100][250/605] Data 0.002 (0.002) Batch 0.929 (0.939) Remain 01:49:40 loss: 2.3713 psnr: 16.8552 Lr: 7.29845e-05
[2025-02-18 01:04:38,734 INFO hook.py line 109 848561] Train: [89/100][300/605] Data 0.003 (0.002) Batch 0.962 (0.939) Remain 01:48:54 loss: 2.3539 psnr: 17.0696 Lr: 7.19632e-05
[2025-02-18 01:05:25,719 INFO hook.py line 109 848561] Train: [89/100][350/605] Data 0.003 (0.002) Batch 0.920 (0.939) Remain 01:48:08 loss: 2.1135 psnr: 20.4412 Lr: 7.09488e-05
[2025-02-18 01:06:12,676 INFO hook.py line 109 848561] Train: [89/100][400/605] Data 0.003 (0.002) Batch 0.961 (0.939) Remain 01:47:21 loss: 2.2464 psnr: 17.4278 Lr: 6.99413e-05
[2025-02-18 01:06:59,726 INFO hook.py line 109 848561] Train: [89/100][450/605] Data 0.002 (0.002) Batch 0.925 (0.939) Remain 01:46:36 loss: 2.2746 psnr: 17.5481 Lr: 6.89408e-05
[2025-02-18 01:07:46,832 INFO hook.py line 109 848561] Train: [89/100][500/605] Data 0.003 (0.002) Batch 0.927 (0.940) Remain 01:45:51 loss: 2.0428 psnr: 19.7408 Lr: 6.79472e-05
[2025-02-18 01:08:34,279 INFO hook.py line 109 848561] Train: [89/100][550/605] Data 0.004 (0.002) Batch 0.933 (0.940) Remain 01:45:10 loss: 2.1380 psnr: 18.8435 Lr: 6.69606e-05
[2025-02-18 01:09:20,628 INFO hook.py line 109 848561] Train: [89/100][600/605] Data 0.002 (0.002) Batch 0.880 (0.939) Remain 01:44:15 loss: 2.1280 psnr: 18.1920 Lr: 6.59810e-05
[2025-02-18 01:09:25,047 INFO misc.py line 135 848561] Train result: loss: 2.2249 rgb_loss: 0.7560 psnr: 18.1198 depth_loss: 0.0635 feat_loss: 1.4054 
[2025-02-18 01:09:25,048 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:10:15,718 INFO hook.py line 109 848561] Train: [90/100][50/605] Data 0.002 (0.002) Batch 0.945 (0.935) Remain 01:42:56 loss: 2.0206 psnr: 19.6132 Lr: 6.49114e-05
[2025-02-18 01:11:02,448 INFO hook.py line 109 848561] Train: [90/100][100/605] Data 0.003 (0.002) Batch 0.950 (0.935) Remain 01:42:08 loss: 2.2080 psnr: 18.0084 Lr: 6.39465e-05
[2025-02-18 01:11:49,352 INFO hook.py line 109 848561] Train: [90/100][150/605] Data 0.003 (0.002) Batch 0.913 (0.936) Remain 01:41:28 loss: 2.2808 psnr: 17.1679 Lr: 6.30076e-05
[2025-02-18 01:12:36,139 INFO hook.py line 109 848561] Train: [90/100][200/605] Data 0.003 (0.002) Batch 0.974 (0.936) Remain 01:40:41 loss: 2.4118 psnr: 16.2827 Lr: 6.20565e-05
[2025-02-18 01:13:23,133 INFO hook.py line 109 848561] Train: [90/100][250/605] Data 0.002 (0.002) Batch 0.959 (0.937) Remain 01:39:59 loss: 2.0134 psnr: 19.9296 Lr: 6.11123e-05
[2025-02-18 01:14:10,044 INFO hook.py line 109 848561] Train: [90/100][300/605] Data 0.003 (0.002) Batch 0.933 (0.937) Remain 01:39:14 loss: 2.1712 psnr: 18.6278 Lr: 6.01752e-05
[2025-02-18 01:14:57,047 INFO hook.py line 109 848561] Train: [90/100][350/605] Data 0.001 (0.002) Batch 0.934 (0.937) Remain 01:38:30 loss: 2.1171 psnr: 18.4582 Lr: 5.92451e-05
[2025-02-18 01:15:43,884 INFO hook.py line 109 848561] Train: [90/100][400/605] Data 0.003 (0.002) Batch 0.957 (0.937) Remain 01:37:42 loss: 2.3873 psnr: 16.5648 Lr: 5.83221e-05
[2025-02-18 01:16:30,922 INFO hook.py line 109 848561] Train: [90/100][450/605] Data 0.003 (0.002) Batch 0.945 (0.938) Remain 01:36:58 loss: 2.2187 psnr: 17.5628 Lr: 5.74061e-05
[2025-02-18 01:17:17,979 INFO hook.py line 109 848561] Train: [90/100][500/605] Data 0.003 (0.002) Batch 0.950 (0.938) Remain 01:36:13 loss: 2.1768 psnr: 18.3176 Lr: 5.64971e-05
[2025-02-18 01:18:05,261 INFO hook.py line 109 848561] Train: [90/100][550/605] Data 0.002 (0.002) Batch 0.973 (0.939) Remain 01:35:31 loss: 2.1519 psnr: 19.6009 Lr: 5.55951e-05
[2025-02-18 01:18:51,499 INFO hook.py line 109 848561] Train: [90/100][600/605] Data 0.004 (0.002) Batch 0.864 (0.938) Remain 01:34:37 loss: 2.1518 psnr: 18.1138 Lr: 5.47003e-05
[2025-02-18 01:18:55,892 INFO misc.py line 135 848561] Train result: loss: 2.2232 rgb_loss: 0.7534 psnr: 18.1123 depth_loss: 0.0629 feat_loss: 1.4068 
[2025-02-18 01:18:55,893 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:19:47,014 INFO hook.py line 109 848561] Train: [91/100][50/605] Data 0.002 (0.002) Batch 0.936 (0.939) Remain 01:33:53 loss: 2.3823 psnr: 17.1972 Lr: 5.37241e-05
[2025-02-18 01:20:33,883 INFO hook.py line 109 848561] Train: [91/100][100/605] Data 0.002 (0.002) Batch 0.935 (0.938) Remain 01:33:01 loss: 2.2344 psnr: 18.5184 Lr: 5.28440e-05
[2025-02-18 01:21:20,834 INFO hook.py line 109 848561] Train: [91/100][150/605] Data 0.004 (0.002) Batch 0.910 (0.938) Remain 01:32:16 loss: 2.0829 psnr: 19.0045 Lr: 5.19710e-05
[2025-02-18 01:22:07,662 INFO hook.py line 109 848561] Train: [91/100][200/605] Data 0.003 (0.002) Batch 0.948 (0.938) Remain 01:31:27 loss: 2.1740 psnr: 17.7829 Lr: 5.11051e-05
[2025-02-18 01:22:54,723 INFO hook.py line 109 848561] Train: [91/100][250/605] Data 0.003 (0.002) Batch 0.963 (0.939) Remain 01:30:43 loss: 2.1928 psnr: 18.2670 Lr: 5.02463e-05
[2025-02-18 01:23:41,456 INFO hook.py line 109 848561] Train: [91/100][300/605] Data 0.002 (0.002) Batch 0.949 (0.938) Remain 01:29:53 loss: 2.2243 psnr: 17.7896 Lr: 4.93946e-05
[2025-02-18 01:24:28,297 INFO hook.py line 109 848561] Train: [91/100][350/605] Data 0.003 (0.002) Batch 0.930 (0.938) Remain 01:29:05 loss: 2.0836 psnr: 18.7402 Lr: 4.85500e-05
[2025-02-18 01:25:15,339 INFO hook.py line 109 848561] Train: [91/100][400/605] Data 0.003 (0.002) Batch 0.912 (0.938) Remain 01:28:20 loss: 2.3384 psnr: 17.1446 Lr: 4.77125e-05
[2025-02-18 01:26:02,337 INFO hook.py line 109 848561] Train: [91/100][450/605] Data 0.002 (0.002) Batch 0.920 (0.938) Remain 01:27:34 loss: 2.3676 psnr: 16.2144 Lr: 4.68821e-05
[2025-02-18 01:26:49,425 INFO hook.py line 109 848561] Train: [91/100][500/605] Data 0.002 (0.002) Batch 0.965 (0.939) Remain 01:26:49 loss: 2.2152 psnr: 17.0083 Lr: 4.60589e-05
[2025-02-18 01:27:36,279 INFO hook.py line 109 848561] Train: [91/100][550/605] Data 0.001 (0.002) Batch 0.930 (0.939) Remain 01:26:02 loss: 2.0330 psnr: 19.9518 Lr: 4.52427e-05
[2025-02-18 01:28:22,584 INFO hook.py line 109 848561] Train: [91/100][600/605] Data 0.002 (0.002) Batch 0.864 (0.938) Remain 01:25:09 loss: 2.1254 psnr: 17.9807 Lr: 4.44337e-05
[2025-02-18 01:28:26,950 INFO misc.py line 135 848561] Train result: loss: 2.2167 rgb_loss: 0.7484 psnr: 18.1237 depth_loss: 0.0626 feat_loss: 1.4057 
[2025-02-18 01:28:26,952 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:29:17,847 INFO hook.py line 109 848561] Train: [92/100][50/605] Data 0.002 (0.002) Batch 0.919 (0.937) Remain 01:24:13 loss: 1.9889 psnr: 21.0731 Lr: 4.35520e-05
[2025-02-18 01:30:04,742 INFO hook.py line 109 848561] Train: [92/100][100/605] Data 0.003 (0.002) Batch 0.941 (0.937) Remain 01:23:29 loss: 2.2315 psnr: 18.1831 Lr: 4.27580e-05
[2025-02-18 01:30:51,667 INFO hook.py line 109 848561] Train: [92/100][150/605] Data 0.002 (0.002) Batch 0.941 (0.938) Remain 01:22:45 loss: 2.3406 psnr: 16.6363 Lr: 4.19712e-05
[2025-02-18 01:31:38,658 INFO hook.py line 109 848561] Train: [92/100][200/605] Data 0.002 (0.002) Batch 0.933 (0.938) Remain 01:22:01 loss: 2.3266 psnr: 17.2235 Lr: 4.11914e-05
[2025-02-18 01:32:25,691 INFO hook.py line 109 848561] Train: [92/100][250/605] Data 0.004 (0.002) Batch 0.935 (0.939) Remain 01:21:16 loss: 2.2090 psnr: 17.9219 Lr: 4.04189e-05
[2025-02-18 01:33:12,595 INFO hook.py line 109 848561] Train: [92/100][300/605] Data 0.002 (0.002) Batch 0.959 (0.939) Remain 01:20:29 loss: 2.2609 psnr: 17.8323 Lr: 3.96535e-05
[2025-02-18 01:33:59,821 INFO hook.py line 109 848561] Train: [92/100][350/605] Data 0.002 (0.002) Batch 0.945 (0.939) Remain 01:19:46 loss: 1.9592 psnr: 21.4014 Lr: 3.88953e-05
[2025-02-18 01:34:46,623 INFO hook.py line 109 848561] Train: [92/100][400/605] Data 0.003 (0.002) Batch 0.964 (0.939) Remain 01:18:57 loss: 2.1128 psnr: 19.1828 Lr: 3.81443e-05
[2025-02-18 01:35:33,676 INFO hook.py line 109 848561] Train: [92/100][450/605] Data 0.002 (0.002) Batch 0.927 (0.939) Remain 01:18:11 loss: 2.1245 psnr: 18.8330 Lr: 3.74004e-05
[2025-02-18 01:36:20,739 INFO hook.py line 109 848561] Train: [92/100][500/605] Data 0.003 (0.002) Batch 0.939 (0.939) Remain 01:17:25 loss: 2.3733 psnr: 17.0377 Lr: 3.66638e-05
[2025-02-18 01:37:07,589 INFO hook.py line 109 848561] Train: [92/100][550/605] Data 0.003 (0.002) Batch 0.898 (0.939) Remain 01:16:37 loss: 2.4330 psnr: 16.5535 Lr: 3.59343e-05
[2025-02-18 01:37:53,738 INFO hook.py line 109 848561] Train: [92/100][600/605] Data 0.002 (0.002) Batch 0.891 (0.938) Remain 01:15:44 loss: 2.0194 psnr: 18.7381 Lr: 3.52121e-05
[2025-02-18 01:37:58,101 INFO misc.py line 135 848561] Train result: loss: 2.2056 rgb_loss: 0.7407 psnr: 18.2050 depth_loss: 0.0627 feat_loss: 1.4022 
[2025-02-18 01:37:58,102 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:38:49,712 INFO hook.py line 109 848561] Train: [93/100][50/605] Data 0.002 (0.003) Batch 0.914 (0.946) Remain 01:15:32 loss: 2.3272 psnr: 17.3179 Lr: 3.44401e-05
[2025-02-18 01:39:36,613 INFO hook.py line 109 848561] Train: [93/100][100/605] Data 0.003 (0.002) Batch 0.951 (0.942) Remain 01:14:24 loss: 2.1984 psnr: 18.3028 Lr: 3.37329e-05
[2025-02-18 01:40:23,626 INFO hook.py line 109 848561] Train: [93/100][150/605] Data 0.002 (0.002) Batch 0.986 (0.941) Remain 01:13:35 loss: 2.3399 psnr: 17.2017 Lr: 3.30328e-05
[2025-02-18 01:41:10,628 INFO hook.py line 109 848561] Train: [93/100][200/605] Data 0.002 (0.002) Batch 0.925 (0.941) Remain 01:12:46 loss: 2.2788 psnr: 17.7660 Lr: 3.23400e-05
[2025-02-18 01:41:57,717 INFO hook.py line 109 848561] Train: [93/100][250/605] Data 0.002 (0.002) Batch 0.960 (0.941) Remain 01:12:00 loss: 2.2078 psnr: 18.4780 Lr: 3.16544e-05
[2025-02-18 01:42:44,655 INFO hook.py line 109 848561] Train: [93/100][300/605] Data 0.002 (0.002) Batch 0.946 (0.941) Remain 01:11:11 loss: 2.1839 psnr: 18.4469 Lr: 3.09760e-05
[2025-02-18 01:43:31,906 INFO hook.py line 109 848561] Train: [93/100][350/605] Data 0.002 (0.002) Batch 0.955 (0.941) Remain 01:10:26 loss: 2.2213 psnr: 17.8163 Lr: 3.03049e-05
[2025-02-18 01:44:18,964 INFO hook.py line 109 848561] Train: [93/100][400/605] Data 0.003 (0.002) Batch 0.916 (0.941) Remain 01:09:39 loss: 2.1945 psnr: 17.8110 Lr: 2.96410e-05
[2025-02-18 01:45:05,993 INFO hook.py line 109 848561] Train: [93/100][450/605] Data 0.002 (0.002) Batch 0.969 (0.941) Remain 01:08:52 loss: 2.2731 psnr: 17.7899 Lr: 2.89844e-05
[2025-02-18 01:45:53,244 INFO hook.py line 109 848561] Train: [93/100][500/605] Data 0.002 (0.002) Batch 0.943 (0.942) Remain 01:08:06 loss: 2.3255 psnr: 16.9876 Lr: 2.83350e-05
[2025-02-18 01:46:40,360 INFO hook.py line 109 848561] Train: [93/100][550/605] Data 0.002 (0.002) Batch 0.920 (0.942) Remain 01:07:19 loss: 2.5431 psnr: 16.0756 Lr: 2.76929e-05
[2025-02-18 01:47:26,598 INFO hook.py line 109 848561] Train: [93/100][600/605] Data 0.002 (0.002) Batch 0.878 (0.940) Remain 01:06:26 loss: 2.2136 psnr: 18.4244 Lr: 2.70580e-05
[2025-02-18 01:47:30,958 INFO misc.py line 135 848561] Train result: loss: 2.2100 rgb_loss: 0.7429 psnr: 18.2268 depth_loss: 0.0631 feat_loss: 1.4040 
[2025-02-18 01:47:30,959 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:48:22,623 INFO hook.py line 109 848561] Train: [94/100][50/605] Data 0.003 (0.003) Batch 0.941 (0.948) Remain 01:06:07 loss: 2.1667 psnr: 18.5429 Lr: 2.63681e-05
[2025-02-18 01:49:09,439 INFO hook.py line 109 848561] Train: [94/100][100/605] Data 0.002 (0.002) Batch 0.919 (0.942) Remain 01:04:55 loss: 2.1477 psnr: 18.9539 Lr: 2.57485e-05
[2025-02-18 01:49:56,610 INFO hook.py line 109 848561] Train: [94/100][150/605] Data 0.003 (0.002) Batch 0.905 (0.942) Remain 01:04:09 loss: 2.2091 psnr: 18.3916 Lr: 2.51362e-05
[2025-02-18 01:50:43,867 INFO hook.py line 109 848561] Train: [94/100][200/605] Data 0.003 (0.002) Batch 0.938 (0.943) Remain 01:03:25 loss: 2.2385 psnr: 17.4954 Lr: 2.45311e-05
[2025-02-18 01:51:30,821 INFO hook.py line 109 848561] Train: [94/100][250/605] Data 0.001 (0.002) Batch 0.933 (0.942) Remain 01:02:35 loss: 2.0167 psnr: 20.5015 Lr: 2.39334e-05
[2025-02-18 01:52:17,652 INFO hook.py line 109 848561] Train: [94/100][300/605] Data 0.002 (0.002) Batch 0.959 (0.941) Remain 01:01:44 loss: 2.2809 psnr: 16.5660 Lr: 2.33429e-05
[2025-02-18 01:53:04,367 INFO hook.py line 109 848561] Train: [94/100][350/605] Data 0.002 (0.002) Batch 0.912 (0.940) Remain 01:00:53 loss: 2.0908 psnr: 19.8896 Lr: 2.27598e-05
[2025-02-18 01:53:51,463 INFO hook.py line 109 848561] Train: [94/100][400/605] Data 0.002 (0.002) Batch 0.956 (0.941) Remain 01:00:06 loss: 2.5142 psnr: 16.2862 Lr: 2.21839e-05
[2025-02-18 01:54:38,487 INFO hook.py line 109 848561] Train: [94/100][450/605] Data 0.002 (0.002) Batch 0.930 (0.941) Remain 00:59:19 loss: 1.9835 psnr: 21.0382 Lr: 2.16153e-05
[2025-02-18 01:55:25,374 INFO hook.py line 109 848561] Train: [94/100][500/605] Data 0.002 (0.002) Batch 0.948 (0.940) Remain 00:58:31 loss: 2.3292 psnr: 16.9548 Lr: 2.10541e-05
[2025-02-18 01:56:12,388 INFO hook.py line 109 848561] Train: [94/100][550/605] Data 0.003 (0.002) Batch 0.959 (0.940) Remain 00:57:44 loss: 2.1969 psnr: 18.1002 Lr: 2.05001e-05
[2025-02-18 01:56:58,737 INFO hook.py line 109 848561] Train: [94/100][600/605] Data 0.003 (0.002) Batch 0.878 (0.939) Remain 00:56:53 loss: 2.0795 psnr: 18.3584 Lr: 1.99535e-05
[2025-02-18 01:57:03,097 INFO misc.py line 135 848561] Train result: loss: 2.2063 rgb_loss: 0.7403 psnr: 18.2280 depth_loss: 0.0624 feat_loss: 1.4036 
[2025-02-18 01:57:03,098 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 01:57:54,342 INFO hook.py line 109 848561] Train: [95/100][50/605] Data 0.002 (0.002) Batch 0.944 (0.943) Remain 00:56:16 loss: 2.1773 psnr: 17.7999 Lr: 1.93607e-05
[2025-02-18 01:58:41,681 INFO hook.py line 109 848561] Train: [95/100][100/605] Data 0.002 (0.002) Batch 0.939 (0.945) Remain 00:55:36 loss: 2.3021 psnr: 17.1228 Lr: 1.88294e-05
[2025-02-18 01:59:28,362 INFO hook.py line 109 848561] Train: [95/100][150/605] Data 0.003 (0.002) Batch 0.932 (0.941) Remain 00:54:35 loss: 2.2557 psnr: 17.4284 Lr: 1.83055e-05
[2025-02-18 02:00:15,372 INFO hook.py line 109 848561] Train: [95/100][200/605] Data 0.001 (0.002) Batch 0.956 (0.941) Remain 00:53:47 loss: 2.2360 psnr: 17.6478 Lr: 1.77889e-05
[2025-02-18 02:01:02,270 INFO hook.py line 109 848561] Train: [95/100][250/605] Data 0.003 (0.002) Batch 0.903 (0.940) Remain 00:52:58 loss: 2.2470 psnr: 17.7189 Lr: 1.72797e-05
[2025-02-18 02:01:49,324 INFO hook.py line 109 848561] Train: [95/100][300/605] Data 0.002 (0.002) Batch 0.938 (0.940) Remain 00:52:11 loss: 2.3198 psnr: 16.6402 Lr: 1.67778e-05
[2025-02-18 02:02:36,127 INFO hook.py line 109 848561] Train: [95/100][350/605] Data 0.003 (0.002) Batch 0.916 (0.940) Remain 00:51:22 loss: 2.2625 psnr: 18.1602 Lr: 1.62832e-05
[2025-02-18 02:03:22,957 INFO hook.py line 109 848561] Train: [95/100][400/605] Data 0.002 (0.002) Batch 0.928 (0.939) Remain 00:50:34 loss: 2.1313 psnr: 19.6387 Lr: 1.57960e-05
[2025-02-18 02:04:10,031 INFO hook.py line 109 848561] Train: [95/100][450/605] Data 0.002 (0.002) Batch 0.932 (0.940) Remain 00:49:48 loss: 2.4358 psnr: 16.4097 Lr: 1.53162e-05
[2025-02-18 02:04:56,953 INFO hook.py line 109 848561] Train: [95/100][500/605] Data 0.003 (0.002) Batch 0.927 (0.940) Remain 00:49:00 loss: 2.0838 psnr: 20.3221 Lr: 1.48436e-05
[2025-02-18 02:05:43,833 INFO hook.py line 109 848561] Train: [95/100][550/605] Data 0.002 (0.002) Batch 0.941 (0.939) Remain 00:48:13 loss: 2.2522 psnr: 18.5717 Lr: 1.43785e-05
[2025-02-18 02:06:30,195 INFO hook.py line 109 848561] Train: [95/100][600/605] Data 0.002 (0.002) Batch 0.865 (0.938) Remain 00:47:23 loss: 2.2506 psnr: 16.7050 Lr: 1.39207e-05
[2025-02-18 02:06:34,509 INFO misc.py line 135 848561] Train result: loss: 2.2094 rgb_loss: 0.7397 psnr: 18.2470 depth_loss: 0.0640 feat_loss: 1.4057 
[2025-02-18 02:06:34,509 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 02:07:25,572 INFO hook.py line 109 848561] Train: [96/100][50/605] Data 0.002 (0.002) Batch 0.938 (0.941) Remain 00:46:39 loss: 2.0805 psnr: 18.8166 Lr: 1.34256e-05
[2025-02-18 02:08:12,955 INFO hook.py line 109 848561] Train: [96/100][100/605] Data 0.002 (0.002) Batch 0.939 (0.944) Remain 00:46:02 loss: 2.3034 psnr: 17.1641 Lr: 1.29833e-05
[2025-02-18 02:08:59,811 INFO hook.py line 109 848561] Train: [96/100][150/605] Data 0.003 (0.002) Batch 0.910 (0.942) Remain 00:45:08 loss: 2.4238 psnr: 16.2038 Lr: 1.25484e-05
[2025-02-18 02:09:46,582 INFO hook.py line 109 848561] Train: [96/100][200/605] Data 0.003 (0.002) Batch 0.939 (0.940) Remain 00:44:16 loss: 2.1210 psnr: 18.5797 Lr: 1.21208e-05
[2025-02-18 02:10:33,343 INFO hook.py line 109 848561] Train: [96/100][250/605] Data 0.002 (0.002) Batch 0.907 (0.939) Remain 00:43:26 loss: 2.1515 psnr: 18.6770 Lr: 1.17006e-05
[2025-02-18 02:11:20,137 INFO hook.py line 109 848561] Train: [96/100][300/605] Data 0.001 (0.002) Batch 0.924 (0.939) Remain 00:42:37 loss: 1.9770 psnr: 20.6667 Lr: 1.12878e-05
[2025-02-18 02:12:07,240 INFO hook.py line 109 848561] Train: [96/100][350/605] Data 0.003 (0.002) Batch 0.937 (0.939) Remain 00:41:52 loss: 2.1940 psnr: 17.7844 Lr: 1.08824e-05
[2025-02-18 02:12:54,034 INFO hook.py line 109 848561] Train: [96/100][400/605] Data 0.003 (0.002) Batch 0.919 (0.939) Remain 00:41:04 loss: 2.2714 psnr: 17.1763 Lr: 1.04844e-05
[2025-02-18 02:13:41,133 INFO hook.py line 109 848561] Train: [96/100][450/605] Data 0.002 (0.002) Batch 0.934 (0.939) Remain 00:40:18 loss: 2.2116 psnr: 18.1036 Lr: 1.00937e-05
[2025-02-18 02:14:28,113 INFO hook.py line 109 848561] Train: [96/100][500/605] Data 0.003 (0.002) Batch 0.927 (0.939) Remain 00:39:31 loss: 2.2331 psnr: 17.5488 Lr: 9.71046e-06
[2025-02-18 02:15:15,212 INFO hook.py line 109 848561] Train: [96/100][550/605] Data 0.002 (0.002) Batch 0.927 (0.939) Remain 00:38:45 loss: 2.1145 psnr: 19.2833 Lr: 9.33461e-06
[2025-02-18 02:16:01,831 INFO hook.py line 109 848561] Train: [96/100][600/605] Data 0.002 (0.002) Batch 0.864 (0.939) Remain 00:37:56 loss: 2.1812 psnr: 18.6259 Lr: 8.96615e-06
[2025-02-18 02:16:06,167 INFO misc.py line 135 848561] Train result: loss: 2.2127 rgb_loss: 0.7463 psnr: 18.1560 depth_loss: 0.0620 feat_loss: 1.4045 
[2025-02-18 02:16:06,168 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 02:16:57,138 INFO hook.py line 109 848561] Train: [97/100][50/605] Data 0.003 (0.003) Batch 0.950 (0.938) Remain 00:37:02 loss: 2.2113 psnr: 17.7659 Lr: 8.56941e-06
[2025-02-18 02:17:44,134 INFO hook.py line 109 848561] Train: [97/100][100/605] Data 0.003 (0.003) Batch 0.976 (0.939) Remain 00:36:17 loss: 2.1624 psnr: 17.7226 Lr: 8.21650e-06
[2025-02-18 02:18:31,171 INFO hook.py line 109 848561] Train: [97/100][150/605] Data 0.002 (0.003) Batch 0.954 (0.939) Remain 00:35:32 loss: 2.1768 psnr: 18.0677 Lr: 7.87100e-06
[2025-02-18 02:19:17,862 INFO hook.py line 109 848561] Train: [97/100][200/605] Data 0.003 (0.003) Batch 0.912 (0.938) Remain 00:34:42 loss: 2.2734 psnr: 17.2758 Lr: 7.53292e-06
[2025-02-18 02:20:04,551 INFO hook.py line 109 848561] Train: [97/100][250/605] Data 0.002 (0.003) Batch 0.930 (0.937) Remain 00:33:53 loss: 2.1649 psnr: 18.4021 Lr: 7.20224e-06
[2025-02-18 02:20:51,321 INFO hook.py line 109 848561] Train: [97/100][300/605] Data 0.002 (0.003) Batch 0.933 (0.937) Remain 00:33:06 loss: 2.2687 psnr: 17.2178 Lr: 6.87899e-06
[2025-02-18 02:21:38,089 INFO hook.py line 109 848561] Train: [97/100][350/605] Data 0.002 (0.003) Batch 0.927 (0.937) Remain 00:32:18 loss: 2.0144 psnr: 19.2926 Lr: 6.56315e-06
[2025-02-18 02:22:24,944 INFO hook.py line 109 848561] Train: [97/100][400/605] Data 0.002 (0.002) Batch 0.983 (0.937) Remain 00:31:32 loss: 2.2873 psnr: 17.8569 Lr: 6.25473e-06
[2025-02-18 02:23:11,830 INFO hook.py line 109 848561] Train: [97/100][450/605] Data 0.002 (0.002) Batch 0.953 (0.937) Remain 00:30:45 loss: 2.0149 psnr: 20.1946 Lr: 5.95373e-06
[2025-02-18 02:23:58,758 INFO hook.py line 109 848561] Train: [97/100][500/605] Data 0.002 (0.002) Batch 0.934 (0.937) Remain 00:29:59 loss: 2.4536 psnr: 16.5546 Lr: 5.66016e-06
[2025-02-18 02:24:45,871 INFO hook.py line 109 848561] Train: [97/100][550/605] Data 0.002 (0.002) Batch 0.945 (0.937) Remain 00:29:13 loss: 2.1576 psnr: 18.6556 Lr: 5.37401e-06
[2025-02-18 02:25:32,171 INFO hook.py line 109 848561] Train: [97/100][600/605] Data 0.002 (0.002) Batch 0.889 (0.937) Remain 00:28:24 loss: 2.2157 psnr: 17.9254 Lr: 5.09530e-06
[2025-02-18 02:25:36,556 INFO misc.py line 135 848561] Train result: loss: 2.2114 rgb_loss: 0.7458 psnr: 18.1707 depth_loss: 0.0628 feat_loss: 1.4028 
[2025-02-18 02:25:36,557 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 02:26:27,555 INFO hook.py line 109 848561] Train: [98/100][50/605] Data 0.003 (0.002) Batch 0.935 (0.938) Remain 00:27:34 loss: 2.3009 psnr: 17.1203 Lr: 4.79729e-06
[2025-02-18 02:27:14,368 INFO hook.py line 109 848561] Train: [98/100][100/605] Data 0.002 (0.002) Batch 0.934 (0.937) Remain 00:26:46 loss: 2.1162 psnr: 18.8259 Lr: 4.53419e-06
[2025-02-18 02:28:01,804 INFO hook.py line 109 848561] Train: [98/100][150/605] Data 0.003 (0.002) Batch 0.933 (0.941) Remain 00:26:06 loss: 2.1564 psnr: 18.3967 Lr: 4.27852e-06
[2025-02-18 02:28:48,928 INFO hook.py line 109 848561] Train: [98/100][200/605] Data 0.002 (0.002) Batch 0.968 (0.941) Remain 00:25:20 loss: 2.2964 psnr: 17.4908 Lr: 4.03028e-06
[2025-02-18 02:29:36,043 INFO hook.py line 109 848561] Train: [98/100][250/605] Data 0.003 (0.002) Batch 0.960 (0.942) Remain 00:24:33 loss: 2.3419 psnr: 17.4979 Lr: 3.78949e-06
[2025-02-18 02:30:23,241 INFO hook.py line 109 848561] Train: [98/100][300/605] Data 0.002 (0.002) Batch 0.948 (0.942) Remain 00:23:47 loss: 2.0709 psnr: 19.0498 Lr: 3.55613e-06
[2025-02-18 02:31:10,279 INFO hook.py line 109 848561] Train: [98/100][350/605] Data 0.003 (0.002) Batch 0.919 (0.942) Remain 00:22:59 loss: 2.2811 psnr: 17.8751 Lr: 3.33022e-06
[2025-02-18 02:31:57,123 INFO hook.py line 109 848561] Train: [98/100][400/605] Data 0.003 (0.002) Batch 0.940 (0.941) Remain 00:22:11 loss: 2.1506 psnr: 19.2003 Lr: 3.11176e-06
[2025-02-18 02:32:44,345 INFO hook.py line 109 848561] Train: [98/100][450/605] Data 0.003 (0.002) Batch 0.941 (0.942) Remain 00:21:25 loss: 2.1378 psnr: 18.9511 Lr: 2.90074e-06
[2025-02-18 02:33:31,377 INFO hook.py line 109 848561] Train: [98/100][500/605] Data 0.003 (0.002) Batch 0.946 (0.941) Remain 00:20:37 loss: 2.1277 psnr: 19.0263 Lr: 2.69716e-06
[2025-02-18 02:34:18,160 INFO hook.py line 109 848561] Train: [98/100][550/605] Data 0.001 (0.002) Batch 0.921 (0.941) Remain 00:19:50 loss: 2.1284 psnr: 18.7345 Lr: 2.50104e-06
[2025-02-18 02:35:04,294 INFO hook.py line 109 848561] Train: [98/100][600/605] Data 0.002 (0.002) Batch 0.877 (0.939) Remain 00:19:01 loss: 1.9821 psnr: 20.5806 Lr: 2.31237e-06
[2025-02-18 02:35:08,584 INFO misc.py line 135 848561] Train result: loss: 2.2211 rgb_loss: 0.7538 psnr: 18.0982 depth_loss: 0.0630 feat_loss: 1.4043 
[2025-02-18 02:35:08,586 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 02:35:59,900 INFO hook.py line 109 848561] Train: [99/100][50/605] Data 0.003 (0.003) Batch 0.924 (0.941) Remain 00:18:11 loss: 2.1736 psnr: 18.2254 Lr: 2.11343e-06
[2025-02-18 02:36:46,635 INFO hook.py line 109 848561] Train: [99/100][100/605] Data 0.003 (0.003) Batch 0.919 (0.938) Remain 00:17:20 loss: 2.3401 psnr: 18.1591 Lr: 1.94041e-06
[2025-02-18 02:37:33,559 INFO hook.py line 109 848561] Train: [99/100][150/605] Data 0.001 (0.002) Batch 0.941 (0.938) Remain 00:16:34 loss: 2.2766 psnr: 18.1242 Lr: 1.77485e-06
[2025-02-18 02:38:20,789 INFO hook.py line 109 848561] Train: [99/100][200/605] Data 0.002 (0.002) Batch 0.962 (0.940) Remain 00:15:49 loss: 2.0612 psnr: 19.8986 Lr: 1.61674e-06
[2025-02-18 02:39:07,721 INFO hook.py line 109 848561] Train: [99/100][250/605] Data 0.002 (0.002) Batch 0.965 (0.939) Remain 00:15:01 loss: 1.9524 psnr: 20.0699 Lr: 1.46608e-06
[2025-02-18 02:39:54,679 INFO hook.py line 109 848561] Train: [99/100][300/605] Data 0.002 (0.002) Batch 0.933 (0.939) Remain 00:14:14 loss: 2.4545 psnr: 16.3733 Lr: 1.32289e-06
[2025-02-18 02:40:41,745 INFO hook.py line 109 848561] Train: [99/100][350/605] Data 0.002 (0.002) Batch 0.961 (0.940) Remain 00:13:28 loss: 2.4064 psnr: 15.9795 Lr: 1.18715e-06
[2025-02-18 02:41:28,725 INFO hook.py line 109 848561] Train: [99/100][400/605] Data 0.003 (0.002) Batch 0.918 (0.940) Remain 00:12:41 loss: 2.2421 psnr: 18.3655 Lr: 1.05888e-06
[2025-02-18 02:42:15,455 INFO hook.py line 109 848561] Train: [99/100][450/605] Data 0.002 (0.002) Batch 0.966 (0.939) Remain 00:11:53 loss: 2.0431 psnr: 19.7136 Lr: 9.38064e-07
[2025-02-18 02:43:02,491 INFO hook.py line 109 848561] Train: [99/100][500/605] Data 0.002 (0.002) Batch 0.929 (0.939) Remain 00:11:06 loss: 2.2241 psnr: 17.5057 Lr: 8.24714e-07
[2025-02-18 02:43:49,800 INFO hook.py line 109 848561] Train: [99/100][550/605] Data 0.004 (0.002) Batch 0.977 (0.940) Remain 00:10:20 loss: 2.1977 psnr: 18.1654 Lr: 7.20871e-07
[2025-02-18 02:44:35,570 INFO hook.py line 109 848561] Train: [99/100][600/605] Data 0.002 (0.002) Batch 0.855 (0.938) Remain 00:09:32 loss: 2.0903 psnr: 18.9793 Lr: 6.22298e-07
[2025-02-18 02:44:39,855 INFO misc.py line 135 848561] Train result: loss: 2.2126 rgb_loss: 0.7443 psnr: 18.2041 depth_loss: 0.0628 feat_loss: 1.4055 
[2025-02-18 02:44:39,856 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth
[2025-02-18 02:45:31,034 INFO hook.py line 109 848561] Train: [100/100][50/605] Data 0.003 (0.002) Batch 0.937 (0.938) Remain 00:08:40 loss: 2.2876 psnr: 16.5893 Lr: 5.22490e-07
[2025-02-18 02:46:17,622 INFO hook.py line 109 848561] Train: [100/100][100/605] Data 0.002 (0.002) Batch 0.905 (0.935) Remain 00:07:52 loss: 2.1980 psnr: 17.9395 Lr: 4.39594e-07
[2025-02-18 02:47:04,556 INFO hook.py line 109 848561] Train: [100/100][150/605] Data 0.004 (0.002) Batch 0.946 (0.936) Remain 00:07:05 loss: 2.2826 psnr: 16.8843 Lr: 3.64164e-07
[2025-02-18 02:47:51,713 INFO hook.py line 109 848561] Train: [100/100][200/605] Data 0.002 (0.002) Batch 0.933 (0.938) Remain 00:06:19 loss: 2.0242 psnr: 21.0127 Lr: 2.96200e-07
[2025-02-18 02:48:38,588 INFO hook.py line 109 848561] Train: [100/100][250/605] Data 0.002 (0.002) Batch 0.949 (0.938) Remain 00:05:32 loss: 2.0732 psnr: 19.3931 Lr: 2.35704e-07
[2025-02-18 02:49:25,636 INFO hook.py line 109 848561] Train: [100/100][300/605] Data 0.002 (0.002) Batch 0.948 (0.938) Remain 00:04:46 loss: 2.2886 psnr: 17.3458 Lr: 1.82676e-07
[2025-02-18 02:50:12,434 INFO hook.py line 109 848561] Train: [100/100][350/605] Data 0.002 (0.002) Batch 0.915 (0.938) Remain 00:03:59 loss: 2.1833 psnr: 18.5032 Lr: 1.37116e-07
[2025-02-18 02:50:59,257 INFO hook.py line 109 848561] Train: [100/100][400/605] Data 0.002 (0.002) Batch 0.933 (0.938) Remain 00:03:12 loss: 2.3864 psnr: 16.8858 Lr: 9.90237e-08
[2025-02-18 02:51:46,209 INFO hook.py line 109 848561] Train: [100/100][450/605] Data 0.002 (0.002) Batch 0.920 (0.938) Remain 00:02:25 loss: 2.2687 psnr: 18.3758 Lr: 6.84004e-08
[2025-02-18 02:52:32,770 INFO hook.py line 109 848561] Train: [100/100][500/605] Data 0.002 (0.002) Batch 0.964 (0.937) Remain 00:01:38 loss: 2.0730 psnr: 19.8567 Lr: 4.52460e-08
[2025-02-18 02:53:19,717 INFO hook.py line 109 848561] Train: [100/100][550/605] Data 0.003 (0.002) Batch 0.923 (0.937) Remain 00:00:51 loss: 2.2962 psnr: 17.1334 Lr: 2.95606e-08
[2025-02-18 02:54:05,991 INFO hook.py line 109 848561] Train: [100/100][600/605] Data 0.003 (0.002) Batch 0.879 (0.936) Remain 00:00:04 loss: 2.2306 psnr: 18.0474 Lr: 2.13445e-08
[2025-02-18 02:54:10,297 INFO misc.py line 135 848561] Train result: loss: 2.2201 rgb_loss: 0.7512 psnr: 18.1208 depth_loss: 0.0631 feat_loss: 1.4058 
[2025-02-18 02:54:10,299 INFO misc.py line 173 848561] Saving checkpoint to: exp/scannet/pretrain-gs-v4-spunet-base-m3/model/model_last.pth