log
Browse files- logs/train_s1.log +75 -0
logs/train_s1.log
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
building scenes 6468 tree scenes 5990 ground donors 5537
|
| 2 |
+
earthview singles (4136, 384, 384, 3) real pairs (1619, 2, 384, 384, 3)
|
| 3 |
+
step 100 67s loss 1.2406 l2sp 4.45
|
| 4 |
+
step 200 103s loss 1.1174 l2sp 18.39
|
| 5 |
+
step 300 130s loss 0.7714 l2sp 32.45
|
| 6 |
+
step 400 160s loss 0.7715 l2sp 42.43
|
| 7 |
+
step 500 187s loss 0.6585 l2sp 51.54
|
| 8 |
+
step 600 223s loss 0.6234 l2sp 57.77
|
| 9 |
+
step 700 251s loss 0.6430 l2sp 60.68
|
| 10 |
+
step 800 277s loss 0.5319 l2sp 64.78
|
| 11 |
+
snapshot 5
|
| 12 |
+
step 900 307s loss 0.5194 l2sp 66.48
|
| 13 |
+
step 1000 334s loss 0.4526 l2sp 69.17
|
| 14 |
+
step 1100 372s loss 0.6404 l2sp 70.41
|
| 15 |
+
step 1200 404s loss 0.8859 l2sp 73.77
|
| 16 |
+
step 1300 432s loss 0.5095 l2sp 77.63
|
| 17 |
+
step 1400 458s loss 0.5001 l2sp 80.27
|
| 18 |
+
step 1500 487s loss 0.5588 l2sp 79.66
|
| 19 |
+
step 1600 514s loss 0.5840 l2sp 82.55
|
| 20 |
+
step 1700 540s loss 0.4543 l2sp 82.80
|
| 21 |
+
step 1800 567s loss 0.5304 l2sp 85.65
|
| 22 |
+
step 1900 592s loss 0.4350 l2sp 88.41
|
| 23 |
+
snapshot 10
|
| 24 |
+
step 2000 619s loss 0.5535 l2sp 89.17
|
| 25 |
+
step 2100 643s loss 0.5253 l2sp 92.85
|
| 26 |
+
step 2200 678s loss 0.5951 l2sp 91.09
|
| 27 |
+
step 2300 702s loss 0.5194 l2sp 90.69
|
| 28 |
+
step 2400 726s loss 0.7137 l2sp 90.49
|
| 29 |
+
step 2500 753s loss 0.4488 l2sp 91.55
|
| 30 |
+
step 2600 783s loss 0.4640 l2sp 95.08
|
| 31 |
+
step 2700 817s loss 0.6564 l2sp 96.49
|
| 32 |
+
step 2800 847s loss 0.4316 l2sp 98.89
|
| 33 |
+
step 2900 885s loss 0.4319 l2sp 100.45
|
| 34 |
+
snapshot 15
|
| 35 |
+
step 3000 918s loss 0.5337 l2sp 99.97
|
| 36 |
+
step 3100 948s loss 0.4463 l2sp 99.96
|
| 37 |
+
step 3200 974s loss 0.4486 l2sp 99.71
|
| 38 |
+
step 3300 1002s loss 0.4392 l2sp 100.50
|
| 39 |
+
step 3400 1036s loss 0.3755 l2sp 100.68
|
| 40 |
+
step 3500 1066s loss 0.4239 l2sp 101.85
|
| 41 |
+
step 3600 1099s loss 0.5196 l2sp 101.12
|
| 42 |
+
step 3700 1133s loss 0.4081 l2sp 103.43
|
| 43 |
+
step 3800 1160s loss 0.3870 l2sp 102.82
|
| 44 |
+
step 3900 1193s loss 0.4453 l2sp 102.47
|
| 45 |
+
snapshot 20
|
| 46 |
+
TRAIN_DONE 3929
|
| 47 |
+
Exception in thread Thread-1 (_pin_memory_loop):
|
| 48 |
+
Traceback (most recent call last):
|
| 49 |
+
File "/opt/conda/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
|
| 50 |
+
self.run()
|
| 51 |
+
File "/opt/conda/lib/python3.11/threading.py", line 982, in run
|
| 52 |
+
self._target(*self._args, **self._kwargs)
|
| 53 |
+
File "/opt/conda/lib/python3.11/site-packages/torch/utils/data/_utils/pin_memory.py", line 59, in _pin_memory_loop
|
| 54 |
+
do_one_step()
|
| 55 |
+
File "/opt/conda/lib/python3.11/site-packages/torch/utils/data/_utils/pin_memory.py", line 35, in do_one_step
|
| 56 |
+
r = in_queue.get(timeout=MP_STATUS_CHECK_INTERVAL)
|
| 57 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 58 |
+
File "/opt/conda/lib/python3.11/multiprocessing/queues.py", line 122, in get
|
| 59 |
+
return _ForkingPickler.loads(res)
|
| 60 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 61 |
+
File "/opt/conda/lib/python3.11/site-packages/torch/multiprocessing/reductions.py", line 541, in rebuild_storage_fd
|
| 62 |
+
fd = df.detach()
|
| 63 |
+
^^^^^^^^^^^
|
| 64 |
+
File "/opt/conda/lib/python3.11/multiprocessing/resource_sharer.py", line 57, in detach
|
| 65 |
+
with _resource_sharer.get_connection(self._id) as conn:
|
| 66 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 67 |
+
File "/opt/conda/lib/python3.11/multiprocessing/resource_sharer.py", line 86, in get_connection
|
| 68 |
+
c = Client(address, authkey=process.current_process().authkey)
|
| 69 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 70 |
+
File "/opt/conda/lib/python3.11/multiprocessing/connection.py", line 519, in Client
|
| 71 |
+
c = SocketClient(address)
|
| 72 |
+
^^^^^^^^^^^^^^^^^^^^^
|
| 73 |
+
File "/opt/conda/lib/python3.11/multiprocessing/connection.py", line 647, in SocketClient
|
| 74 |
+
s.connect(address)
|
| 75 |
+
ConnectionRefusedError: [Errno 111] Connection refused
|