-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathoutput2.log
2435 lines (2398 loc) · 154 KB
/
output2.log
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
INFO:root:
----------Sat May 20 15:55:58 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 32, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[32,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(32, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72362576
INFO:root:Start Training: Sat May 20 15:56:05 2023
INFO:root:Model Save at ./save/598165_epoch0.model/.optim,
INFO:root:Epoch 0: train_loss 1.284652, train_acc 0.038, dev_loss 1.110203, dev_acc 0.074,
time 26.759 s/epoch, total time 26.759 s, time left 1311.208 s
INFO:root:Epoch 1: train_loss 1.018708, train_acc 0.16, dev_loss 1.110203, dev_acc 0.074,
time 16.803 s/epoch, total time 33.606 s, time left 806.554 s
INFO:root:Model Save at ./save/598165_epoch2.model/.optim,
INFO:root:Epoch 2: train_loss 0.833536, train_acc 0.352, dev_loss 0.695961, dev_acc 0.484,
time 19.541 s/epoch, total time 58.623 s, time left 918.422 s
INFO:root:Epoch 3: train_loss 0.731334, train_acc 0.448, dev_loss 0.695961, dev_acc 0.484,
time 16.332 s/epoch, total time 65.329 s, time left 751.287 s
INFO:root:Model Save at ./save/598165_epoch4.model/.optim,
INFO:root:Epoch 4: train_loss 0.649244, train_acc 0.505, dev_loss 0.537985, dev_acc 0.599,
time 18.097 s/epoch, total time 90.484 s, time left 814.355 s
INFO:root:Epoch 5: train_loss 0.58516, train_acc 0.548, dev_loss 0.537985, dev_acc 0.599,
time 16.215 s/epoch, total time 97.292 s, time left 713.476 s
INFO:root:Model Save at ./save/598165_epoch6.model/.optim,
INFO:root:Epoch 6: train_loss 0.540793, train_acc 0.583, dev_loss 0.457253, dev_acc 0.651,
time 17.467 s/epoch, total time 122.268 s, time left 751.073 s
INFO:root:Epoch 7: train_loss 0.501366, train_acc 0.611, dev_loss 0.457253, dev_acc 0.651,
time 16.137 s/epoch, total time 129.093 s, time left 677.738 s
INFO:root:Model Save at ./save/598165_epoch8.model/.optim,
INFO:root:Epoch 8: train_loss 0.470457, train_acc 0.638, dev_loss 0.409527, dev_acc 0.685,
time 17.177 s/epoch, total time 154.591 s, time left 704.248 s
INFO:root:Epoch 9: train_loss 0.441258, train_acc 0.661, dev_loss 0.409527, dev_acc 0.685,
time 16.139 s/epoch, total time 161.389 s, time left 645.554 s
INFO:root:Model Save at ./save/598165_epoch10.model/.optim,
INFO:root:Epoch 10: train_loss 0.419008, train_acc 0.679, dev_loss 0.34338, dev_acc 0.746,
time 16.938 s/epoch, total time 186.315 s, time left 660.57 s
INFO:root:Epoch 11: train_loss 0.387725, train_acc 0.709, dev_loss 0.34338, dev_acc 0.746,
time 16.094 s/epoch, total time 193.123 s, time left 611.558 s
INFO:root:Model Save at ./save/598165_epoch12.model/.optim,
INFO:root:Epoch 12: train_loss 0.379107, train_acc 0.712, dev_loss 0.314186, dev_acc 0.764,
time 16.785 s/epoch, total time 218.205 s, time left 621.046 s
INFO:root:Epoch 13: train_loss 0.371229, train_acc 0.718, dev_loss 0.314186, dev_acc 0.764,
time 16.072 s/epoch, total time 225.007 s, time left 578.589 s
INFO:root:Model Save at ./save/598165_epoch14.model/.optim,
INFO:root:Epoch 14: train_loss 0.363128, train_acc 0.723, dev_loss 0.30817, dev_acc 0.77,
time 16.886 s/epoch, total time 253.284 s, time left 590.996 s
INFO:root:Epoch 15: train_loss 0.357795, train_acc 0.729, dev_loss 0.30817, dev_acc 0.77,
time 16.251 s/epoch, total time 260.016 s, time left 552.534 s
INFO:root:Model Save at ./save/598165_epoch16.model/.optim,
INFO:root:Epoch 16: train_loss 0.352215, train_acc 0.73, dev_loss 0.293071, dev_acc 0.781,
time 16.772 s/epoch, total time 285.129 s, time left 553.486 s
INFO:root:Epoch 17: train_loss 0.348491, train_acc 0.736, dev_loss 0.293071, dev_acc 0.781,
time 16.213 s/epoch, total time 291.833 s, time left 518.814 s
INFO:root:Model Save at ./save/598165_epoch18.model/.optim,
INFO:root:Epoch 18: train_loss 0.343448, train_acc 0.741, dev_loss 0.288747, dev_acc 0.786,
time 16.722 s/epoch, total time 317.719 s, time left 518.384 s
INFO:root:Epoch 19: train_loss 0.337691, train_acc 0.744, dev_loss 0.288747, dev_acc 0.786,
time 16.223 s/epoch, total time 324.458 s, time left 486.688 s
INFO:root:Model Save at ./save/598165_epoch20.model/.optim,
INFO:root:Epoch 20: train_loss 0.332422, train_acc 0.747, dev_loss 0.276705, dev_acc 0.796,
time 16.645 s/epoch, total time 349.536 s, time left 482.693 s
INFO:root:Epoch 21: train_loss 0.323146, train_acc 0.754, dev_loss 0.276705, dev_acc 0.796,
time 16.198 s/epoch, total time 356.358 s, time left 453.546 s
INFO:root:Model Save at ./save/598165_epoch22.model/.optim,
INFO:root:Epoch 22: train_loss 0.319013, train_acc 0.758, dev_loss 0.267716, dev_acc 0.803,
time 16.592 s/epoch, total time 381.62 s, time left 447.988 s
INFO:root:Epoch 23: train_loss 0.318743, train_acc 0.759, dev_loss 0.267716, dev_acc 0.803,
time 16.186 s/epoch, total time 388.467 s, time left 420.839 s
INFO:root:Model Save at ./save/598165_epoch24.model/.optim,
INFO:root:Epoch 24: train_loss 0.315352, train_acc 0.761, dev_loss 0.262881, dev_acc 0.806,
time 16.523 s/epoch, total time 413.08 s, time left 413.08 s
INFO:root:Epoch 25: train_loss 0.31451, train_acc 0.763, dev_loss 0.262881, dev_acc 0.806,
time 16.147 s/epoch, total time 419.824 s, time left 387.53 s
INFO:root:Model Save at ./save/598165_epoch26.model/.optim,
INFO:root:Epoch 26: train_loss 0.311915, train_acc 0.764, dev_loss 0.257286, dev_acc 0.807,
time 16.493 s/epoch, total time 445.316 s, time left 379.343 s
INFO:root:Epoch 27: train_loss 0.309001, train_acc 0.766, dev_loss 0.257286, dev_acc 0.807,
time 16.145 s/epoch, total time 452.05 s, time left 355.182 s
INFO:root:Model Save at ./save/598165_epoch28.model/.optim,
INFO:root:Epoch 28: train_loss 0.308249, train_acc 0.765, dev_loss 0.254245, dev_acc 0.808,
time 16.455 s/epoch, total time 477.194 s, time left 345.554 s
INFO:root:Epoch 29: train_loss 0.308599, train_acc 0.767, dev_loss 0.254245, dev_acc 0.808,
time 16.135 s/epoch, total time 484.052 s, time left 322.701 s
INFO:root:Model Save at ./save/598165_epoch30.model/.optim,
INFO:root:Epoch 30: train_loss 0.30611, train_acc 0.768, dev_loss 0.254231, dev_acc 0.808,
time 16.439 s/epoch, total time 509.603 s, time left 312.338 s
INFO:root:Epoch 31: train_loss 0.302354, train_acc 0.771, dev_loss 0.254231, dev_acc 0.808,
time 16.136 s/epoch, total time 516.359 s, time left 290.452 s
INFO:root:Model Save at ./save/598165_epoch32.model/.optim,
INFO:root:Epoch 32: train_loss 0.301826, train_acc 0.769, dev_loss 0.24929, dev_acc 0.816,
time 16.414 s/epoch, total time 541.676 s, time left 279.045 s
INFO:root:Epoch 33: train_loss 0.30223, train_acc 0.772, dev_loss 0.24929, dev_acc 0.816,
time 16.129 s/epoch, total time 548.401 s, time left 258.071 s
INFO:root:Model Save at ./save/598165_epoch34.model/.optim,
INFO:root:Epoch 34: train_loss 0.300785, train_acc 0.772, dev_loss 0.249623, dev_acc 0.817,
time 16.391 s/epoch, total time 573.68 s, time left 245.863 s
INFO:root:Epoch 35: train_loss 0.299538, train_acc 0.772, dev_loss 0.249623, dev_acc 0.817,
time 16.125 s/epoch, total time 580.484 s, time left 225.744 s
INFO:root:Model Save at ./save/598165_epoch36.model/.optim,
INFO:root:Epoch 36: train_loss 0.30018, train_acc 0.773, dev_loss 0.247737, dev_acc 0.819,
time 16.44 s/epoch, total time 608.27 s, time left 213.717 s
INFO:root:Epoch 37: train_loss 0.299195, train_acc 0.772, dev_loss 0.247737, dev_acc 0.819,
time 16.184 s/epoch, total time 614.993 s, time left 194.208 s
INFO:root:Epoch 38: train_loss 0.298713, train_acc 0.771, dev_loss 0.24975, dev_acc 0.817,
time 15.945 s/epoch, total time 621.867 s, time left 175.398 s
INFO:root:Epoch 39: train_loss 0.297571, train_acc 0.774, dev_loss 0.24975, dev_acc 0.817,
time 15.715 s/epoch, total time 628.607 s, time left 157.152 s
INFO:root:Epoch 40: train_loss 0.296318, train_acc 0.775, dev_loss 0.24733, dev_acc 0.816,
time 15.506 s/epoch, total time 635.742 s, time left 139.553 s
INFO:root:Epoch 41: train_loss 0.298582, train_acc 0.773, dev_loss 0.24733, dev_acc 0.816,
time 15.3 s/epoch, total time 642.601 s, time left 122.4 s
INFO:root:Epoch 42: train_loss 0.296569, train_acc 0.775, dev_loss 0.245839, dev_acc 0.818,
time 15.113 s/epoch, total time 649.839 s, time left 105.788 s
INFO:root:Epoch 43: train_loss 0.296515, train_acc 0.774, dev_loss 0.245839, dev_acc 0.818,
time 14.927 s/epoch, total time 656.774 s, time left 89.56 s
INFO:root:Epoch 44: train_loss 0.296418, train_acc 0.774, dev_loss 0.246372, dev_acc 0.816,
time 14.759 s/epoch, total time 664.158 s, time left 73.795 s
INFO:root:Epoch 45: train_loss 0.29416, train_acc 0.775, dev_loss 0.246372, dev_acc 0.816,
time 14.594 s/epoch, total time 671.306 s, time left 58.374 s
INFO:root:Epoch 46: train_loss 0.295211, train_acc 0.777, dev_loss 0.245679, dev_acc 0.817,
time 14.44 s/epoch, total time 678.688 s, time left 43.321 s
INFO:root:Epoch 47: train_loss 0.295508, train_acc 0.775, dev_loss 0.245679, dev_acc 0.817,
time 14.291 s/epoch, total time 685.946 s, time left 28.581 s
INFO:root:Epoch 48: train_loss 0.294346, train_acc 0.776, dev_loss 0.245738, dev_acc 0.819,
time 14.155 s/epoch, total time 693.591 s, time left 14.155 s
INFO:root:Epoch 49: train_loss 0.298047, train_acc 0.773, dev_loss 0.2454, dev_acc 0.817,
time 14.02 s/epoch, total time 700.991 s, time left 0.0 s
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 32, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[32,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(32, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72362576
INFO:root:Best epoch: 36, best acc: 0.8189781526548673
Final train_loss: 0.298047 dev_loss: 0.2454
Final train_acc: 0.7733 dev_acc: 0.81744
Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:
----------Sat May 20 16:13:58 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(64, 96, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[96,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(96, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72437232
INFO:root:Start Training: Sat May 20 16:14:05 2023
INFO:root:Model Save at ./save/599245_epoch0.model/.optim,
INFO:root:Epoch 0: train_loss 1.244269, train_acc 0.053, dev_loss 1.071423, dev_acc 0.108,
time 35.311 s/epoch, total time 35.311 s, time left 1730.229 s
INFO:root:Epoch 1: train_loss 0.932753, train_acc 0.255, dev_loss 1.071423, dev_acc 0.108,
time 21.38 s/epoch, total time 42.76 s, time left 1026.244 s
INFO:root:Model Save at ./save/599245_epoch2.model/.optim,
INFO:root:Epoch 2: train_loss 0.753648, train_acc 0.429, dev_loss 0.645191, dev_acc 0.525,
time 23.051 s/epoch, total time 69.152 s, time left 1083.384 s
INFO:root:Epoch 3: train_loss 0.677647, train_acc 0.499, dev_loss 0.645191, dev_acc 0.525,
time 19.135 s/epoch, total time 76.539 s, time left 880.2 s
INFO:root:Model Save at ./save/599245_epoch4.model/.optim,
INFO:root:Epoch 4: train_loss 0.626288, train_acc 0.542, dev_loss 0.541442, dev_acc 0.613,
time 20.529 s/epoch, total time 102.644 s, time left 923.794 s
INFO:root:Epoch 5: train_loss 0.581798, train_acc 0.573, dev_loss 0.541442, dev_acc 0.613,
time 18.331 s/epoch, total time 109.986 s, time left 806.565 s
INFO:root:Model Save at ./save/599245_epoch6.model/.optim,
INFO:root:Epoch 6: train_loss 0.530608, train_acc 0.604, dev_loss 0.456204, dev_acc 0.646,
time 19.481 s/epoch, total time 136.37 s, time left 837.704 s
INFO:root:Epoch 7: train_loss 0.486889, train_acc 0.629, dev_loss 0.456204, dev_acc 0.646,
time 17.971 s/epoch, total time 143.766 s, time left 754.771 s
INFO:root:Model Save at ./save/599245_epoch8.model/.optim,
INFO:root:Epoch 8: train_loss 0.448344, train_acc 0.655, dev_loss 0.387257, dev_acc 0.704,
time 18.945 s/epoch, total time 170.501 s, time left 776.727 s
INFO:root:Epoch 9: train_loss 0.415267, train_acc 0.679, dev_loss 0.387257, dev_acc 0.704,
time 17.782 s/epoch, total time 177.819 s, time left 711.276 s
INFO:root:Model Save at ./save/599245_epoch10.model/.optim,
INFO:root:Epoch 10: train_loss 0.393135, train_acc 0.7, dev_loss 0.338353, dev_acc 0.747,
time 18.548 s/epoch, total time 204.029 s, time left 723.377 s
INFO:root:Epoch 11: train_loss 0.360749, train_acc 0.726, dev_loss 0.338353, dev_acc 0.747,
time 17.608 s/epoch, total time 211.297 s, time left 669.107 s
INFO:root:Model Save at ./save/599245_epoch12.model/.optim,
INFO:root:Epoch 12: train_loss 0.349959, train_acc 0.734, dev_loss 0.303442, dev_acc 0.777,
time 18.264 s/epoch, total time 237.428 s, time left 675.755 s
INFO:root:Epoch 13: train_loss 0.343226, train_acc 0.74, dev_loss 0.303442, dev_acc 0.777,
time 17.485 s/epoch, total time 244.795 s, time left 629.473 s
INFO:root:Model Save at ./save/599245_epoch14.model/.optim,
INFO:root:Epoch 14: train_loss 0.336154, train_acc 0.743, dev_loss 0.292345, dev_acc 0.782,
time 18.068 s/epoch, total time 271.023 s, time left 632.387 s
INFO:root:Epoch 15: train_loss 0.330292, train_acc 0.751, dev_loss 0.292345, dev_acc 0.782,
time 17.401 s/epoch, total time 278.42 s, time left 591.642 s
INFO:root:Model Save at ./save/599245_epoch16.model/.optim,
INFO:root:Epoch 16: train_loss 0.328215, train_acc 0.752, dev_loss 0.283134, dev_acc 0.793,
time 17.881 s/epoch, total time 303.979 s, time left 590.076 s
INFO:root:Epoch 17: train_loss 0.321222, train_acc 0.757, dev_loss 0.283134, dev_acc 0.793,
time 17.294 s/epoch, total time 311.298 s, time left 553.419 s
INFO:root:Model Save at ./save/599245_epoch18.model/.optim,
INFO:root:Epoch 18: train_loss 0.316574, train_acc 0.76, dev_loss 0.279935, dev_acc 0.798,
time 17.801 s/epoch, total time 338.219 s, time left 551.831 s
INFO:root:
----------Sat May 20 16:19:48 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(64, 96, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[96,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(96, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72437232
INFO:root:Start Training: Sat May 20 16:19:52 2023
INFO:root:
----------Sat May 20 16:28:37 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 16, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[16,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(16, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72352912
INFO:root:Start Training: Sat May 20 16:28:43 2023
INFO:root:Model Save at ./save/600123_epoch0.model/.optim,
INFO:root:Epoch 0: train_loss 1.254006, train_acc 0.052, dev_loss 1.060399, dev_acc 0.139,
time 27.844 s/epoch, total time 27.844 s, time left 1364.353 s
INFO:root:Epoch 1: train_loss 0.966116, train_acc 0.23, dev_loss 1.060399, dev_acc 0.139,
time 17.267 s/epoch, total time 34.535 s, time left 828.837 s
INFO:root:Model Save at ./save/600123_epoch2.model/.optim,
INFO:root:Epoch 2: train_loss 0.814589, train_acc 0.374, dev_loss 0.703881, dev_acc 0.476,
time 20.327 s/epoch, total time 60.98 s, time left 955.347 s
INFO:root:Epoch 3: train_loss 0.732826, train_acc 0.452, dev_loss 0.703881, dev_acc 0.476,
time 16.928 s/epoch, total time 67.711 s, time left 778.676 s
INFO:root:Model Save at ./save/600123_epoch4.model/.optim,
INFO:root:Epoch 4: train_loss 0.669669, train_acc 0.503, dev_loss 0.575257, dev_acc 0.576,
time 18.736 s/epoch, total time 93.681 s, time left 843.125 s
INFO:root:Epoch 5: train_loss 0.60413, train_acc 0.541, dev_loss 0.575257, dev_acc 0.576,
time 16.726 s/epoch, total time 100.355 s, time left 735.939 s
INFO:root:Model Save at ./save/600123_epoch6.model/.optim,
INFO:root:Epoch 6: train_loss 0.552399, train_acc 0.576, dev_loss 0.474825, dev_acc 0.633,
time 17.973 s/epoch, total time 125.814 s, time left 772.859 s
INFO:root:Epoch 7: train_loss 0.515526, train_acc 0.603, dev_loss 0.474825, dev_acc 0.633,
time 16.562 s/epoch, total time 132.494 s, time left 695.595 s
INFO:root:Model Save at ./save/600123_epoch8.model/.optim,
INFO:root:Epoch 8: train_loss 0.481183, train_acc 0.626, dev_loss 0.421702, dev_acc 0.665,
time 17.574 s/epoch, total time 158.168 s, time left 720.545 s
INFO:root:Epoch 9: train_loss 0.455942, train_acc 0.651, dev_loss 0.421702, dev_acc 0.665,
time 16.481 s/epoch, total time 164.808 s, time left 659.232 s
INFO:root:Model Save at ./save/600123_epoch10.model/.optim,
INFO:root:Epoch 10: train_loss 0.43469, train_acc 0.665, dev_loss 0.36486, dev_acc 0.717,
time 17.34 s/epoch, total time 190.735 s, time left 676.242 s
INFO:root:Epoch 11: train_loss 0.401892, train_acc 0.691, dev_loss 0.36486, dev_acc 0.717,
time 16.448 s/epoch, total time 197.378 s, time left 625.031 s
INFO:root:Model Save at ./save/600123_epoch12.model/.optim,
INFO:root:Epoch 12: train_loss 0.390743, train_acc 0.7, dev_loss 0.3374, dev_acc 0.747,
time 17.158 s/epoch, total time 223.05 s, time left 634.834 s
INFO:root:Epoch 13: train_loss 0.386389, train_acc 0.705, dev_loss 0.3374, dev_acc 0.747,
time 16.408 s/epoch, total time 229.715 s, time left 590.696 s
INFO:root:Model Save at ./save/600123_epoch14.model/.optim,
INFO:root:Epoch 14: train_loss 0.381681, train_acc 0.707, dev_loss 0.328241, dev_acc 0.751,
time 16.976 s/epoch, total time 254.641 s, time left 594.163 s
INFO:root:Epoch 15: train_loss 0.37581, train_acc 0.714, dev_loss 0.328241, dev_acc 0.751,
time 16.332 s/epoch, total time 261.309 s, time left 555.282 s
INFO:root:Model Save at ./save/600123_epoch16.model/.optim,
INFO:root:Epoch 16: train_loss 0.370873, train_acc 0.717, dev_loss 0.312286, dev_acc 0.76,
time 16.827 s/epoch, total time 286.053 s, time left 555.28 s
INFO:root:Epoch 17: train_loss 0.367459, train_acc 0.719, dev_loss 0.312286, dev_acc 0.76,
time 16.253 s/epoch, total time 292.559 s, time left 520.104 s
INFO:root:Model Save at ./save/600123_epoch18.model/.optim,
INFO:root:Epoch 18: train_loss 0.362016, train_acc 0.723, dev_loss 0.312607, dev_acc 0.768,
time 16.734 s/epoch, total time 317.946 s, time left 518.754 s
INFO:root:Epoch 19: train_loss 0.356279, train_acc 0.728, dev_loss 0.312607, dev_acc 0.768,
time 16.224 s/epoch, total time 324.48 s, time left 486.721 s
INFO:root:Model Save at ./save/600123_epoch20.model/.optim,
INFO:root:Epoch 20: train_loss 0.350712, train_acc 0.736, dev_loss 0.29396, dev_acc 0.777,
time 16.651 s/epoch, total time 349.661 s, time left 482.865 s
INFO:root:Epoch 21: train_loss 0.343493, train_acc 0.739, dev_loss 0.29396, dev_acc 0.777,
time 16.19 s/epoch, total time 356.18 s, time left 453.321 s
INFO:root:
----------Sat May 20 16:34:49 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 16, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[16,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(16, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 384, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[384,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
17: Conv(384, 512, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[512,], None, Kw=None, fan=None, i=None, bound=None)
18: relu()
19: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(2048, 4096, float32[4096,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(4096, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 82808592
INFO:root:Start Training: Sat May 20 16:34:55 2023
INFO:root:
----------Sat May 20 16:36:00 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 16, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[16,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(16, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 384, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[384,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
17: Conv(384, 512, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[512,], None, Kw=None, fan=None, i=None, bound=None)
18: relu()
19: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(2048, 4096, float32[4096,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(4096, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 82808592
INFO:root:Start Training: Sat May 20 16:36:06 2023
INFO:root:Model Save at ./save/600566_epoch0.model/.optim,
INFO:root:Epoch 0: train_loss 1.290024, train_acc 0.028, dev_loss 1.137833, dev_acc 0.069,
time 37.073 s/epoch, total time 37.073 s, time left 1816.575 s
INFO:root:Epoch 1: train_loss 1.110625, train_acc 0.076, dev_loss 1.137833, dev_acc 0.069,
time 23.382 s/epoch, total time 46.763 s, time left 1122.312 s
INFO:root:Model Save at ./save/600566_epoch2.model/.optim,
INFO:root:Epoch 2: train_loss 0.947488, train_acc 0.229, dev_loss 0.755075, dev_acc 0.427,
time 25.799 s/epoch, total time 77.398 s, time left 1212.575 s
INFO:root:Epoch 3: train_loss 0.820123, train_acc 0.385, dev_loss 0.755075, dev_acc 0.427,
time 21.786 s/epoch, total time 87.142 s, time left 1002.138 s
INFO:root:Model Save at ./save/600566_epoch4.model/.optim,
INFO:root:Epoch 4: train_loss 0.753191, train_acc 0.45, dev_loss 0.626055, dev_acc 0.558,
time 23.514 s/epoch, total time 117.572 s, time left 1058.15 s
INFO:root:Epoch 5: train_loss 0.702873, train_acc 0.487, dev_loss 0.626055, dev_acc 0.558,
time 21.233 s/epoch, total time 127.397 s, time left 934.243 s
INFO:root:Model Save at ./save/600566_epoch6.model/.optim,
INFO:root:Epoch 6: train_loss 0.65604, train_acc 0.52, dev_loss 0.554318, dev_acc 0.598,
time 22.522 s/epoch, total time 157.652 s, time left 968.434 s
INFO:root:Epoch 7: train_loss 0.6019, train_acc 0.552, dev_loss 0.554318, dev_acc 0.598,
time 20.933 s/epoch, total time 167.462 s, time left 879.178 s
INFO:root:Model Save at ./save/600566_epoch8.model/.optim,
INFO:root:Epoch 8: train_loss 0.553742, train_acc 0.584, dev_loss 0.476938, dev_acc 0.641,
time 22.086 s/epoch, total time 198.776 s, time left 905.535 s
INFO:root:Epoch 9: train_loss 0.518042, train_acc 0.609, dev_loss 0.476938, dev_acc 0.641,
time 20.85 s/epoch, total time 208.499 s, time left 833.998 s
INFO:root:Model Save at ./save/600566_epoch10.model/.optim,
INFO:root:Epoch 10: train_loss 0.484087, train_acc 0.635, dev_loss 0.403857, dev_acc 0.688,
time 21.889 s/epoch, total time 240.774 s, time left 853.654 s
INFO:root:Epoch 11: train_loss 0.444106, train_acc 0.663, dev_loss 0.403857, dev_acc 0.688,
time 20.87 s/epoch, total time 250.438 s, time left 793.054 s
INFO:root:Model Save at ./save/600566_epoch12.model/.optim,
INFO:root:Epoch 12: train_loss 0.430178, train_acc 0.673, dev_loss 0.360929, dev_acc 0.724,
time 21.635 s/epoch, total time 281.257 s, time left 800.502 s
INFO:root:Epoch 13: train_loss 0.413802, train_acc 0.684, dev_loss 0.360929, dev_acc 0.724,
time 20.791 s/epoch, total time 291.068 s, time left 748.46 s
INFO:root:Model Save at ./save/600566_epoch14.model/.optim,
INFO:root:Epoch 14: train_loss 0.406684, train_acc 0.687, dev_loss 0.342988, dev_acc 0.741,
time 21.447 s/epoch, total time 321.706 s, time left 750.648 s
INFO:root:Epoch 15: train_loss 0.400351, train_acc 0.695, dev_loss 0.342988, dev_acc 0.741,
time 20.718 s/epoch, total time 331.487 s, time left 704.41 s
INFO:root:Model Save at ./save/600566_epoch16.model/.optim,
INFO:root:Epoch 16: train_loss 0.392157, train_acc 0.702, dev_loss 0.329585, dev_acc 0.753,
time 21.334 s/epoch, total time 362.683 s, time left 704.032 s
INFO:root:Epoch 17: train_loss 0.387899, train_acc 0.705, dev_loss 0.329585, dev_acc 0.753,
time 20.687 s/epoch, total time 372.369 s, time left 661.99 s
INFO:root:Epoch 18: train_loss 0.379704, train_acc 0.715, dev_loss 0.335419, dev_acc 0.747,
time 20.13 s/epoch, total time 382.474 s, time left 624.036 s
INFO:root:Epoch 19: train_loss 0.372211, train_acc 0.718, dev_loss 0.335419, dev_acc 0.747,
time 19.617 s/epoch, total time 392.343 s, time left 588.515 s
INFO:root:Model Save at ./save/600566_epoch20.model/.optim,
INFO:root:Epoch 20: train_loss 0.368567, train_acc 0.721, dev_loss 0.310211, dev_acc 0.77,
time 20.153 s/epoch, total time 423.22 s, time left 584.447 s
INFO:root:Epoch 21: train_loss 0.357238, train_acc 0.727, dev_loss 0.310211, dev_acc 0.77,
time 19.679 s/epoch, total time 432.949 s, time left 551.026 s
INFO:root:Model Save at ./save/600566_epoch22.model/.optim,
INFO:root:Epoch 22: train_loss 0.354091, train_acc 0.732, dev_loss 0.299029, dev_acc 0.779,
time 20.164 s/epoch, total time 463.78 s, time left 544.437 s
INFO:root:Epoch 23: train_loss 0.353426, train_acc 0.732, dev_loss 0.299029, dev_acc 0.779,
time 19.737 s/epoch, total time 473.68 s, time left 513.153 s
INFO:root:Model Save at ./save/600566_epoch24.model/.optim,
INFO:root:Epoch 24: train_loss 0.35108, train_acc 0.735, dev_loss 0.297788, dev_acc 0.78,
time 20.173 s/epoch, total time 504.333 s, time left 504.333 s
INFO:root:Epoch 25: train_loss 0.348088, train_acc 0.736, dev_loss 0.297788, dev_acc 0.78,
time 19.771 s/epoch, total time 514.04 s, time left 474.499 s
INFO:root:Model Save at ./save/600566_epoch26.model/.optim,
INFO:root:Epoch 26: train_loss 0.346048, train_acc 0.736, dev_loss 0.297226, dev_acc 0.78,
time 20.174 s/epoch, total time 544.691 s, time left 463.996 s
INFO:root:Epoch 27: train_loss 0.345359, train_acc 0.737, dev_loss 0.297226, dev_acc 0.78,
time 19.801 s/epoch, total time 554.419 s, time left 435.615 s
INFO:root:Model Save at ./save/600566_epoch28.model/.optim,
INFO:root:Epoch 28: train_loss 0.34429, train_acc 0.738, dev_loss 0.294403, dev_acc 0.784,
time 20.263 s/epoch, total time 587.619 s, time left 425.517 s
INFO:root:Epoch 29: train_loss 0.342458, train_acc 0.741, dev_loss 0.294403, dev_acc 0.784,
time 19.921 s/epoch, total time 597.628 s, time left 398.419 s
INFO:root:Model Save at ./save/600566_epoch30.model/.optim,
INFO:root:Epoch 30: train_loss 0.342458, train_acc 0.74, dev_loss 0.289787, dev_acc 0.789,
time 20.268 s/epoch, total time 628.316 s, time left 385.097 s
INFO:root:Epoch 31: train_loss 0.337309, train_acc 0.745, dev_loss 0.289787, dev_acc 0.789,
time 19.938 s/epoch, total time 638.018 s, time left 358.885 s
INFO:root:Epoch 32: train_loss 0.336559, train_acc 0.744, dev_loss 0.28699, dev_acc 0.783,
time 19.636 s/epoch, total time 647.982 s, time left 333.809 s
INFO:root:Epoch 33: train_loss 0.337245, train_acc 0.743, dev_loss 0.28699, dev_acc 0.783,
time 19.355 s/epoch, total time 658.066 s, time left 309.678 s
INFO:root:Model Save at ./save/600566_epoch34.model/.optim,
INFO:root:Epoch 34: train_loss 0.337359, train_acc 0.744, dev_loss 0.285883, dev_acc 0.79,
time 19.679 s/epoch, total time 688.778 s, time left 295.191 s
INFO:root:Epoch 35: train_loss 0.334774, train_acc 0.746, dev_loss 0.285883, dev_acc 0.79,
time 19.403 s/epoch, total time 698.524 s, time left 271.648 s
INFO:root:Epoch 36: train_loss 0.336551, train_acc 0.745, dev_loss 0.286406, dev_acc 0.787,
time 19.149 s/epoch, total time 708.525 s, time left 248.941 s
INFO:root:Epoch 37: train_loss 0.334551, train_acc 0.746, dev_loss 0.286406, dev_acc 0.787,
time 18.913 s/epoch, total time 718.685 s, time left 226.953 s
INFO:root:Model Save at ./save/600566_epoch38.model/.optim,
INFO:root:Epoch 38: train_loss 0.335004, train_acc 0.746, dev_loss 0.285388, dev_acc 0.794,
time 19.238 s/epoch, total time 750.283 s, time left 211.618 s
INFO:root:Epoch 39: train_loss 0.334148, train_acc 0.748, dev_loss 0.285388, dev_acc 0.794,
time 19.003 s/epoch, total time 760.138 s, time left 190.034 s
INFO:root:Model Save at ./save/600566_epoch40.model/.optim,
INFO:root:Epoch 40: train_loss 0.335264, train_acc 0.747, dev_loss 0.282143, dev_acc 0.795,
time 19.294 s/epoch, total time 791.041 s, time left 173.643 s
INFO:root:Epoch 41: train_loss 0.333246, train_acc 0.749, dev_loss 0.282143, dev_acc 0.795,
time 19.07 s/epoch, total time 800.957 s, time left 152.563 s
INFO:root:Epoch 42: train_loss 0.332439, train_acc 0.747, dev_loss 0.283081, dev_acc 0.794,
time 18.859 s/epoch, total time 810.956 s, time left 132.016 s
INFO:root:Epoch 43: train_loss 0.333584, train_acc 0.748, dev_loss 0.283081, dev_acc 0.794,
time 18.657 s/epoch, total time 820.886 s, time left 111.939 s
INFO:root:Model Save at ./save/600566_epoch44.model/.optim,
INFO:root:Epoch 44: train_loss 0.33161, train_acc 0.75, dev_loss 0.282902, dev_acc 0.797,
time 18.934 s/epoch, total time 852.043 s, time left 94.671 s
INFO:root:Epoch 45: train_loss 0.331417, train_acc 0.749, dev_loss 0.282902, dev_acc 0.797,
time 18.739 s/epoch, total time 862.012 s, time left 74.958 s
INFO:root:Model Save at ./save/600566_epoch46.model/.optim,
INFO:root:Epoch 46: train_loss 0.331596, train_acc 0.75, dev_loss 0.281778, dev_acc 0.799,
time 18.997 s/epoch, total time 892.857 s, time left 56.991 s
INFO:root:Epoch 47: train_loss 0.330719, train_acc 0.75, dev_loss 0.281778, dev_acc 0.799,
time 18.803 s/epoch, total time 902.562 s, time left 37.607 s
INFO:root:Epoch 48: train_loss 0.329481, train_acc 0.75, dev_loss 0.282213, dev_acc 0.798,
time 18.625 s/epoch, total time 912.618 s, time left 18.625 s
INFO:root:Epoch 49: train_loss 0.332422, train_acc 0.748, dev_loss 0.283607, dev_acc 0.794,
time 18.455 s/epoch, total time 922.771 s, time left 0.0 s
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 16, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[16,], None, Kw=None, fan=None, i=None, bound=None)
1: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
2: relu()
3: Dropout(0.05, is_train=False)
4: Conv(16, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
6: relu()
7: Dropout(0.05, is_train=False)
8: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
9: relu()
10: Dropout(0.05, is_train=False)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.05, is_train=False)
14: Conv(256, 384, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[384,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.05, is_train=False)
17: Conv(384, 512, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[512,], None, Kw=None, fan=None, i=None, bound=None)
18: relu()
19: Dropout(0.05, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(2048, 4096, float32[4096,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(4096, 1024, float32[1024,], None)
4: relu()
5: Dropout(0.05, is_train=False)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.05, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.05, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 82808592
INFO:root:Best epoch: 46, best acc: 0.7986379977876107
Final train_loss: 0.332422 dev_loss: 0.283607
Final train_acc: 0.74831 dev_acc: 0.793847
Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'lr': 5e-05, 'betas': (0.9, 0.8), 'dropout': 0.05, 'batch_size': 512, 'num_workers': 8, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:
----------Sun May 21 06:35:06 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'batch_size': 512, 'num_workers': 8, 'lr': 5e-05, 'betas': (0.9, 0.9), 'dropout': 0.1, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:
----------Sun May 21 06:37:05 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'batch_size': 512, 'num_workers': 8, 'lr': 5e-05, 'betas': (0.9, 0.9), 'dropout': 0.1, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:
----------Sun May 21 06:38:32 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'batch_size': 512, 'num_workers': 8, 'lr': 5e-05, 'betas': (0.9, 0.9), 'dropout': 0.1, 'enable_scheduler': True, 'milestones': [10, 20, 30, 40, 60, 70, 80], 'gamma': 0.3}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 32, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[32,], None, Kw=None, fan=None, i=None, bound=None)
1: relu()
2: Dropout(0.1, is_train=False)
3: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
4: Conv(32, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: relu()
6: Dropout(0.1, is_train=False)
7: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
8: relu()
9: Dropout(0.1, is_train=False)
10: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.1, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.1, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.1, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.1, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.1, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72362576
INFO:root:Start Training: Sun May 21 06:38:40 2023
INFO:root:Model Save at ./save/651120_epoch0.model/.optim,
INFO:root:Epoch 0: train_loss 1.223173, train_acc 0.061, dev_loss 1.026554, dev_acc 0.217,
time 29.503 s/epoch, total time 29.503 s, time left 1445.631 s
INFO:root:Epoch 1: train_loss 0.891583, train_acc 0.312, dev_loss 1.026554, dev_acc 0.217,
time 18.453 s/epoch, total time 36.906 s, time left 885.748 s
INFO:root:Model Save at ./save/651120_epoch2.model/.optim,
INFO:root:Epoch 2: train_loss 0.716236, train_acc 0.461, dev_loss 0.62775, dev_acc 0.546,
time 21.461 s/epoch, total time 64.384 s, time left 1008.685 s
INFO:root:Epoch 3: train_loss 0.622206, train_acc 0.534, dev_loss 0.62775, dev_acc 0.546,
time 17.959 s/epoch, total time 71.835 s, time left 826.101 s
INFO:root:Model Save at ./save/651120_epoch4.model/.optim,
INFO:root:Epoch 4: train_loss 0.550197, train_acc 0.579, dev_loss 0.482189, dev_acc 0.641,
time 19.7 s/epoch, total time 98.5 s, time left 886.496 s
INFO:root:Epoch 5: train_loss 0.491548, train_acc 0.619, dev_loss 0.482189, dev_acc 0.641,
time 17.661 s/epoch, total time 105.966 s, time left 777.084 s
INFO:root:Model Save at ./save/651120_epoch6.model/.optim,
INFO:root:Epoch 6: train_loss 0.447559, train_acc 0.653, dev_loss 0.393293, dev_acc 0.709,
time 18.955 s/epoch, total time 132.685 s, time left 815.062 s
INFO:root:Epoch 7: train_loss 0.407935, train_acc 0.687, dev_loss 0.393293, dev_acc 0.709,
time 17.511 s/epoch, total time 140.087 s, time left 735.457 s
INFO:root:Model Save at ./save/651120_epoch8.model/.optim,
INFO:root:Epoch 8: train_loss 0.383365, train_acc 0.708, dev_loss 0.340873, dev_acc 0.753,
time 18.647 s/epoch, total time 167.822 s, time left 764.524 s
INFO:root:Epoch 9: train_loss 0.362699, train_acc 0.725, dev_loss 0.340873, dev_acc 0.753,
time 17.52 s/epoch, total time 175.202 s, time left 700.81 s
INFO:root:Model Save at ./save/651120_epoch10.model/.optim,
INFO:root:Epoch 10: train_loss 0.34515, train_acc 0.741, dev_loss 0.306627, dev_acc 0.779,
time 18.457 s/epoch, total time 203.022 s, time left 719.804 s
INFO:root:Epoch 11: train_loss 0.319073, train_acc 0.761, dev_loss 0.306627, dev_acc 0.779,
time 17.534 s/epoch, total time 210.408 s, time left 666.293 s
INFO:root:Model Save at ./save/651120_epoch12.model/.optim,
INFO:root:Epoch 12: train_loss 0.306086, train_acc 0.77, dev_loss 0.278592, dev_acc 0.803,
time 18.297 s/epoch, total time 237.855 s, time left 676.972 s
INFO:root:Epoch 13: train_loss 0.29979, train_acc 0.775, dev_loss 0.278592, dev_acc 0.803,
time 17.517 s/epoch, total time 245.237 s, time left 630.608 s
INFO:root:Model Save at ./save/651120_epoch14.model/.optim,
INFO:root:Epoch 14: train_loss 0.296533, train_acc 0.776, dev_loss 0.265181, dev_acc 0.814,
time 18.145 s/epoch, total time 272.18 s, time left 635.086 s
INFO:root:Epoch 15: train_loss 0.290006, train_acc 0.783, dev_loss 0.265181, dev_acc 0.814,
time 17.472 s/epoch, total time 279.558 s, time left 594.06 s
INFO:root:Model Save at ./save/651120_epoch16.model/.optim,
INFO:root:Epoch 16: train_loss 0.286662, train_acc 0.784, dev_loss 0.256414, dev_acc 0.818,
time 18.023 s/epoch, total time 306.389 s, time left 594.755 s
INFO:root:Epoch 17: train_loss 0.282093, train_acc 0.788, dev_loss 0.256414, dev_acc 0.818,
time 17.431 s/epoch, total time 313.766 s, time left 557.806 s
INFO:root:Model Save at ./save/651120_epoch18.model/.optim,
INFO:root:Epoch 18: train_loss 0.277584, train_acc 0.791, dev_loss 0.252775, dev_acc 0.821,
time 17.924 s/epoch, total time 340.548 s, time left 555.632 s
INFO:root:Epoch 19: train_loss 0.271268, train_acc 0.796, dev_loss 0.252775, dev_acc 0.821,
time 17.402 s/epoch, total time 348.041 s, time left 522.061 s
INFO:root:Model Save at ./save/651120_epoch20.model/.optim,
INFO:root:Epoch 20: train_loss 0.269156, train_acc 0.797, dev_loss 0.237129, dev_acc 0.828,
time 17.827 s/epoch, total time 374.36 s, time left 516.973 s
INFO:root:Epoch 21: train_loss 0.261111, train_acc 0.804, dev_loss 0.237129, dev_acc 0.828,
time 17.357 s/epoch, total time 381.855 s, time left 485.997 s
INFO:root:Model Save at ./save/651120_epoch22.model/.optim,
INFO:root:Epoch 22: train_loss 0.25628, train_acc 0.805, dev_loss 0.235299, dev_acc 0.837,
time 17.752 s/epoch, total time 408.297 s, time left 479.305 s
INFO:root:Epoch 23: train_loss 0.255423, train_acc 0.805, dev_loss 0.235299, dev_acc 0.837,
time 17.32 s/epoch, total time 415.685 s, time left 450.326 s
INFO:root:Model Save at ./save/651120_epoch24.model/.optim,
INFO:root:Epoch 24: train_loss 0.252735, train_acc 0.808, dev_loss 0.229614, dev_acc 0.839,
time 17.675 s/epoch, total time 441.874 s, time left 441.874 s
INFO:root:Epoch 25: train_loss 0.252685, train_acc 0.809, dev_loss 0.229614, dev_acc 0.839,
time 17.28 s/epoch, total time 449.281 s, time left 414.721 s
INFO:root:Epoch 26: train_loss 0.251119, train_acc 0.81, dev_loss 0.229193, dev_acc 0.836,
time 16.919 s/epoch, total time 456.807 s, time left 389.132 s
INFO:root:Epoch 27: train_loss 0.250584, train_acc 0.81, dev_loss 0.229193, dev_acc 0.836,
time 16.585 s/epoch, total time 464.392 s, time left 364.879 s
INFO:root:Model Save at ./save/651120_epoch28.model/.optim,
INFO:root:Epoch 28: train_loss 0.247515, train_acc 0.811, dev_loss 0.226174, dev_acc 0.845,
time 16.923 s/epoch, total time 490.774 s, time left 355.388 s
INFO:root:Epoch 29: train_loss 0.246947, train_acc 0.811, dev_loss 0.226174, dev_acc 0.845,
time 16.606 s/epoch, total time 498.171 s, time left 332.114 s
INFO:root:Epoch 30: train_loss 0.244801, train_acc 0.816, dev_loss 0.226369, dev_acc 0.842,
time 16.319 s/epoch, total time 505.902 s, time left 310.069 s
INFO:root:Epoch 31: train_loss 0.242885, train_acc 0.815, dev_loss 0.226369, dev_acc 0.842,
time 16.043 s/epoch, total time 513.366 s, time left 288.768 s
INFO:root:Epoch 32: train_loss 0.242357, train_acc 0.817, dev_loss 0.2218, dev_acc 0.843,
time 15.792 s/epoch, total time 521.141 s, time left 268.467 s
INFO:root:Epoch 33: train_loss 0.242278, train_acc 0.817, dev_loss 0.2218, dev_acc 0.843,
time 15.553 s/epoch, total time 528.788 s, time left 248.841 s
INFO:root:Epoch 34: train_loss 0.241146, train_acc 0.816, dev_loss 0.220658, dev_acc 0.841,
time 15.339 s/epoch, total time 536.861 s, time left 230.083 s
INFO:root:Epoch 35: train_loss 0.239666, train_acc 0.818, dev_loss 0.220658, dev_acc 0.841,
time 15.13 s/epoch, total time 544.667 s, time left 211.815 s
INFO:root:Model Save at ./save/651120_epoch36.model/.optim,
INFO:root:Epoch 36: train_loss 0.240546, train_acc 0.817, dev_loss 0.218924, dev_acc 0.849,
time 15.45 s/epoch, total time 571.643 s, time left 200.847 s
INFO:root:Epoch 37: train_loss 0.238861, train_acc 0.819, dev_loss 0.218924, dev_acc 0.849,
time 15.243 s/epoch, total time 579.223 s, time left 182.912 s
INFO:root:
----------Sun May 21 06:48:32 2023----------
INFO:root:Config: {'use_cuda': 1, 'preprocess': True, 'val_ratio': 0.05, 'data_dir': './cifar-10-batches-py', 'save_dir': './save', 'model': 'realsmallcnn', 'criterion': 'jittor_cel', 'enable_sinkhorn': False, 'n_input': [3, 16, 16], 'epoch': 50, 'eval_epoch': 2, 'batch_size': 512, 'num_workers': 8, 'lr': 5e-05, 'betas': (0.9, 0.9), 'dropout': 0.1, 'enable_scheduler': True, 'milestones': [15, 30, 40, 60, 70, 80], 'gamma': 0.4}
INFO:root:Model: RealSmallCNN(
features: Sequential(
0: Conv(3, 32, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[32,], None, Kw=None, fan=None, i=None, bound=None)
1: relu()
2: Dropout(0.1, is_train=False)
3: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
4: Conv(32, 64, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[64,], None, Kw=None, fan=None, i=None, bound=None)
5: relu()
6: Dropout(0.1, is_train=False)
7: Conv(64, 128, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[128,], None, Kw=None, fan=None, i=None, bound=None)
8: relu()
9: Dropout(0.1, is_train=False)
10: Pool((2, 2), (2, 2), padding=(0, 0), dilation=None, return_indices=None, ceil_mode=False, count_include_pad=False, op=maximum)
11: Conv(128, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
12: relu()
13: Dropout(0.1, is_train=False)
14: Conv(256, 256, (3, 3), (1, 1), (1, 1), (1, 1), 1, float32[256,], None, Kw=None, fan=None, i=None, bound=None)
15: relu()
16: Dropout(0.1, is_train=False)
)
avgpool: AdaptiveAvgPool2d((2, 2))
classifier: Sequential(
0: Linear(1024, 2048, float32[2048,], None)
1: relu()
2: Dropout(0.1, is_train=False)
3: Linear(2048, 1024, float32[1024,], None)
)
tail: Sequential(
0: Linear(4096, 8192, float32[8192,], None)
1: relu()
2: Dropout(0.1, is_train=False)
3: Linear(8192, 4096, float32[4096,], None)
4: relu()
5: Dropout(0.1, is_train=False)
6: Linear(4096, 16, float32[16,], None)
)
) , Params num: 72362576
INFO:root:Start Training: Sun May 21 06:48:38 2023
INFO:root:Model Save at ./save/651718_epoch0.model/.optim,
INFO:root:Epoch 0: train_loss 1.226971, train_acc 0.054, dev_loss 1.019255, dev_acc 0.169,
time 28.393 s/epoch, total time 28.393 s, time left 1391.241 s
INFO:root:Epoch 1: train_loss 0.856456, train_acc 0.327, dev_loss 1.019255, dev_acc 0.169,
time 17.941 s/epoch, total time 35.882 s, time left 861.178 s
INFO:root:Model Save at ./save/651718_epoch2.model/.optim,
INFO:root:Epoch 2: train_loss 0.695996, train_acc 0.481, dev_loss 0.609635, dev_acc 0.559,
time 20.809 s/epoch, total time 62.426 s, time left 978.01 s
INFO:root:Epoch 3: train_loss 0.627778, train_acc 0.538, dev_loss 0.609635, dev_acc 0.559,
time 17.48 s/epoch, total time 69.921 s, time left 804.095 s
INFO:root:Model Save at ./save/651718_epoch4.model/.optim,
INFO:root:Epoch 4: train_loss 0.575177, train_acc 0.582, dev_loss 0.514592, dev_acc 0.634,
time 19.534 s/epoch, total time 97.669 s, time left 879.021 s
INFO:root:Epoch 5: train_loss 0.521915, train_acc 0.616, dev_loss 0.514592, dev_acc 0.634,
time 17.527 s/epoch, total time 105.164 s, time left 771.204 s
INFO:root:Model Save at ./save/651718_epoch6.model/.optim,
INFO:root:Epoch 6: train_loss 0.473494, train_acc 0.641, dev_loss 0.41135, dev_acc 0.698,
time 18.671 s/epoch, total time 130.696 s, time left 802.849 s
INFO:root:Epoch 7: train_loss 0.431901, train_acc 0.672, dev_loss 0.41135, dev_acc 0.698,
time 17.274 s/epoch, total time 138.189 s, time left 725.493 s
INFO:root:Model Save at ./save/651718_epoch8.model/.optim,
INFO:root:Epoch 8: train_loss 0.400862, train_acc 0.693, dev_loss 0.359003, dev_acc 0.74,
time 18.151 s/epoch, total time 163.355 s, time left 744.172 s
INFO:root:Epoch 9: train_loss 0.376005, train_acc 0.715, dev_loss 0.359003, dev_acc 0.74,
time 17.088 s/epoch, total time 170.88 s, time left 683.519 s
INFO:root:Model Save at ./save/651718_epoch10.model/.optim,
INFO:root:Epoch 10: train_loss 0.356783, train_acc 0.728, dev_loss 0.30984, dev_acc 0.775,
time 17.826 s/epoch, total time 196.089 s, time left 695.226 s
INFO:root:Epoch 11: train_loss 0.339827, train_acc 0.744, dev_loss 0.30984, dev_acc 0.775,
time 16.964 s/epoch, total time 203.565 s, time left 644.621 s
INFO:root:Model Save at ./save/651718_epoch12.model/.optim,
INFO:root:Epoch 12: train_loss 0.326352, train_acc 0.754, dev_loss 0.293794, dev_acc 0.791,
time 17.591 s/epoch, total time 228.689 s, time left 650.884 s
INFO:root:Epoch 13: train_loss 0.317647, train_acc 0.761, dev_loss 0.293794, dev_acc 0.791,
time 16.87 s/epoch, total time 236.176 s, time left 607.309 s
INFO:root:Model Save at ./save/651718_epoch14.model/.optim,
INFO:root:Epoch 14: train_loss 0.302374, train_acc 0.774, dev_loss 0.275971, dev_acc 0.8,
time 17.426 s/epoch, total time 261.391 s, time left 609.913 s
INFO:root:Epoch 15: train_loss 0.293875, train_acc 0.78, dev_loss 0.275971, dev_acc 0.8,
time 16.807 s/epoch, total time 268.919 s, time left 571.452 s
INFO:root:Model Save at ./save/651718_epoch16.model/.optim,
INFO:root:Epoch 16: train_loss 0.271489, train_acc 0.798, dev_loss 0.259004, dev_acc 0.812,
time 17.312 s/epoch, total time 294.304 s, time left 571.297 s
INFO:root:Epoch 17: train_loss 0.263978, train_acc 0.803, dev_loss 0.259004, dev_acc 0.812,
time 16.762 s/epoch, total time 301.717 s, time left 536.386 s
INFO:root:Model Save at ./save/651718_epoch18.model/.optim,
INFO:root:Epoch 18: train_loss 0.257309, train_acc 0.808, dev_loss 0.255708, dev_acc 0.815,
time 17.214 s/epoch, total time 327.057 s, time left 533.619 s
INFO:root:Epoch 19: train_loss 0.253227, train_acc 0.811, dev_loss 0.255708, dev_acc 0.815,
time 16.724 s/epoch, total time 334.489 s, time left 501.733 s
INFO:root:Model Save at ./save/651718_epoch20.model/.optim,
INFO:root:Epoch 20: train_loss 0.249008, train_acc 0.814, dev_loss 0.233592, dev_acc 0.83,
time 17.129 s/epoch, total time 359.719 s, time left 496.755 s
INFO:root:Epoch 21: train_loss 0.245069, train_acc 0.814, dev_loss 0.233592, dev_acc 0.83,
time 16.691 s/epoch, total time 367.209 s, time left 467.357 s
INFO:root:Model Save at ./save/651718_epoch22.model/.optim,
INFO:root:Epoch 22: train_loss 0.237717, train_acc 0.82, dev_loss 0.229805, dev_acc 0.833,
time 17.066 s/epoch, total time 392.518 s, time left 460.782 s
INFO:root:Epoch 23: train_loss 0.233578, train_acc 0.821, dev_loss 0.229805, dev_acc 0.833,
time 16.663 s/epoch, total time 399.92 s, time left 433.246 s
INFO:root:Model Save at ./save/651718_epoch24.model/.optim,
INFO:root:Epoch 24: train_loss 0.231843, train_acc 0.826, dev_loss 0.223782, dev_acc 0.839,
time 17.071 s/epoch, total time 426.774 s, time left 426.774 s
INFO:root:Epoch 25: train_loss 0.227144, train_acc 0.827, dev_loss 0.223782, dev_acc 0.839,
time 16.7 s/epoch, total time 434.201 s, time left 400.801 s
INFO:root:Model Save at ./save/651718_epoch26.model/.optim,
INFO:root:Epoch 26: train_loss 0.222345, train_acc 0.829, dev_loss 0.219971, dev_acc 0.846,
time 17.018 s/epoch, total time 459.486 s, time left 391.414 s
INFO:root:Epoch 27: train_loss 0.217472, train_acc 0.834, dev_loss 0.219971, dev_acc 0.846,
time 16.68 s/epoch, total time 467.027 s, time left 366.95 s
INFO:root:Epoch 28: train_loss 0.212781, train_acc 0.838, dev_loss 0.210585, dev_acc 0.843,
time 16.368 s/epoch, total time 474.661 s, time left 343.72 s
INFO:root:Epoch 29: train_loss 0.207502, train_acc 0.842, dev_loss 0.210585, dev_acc 0.843,
time 16.074 s/epoch, total time 482.213 s, time left 321.476 s
INFO:root:Epoch 30: train_loss 0.204201, train_acc 0.844, dev_loss 0.201466, dev_acc 0.844,
time 15.81 s/epoch, total time 490.123 s, time left 300.398 s
INFO:root:Epoch 31: train_loss 0.194871, train_acc 0.851, dev_loss 0.201466, dev_acc 0.844,
time 15.557 s/epoch, total time 497.814 s, time left 280.02 s
INFO:root:Model Save at ./save/651718_epoch32.model/.optim,
INFO:root:Epoch 32: train_loss 0.193681, train_acc 0.852, dev_loss 0.196596, dev_acc 0.854,
time 15.86 s/epoch, total time 523.368 s, time left 269.614 s
INFO:root:Epoch 33: train_loss 0.189621, train_acc 0.856, dev_loss 0.196596, dev_acc 0.854,
time 15.616 s/epoch, total time 530.934 s, time left 249.851 s
INFO:root:Model Save at ./save/651718_epoch34.model/.optim,
INFO:root:Epoch 34: train_loss 0.187187, train_acc 0.857, dev_loss 0.190937, dev_acc 0.858,
time 15.892 s/epoch, total time 556.233 s, time left 238.386 s
INFO:root:Epoch 35: train_loss 0.187928, train_acc 0.856, dev_loss 0.190937, dev_acc 0.858,
time 15.657 s/epoch, total time 563.668 s, time left 219.204 s
INFO:root:Model Save at ./save/651718_epoch36.model/.optim,
INFO:root:Epoch 36: train_loss 0.184503, train_acc 0.859, dev_loss 0.189771, dev_acc 0.864,
time 15.925 s/epoch, total time 589.242 s, time left 207.031 s
INFO:root:Epoch 37: train_loss 0.182603, train_acc 0.859, dev_loss 0.189771, dev_acc 0.864,
time 15.703 s/epoch, total time 596.722 s, time left 188.439 s
INFO:root:Model Save at ./save/651718_epoch38.model/.optim,
INFO:root:Epoch 38: train_loss 0.18002, train_acc 0.861, dev_loss 0.185513, dev_acc 0.869,
time 15.961 s/epoch, total time 622.48 s, time left 175.571 s
INFO:root:Epoch 39: train_loss 0.18037, train_acc 0.861, dev_loss 0.185513, dev_acc 0.869,
time 15.748 s/epoch, total time 629.911 s, time left 157.478 s
INFO:root:Model Save at ./save/651718_epoch40.model/.optim,
INFO:root:Epoch 40: train_loss 0.17585, train_acc 0.863, dev_loss 0.181592, dev_acc 0.87,
time 15.996 s/epoch, total time 655.829 s, time left 143.963 s
INFO:root:Epoch 41: train_loss 0.173674, train_acc 0.866, dev_loss 0.181592, dev_acc 0.87,
time 15.791 s/epoch, total time 663.219 s, time left 126.327 s
INFO:root:Model Save at ./save/651718_epoch42.model/.optim,
INFO:root:Epoch 42: train_loss 0.171789, train_acc 0.867, dev_loss 0.178745, dev_acc 0.872,
time 16.027 s/epoch, total time 689.162 s, time left 112.189 s
INFO:root:Epoch 43: train_loss 0.17096, train_acc 0.868, dev_loss 0.178745, dev_acc 0.872,
time 15.832 s/epoch, total time 696.607 s, time left 94.992 s
INFO:root:Epoch 44: train_loss 0.170896, train_acc 0.869, dev_loss 0.177433, dev_acc 0.871,
time 15.653 s/epoch, total time 704.395 s, time left 78.266 s
INFO:root:Epoch 45: train_loss 0.170814, train_acc 0.869, dev_loss 0.177433, dev_acc 0.871,
time 15.477 s/epoch, total time 711.926 s, time left 61.907 s
INFO:root:Epoch 46: train_loss 0.16903, train_acc 0.869, dev_loss 0.178133, dev_acc 0.865,
time 15.315 s/epoch, total time 719.787 s, time left 45.944 s