-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtrain_RNN.out
7189 lines (5188 loc) · 104 KB
/
train_RNN.out
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
Sun Jul 21 07:38:12 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.23.08 Driver Version: 545.23.08 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA H100 80GB HBM3 Off | 00000000:4E:00.0 Off | 0 |
| N/A 34C P0 111W / 700W | 42008MiB / 81559MiB | 0% Default |
| | | Disabled |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 69135 C python 41994MiB |
+---------------------------------------------------------------------------------------+
Loading training data from disc...
Summary of all training data
Total sample count = 1081614
Class Count
0 AGN 76258
1 CART 8207
2 Cepheid 13771
3 Delta Scuti 20650
4 Dwarf Novae 8025
5 EB 66454
6 ILOT 7461
7 KN 4426
8 M-dwarf Flare 1859
9 PISN 63586
10 RR Lyrae 14033
11 SLSN 66088
12 SNI91bg 28637
13 SNII 301544
14 SNIa 120739
15 SNIax 28030
16 SNIb/c 168254
17 TDE 66000
18 uLens 17592
Summary of training data used
Class Count
0 AGN 38113
1 CART 7807
2 Cepheid 13088
3 Delta Scuti 19611
4 Dwarf Novae 7608
5 EB 38036
6 ILOT 7090
7 KN 4211
8 M-dwarf Flare 1780
9 PISN 37996
10 RR Lyrae 13278
11 SLSN 37993
12 SNI91bg 27207
13 SNII 38018
14 SNIa 38000
15 SNIax 26610
16 SNIb/c 37935
17 TDE 38023
18 uLens 16652
Summary of validation data used
Class Count
0 AGN 1887
1 CART 400
2 Cepheid 683
3 Delta Scuti 1039
4 Dwarf Novae 417
5 EB 1964
6 ILOT 371
7 KN 215
8 M-dwarf Flare 79
9 PISN 2004
10 RR Lyrae 755
11 SLSN 2007
12 SNI91bg 1430
13 SNII 1982
14 SNIa 2000
15 SNIax 1420
16 SNIb/c 2065
17 TDE 1977
18 uLens 940
TS Input Dim: 5 | Static Input Dim: 23 | Output Dim: 26
Creating augmented validation data set
Start of epoch 0:
Avg training loss: 0.2720
Avg val loss: 0.2390
Time taken: 72.68s
Best model is at epoch 0. Saving...
==========
Start of epoch 1:
Avg training loss: 0.2113
Avg val loss: 0.2197
Time taken: 40.68s
Best model is at epoch 1. Saving...
==========
Start of epoch 2:
Avg training loss: 0.1849
Avg val loss: 0.2378
Time taken: 44.17s
==========
Start of epoch 3:
Avg training loss: 0.2234
Avg val loss: 0.3215
Time taken: 32.86s
==========
Start of epoch 4:
Avg training loss: 0.1860
Avg val loss: 0.1919
Time taken: 37.87s
Best model is at epoch 4. Saving...
==========
Start of epoch 5:
Avg training loss: 0.1904
Avg val loss: 0.2285
Time taken: 35.08s
==========
Start of epoch 6:
Avg training loss: 0.1742
Avg val loss: 0.1803
Time taken: 35.39s
Best model is at epoch 6. Saving...
==========
Start of epoch 7:
Avg training loss: 0.1694
Avg val loss: 0.1826
Time taken: 36.08s
==========
Start of epoch 8:
Avg training loss: 0.1449
Avg val loss: 0.1689
Time taken: 39.90s
Best model is at epoch 8. Saving...
==========
Start of epoch 9:
Avg training loss: 0.2099
Avg val loss: 0.2642
Time taken: 32.52s
==========
Start of epoch 10:
Avg training loss: 0.1898
Avg val loss: 0.2102
Time taken: 31.80s
==========
Start of epoch 11:
Avg training loss: 0.1486
Avg val loss: 0.1792
Time taken: 43.15s
==========
Start of epoch 12:
Avg training loss: 0.1712
Avg val loss: 0.2009
Time taken: 33.84s
==========
Start of epoch 13:
Avg training loss: 0.1765
Avg val loss: 0.2532
Time taken: 33.76s
==========
Start of epoch 14:
Avg training loss: 0.1420
Avg val loss: 0.1551
Time taken: 37.47s
Best model is at epoch 14. Saving...
==========
Start of epoch 15:
Avg training loss: 0.1834
Avg val loss: 0.2246
Time taken: 33.30s
==========
Start of epoch 16:
Avg training loss: 0.1480
Avg val loss: 0.1560
Time taken: 35.12s
==========
Start of epoch 17:
Avg training loss: 0.1789
Avg val loss: 0.2480
Time taken: 33.38s
==========
Start of epoch 18:
Avg training loss: 0.1974
Avg val loss: 0.3223
Time taken: 31.03s
==========
Start of epoch 19:
Avg training loss: 0.1766
Avg val loss: 0.2735
Time taken: 33.20s
==========
Start of epoch 20:
Avg training loss: 0.1477
Avg val loss: 0.1542
Time taken: 34.89s
Best model is at epoch 20. Saving...
==========
Start of epoch 21:
Avg training loss: 0.1279
Avg val loss: 0.1445
Time taken: 39.65s
Best model is at epoch 21. Saving...
==========
Start of epoch 22:
Avg training loss: 0.1113
Avg val loss: 0.1481
Time taken: 43.00s
==========
Start of epoch 23:
Avg training loss: 0.1098
Avg val loss: 0.1443
Time taken: 43.27s
Best model is at epoch 23. Saving...
==========
Start of epoch 24:
Avg training loss: 0.1718
Avg val loss: 0.2061
Time taken: 32.25s
==========
Start of epoch 25:
Avg training loss: 0.1420
Avg val loss: 0.1473
Time taken: 35.79s
==========
Start of epoch 26:
Avg training loss: 0.1157
Avg val loss: 0.1365
Time taken: 39.12s
Best model is at epoch 26. Saving...
==========
Start of epoch 27:
Avg training loss: 0.1229
Avg val loss: 0.1354
Time taken: 38.50s
Best model is at epoch 27. Saving...
==========
Start of epoch 28:
Avg training loss: 0.1234
Avg val loss: 0.1343
Time taken: 36.68s
Best model is at epoch 28. Saving...
==========
Start of epoch 29:
Avg training loss: 0.1308
Avg val loss: 0.1380
Time taken: 36.72s
==========
Start of epoch 30:
Avg training loss: 0.1534
Avg val loss: 0.1757
Time taken: 32.95s
==========
Start of epoch 31:
Avg training loss: 0.1862
Avg val loss: 0.2802
Time taken: 32.50s
==========
Start of epoch 32:
Avg training loss: 0.1039
Avg val loss: 0.1343
Time taken: 42.39s
Best model is at epoch 32. Saving...
==========
Start of epoch 33:
Avg training loss: 0.2047
Avg val loss: 0.2256
Time taken: 32.28s
==========
Start of epoch 34:
Avg training loss: 0.1972
Avg val loss: 0.1929
Time taken: 30.73s
==========
Start of epoch 35:
Avg training loss: 0.1493
Avg val loss: 0.1628
Time taken: 34.49s
==========
Start of epoch 36:
Avg training loss: 0.0964
Avg val loss: 0.1315
Time taken: 42.91s
Best model is at epoch 36. Saving...
==========
Start of epoch 37:
Avg training loss: 0.1143
Avg val loss: 0.1266
Time taken: 38.52s
Best model is at epoch 37. Saving...
==========
Start of epoch 38:
Avg training loss: 0.1047
Avg val loss: 0.1264
Time taken: 38.93s
Best model is at epoch 38. Saving...
==========
Start of epoch 39:
Avg training loss: 0.0908
Avg val loss: 0.1286
Time taken: 43.73s
==========
Start of epoch 40:
Avg training loss: 0.1746
Avg val loss: 0.1707
Time taken: 31.58s
==========
Start of epoch 41:
Avg training loss: 0.0907
Avg val loss: 0.1263
Time taken: 43.81s
Best model is at epoch 41. Saving...
==========
Start of epoch 42:
Avg training loss: 0.1141
Avg val loss: 0.1242
Time taken: 36.73s
Best model is at epoch 42. Saving...
==========
Start of epoch 43:
Avg training loss: 0.0989
Avg val loss: 0.1228
Time taken: 40.58s
Best model is at epoch 43. Saving...
==========
Start of epoch 44:
Avg training loss: 0.1058
Avg val loss: 0.1220
Time taken: 37.74s
Best model is at epoch 44. Saving...
==========
Start of epoch 45:
Avg training loss: 0.1197
Avg val loss: 0.1244
Time taken: 36.72s
==========
Start of epoch 46:
Avg training loss: 0.1745
Avg val loss: 0.1915
Time taken: 31.39s
==========
Start of epoch 47:
Avg training loss: 0.1436
Avg val loss: 0.1501
Time taken: 34.23s
==========
Start of epoch 48:
Avg training loss: 0.0910
Avg val loss: 0.1218
Time taken: 41.20s
Best model is at epoch 48. Saving...
==========
Start of epoch 49:
Avg training loss: 0.0890
Avg val loss: 0.1216
Time taken: 42.36s
Best model is at epoch 49. Saving...
==========
Start of epoch 50:
Avg training loss: 0.1026
Avg val loss: 0.1193
Time taken: 37.75s
Best model is at epoch 50. Saving...
==========
Start of epoch 51:
Avg training loss: 0.1366
Avg val loss: 0.1318
Time taken: 34.59s
==========
Start of epoch 52:
Avg training loss: 0.1173
Avg val loss: 0.1250
Time taken: 35.19s
==========
Start of epoch 53:
Avg training loss: 0.1042
Avg val loss: 0.1182
Time taken: 38.50s
Best model is at epoch 53. Saving...
==========
Start of epoch 54:
Avg training loss: 0.0844
Avg val loss: 0.1195
Time taken: 41.78s
==========
Start of epoch 55:
Avg training loss: 0.0899
Avg val loss: 0.1187
Time taken: 41.29s
==========
Start of epoch 56:
Avg training loss: 0.1101
Avg val loss: 0.1168
Time taken: 36.04s
Best model is at epoch 56. Saving...
==========
Start of epoch 57:
Avg training loss: 0.1232
Avg val loss: 0.1212
Time taken: 35.57s
==========
Start of epoch 58:
Avg training loss: 0.1244
Avg val loss: 0.1246
Time taken: 33.98s
==========
Start of epoch 59:
Avg training loss: 0.1246
Avg val loss: 0.1316
Time taken: 35.37s
==========
Start of epoch 60:
Avg training loss: 0.1807
Avg val loss: 0.2819
Time taken: 31.05s
==========
Start of epoch 61:
Avg training loss: 0.1672
Avg val loss: 0.2442
Time taken: 32.82s
==========
Start of epoch 62:
Avg training loss: 0.1006
Avg val loss: 0.1147
Time taken: 37.77s
Best model is at epoch 62. Saving...
==========
Start of epoch 63:
Avg training loss: 0.0809
Avg val loss: 0.1160
Time taken: 43.20s
==========
Start of epoch 64:
Avg training loss: 0.0940
Avg val loss: 0.1138
Time taken: 38.24s
Best model is at epoch 64. Saving...
==========
Start of epoch 65:
Avg training loss: 0.1653
Avg val loss: 0.1562
Time taken: 32.79s
==========
Start of epoch 66:
Avg training loss: 0.1061
Avg val loss: 0.1131
Time taken: 36.17s
Best model is at epoch 66. Saving...
==========
Start of epoch 67:
Avg training loss: 0.0781
Avg val loss: 0.1145
Time taken: 43.28s
==========
Start of epoch 68:
Avg training loss: 0.0843
Avg val loss: 0.1138
Time taken: 40.22s
==========
Start of epoch 69:
Avg training loss: 0.0828
Avg val loss: 0.1142
Time taken: 41.47s
==========
Start of epoch 70:
Avg training loss: 0.0843
Avg val loss: 0.1139
Time taken: 39.95s
==========
Start of epoch 71:
Avg training loss: 0.1172
Avg val loss: 0.1140
Time taken: 35.77s
==========
Start of epoch 72:
Avg training loss: 0.1356
Avg val loss: 0.1309
Time taken: 33.01s
==========
Start of epoch 73:
Avg training loss: 0.1166
Avg val loss: 0.1169
Time taken: 35.70s
==========
Start of epoch 74:
Avg training loss: 0.0814
Avg val loss: 0.1125
Time taken: 40.36s
Best model is at epoch 74. Saving...
==========
Start of epoch 75:
Avg training loss: 0.0739
Avg val loss: 0.1144
Time taken: 43.50s
==========
Start of epoch 76:
Avg training loss: 0.0948
Avg val loss: 0.1103
Time taken: 37.80s
Best model is at epoch 76. Saving...
==========
Start of epoch 77:
Avg training loss: 0.0696
Avg val loss: 0.1140
Time taken: 44.54s
==========
Start of epoch 78:
Avg training loss: 0.0761
Avg val loss: 0.1125
Time taken: 41.46s
==========
Start of epoch 79:
Avg training loss: 0.1134
Avg val loss: 0.1141
Time taken: 35.89s
==========
Start of epoch 80:
Avg training loss: 0.1980
Avg val loss: 0.1840
Time taken: 30.79s
==========
Start of epoch 81:
Avg training loss: 0.0860
Avg val loss: 0.1089
Time taken: 40.39s
Best model is at epoch 81. Saving...
==========
Start of epoch 82:
Avg training loss: 0.1078
Avg val loss: 0.1107
Time taken: 35.36s
==========
Start of epoch 83:
Avg training loss: 0.0747
Avg val loss: 0.1104
Time taken: 42.61s
==========
Start of epoch 84:
Avg training loss: 0.0771
Avg val loss: 0.1101
Time taken: 40.68s
==========
Start of epoch 85:
Avg training loss: 0.0722
Avg val loss: 0.1114
Time taken: 42.96s
==========
Start of epoch 86:
Avg training loss: 0.1705
Avg val loss: 0.1829
Time taken: 31.45s
==========
Start of epoch 87:
Avg training loss: 0.0896
Avg val loss: 0.1079
Time taken: 39.15s
Best model is at epoch 87. Saving...
==========
Start of epoch 88:
Avg training loss: 0.1623
Avg val loss: 0.1488
Time taken: 31.57s
==========
Start of epoch 89:
Avg training loss: 0.0679
Avg val loss: 0.1096
Time taken: 44.76s
==========
Start of epoch 90:
Avg training loss: 0.1441
Avg val loss: 0.1231
Time taken: 32.46s
==========
Start of epoch 91:
Avg training loss: 0.0760
Avg val loss: 0.1074
Time taken: 41.95s
Best model is at epoch 91. Saving...
==========
Start of epoch 92:
Avg training loss: 0.1216
Avg val loss: 0.1123
Time taken: 33.84s
==========
Start of epoch 93:
Avg training loss: 0.0922
Avg val loss: 0.1061
Time taken: 38.46s
Best model is at epoch 93. Saving...
==========
Start of epoch 94:
Avg training loss: 0.0812
Avg val loss: 0.1065
Time taken: 39.25s
==========
Start of epoch 95:
Avg training loss: 0.0650
Avg val loss: 0.1094
Time taken: 44.90s
==========
Start of epoch 96:
Avg training loss: 0.0775
Avg val loss: 0.1075
Time taken: 39.90s
==========
Start of epoch 97:
Avg training loss: 0.1552
Avg val loss: 0.1358
Time taken: 33.08s
==========
Start of epoch 98:
Avg training loss: 0.0824
Avg val loss: 0.1056
Time taken: 39.12s
Best model is at epoch 98. Saving...
==========
Start of epoch 99:
Avg training loss: 0.0737
Avg val loss: 0.1068
Time taken: 41.93s
==========
Start of epoch 100:
Avg training loss: 0.1055
Avg val loss: 0.1062
Time taken: 35.29s
==========
Start of epoch 101:
Avg training loss: 0.0690
Avg val loss: 0.1068
Time taken: 43.02s
==========
Start of epoch 102:
Avg training loss: 0.1169
Avg val loss: 0.1100
Time taken: 34.03s
==========
Start of epoch 103:
Avg training loss: 0.0694
Avg val loss: 0.1063
Time taken: 42.82s
==========
Start of epoch 104:
Avg training loss: 0.1539
Avg val loss: 0.1342
Time taken: 31.77s
==========
Start of epoch 105:
Avg training loss: 0.0894
Avg val loss: 0.1040
Time taken: 38.69s
Best model is at epoch 105. Saving...
==========
Start of epoch 106:
Avg training loss: 0.0963
Avg val loss: 0.1047
Time taken: 36.19s
==========
Start of epoch 107:
Avg training loss: 0.0728
Avg val loss: 0.1048
Time taken: 41.87s
==========
Start of epoch 108:
Avg training loss: 0.1121
Avg val loss: 0.1073
Time taken: 34.39s
==========
Start of epoch 109:
Avg training loss: 0.0766
Avg val loss: 0.1046
Time taken: 40.94s
==========
Start of epoch 110:
Avg training loss: 0.0660
Avg val loss: 0.1059
Time taken: 42.17s
==========
Start of epoch 111:
Avg training loss: 0.1178
Avg val loss: 0.1084
Time taken: 34.92s
==========
Start of epoch 112:
Avg training loss: 0.1396
Avg val loss: 0.1278
Time taken: 32.55s
==========
Start of epoch 113:
Avg training loss: 0.0874
Avg val loss: 0.1026
Time taken: 38.56s
Best model is at epoch 113. Saving...
==========
Start of epoch 114:
Avg training loss: 0.0896
Avg val loss: 0.1028
Time taken: 37.22s
==========
Start of epoch 115:
Avg training loss: 0.0957
Avg val loss: 0.1038
Time taken: 37.28s
==========
Start of epoch 116:
Avg training loss: 0.0899
Avg val loss: 0.1029
Time taken: 36.74s
==========
Start of epoch 117:
Avg training loss: 0.0901
Avg val loss: 0.1028
Time taken: 38.11s
==========
Start of epoch 118:
Avg training loss: 0.0854
Avg val loss: 0.1025
Time taken: 37.52s
Best model is at epoch 118. Saving...
==========
Start of epoch 119:
Avg training loss: 0.0887
Avg val loss: 0.1023
Time taken: 38.33s
Best model is at epoch 119. Saving...
==========
Start of epoch 120:
Avg training loss: 0.0653
Avg val loss: 0.1039
Time taken: 42.62s
==========
Start of epoch 121:
Avg training loss: 0.0797
Avg val loss: 0.1018
Time taken: 39.76s
Best model is at epoch 121. Saving...
==========
Start of epoch 122:
Avg training loss: 0.0688
Avg val loss: 0.1033
Time taken: 40.95s
==========
Start of epoch 123:
Avg training loss: 0.0897
Avg val loss: 0.1023
Time taken: 37.89s
==========
Start of epoch 124:
Avg training loss: 0.1551
Avg val loss: 0.1403