-
Notifications
You must be signed in to change notification settings - Fork 1
/
train.log
4134 lines (4129 loc) · 349 KB
/
train.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]: current net device: eth0, ip: 172.28.1.189
[INFO]: paddle job envs:
POD_IP=job-3297a8907b20c46a2c7ad7cf9c47f356-trainer-0.job-3297a8907b20c46a2c7ad7cf9c47f356
PADDLE_PORT=12345
PADDLE_TRAINER_ID=0
PADDLE_TRAINERS_NUM=1
PADDLE_USE_CUDA=1
NCCL_SOCKET_IFNAME=eth0
PADDLE_IS_LOCAL=1
OUTPUT_PATH=/root/paddlejob/workspace/output
LOCAL_LOG_PATH=/root/paddlejob/workspace/log
LOCAL_MOUNT_PATH=/mnt/code_20220122173750,/mnt/datasets_20220122173750
JOB_ID=job-3297a8907b20c46a2c7ad7cf9c47f356
TRAINING_ROLE=TRAINER
[INFO]: user command: bash run.sh
[INFO]: start trainer
~/paddlejob/workspace/code /mnt
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple, https://pypi.tuna.tsinghua.edu.cn/simple
Collecting wikipedia2vec==1.0.5
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/89/83/15ab878fe5a93590b80bac8c3a8b0ad5f5dec5d0ea1071f9a17dbce5c33b/wikipedia2vec-1.0.5.tar.gz (1.2 MB)
Preparing metadata (setup.py): started
Preparing metadata (setup.py): finished with status 'done'
Collecting regex
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/82/b9/09143a2072af5571227f1687e44fd9041cc5933fffaf2fbc30394c720141/regex-2022.1.18-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (748 kB)
Collecting transformers==2.3.0
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/50/10/aeefced99c8a59d828a92cc11d213e2743212d3641c87c82d61b035a7d5c/transformers-2.3.0-py3-none-any.whl (447 kB)
Collecting ujson
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/79/66/1f0a9ac8cd225bbf0b34babd22f4b290ae12688d94505d56792e2d7794b6/ujson-5.1.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (43 kB)
Requirement already satisfied: click in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (7.0)
Requirement already satisfied: jieba in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (0.42.1)
Requirement already satisfied: joblib in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (0.14.1)
Collecting lmdb
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/4d/cf/3230b1c9b0bec406abb85a9332ba5805bdd03a1d24025c6bbcfb8ed71539/lmdb-1.3.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (298 kB)
Collecting marisa-trie
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/2d/4d/8a622a03ba1a0798667a737a6f3c703605092572cdbd254db0f25ac50a88/marisa_trie-0.7.7-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.2 MB)
Collecting mwparserfromhell
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/c4/20/a12b478f9a6cfe9c728b2d6b7cb493e451693ace590859109918db6c6a79/mwparserfromhell-0.6.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl (175 kB)
Requirement already satisfied: numpy in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (1.19.5)
Requirement already satisfied: scipy in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (1.1.0)
Requirement already satisfied: six in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (1.16.0)
Requirement already satisfied: tqdm in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (4.27.0)
Requirement already satisfied: sentencepiece in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from transformers==2.3.0->-r requirements.txt (line 3)) (0.1.96)
Collecting boto3
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/fa/9b/42fce3bcb2699ed1596d8b1ea7a84e273b7fec39d893b4ed20d3bd2fc68d/boto3-1.20.41-py3-none-any.whl (131 kB)
Requirement already satisfied: requests in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from transformers==2.3.0->-r requirements.txt (line 3)) (2.24.0)
Collecting sacremoses
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/ec/e5/407e634cbd3b96a9ce6960874c5b66829592ead9ac762bd50662244ce20b/sacremoses-0.0.47-py2.py3-none-any.whl (895 kB)
Collecting jmespath<1.0.0,>=0.7.1
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/07/cb/5f001272b6faeb23c1c9e0acc04d48eaaf5c862c17709d20e3469c6e0139/jmespath-0.10.0-py2.py3-none-any.whl (24 kB)
Collecting botocore<1.24.0,>=1.23.41
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/76/66/7721915980bdc30350bf6d4db297f23733da443fb438e70db3269d876f3a/botocore-1.23.41-py3-none-any.whl (8.5 MB)
Collecting s3transfer<0.6.0,>=0.5.0
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/ab/84/fc3717a7b7f0f6bb08af593127171f08e3e0087c197922da09c01bfe7c3a/s3transfer-0.5.0-py3-none-any.whl (79 kB)
Requirement already satisfied: setuptools in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from marisa-trie->wikipedia2vec==1.0.5->-r requirements.txt (line 1)) (49.2.0)
Requirement already satisfied: certifi>=2017.4.17 in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from requests->transformers==2.3.0->-r requirements.txt (line 3)) (2019.9.11)
Requirement already satisfied: chardet<4,>=3.0.2 in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from requests->transformers==2.3.0->-r requirements.txt (line 3)) (3.0.4)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from requests->transformers==2.3.0->-r requirements.txt (line 3)) (1.25.6)
Requirement already satisfied: idna<3,>=2.5 in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from requests->transformers==2.3.0->-r requirements.txt (line 3)) (2.8)
Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /opt/_internal/cpython-3.7.0/lib/python3.7/site-packages (from botocore<1.24.0,>=1.23.41->boto3->transformers==2.3.0->-r requirements.txt (line 3)) (2.7.3)
Building wheels for collected packages: wikipedia2vec
Building wheel for wikipedia2vec (setup.py): started
Building wheel for wikipedia2vec (setup.py): finished with status 'done'
Created wheel for wikipedia2vec: filename=wikipedia2vec-1.0.5-cp37-cp37m-linux_x86_64.whl size=4895858 sha256=16ca22c59afaf3b3da5dfd90c3155b00e1270d7a6872942542b6d78e556b2330
Stored in directory: /root/.cache/pip/wheels/1b/0a/43/35d67b3c597e56ec204674e57b45e8b8269c50d6cfe6de007b
Successfully built wikipedia2vec
Installing collected packages: jmespath, botocore, s3transfer, regex, sacremoses, mwparserfromhell, marisa-trie, lmdb, boto3, wikipedia2vec, ujson, transformers
Successfully installed boto3-1.20.41 botocore-1.23.41 jmespath-0.10.0 lmdb-1.3.0 marisa-trie-0.7.7 mwparserfromhell-0.6.3 regex-2022.1.18 s3transfer-0.5.0 sacremoses-0.0.47 transformers-2.3.0 ujson-5.1.0 wikipedia2vec-1.0.5
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
WARNING: You are using pip version 21.3; however, version 21.3.1 is available.
You should consider upgrading via the '/opt/_internal/cpython-3.7.0/bin/python -m pip install --upgrade pip' command.
WARNING 2022-01-22 17:38:54,785 launch.py:423] Not found distinct arguments and compiled with cuda or xpu. Default use collective mode
INFO 2022-01-22 17:38:54,787 launch_utils.py:528] Local start 4 processes. First process distributed environment info (Only For Debug):
+=======================================================================================+
| Distributed Envs Value |
+---------------------------------------------------------------------------------------+
| PADDLE_TRAINER_ID 0 |
| PADDLE_CURRENT_ENDPOINT 127.0.0.1:34905 |
| PADDLE_TRAINERS_NUM 4 |
| PADDLE_TRAINER_ENDPOINTS ... 0.1:47185,127.0.0.1:41570,127.0.0.1:38415|
| PADDLE_RANK_IN_NODE 0 |
| PADDLE_LOCAL_DEVICE_IDS 0 |
| PADDLE_WORLD_DEVICE_IDS 0,1,2,3 |
| FLAGS_selected_gpus 0 |
| FLAGS_selected_accelerators 0 |
+=======================================================================================+
INFO 2022-01-22 17:38:54,788 launch_utils.py:532] details abouts PADDLE_TRAINER_ENDPOINTS can be found in log/endpoints.log, and detail running logs maybe found in log/workerlog.0
----------- Configuration Arguments -----------
backend: auto
elastic_server: None
force: False
gpus: None
heter_devices:
heter_worker_num: None
heter_workers:
host: None
http_port: None
ips: 127.0.0.1
job_id: None
log_dir: log
np: None
nproc_per_node: None
run_mode: None
scale: 0
server_num: None
servers:
training_script: main.py
training_script_args: []
worker_num: None
workers:
------------------------------------------------
launch train in GPU mode!
launch proc_id:786 idx:0
launch proc_id:789 idx:1
launch proc_id:792 idx:2
launch proc_id:796 idx:3
/opt/_internal/cpython-3.7.0/lib/python3.7/site-packages/setuptools/distutils_patch.py:26: UserWarning: Distutils was imported before Setuptools. This usage is discouraged and may exhibit undesirable behaviors or errors. Please use Setuptools' objects directly or at least import Setuptools first.
"Distutils was imported before Setuptools. This usage is discouraged "
Neither PyTorch nor TensorFlow >= 2.0 have been found.Models won't be available and only tokenizers, configurationand file/data utilities can be used.
I0122 17:39:06.455045 786 nccl_context.cc:74] init nccl context nranks: 4 local rank: 0 gpu id: 0 ring id: 0
W0122 17:39:07.744225 786 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0122 17:39:07.749609 786 device_context.cc:465] device: 0, cuDNN Version: 7.6.
加载预训练模型......
/opt/_internal/cpython-3.7.0/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for qa_outputs.weight. qa_outputs.weight is not found in the provided dict.
warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
/opt/_internal/cpython-3.7.0/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1436: UserWarning: Skip loading for qa_outputs.bias. qa_outputs.bias is not found in the provided dict.
warnings.warn(("Skip loading for {}. ".format(key) + str(err)))
qa_outputs.weight 参数未加载!!!
qa_outputs.bias 参数未加载!!!
从JSON中加载训练数据集......
0%| | 0/1828 [00:00<?, ?it/s]/opt/_internal/cpython-3.7.0/lib/python3.7/site-packages/paddle/fluid/dygraph/math_op_patch.py:253: UserWarning: The dtype of left and right variables are not the same, left dtype is paddle.float16, but right dtype is paddle.float32, the right dtype will convert to paddle.float16
format(lhs_dtype, rhs_dtype, lhs_dtype))
/opt/_internal/cpython-3.7.0/lib/python3.7/site-packages/paddle/fluid/dygraph/math_op_patch.py:253: UserWarning: The dtype of left and right variables are not the same, left dtype is paddle.float32, but right dtype is paddle.bool, the right dtype will convert to paddle.float32
format(lhs_dtype, rhs_dtype, lhs_dtype))
epoch: 0 loss: 2.0740142: 0%| | 0/1828 [00:03<?, ?it/s]
epoch: 0 loss: 2.0740142: 0%| | 1/1828 [00:03<1:38:48, 3.25s/it]
epoch: 0 loss: 2.0873733: 0%| | 1/1828 [00:05<1:38:48, 3.25s/it]
epoch: 0 loss: 2.0873733: 0%| | 2/1828 [00:05<1:28:32, 2.91s/it]
epoch: 0 loss: 2.0721843: 0%| | 2/1828 [00:07<1:28:32, 2.91s/it]
epoch: 0 loss: 2.0721843: 0%| | 3/1828 [00:07<1:21:23, 2.68s/it]
epoch: 0 loss: 2.0785253: 0%| | 3/1828 [00:09<1:21:23, 2.68s/it]
epoch: 0 loss: 2.0785253: 0%| | 4/1828 [00:09<1:16:25, 2.51s/it]
epoch: 0 loss: 2.0608737: 0%| | 4/1828 [00:11<1:16:25, 2.51s/it]
epoch: 0 loss: 2.0608737: 0%| | 5/1828 [00:11<1:12:48, 2.40s/it]
epoch: 0 loss: 2.0967326: 0%| | 5/1828 [00:13<1:12:48, 2.40s/it]
epoch: 0 loss: 2.0967326: 0%| | 6/1828 [00:13<1:10:20, 2.32s/it]
epoch: 0 loss: 2.0503912: 0%| | 6/1828 [00:16<1:10:20, 2.32s/it]
epoch: 0 loss: 2.0503912: 0%| | 7/1828 [00:16<1:08:39, 2.26s/it]
epoch: 0 loss: 2.0744801: 0%| | 7/1828 [00:18<1:08:39, 2.26s/it]
epoch: 0 loss: 2.0744801: 0%| | 8/1828 [00:18<1:07:30, 2.23s/it]
epoch: 0 loss: 2.0472984: 0%| | 8/1828 [00:20<1:07:30, 2.23s/it]
epoch: 0 loss: 2.0472984: 0%| | 9/1828 [00:20<1:06:36, 2.20s/it]
epoch: 0 loss: 2.0296307: 0%| | 9/1828 [00:22<1:06:36, 2.20s/it]
epoch: 0 loss: 2.0296307: 1%| | 10/1828 [00:22<1:05:58, 2.18s/it]
epoch: 0 loss: 1.9956484: 1%| | 10/1828 [00:24<1:05:58, 2.18s/it]
epoch: 0 loss: 1.9956484: 1%| | 11/1828 [00:24<1:05:34, 2.17s/it]
epoch: 0 loss: 1.9688139: 1%| | 11/1828 [00:26<1:05:34, 2.17s/it]
epoch: 0 loss: 1.9688139: 1%| | 12/1828 [00:26<1:05:12, 2.15s/it]
epoch: 0 loss: 1.9498997: 1%| | 12/1828 [00:28<1:05:12, 2.15s/it]
epoch: 0 loss: 1.9498997: 1%| | 13/1828 [00:28<1:04:56, 2.15s/it]
epoch: 0 loss: 1.9301246: 1%| | 13/1828 [00:30<1:04:56, 2.15s/it]
epoch: 0 loss: 1.9301246: 1%| | 14/1828 [00:30<1:04:45, 2.14s/it]
epoch: 0 loss: 1.8810905: 1%| | 14/1828 [00:33<1:04:45, 2.14s/it]
epoch: 0 loss: 1.8810905: 1%| | 15/1828 [00:33<1:04:44, 2.14s/it]
epoch: 0 loss: 1.8523450: 1%| | 15/1828 [00:35<1:04:44, 2.14s/it]
epoch: 0 loss: 1.8523450: 1%| | 16/1828 [00:35<1:04:31, 2.14s/it]
epoch: 0 loss: 1.8043535: 1%| | 16/1828 [00:37<1:04:31, 2.14s/it]
epoch: 0 loss: 1.8043535: 1%| | 17/1828 [00:37<1:04:19, 2.13s/it]
epoch: 0 loss: 1.7963078: 1%| | 17/1828 [00:39<1:04:19, 2.13s/it]
epoch: 0 loss: 1.7963078: 1%| | 18/1828 [00:39<1:04:19, 2.13s/it]
epoch: 0 loss: 1.7368912: 1%| | 18/1828 [00:41<1:04:19, 2.13s/it]
epoch: 0 loss: 1.7368912: 1%| | 19/1828 [00:41<1:04:07, 2.13s/it]
epoch: 0 loss: 1.7243602: 1%| | 19/1828 [00:43<1:04:07, 2.13s/it]
epoch: 0 loss: 1.7243602: 1%| | 20/1828 [00:43<1:04:05, 2.13s/it]
epoch: 0 loss: 1.7200288: 1%| | 20/1828 [00:45<1:04:05, 2.13s/it]
epoch: 0 loss: 1.7200288: 1%| | 21/1828 [00:45<1:04:04, 2.13s/it]
epoch: 0 loss: 1.6030207: 1%| | 21/1828 [00:47<1:04:04, 2.13s/it]
epoch: 0 loss: 1.6030207: 1%| | 22/1828 [00:47<1:04:02, 2.13s/it]
epoch: 0 loss: 1.7811382: 1%| | 22/1828 [00:50<1:04:02, 2.13s/it]
epoch: 0 loss: 1.7811382: 1%|▏ | 23/1828 [00:50<1:04:01, 2.13s/it]
epoch: 0 loss: 1.6056046: 1%|▏ | 23/1828 [00:52<1:04:01, 2.13s/it]
epoch: 0 loss: 1.6056046: 1%|▏ | 24/1828 [00:52<1:03:55, 2.13s/it]
epoch: 0 loss: 1.6459057: 1%|▏ | 24/1828 [00:54<1:03:55, 2.13s/it]
epoch: 0 loss: 1.6459057: 1%|▏ | 25/1828 [00:54<1:04:00, 2.13s/it]
epoch: 0 loss: 1.5432699: 1%|▏ | 25/1828 [00:56<1:04:00, 2.13s/it]
epoch: 0 loss: 1.5432699: 1%|▏ | 26/1828 [00:56<1:03:56, 2.13s/it]
epoch: 0 loss: 1.5536560: 1%|▏ | 26/1828 [00:58<1:03:56, 2.13s/it]
epoch: 0 loss: 1.5536560: 1%|▏ | 27/1828 [00:58<1:03:56, 2.13s/it]
epoch: 0 loss: 1.5796762: 1%|▏ | 27/1828 [01:00<1:03:56, 2.13s/it]
epoch: 0 loss: 1.5796762: 2%|▏ | 28/1828 [01:00<1:04:00, 2.13s/it]
epoch: 0 loss: 1.6587558: 2%|▏ | 28/1828 [01:02<1:04:00, 2.13s/it]
epoch: 0 loss: 1.6587558: 2%|▏ | 29/1828 [01:02<1:03:57, 2.13s/it]
epoch: 0 loss: 1.2755940: 2%|▏ | 29/1828 [01:05<1:03:57, 2.13s/it]
epoch: 0 loss: 1.2755940: 2%|▏ | 30/1828 [01:05<1:03:58, 2.13s/it]
epoch: 0 loss: 1.3613422: 2%|▏ | 30/1828 [01:07<1:03:58, 2.13s/it]
epoch: 0 loss: 1.3613422: 2%|▏ | 31/1828 [01:07<1:03:51, 2.13s/it]
epoch: 0 loss: 1.3153210: 2%|▏ | 31/1828 [01:09<1:03:51, 2.13s/it]
epoch: 0 loss: 1.3153210: 2%|▏ | 32/1828 [01:09<1:03:54, 2.14s/it]
epoch: 0 loss: 1.4077957: 2%|▏ | 32/1828 [01:11<1:03:54, 2.14s/it]
epoch: 0 loss: 1.4077957: 2%|▏ | 33/1828 [01:11<1:03:52, 2.13s/it]
epoch: 0 loss: 1.1991664: 2%|▏ | 33/1828 [01:13<1:03:52, 2.13s/it]
epoch: 0 loss: 1.1991664: 2%|▏ | 34/1828 [01:13<1:03:50, 2.14s/it]
epoch: 0 loss: 1.4299622: 2%|▏ | 34/1828 [01:15<1:03:50, 2.14s/it]
epoch: 0 loss: 1.4299622: 2%|▏ | 35/1828 [01:15<1:03:53, 2.14s/it]
epoch: 0 loss: 1.4020500: 2%|▏ | 35/1828 [01:17<1:03:53, 2.14s/it]
epoch: 0 loss: 1.4020500: 2%|▏ | 36/1828 [01:17<1:03:50, 2.14s/it]
epoch: 0 loss: 1.3861374: 2%|▏ | 36/1828 [01:19<1:03:50, 2.14s/it]
epoch: 0 loss: 1.3861374: 2%|▏ | 37/1828 [01:19<1:03:47, 2.14s/it]
epoch: 0 loss: 1.1846173: 2%|▏ | 37/1828 [01:22<1:03:47, 2.14s/it]
epoch: 0 loss: 1.1846173: 2%|▏ | 38/1828 [01:22<1:03:41, 2.13s/it]
epoch: 0 loss: 1.3567938: 2%|▏ | 38/1828 [01:24<1:03:41, 2.13s/it]
epoch: 0 loss: 1.3567938: 2%|▏ | 39/1828 [01:24<1:03:43, 2.14s/it]
epoch: 0 loss: 1.1683085: 2%|▏ | 39/1828 [01:26<1:03:43, 2.14s/it]
epoch: 0 loss: 1.1683085: 2%|▏ | 40/1828 [01:26<1:03:39, 2.14s/it]
epoch: 0 loss: 0.8492064: 2%|▏ | 40/1828 [01:28<1:03:39, 2.14s/it]
epoch: 0 loss: 0.8492064: 2%|▏ | 41/1828 [01:28<1:03:36, 2.14s/it]
epoch: 0 loss: 0.8474517: 2%|▏ | 41/1828 [01:30<1:03:36, 2.14s/it]
epoch: 0 loss: 0.8474517: 2%|▏ | 42/1828 [01:30<1:03:35, 2.14s/it]
epoch: 0 loss: 0.7508447: 2%|▏ | 42/1828 [01:32<1:03:35, 2.14s/it]
epoch: 0 loss: 0.7508447: 2%|▏ | 43/1828 [01:32<1:03:30, 2.13s/it]
epoch: 0 loss: 0.7296206: 2%|▏ | 43/1828 [01:34<1:03:30, 2.13s/it]
epoch: 0 loss: 0.7296206: 2%|▏ | 44/1828 [01:34<1:03:30, 2.14s/it]
epoch: 0 loss: 0.5481316: 2%|▏ | 44/1828 [01:37<1:03:30, 2.14s/it]
epoch: 0 loss: 0.5481316: 2%|▏ | 45/1828 [01:37<1:03:23, 2.13s/it]
epoch: 0 loss: 0.6029255: 2%|▏ | 45/1828 [01:39<1:03:23, 2.13s/it]
epoch: 0 loss: 0.6029255: 3%|▎ | 46/1828 [01:39<1:03:24, 2.13s/it]
epoch: 0 loss: 0.7369277: 3%|▎ | 46/1828 [01:41<1:03:24, 2.13s/it]
epoch: 0 loss: 0.7369277: 3%|▎ | 47/1828 [01:41<1:03:16, 2.13s/it]
epoch: 0 loss: 0.3889126: 3%|▎ | 47/1828 [01:43<1:03:16, 2.13s/it]
epoch: 0 loss: 0.3889126: 3%|▎ | 48/1828 [01:43<1:03:15, 2.13s/it]
epoch: 0 loss: 0.6297967: 3%|▎ | 48/1828 [01:45<1:03:15, 2.13s/it]
epoch: 0 loss: 0.6297967: 3%|▎ | 49/1828 [01:45<1:03:10, 2.13s/it]
epoch: 0 loss: 0.5848452: 3%|▎ | 49/1828 [01:47<1:03:10, 2.13s/it]
epoch: 0 loss: 0.5848452: 3%|▎ | 50/1828 [01:47<1:03:10, 2.13s/it]
epoch: 0 loss: 0.3675669: 3%|▎ | 50/1828 [01:49<1:03:10, 2.13s/it]
epoch: 0 loss: 0.3675669: 3%|▎ | 51/1828 [01:49<1:03:13, 2.13s/it]
epoch: 0 loss: 0.8343396: 3%|▎ | 51/1828 [01:51<1:03:13, 2.13s/it]
epoch: 0 loss: 0.8343396: 3%|▎ | 52/1828 [01:51<1:03:07, 2.13s/it]
epoch: 0 loss: 0.6324261: 3%|▎ | 52/1828 [01:54<1:03:07, 2.13s/it]
epoch: 0 loss: 0.6324261: 3%|▎ | 53/1828 [01:54<1:03:15, 2.14s/it]
epoch: 0 loss: 0.4248326: 3%|▎ | 53/1828 [01:56<1:03:15, 2.14s/it]
epoch: 0 loss: 0.4248326: 3%|▎ | 54/1828 [01:56<1:03:08, 2.14s/it]
epoch: 0 loss: 0.3622353: 3%|▎ | 54/1828 [01:58<1:03:08, 2.14s/it]
epoch: 0 loss: 0.3622353: 3%|▎ | 55/1828 [01:58<1:03:05, 2.14s/it]
epoch: 0 loss: 0.5921545: 3%|▎ | 55/1828 [02:00<1:03:05, 2.14s/it]
epoch: 0 loss: 0.5921545: 3%|▎ | 56/1828 [02:00<1:03:04, 2.14s/it]
epoch: 0 loss: 0.4478313: 3%|▎ | 56/1828 [02:02<1:03:04, 2.14s/it]
epoch: 0 loss: 0.4478313: 3%|▎ | 57/1828 [02:02<1:03:02, 2.14s/it]
epoch: 0 loss: 0.8899173: 3%|▎ | 57/1828 [02:04<1:03:02, 2.14s/it]
epoch: 0 loss: 0.8899173: 3%|▎ | 58/1828 [02:04<1:03:02, 2.14s/it]
epoch: 0 loss: 0.2030278: 3%|▎ | 58/1828 [02:06<1:03:02, 2.14s/it]
epoch: 0 loss: 0.2030278: 3%|▎ | 59/1828 [02:06<1:02:58, 2.14s/it]
epoch: 0 loss: 0.2539483: 3%|▎ | 59/1828 [02:09<1:02:58, 2.14s/it]
epoch: 0 loss: 0.2539483: 3%|▎ | 60/1828 [02:09<1:02:59, 2.14s/it]
epoch: 0 loss: 0.7051185: 3%|▎ | 60/1828 [02:11<1:02:59, 2.14s/it]
epoch: 0 loss: 0.7051185: 3%|▎ | 61/1828 [02:11<1:02:54, 2.14s/it]
epoch: 0 loss: 0.3030353: 3%|▎ | 61/1828 [02:13<1:02:54, 2.14s/it]
epoch: 0 loss: 0.3030353: 3%|▎ | 62/1828 [02:13<1:02:48, 2.13s/it]
epoch: 0 loss: 0.7258384: 3%|▎ | 62/1828 [02:15<1:02:48, 2.13s/it]
epoch: 0 loss: 0.7258384: 3%|▎ | 63/1828 [02:15<1:02:50, 2.14s/it]
epoch: 0 loss: 0.7213075: 3%|▎ | 63/1828 [02:17<1:02:50, 2.14s/it]
epoch: 0 loss: 0.7213075: 4%|▎ | 64/1828 [02:17<1:02:49, 2.14s/it]
epoch: 0 loss: 0.3119401: 4%|▎ | 64/1828 [02:19<1:02:49, 2.14s/it]
epoch: 0 loss: 0.3119401: 4%|▎ | 65/1828 [02:19<1:02:46, 2.14s/it]
epoch: 0 loss: 0.3981437: 4%|▎ | 65/1828 [02:21<1:02:46, 2.14s/it]
epoch: 0 loss: 0.3981437: 4%|▎ | 66/1828 [02:21<1:02:34, 2.13s/it]
epoch: 0 loss: 0.5302190: 4%|▎ | 66/1828 [02:24<1:02:34, 2.13s/it]
epoch: 0 loss: 0.5302190: 4%|▎ | 67/1828 [02:24<1:02:34, 2.13s/it]
epoch: 0 loss: 0.4380422: 4%|▎ | 67/1828 [02:26<1:02:34, 2.13s/it]
epoch: 0 loss: 0.4380422: 4%|▎ | 68/1828 [02:26<1:02:33, 2.13s/it]
epoch: 0 loss: 0.6587633: 4%|▎ | 68/1828 [02:28<1:02:33, 2.13s/it]
epoch: 0 loss: 0.6587633: 4%|▍ | 69/1828 [02:28<1:02:30, 2.13s/it]
epoch: 0 loss: 0.3062908: 4%|▍ | 69/1828 [02:30<1:02:30, 2.13s/it]
epoch: 0 loss: 0.3062908: 4%|▍ | 70/1828 [02:30<1:02:25, 2.13s/it]
epoch: 0 loss: 0.6017177: 4%|▍ | 70/1828 [02:32<1:02:25, 2.13s/it]
epoch: 0 loss: 0.6017177: 4%|▍ | 71/1828 [02:32<1:02:20, 2.13s/it]
epoch: 0 loss: 0.3156212: 4%|▍ | 71/1828 [02:34<1:02:20, 2.13s/it]
epoch: 0 loss: 0.3156212: 4%|▍ | 72/1828 [02:34<1:02:19, 2.13s/it]
epoch: 0 loss: 0.2364967: 4%|▍ | 72/1828 [02:36<1:02:19, 2.13s/it]
epoch: 0 loss: 0.2364967: 4%|▍ | 73/1828 [02:36<1:02:14, 2.13s/it]
epoch: 0 loss: 0.3155812: 4%|▍ | 73/1828 [02:38<1:02:14, 2.13s/it]
epoch: 0 loss: 0.3155812: 4%|▍ | 74/1828 [02:38<1:02:14, 2.13s/it]
epoch: 0 loss: 0.2428536: 4%|▍ | 74/1828 [02:41<1:02:14, 2.13s/it]
epoch: 0 loss: 0.2428536: 4%|▍ | 75/1828 [02:41<1:02:09, 2.13s/it]
epoch: 0 loss: 0.3060207: 4%|▍ | 75/1828 [02:43<1:02:09, 2.13s/it]
epoch: 0 loss: 0.3060207: 4%|▍ | 76/1828 [02:43<1:02:06, 2.13s/it]
epoch: 0 loss: 0.5137466: 4%|▍ | 76/1828 [02:45<1:02:06, 2.13s/it]
epoch: 0 loss: 0.5137466: 4%|▍ | 77/1828 [02:45<1:02:14, 2.13s/it]
epoch: 0 loss: 0.5586309: 4%|▍ | 77/1828 [02:47<1:02:14, 2.13s/it]
epoch: 0 loss: 0.5586309: 4%|▍ | 78/1828 [02:47<1:02:13, 2.13s/it]
epoch: 0 loss: 0.2651724: 4%|▍ | 78/1828 [02:49<1:02:13, 2.13s/it]
epoch: 0 loss: 0.2651724: 4%|▍ | 79/1828 [02:49<1:02:10, 2.13s/it]
epoch: 0 loss: 0.4218388: 4%|▍ | 79/1828 [02:51<1:02:10, 2.13s/it]
epoch: 0 loss: 0.4218388: 4%|▍ | 80/1828 [02:51<1:02:03, 2.13s/it]
epoch: 0 loss: 0.2499869: 4%|▍ | 80/1828 [02:53<1:02:03, 2.13s/it]
epoch: 0 loss: 0.2499869: 4%|▍ | 81/1828 [02:53<1:02:02, 2.13s/it]
epoch: 0 loss: 0.1282679: 4%|▍ | 81/1828 [02:55<1:02:02, 2.13s/it]
epoch: 0 loss: 0.1282679: 4%|▍ | 82/1828 [02:55<1:01:57, 2.13s/it]
epoch: 0 loss: 0.4946347: 4%|▍ | 82/1828 [02:58<1:01:57, 2.13s/it]
epoch: 0 loss: 0.4946347: 5%|▍ | 83/1828 [02:58<1:01:55, 2.13s/it]
epoch: 0 loss: 0.2014481: 5%|▍ | 83/1828 [03:00<1:01:55, 2.13s/it]
epoch: 0 loss: 0.2014481: 5%|▍ | 84/1828 [03:00<1:01:51, 2.13s/it]
epoch: 0 loss: 0.7813249: 5%|▍ | 84/1828 [03:02<1:01:51, 2.13s/it]
epoch: 0 loss: 0.7813249: 5%|▍ | 85/1828 [03:02<1:01:50, 2.13s/it]
epoch: 0 loss: 0.2607917: 5%|▍ | 85/1828 [03:04<1:01:50, 2.13s/it]
epoch: 0 loss: 0.2607917: 5%|▍ | 86/1828 [03:04<1:01:47, 2.13s/it]
epoch: 0 loss: 0.3760445: 5%|▍ | 86/1828 [03:06<1:01:47, 2.13s/it]
epoch: 0 loss: 0.3760445: 5%|▍ | 87/1828 [03:06<1:01:44, 2.13s/it]
epoch: 0 loss: 0.4350195: 5%|▍ | 87/1828 [03:08<1:01:44, 2.13s/it]
epoch: 0 loss: 0.4350195: 5%|▍ | 88/1828 [03:08<1:01:48, 2.13s/it]
epoch: 0 loss: 0.3250186: 5%|▍ | 88/1828 [03:10<1:01:48, 2.13s/it]
epoch: 0 loss: 0.3250186: 5%|▍ | 89/1828 [03:10<1:01:40, 2.13s/it]
epoch: 0 loss: 0.2554210: 5%|▍ | 89/1828 [03:13<1:01:40, 2.13s/it]
epoch: 0 loss: 0.2554210: 5%|▍ | 90/1828 [03:13<1:01:45, 2.13s/it]
epoch: 0 loss: 0.5169561: 5%|▍ | 90/1828 [03:15<1:01:45, 2.13s/it]
epoch: 0 loss: 0.5169561: 5%|▍ | 91/1828 [03:15<1:01:48, 2.14s/it]
epoch: 0 loss: 0.0491808: 5%|▍ | 91/1828 [03:17<1:01:48, 2.14s/it]
epoch: 0 loss: 0.0491808: 5%|▌ | 92/1828 [03:17<1:02:22, 2.16s/it]
epoch: 0 loss: 0.6991525: 5%|▌ | 92/1828 [03:19<1:02:22, 2.16s/it]
epoch: 0 loss: 0.6991525: 5%|▌ | 93/1828 [03:19<1:02:05, 2.15s/it]
epoch: 0 loss: 0.3331533: 5%|▌ | 93/1828 [03:21<1:02:05, 2.15s/it]
epoch: 0 loss: 0.3331533: 5%|▌ | 94/1828 [03:21<1:01:50, 2.14s/it]
epoch: 0 loss: 0.3901696: 5%|▌ | 94/1828 [03:23<1:01:50, 2.14s/it]
epoch: 0 loss: 0.3901696: 5%|▌ | 95/1828 [03:23<1:01:45, 2.14s/it]
epoch: 0 loss: 0.6842455: 5%|▌ | 95/1828 [03:25<1:01:45, 2.14s/it]
epoch: 0 loss: 0.6842455: 5%|▌ | 96/1828 [03:25<1:01:35, 2.13s/it]
epoch: 0 loss: 0.3874707: 5%|▌ | 96/1828 [03:27<1:01:35, 2.13s/it]
epoch: 0 loss: 0.3874707: 5%|▌ | 97/1828 [03:27<1:01:31, 2.13s/it]
epoch: 0 loss: 0.4303322: 5%|▌ | 97/1828 [03:30<1:01:31, 2.13s/it]
epoch: 0 loss: 0.4303322: 5%|▌ | 98/1828 [03:30<1:01:26, 2.13s/it]
epoch: 0 loss: 0.1597482: 5%|▌ | 98/1828 [03:32<1:01:26, 2.13s/it]
epoch: 0 loss: 0.1597482: 5%|▌ | 99/1828 [03:32<1:01:22, 2.13s/it]
epoch: 0 loss: 0.4297054: 5%|▌ | 99/1828 [03:34<1:01:22, 2.13s/it]
epoch: 0 loss: 0.4297054: 5%|▌ | 100/1828 [03:34<1:01:19, 2.13s/it]
epoch: 0 loss: 0.0657619: 5%|▌ | 100/1828 [03:36<1:01:19, 2.13s/it]
epoch: 0 loss: 0.0657619: 6%|▌ | 101/1828 [03:36<1:01:21, 2.13s/it]
epoch: 0 loss: 0.5629160: 6%|▌ | 101/1828 [03:38<1:01:21, 2.13s/it]
epoch: 0 loss: 0.5629160: 6%|▌ | 102/1828 [03:38<1:01:24, 2.13s/it]
epoch: 0 loss: 0.3981894: 6%|▌ | 102/1828 [03:40<1:01:24, 2.13s/it]
epoch: 0 loss: 0.3981894: 6%|▌ | 103/1828 [03:40<1:01:15, 2.13s/it]
epoch: 0 loss: 0.4235135: 6%|▌ | 103/1828 [03:42<1:01:15, 2.13s/it]
epoch: 0 loss: 0.4235135: 6%|▌ | 104/1828 [03:42<1:01:13, 2.13s/it]
epoch: 0 loss: 0.1823353: 6%|▌ | 104/1828 [03:45<1:01:13, 2.13s/it]
epoch: 0 loss: 0.1823353: 6%|▌ | 105/1828 [03:45<1:01:10, 2.13s/it]
epoch: 0 loss: 0.3462193: 6%|▌ | 105/1828 [03:47<1:01:10, 2.13s/it]
epoch: 0 loss: 0.3462193: 6%|▌ | 106/1828 [03:47<1:01:10, 2.13s/it]
epoch: 0 loss: 0.4729741: 6%|▌ | 106/1828 [03:49<1:01:10, 2.13s/it]
epoch: 0 loss: 0.4729741: 6%|▌ | 107/1828 [03:49<1:01:10, 2.13s/it]
epoch: 0 loss: 0.3240245: 6%|▌ | 107/1828 [03:51<1:01:10, 2.13s/it]
epoch: 0 loss: 0.3240245: 6%|▌ | 108/1828 [03:51<1:01:06, 2.13s/it]
epoch: 0 loss: 0.4387518: 6%|▌ | 108/1828 [03:53<1:01:06, 2.13s/it]
epoch: 0 loss: 0.4387518: 6%|▌ | 109/1828 [03:53<1:01:07, 2.13s/it]
epoch: 0 loss: 0.1772419: 6%|▌ | 109/1828 [03:55<1:01:07, 2.13s/it]
epoch: 0 loss: 0.1772419: 6%|▌ | 110/1828 [03:55<1:01:02, 2.13s/it]
epoch: 0 loss: 0.1754088: 6%|▌ | 110/1828 [03:57<1:01:02, 2.13s/it]
epoch: 0 loss: 0.1754088: 6%|▌ | 111/1828 [03:57<1:01:02, 2.13s/it]
epoch: 0 loss: 0.2489017: 6%|▌ | 111/1828 [03:59<1:01:02, 2.13s/it]
epoch: 0 loss: 0.2489017: 6%|▌ | 112/1828 [03:59<1:00:59, 2.13s/it]
epoch: 0 loss: 0.2361374: 6%|▌ | 112/1828 [04:02<1:00:59, 2.13s/it]
epoch: 0 loss: 0.2361374: 6%|▌ | 113/1828 [04:02<1:00:59, 2.13s/it]
epoch: 0 loss: 0.5070921: 6%|▌ | 113/1828 [04:04<1:00:59, 2.13s/it]
epoch: 0 loss: 0.5070921: 6%|▌ | 114/1828 [04:04<1:00:55, 2.13s/it]
epoch: 0 loss: 0.3831331: 6%|▌ | 114/1828 [04:06<1:00:55, 2.13s/it]
epoch: 0 loss: 0.3831331: 6%|▋ | 115/1828 [04:06<1:00:52, 2.13s/it]
epoch: 0 loss: 0.3427057: 6%|▋ | 115/1828 [04:08<1:00:52, 2.13s/it]
epoch: 0 loss: 0.3427057: 6%|▋ | 116/1828 [04:08<1:00:54, 2.13s/it]
epoch: 0 loss: 0.5897053: 6%|▋ | 116/1828 [04:10<1:00:54, 2.13s/it]
epoch: 0 loss: 0.5897053: 6%|▋ | 117/1828 [04:10<1:00:48, 2.13s/it]
epoch: 0 loss: 0.7503001: 6%|▋ | 117/1828 [04:12<1:00:48, 2.13s/it]
epoch: 0 loss: 0.7503001: 6%|▋ | 118/1828 [04:12<1:00:45, 2.13s/it]
epoch: 0 loss: 0.7444749: 6%|▋ | 118/1828 [04:14<1:00:45, 2.13s/it]
epoch: 0 loss: 0.7444749: 7%|▋ | 119/1828 [04:14<1:00:45, 2.13s/it]
epoch: 0 loss: 0.3798183: 7%|▋ | 119/1828 [04:17<1:00:45, 2.13s/it]
epoch: 0 loss: 0.3798183: 7%|▋ | 120/1828 [04:17<1:01:42, 2.17s/it]
epoch: 0 loss: 0.5294960: 7%|▋ | 120/1828 [04:19<1:01:42, 2.17s/it]
epoch: 0 loss: 0.5294960: 7%|▋ | 121/1828 [04:19<1:01:25, 2.16s/it]
epoch: 0 loss: 0.2160780: 7%|▋ | 121/1828 [04:21<1:01:25, 2.16s/it]
epoch: 0 loss: 0.2160780: 7%|▋ | 122/1828 [04:21<1:01:18, 2.16s/it]
epoch: 0 loss: 0.5091438: 7%|▋ | 122/1828 [04:23<1:01:18, 2.16s/it]
epoch: 0 loss: 0.5091438: 7%|▋ | 123/1828 [04:23<1:01:04, 2.15s/it]
epoch: 0 loss: 0.2842860: 7%|▋ | 123/1828 [04:25<1:01:04, 2.15s/it]
epoch: 0 loss: 0.2842860: 7%|▋ | 124/1828 [04:25<1:00:52, 2.14s/it]
epoch: 0 loss: 0.3500210: 7%|▋ | 124/1828 [04:27<1:00:52, 2.14s/it]
epoch: 0 loss: 0.3500210: 7%|▋ | 125/1828 [04:27<1:00:42, 2.14s/it]
epoch: 0 loss: 0.7081708: 7%|▋ | 125/1828 [04:29<1:00:42, 2.14s/it]
epoch: 0 loss: 0.7081708: 7%|▋ | 126/1828 [04:29<1:00:35, 2.14s/it]
epoch: 0 loss: 0.1434834: 7%|▋ | 126/1828 [04:32<1:00:35, 2.14s/it]
epoch: 0 loss: 0.1434834: 7%|▋ | 127/1828 [04:32<1:00:27, 2.13s/it]
epoch: 0 loss: 0.2430250: 7%|▋ | 127/1828 [04:34<1:00:27, 2.13s/it]
epoch: 0 loss: 0.2430250: 7%|▋ | 128/1828 [04:34<1:00:24, 2.13s/it]
epoch: 0 loss: 0.2294871: 7%|▋ | 128/1828 [04:36<1:00:24, 2.13s/it]
epoch: 0 loss: 0.2294871: 7%|▋ | 129/1828 [04:36<1:00:25, 2.13s/it]
epoch: 0 loss: 0.3343146: 7%|▋ | 129/1828 [04:38<1:00:25, 2.13s/it]
epoch: 0 loss: 0.3343146: 7%|▋ | 130/1828 [04:38<1:00:22, 2.13s/it]
epoch: 0 loss: 0.1815944: 7%|▋ | 130/1828 [04:40<1:00:22, 2.13s/it]
epoch: 0 loss: 0.1815944: 7%|▋ | 131/1828 [04:40<1:00:18, 2.13s/it]
epoch: 0 loss: 0.2768756: 7%|▋ | 131/1828 [04:42<1:00:18, 2.13s/it]
epoch: 0 loss: 0.2768756: 7%|▋ | 132/1828 [04:42<1:00:09, 2.13s/it]
epoch: 0 loss: 0.3644373: 7%|▋ | 132/1828 [04:44<1:00:09, 2.13s/it]
epoch: 0 loss: 0.3644373: 7%|▋ | 133/1828 [04:44<1:00:12, 2.13s/it]
epoch: 0 loss: 0.5415072: 7%|▋ | 133/1828 [04:47<1:00:12, 2.13s/it]
epoch: 0 loss: 0.5415072: 7%|▋ | 134/1828 [04:47<1:00:09, 2.13s/it]
epoch: 0 loss: 0.6164200: 7%|▋ | 134/1828 [04:49<1:00:09, 2.13s/it]
epoch: 0 loss: 0.6164200: 7%|▋ | 135/1828 [04:49<1:00:06, 2.13s/it]
epoch: 0 loss: 0.2420432: 7%|▋ | 135/1828 [04:51<1:00:06, 2.13s/it]
epoch: 0 loss: 0.2420432: 7%|▋ | 136/1828 [04:51<1:00:04, 2.13s/it]
epoch: 0 loss: 0.2836215: 7%|▋ | 136/1828 [04:53<1:00:04, 2.13s/it]
epoch: 0 loss: 0.2836215: 7%|▋ | 137/1828 [04:53<1:00:01, 2.13s/it]
epoch: 0 loss: 0.2391577: 7%|▋ | 137/1828 [04:55<1:00:01, 2.13s/it]
epoch: 0 loss: 0.2391577: 8%|▊ | 138/1828 [04:55<59:59, 2.13s/it]
epoch: 0 loss: 0.4926598: 8%|▊ | 138/1828 [04:57<59:59, 2.13s/it]
epoch: 0 loss: 0.4926598: 8%|▊ | 139/1828 [04:57<59:59, 2.13s/it]
epoch: 0 loss: 0.3459783: 8%|▊ | 139/1828 [04:59<59:59, 2.13s/it]
epoch: 0 loss: 0.3459783: 8%|▊ | 140/1828 [04:59<1:00:01, 2.13s/it]
epoch: 0 loss: 0.2336525: 8%|▊ | 140/1828 [05:01<1:00:01, 2.13s/it]
epoch: 0 loss: 0.2336525: 8%|▊ | 141/1828 [05:01<59:53, 2.13s/it]
epoch: 0 loss: 0.3025113: 8%|▊ | 141/1828 [05:04<59:53, 2.13s/it]
epoch: 0 loss: 0.3025113: 8%|▊ | 142/1828 [05:04<59:53, 2.13s/it]
epoch: 0 loss: 0.6064665: 8%|▊ | 142/1828 [05:06<59:53, 2.13s/it]
epoch: 0 loss: 0.6064665: 8%|▊ | 143/1828 [05:06<59:49, 2.13s/it]
epoch: 0 loss: 0.7904705: 8%|▊ | 143/1828 [05:08<59:49, 2.13s/it]
epoch: 0 loss: 0.7904705: 8%|▊ | 144/1828 [05:08<59:48, 2.13s/it]
epoch: 0 loss: 0.5279516: 8%|▊ | 144/1828 [05:10<59:48, 2.13s/it]
epoch: 0 loss: 0.5279516: 8%|▊ | 145/1828 [05:10<59:45, 2.13s/it]
epoch: 0 loss: 0.5225759: 8%|▊ | 145/1828 [05:12<59:45, 2.13s/it]
epoch: 0 loss: 0.5225759: 8%|▊ | 146/1828 [05:12<59:38, 2.13s/it]
epoch: 0 loss: 0.7213981: 8%|▊ | 146/1828 [05:14<59:38, 2.13s/it]
epoch: 0 loss: 0.7213981: 8%|▊ | 147/1828 [05:14<59:44, 2.13s/it]
epoch: 0 loss: 0.2243426: 8%|▊ | 147/1828 [05:16<59:44, 2.13s/it]
epoch: 0 loss: 0.2243426: 8%|▊ | 148/1828 [05:16<59:45, 2.13s/it]
epoch: 0 loss: 0.2501247: 8%|▊ | 148/1828 [05:18<59:45, 2.13s/it]
epoch: 0 loss: 0.2501247: 8%|▊ | 149/1828 [05:18<59:47, 2.14s/it]
epoch: 0 loss: 0.1683204: 8%|▊ | 149/1828 [05:21<59:47, 2.14s/it]
epoch: 0 loss: 0.1683204: 8%|▊ | 150/1828 [05:21<59:49, 2.14s/it]
epoch: 0 loss: 0.2201821: 8%|▊ | 150/1828 [05:23<59:49, 2.14s/it]
epoch: 0 loss: 0.2201821: 8%|▊ | 151/1828 [05:23<59:50, 2.14s/it]
epoch: 0 loss: 0.7644632: 8%|▊ | 151/1828 [05:25<59:50, 2.14s/it]
epoch: 0 loss: 0.7644632: 8%|▊ | 152/1828 [05:25<59:48, 2.14s/it]
epoch: 0 loss: 0.3450668: 8%|▊ | 152/1828 [05:27<59:48, 2.14s/it]
epoch: 0 loss: 0.3450668: 8%|▊ | 153/1828 [05:27<59:45, 2.14s/it]
epoch: 0 loss: 0.6916186: 8%|▊ | 153/1828 [05:29<59:45, 2.14s/it]
epoch: 0 loss: 0.6916186: 8%|▊ | 154/1828 [05:29<59:42, 2.14s/it]
epoch: 0 loss: 0.1676807: 8%|▊ | 154/1828 [05:31<59:42, 2.14s/it]
epoch: 0 loss: 0.1676807: 8%|▊ | 155/1828 [05:31<59:38, 2.14s/it]
epoch: 0 loss: 0.3799623: 8%|▊ | 155/1828 [05:33<59:38, 2.14s/it]
epoch: 0 loss: 0.3799623: 9%|▊ | 156/1828 [05:33<59:37, 2.14s/it]
epoch: 0 loss: 0.3790281: 9%|▊ | 156/1828 [05:36<59:37, 2.14s/it]
epoch: 0 loss: 0.3790281: 9%|▊ | 157/1828 [05:36<59:34, 2.14s/it]
epoch: 0 loss: 0.1535501: 9%|▊ | 157/1828 [05:38<59:34, 2.14s/it]
epoch: 0 loss: 0.1535501: 9%|▊ | 158/1828 [05:38<59:34, 2.14s/it]
epoch: 0 loss: 0.2255445: 9%|▊ | 158/1828 [05:40<59:34, 2.14s/it]
epoch: 0 loss: 0.2255445: 9%|▊ | 159/1828 [05:40<59:28, 2.14s/it]
epoch: 0 loss: 0.4332640: 9%|▊ | 159/1828 [05:42<59:28, 2.14s/it]
epoch: 0 loss: 0.4332640: 9%|▉ | 160/1828 [05:42<59:23, 2.14s/it]
epoch: 0 loss: 0.3343067: 9%|▉ | 160/1828 [05:44<59:23, 2.14s/it]
epoch: 0 loss: 0.3343067: 9%|▉ | 161/1828 [05:44<59:19, 2.14s/it]
epoch: 0 loss: 0.2299035: 9%|▉ | 161/1828 [05:46<59:19, 2.14s/it]
epoch: 0 loss: 0.2299035: 9%|▉ | 162/1828 [05:46<59:12, 2.13s/it]
epoch: 0 loss: 0.1747071: 9%|▉ | 162/1828 [05:48<59:12, 2.13s/it]
epoch: 0 loss: 0.1747071: 9%|▉ | 163/1828 [05:48<59:09, 2.13s/it]
epoch: 0 loss: 0.4888557: 9%|▉ | 163/1828 [05:51<59:09, 2.13s/it]
epoch: 0 loss: 0.4888557: 9%|▉ | 164/1828 [05:51<59:01, 2.13s/it]
epoch: 0 loss: 0.3835825: 9%|▉ | 164/1828 [05:53<59:01, 2.13s/it]
epoch: 0 loss: 0.3835825: 9%|▉ | 165/1828 [05:53<58:55, 2.13s/it]
epoch: 0 loss: 0.1457020: 9%|▉ | 165/1828 [05:55<58:55, 2.13s/it]
epoch: 0 loss: 0.1457020: 9%|▉ | 166/1828 [05:55<58:56, 2.13s/it]
epoch: 0 loss: 0.5473363: 9%|▉ | 166/1828 [05:57<58:56, 2.13s/it]
epoch: 0 loss: 0.5473363: 9%|▉ | 167/1828 [05:57<58:56, 2.13s/it]
epoch: 0 loss: 0.3940726: 9%|▉ | 167/1828 [05:59<58:56, 2.13s/it]
epoch: 0 loss: 0.3940726: 9%|▉ | 168/1828 [05:59<58:57, 2.13s/it]
epoch: 0 loss: 0.4629080: 9%|▉ | 168/1828 [06:01<58:57, 2.13s/it]
epoch: 0 loss: 0.4629080: 9%|▉ | 169/1828 [06:01<58:46, 2.13s/it]
epoch: 0 loss: 0.1686856: 9%|▉ | 169/1828 [06:03<58:46, 2.13s/it]
epoch: 0 loss: 0.1686856: 9%|▉ | 170/1828 [06:03<58:46, 2.13s/it]
epoch: 0 loss: 0.3092990: 9%|▉ | 170/1828 [06:05<58:46, 2.13s/it]
epoch: 0 loss: 0.3092990: 9%|▉ | 171/1828 [06:05<58:45, 2.13s/it]
epoch: 0 loss: 0.2842376: 9%|▉ | 171/1828 [06:08<58:45, 2.13s/it]
epoch: 0 loss: 0.2842376: 9%|▉ | 172/1828 [06:08<58:44, 2.13s/it]
epoch: 0 loss: 0.3280693: 9%|▉ | 172/1828 [06:10<58:44, 2.13s/it]
epoch: 0 loss: 0.3280693: 9%|▉ | 173/1828 [06:10<58:47, 2.13s/it]
epoch: 0 loss: 0.3789074: 9%|▉ | 173/1828 [06:12<58:47, 2.13s/it]
epoch: 0 loss: 0.3789074: 10%|▉ | 174/1828 [06:12<58:40, 2.13s/it]
epoch: 0 loss: 0.3017021: 10%|▉ | 174/1828 [06:14<58:40, 2.13s/it]
epoch: 0 loss: 0.3017021: 10%|▉ | 175/1828 [06:14<58:41, 2.13s/it]
epoch: 0 loss: 0.1747161: 10%|▉ | 175/1828 [06:16<58:41, 2.13s/it]
epoch: 0 loss: 0.1747161: 10%|▉ | 176/1828 [06:16<58:40, 2.13s/it]
epoch: 0 loss: 0.3042456: 10%|▉ | 176/1828 [06:18<58:40, 2.13s/it]
epoch: 0 loss: 0.3042456: 10%|▉ | 177/1828 [06:18<58:39, 2.13s/it]
epoch: 0 loss: 0.3385718: 10%|▉ | 177/1828 [06:20<58:39, 2.13s/it]
epoch: 0 loss: 0.3385718: 10%|▉ | 178/1828 [06:20<58:35, 2.13s/it]
epoch: 0 loss: 0.4585269: 10%|▉ | 178/1828 [06:22<58:35, 2.13s/it]
epoch: 0 loss: 0.4585269: 10%|▉ | 179/1828 [06:22<58:32, 2.13s/it]
epoch: 0 loss: 0.1976745: 10%|▉ | 179/1828 [06:25<58:32, 2.13s/it]
epoch: 0 loss: 0.1976745: 10%|▉ | 180/1828 [06:25<58:29, 2.13s/it]
epoch: 0 loss: 0.1727213: 10%|▉ | 180/1828 [06:27<58:29, 2.13s/it]
epoch: 0 loss: 0.1727213: 10%|▉ | 181/1828 [06:27<58:26, 2.13s/it]
epoch: 0 loss: 0.2487447: 10%|▉ | 181/1828 [06:29<58:26, 2.13s/it]
epoch: 0 loss: 0.2487447: 10%|▉ | 182/1828 [06:29<58:34, 2.13s/it]
epoch: 0 loss: 0.1661988: 10%|▉ | 182/1828 [06:31<58:34, 2.13s/it]
epoch: 0 loss: 0.1661988: 10%|█ | 183/1828 [06:31<58:30, 2.13s/it]
epoch: 0 loss: 0.1420110: 10%|█ | 183/1828 [06:33<58:30, 2.13s/it]
epoch: 0 loss: 0.1420110: 10%|█ | 184/1828 [06:33<58:27, 2.13s/it]
epoch: 0 loss: 0.5070161: 10%|█ | 184/1828 [06:35<58:27, 2.13s/it]
epoch: 0 loss: 0.5070161: 10%|█ | 185/1828 [06:35<58:25, 2.13s/it]
epoch: 0 loss: 0.3791830: 10%|█ | 185/1828 [06:37<58:25, 2.13s/it]
epoch: 0 loss: 0.3791830: 10%|█ | 186/1828 [06:37<58:20, 2.13s/it]
epoch: 0 loss: 0.5272597: 10%|█ | 186/1828 [06:40<58:20, 2.13s/it]
epoch: 0 loss: 0.5272597: 10%|█ | 187/1828 [06:40<58:20, 2.13s/it]
epoch: 0 loss: 0.3147841: 10%|█ | 187/1828 [06:42<58:20, 2.13s/it]
epoch: 0 loss: 0.3147841: 10%|█ | 188/1828 [06:42<58:11, 2.13s/it]
epoch: 0 loss: 0.7570719: 10%|█ | 188/1828 [06:44<58:11, 2.13s/it]
epoch: 0 loss: 0.7570719: 10%|█ | 189/1828 [06:44<57:00, 2.09s/it]
epoch: 0 loss: 0.1743796: 10%|█ | 189/1828 [06:46<57:00, 2.09s/it]
epoch: 0 loss: 0.1743796: 10%|█ | 190/1828 [06:46<57:21, 2.10s/it]
epoch: 0 loss: 0.3964991: 10%|█ | 190/1828 [06:48<57:21, 2.10s/it]
epoch: 0 loss: 0.3964991: 10%|█ | 191/1828 [06:48<57:33, 2.11s/it]
epoch: 0 loss: 0.1177391: 10%|█ | 191/1828 [06:50<57:33, 2.11s/it]
epoch: 0 loss: 0.1177391: 11%|█ | 192/1828 [06:50<57:44, 2.12s/it]
epoch: 0 loss: 0.4566078: 11%|█ | 192/1828 [06:52<57:44, 2.12s/it]
epoch: 0 loss: 0.4566078: 11%|█ | 193/1828 [06:52<57:49, 2.12s/it]
epoch: 0 loss: 0.6946992: 11%|█ | 193/1828 [06:54<57:49, 2.12s/it]
epoch: 0 loss: 0.6946992: 11%|█ | 194/1828 [06:54<57:48, 2.12s/it]
epoch: 0 loss: 0.2002687: 11%|█ | 194/1828 [06:56<57:48, 2.12s/it]
epoch: 0 loss: 0.2002687: 11%|█ | 195/1828 [06:56<57:51, 2.13s/it]
epoch: 0 loss: 0.2298083: 11%|█ | 195/1828 [06:59<57:51, 2.13s/it]
epoch: 0 loss: 0.2298083: 11%|█ | 196/1828 [06:59<57:51, 2.13s/it]
epoch: 0 loss: 0.2598379: 11%|█ | 196/1828 [07:01<57:51, 2.13s/it]
epoch: 0 loss: 0.2598379: 11%|█ | 197/1828 [07:01<57:50, 2.13s/it]
epoch: 0 loss: 0.1631857: 11%|█ | 197/1828 [07:03<57:50, 2.13s/it]
epoch: 0 loss: 0.1631857: 11%|█ | 198/1828 [07:03<57:47, 2.13s/it]
epoch: 0 loss: 0.1888632: 11%|█ | 198/1828 [07:05<57:47, 2.13s/it]
epoch: 0 loss: 0.1888632: 11%|█ | 199/1828 [07:05<57:49, 2.13s/it]
epoch: 0 loss: 0.4708321: 11%|█ | 199/1828 [07:07<57:49, 2.13s/it]
epoch: 0 loss: 0.4708321: 11%|█ | 200/1828 [07:07<57:46, 2.13s/it]
epoch: 0 loss: 0.2533686: 11%|█ | 200/1828 [07:09<57:46, 2.13s/it]
epoch: 0 loss: 0.2533686: 11%|█ | 201/1828 [07:09<57:46, 2.13s/it]
epoch: 0 loss: 0.5885035: 11%|█ | 201/1828 [07:11<57:46, 2.13s/it]
epoch: 0 loss: 0.5885035: 11%|█ | 202/1828 [07:11<57:39, 2.13s/it]
epoch: 0 loss: 0.1623174: 11%|█ | 202/1828 [07:13<57:39, 2.13s/it]
epoch: 0 loss: 0.1623174: 11%|█ | 203/1828 [07:13<57:37, 2.13s/it]
epoch: 0 loss: 0.6667503: 11%|█ | 203/1828 [07:16<57:37, 2.13s/it]
epoch: 0 loss: 0.6667503: 11%|█ | 204/1828 [07:16<57:42, 2.13s/it]
epoch: 0 loss: 0.1982317: 11%|█ | 204/1828 [07:18<57:42, 2.13s/it]
epoch: 0 loss: 0.1982317: 11%|█ | 205/1828 [07:18<57:42, 2.13s/it]
epoch: 0 loss: 0.3021216: 11%|█ | 205/1828 [07:20<57:42, 2.13s/it]
epoch: 0 loss: 0.3021216: 11%|█▏ | 206/1828 [07:20<57:48, 2.14s/it]
epoch: 0 loss: 0.2996230: 11%|█▏ | 206/1828 [07:22<57:48, 2.14s/it]
epoch: 0 loss: 0.2996230: 11%|█▏ | 207/1828 [07:22<57:42, 2.14s/it]
epoch: 0 loss: 0.3565491: 11%|█▏ | 207/1828 [07:24<57:42, 2.14s/it]
epoch: 0 loss: 0.3565491: 11%|█▏ | 208/1828 [07:24<57:38, 2.13s/it]
epoch: 0 loss: 0.2617648: 11%|█▏ | 208/1828 [07:26<57:38, 2.13s/it]
epoch: 0 loss: 0.2617648: 11%|█▏ | 209/1828 [07:26<57:33, 2.13s/it]
epoch: 0 loss: 0.3237803: 11%|█▏ | 209/1828 [07:28<57:33, 2.13s/it]
epoch: 0 loss: 0.3237803: 11%|█▏ | 210/1828 [07:28<57:29, 2.13s/it]
epoch: 0 loss: 0.2774391: 11%|█▏ | 210/1828 [07:31<57:29, 2.13s/it]
epoch: 0 loss: 0.2774391: 12%|█▏ | 211/1828 [07:31<57:27, 2.13s/it]
epoch: 0 loss: 0.1990373: 12%|█▏ | 211/1828 [07:33<57:27, 2.13s/it]
epoch: 0 loss: 0.1990373: 12%|█▏ | 212/1828 [07:33<57:27, 2.13s/it]
epoch: 0 loss: 0.3406556: 12%|█▏ | 212/1828 [07:35<57:27, 2.13s/it]
epoch: 0 loss: 0.3406556: 12%|█▏ | 213/1828 [07:35<57:31, 2.14s/it]
epoch: 0 loss: 0.4049346: 12%|█▏ | 213/1828 [07:37<57:31, 2.14s/it]
epoch: 0 loss: 0.4049346: 12%|█▏ | 214/1828 [07:37<57:25, 2.13s/it]
epoch: 0 loss: 0.2477795: 12%|█▏ | 214/1828 [07:39<57:25, 2.13s/it]
epoch: 0 loss: 0.2477795: 12%|█▏ | 215/1828 [07:39<57:22, 2.13s/it]
epoch: 0 loss: 0.2203858: 12%|█▏ | 215/1828 [07:41<57:22, 2.13s/it]
epoch: 0 loss: 0.2203858: 12%|█▏ | 216/1828 [07:41<57:21, 2.14s/it]
epoch: 0 loss: 0.4694299: 12%|█▏ | 216/1828 [07:43<57:21, 2.14s/it]
epoch: 0 loss: 0.4694299: 12%|█▏ | 217/1828 [07:43<57:23, 2.14s/it]
epoch: 0 loss: 0.4645203: 12%|█▏ | 217/1828 [07:46<57:23, 2.14s/it]
epoch: 0 loss: 0.4645203: 12%|█▏ | 218/1828 [07:46<57:20, 2.14s/it]
epoch: 0 loss: 0.2350054: 12%|█▏ | 218/1828 [07:48<57:20, 2.14s/it]
epoch: 0 loss: 0.2350054: 12%|█▏ | 219/1828 [07:48<57:16, 2.14s/it]
epoch: 0 loss: 0.1222693: 12%|█▏ | 219/1828 [07:50<57:16, 2.14s/it]
epoch: 0 loss: 0.1222693: 12%|█▏ | 220/1828 [07:50<57:16, 2.14s/it]
epoch: 0 loss: 0.0650269: 12%|█▏ | 220/1828 [07:52<57:16, 2.14s/it]
epoch: 0 loss: 0.0650269: 12%|█▏ | 221/1828 [07:52<57:11, 2.14s/it]
epoch: 0 loss: 0.3542182: 12%|█▏ | 221/1828 [07:54<57:11, 2.14s/it]
epoch: 0 loss: 0.3542182: 12%|█▏ | 222/1828 [07:54<57:06, 2.13s/it]
epoch: 0 loss: 0.3341789: 12%|█▏ | 222/1828 [07:56<57:06, 2.13s/it]
epoch: 0 loss: 0.3341789: 12%|█▏ | 223/1828 [07:56<56:59, 2.13s/it]
epoch: 0 loss: 0.2004700: 12%|█▏ | 223/1828 [07:58<56:59, 2.13s/it]
epoch: 0 loss: 0.2004700: 12%|█▏ | 224/1828 [07:58<56:58, 2.13s/it]
epoch: 0 loss: 0.2688370: 12%|█▏ | 224/1828 [08:00<56:58, 2.13s/it]
epoch: 0 loss: 0.2688370: 12%|█▏ | 225/1828 [08:00<56:55, 2.13s/it]
epoch: 0 loss: 0.0879864: 12%|█▏ | 225/1828 [08:03<56:55, 2.13s/it]
epoch: 0 loss: 0.0879864: 12%|█▏ | 226/1828 [08:03<56:51, 2.13s/it]
epoch: 0 loss: 0.4197745: 12%|█▏ | 226/1828 [08:05<56:51, 2.13s/it]
epoch: 0 loss: 0.4197745: 12%|█▏ | 227/1828 [08:05<56:55, 2.13s/it]
epoch: 0 loss: 0.1194392: 12%|█▏ | 227/1828 [08:07<56:55, 2.13s/it]
epoch: 0 loss: 0.1194392: 12%|█▏ | 228/1828 [08:07<56:50, 2.13s/it]
epoch: 0 loss: 0.3268197: 12%|█▏ | 228/1828 [08:09<56:50, 2.13s/it]
epoch: 0 loss: 0.3268197: 13%|█▎ | 229/1828 [08:09<56:50, 2.13s/it]
epoch: 0 loss: 0.7492452: 13%|█▎ | 229/1828 [08:11<56:50, 2.13s/it]
epoch: 0 loss: 0.7492452: 13%|█▎ | 230/1828 [08:11<56:44, 2.13s/it]
epoch: 0 loss: 0.3893861: 13%|█▎ | 230/1828 [08:13<56:44, 2.13s/it]
epoch: 0 loss: 0.3893861: 13%|█▎ | 231/1828 [08:13<56:40, 2.13s/it]
epoch: 0 loss: 0.5350035: 13%|█▎ | 231/1828 [08:15<56:40, 2.13s/it]
epoch: 0 loss: 0.5350035: 13%|█▎ | 232/1828 [08:15<56:40, 2.13s/it]
epoch: 0 loss: 0.2825365: 13%|█▎ | 232/1828 [08:17<56:40, 2.13s/it]
epoch: 0 loss: 0.2825365: 13%|█▎ | 233/1828 [08:17<56:41, 2.13s/it]
epoch: 0 loss: 0.3328047: 13%|█▎ | 233/1828 [08:20<56:41, 2.13s/it]
epoch: 0 loss: 0.3328047: 13%|█▎ | 234/1828 [08:20<56:46, 2.14s/it]
epoch: 0 loss: 0.2784316: 13%|█▎ | 234/1828 [08:22<56:46, 2.14s/it]
epoch: 0 loss: 0.2784316: 13%|█▎ | 235/1828 [08:22<56:40, 2.13s/it]
epoch: 0 loss: 0.2267757: 13%|█▎ | 235/1828 [08:24<56:40, 2.13s/it]
epoch: 0 loss: 0.2267757: 13%|█▎ | 236/1828 [08:24<56:35, 2.13s/it]
epoch: 0 loss: 0.2740307: 13%|█▎ | 236/1828 [08:26<56:35, 2.13s/it]
epoch: 0 loss: 0.2740307: 13%|█▎ | 237/1828 [08:26<56:29, 2.13s/it]
epoch: 0 loss: 0.2049000: 13%|█▎ | 237/1828 [08:28<56:29, 2.13s/it]
epoch: 0 loss: 0.2049000: 13%|█▎ | 238/1828 [08:28<56:29, 2.13s/it]
epoch: 0 loss: 0.1063681: 13%|█▎ | 238/1828 [08:30<56:29, 2.13s/it]
epoch: 0 loss: 0.1063681: 13%|█▎ | 239/1828 [08:30<56:26, 2.13s/it]
epoch: 0 loss: 0.3389107: 13%|█▎ | 239/1828 [08:32<56:26, 2.13s/it]
epoch: 0 loss: 0.3389107: 13%|█▎ | 240/1828 [08:32<56:23, 2.13s/it]
epoch: 0 loss: 0.4755172: 13%|█▎ | 240/1828 [08:35<56:23, 2.13s/it]
epoch: 0 loss: 0.4755172: 13%|█▎ | 241/1828 [08:35<56:23, 2.13s/it]
epoch: 0 loss: 0.4129283: 13%|█▎ | 241/1828 [08:37<56:23, 2.13s/it]
epoch: 0 loss: 0.4129283: 13%|█▎ | 242/1828 [08:37<56:19, 2.13s/it]
epoch: 0 loss: 0.4057980: 13%|█▎ | 242/1828 [08:39<56:19, 2.13s/it]
epoch: 0 loss: 0.4057980: 13%|█▎ | 243/1828 [08:39<56:18, 2.13s/it]
epoch: 0 loss: 0.2337068: 13%|█▎ | 243/1828 [08:41<56:18, 2.13s/it]
epoch: 0 loss: 0.2337068: 13%|█▎ | 244/1828 [08:41<56:17, 2.13s/it]
epoch: 0 loss: 0.1582389: 13%|█▎ | 244/1828 [08:43<56:17, 2.13s/it]
epoch: 0 loss: 0.1582389: 13%|█▎ | 245/1828 [08:43<56:13, 2.13s/it]
epoch: 0 loss: 0.3599120: 13%|█▎ | 245/1828 [08:45<56:13, 2.13s/it]
epoch: 0 loss: 0.3599120: 13%|█▎ | 246/1828 [08:45<56:10, 2.13s/it]
epoch: 0 loss: 0.2959028: 13%|█▎ | 246/1828 [08:47<56:10, 2.13s/it]
epoch: 0 loss: 0.2959028: 14%|█▎ | 247/1828 [08:47<56:10, 2.13s/it]
epoch: 0 loss: 0.2258265: 14%|█▎ | 247/1828 [08:49<56:10, 2.13s/it]
epoch: 0 loss: 0.2258265: 14%|█▎ | 248/1828 [08:49<56:10, 2.13s/it]
epoch: 0 loss: 0.1401720: 14%|█▎ | 248/1828 [08:52<56:10, 2.13s/it]
epoch: 0 loss: 0.1401720: 14%|█▎ | 249/1828 [08:52<56:08, 2.13s/it]
epoch: 0 loss: 0.1670344: 14%|█▎ | 249/1828 [08:54<56:08, 2.13s/it]
epoch: 0 loss: 0.1670344: 14%|█▎ | 250/1828 [08:54<56:00, 2.13s/it]
epoch: 0 loss: 0.1522811: 14%|█▎ | 250/1828 [08:56<56:00, 2.13s/it]
epoch: 0 loss: 0.1522811: 14%|█▎ | 251/1828 [08:56<55:55, 2.13s/it]
epoch: 0 loss: 0.6681911: 14%|█▎ | 251/1828 [08:58<55:55, 2.13s/it]
epoch: 0 loss: 0.6681911: 14%|█▍ | 252/1828 [08:58<55:54, 2.13s/it]
epoch: 0 loss: 0.3054271: 14%|█▍ | 252/1828 [09:00<55:54, 2.13s/it]
epoch: 0 loss: 0.3054271: 14%|█▍ | 253/1828 [09:00<55:54, 2.13s/it]
epoch: 0 loss: 0.0923404: 14%|█▍ | 253/1828 [09:02<55:54, 2.13s/it]
epoch: 0 loss: 0.0923404: 14%|█▍ | 254/1828 [09:02<55:48, 2.13s/it]
epoch: 0 loss: 0.1596135: 14%|█▍ | 254/1828 [09:04<55:48, 2.13s/it]
epoch: 0 loss: 0.1596135: 14%|█▍ | 255/1828 [09:04<55:50, 2.13s/it]
epoch: 0 loss: 0.1505734: 14%|█▍ | 255/1828 [09:06<55:50, 2.13s/it]
epoch: 0 loss: 0.1505734: 14%|█▍ | 256/1828 [09:06<55:47, 2.13s/it]
epoch: 0 loss: 0.1757742: 14%|█▍ | 256/1828 [09:09<55:47, 2.13s/it]
epoch: 0 loss: 0.1757742: 14%|█▍ | 257/1828 [09:09<55:44, 2.13s/it]
epoch: 0 loss: 0.2396596: 14%|█▍ | 257/1828 [09:11<55:44, 2.13s/it]
epoch: 0 loss: 0.2396596: 14%|█▍ | 258/1828 [09:11<55:39, 2.13s/it]
epoch: 0 loss: 0.3264573: 14%|█▍ | 258/1828 [09:13<55:39, 2.13s/it]
epoch: 0 loss: 0.3264573: 14%|█▍ | 259/1828 [09:13<55:37, 2.13s/it]
epoch: 0 loss: 0.2466870: 14%|█▍ | 259/1828 [09:15<55:37, 2.13s/it]
epoch: 0 loss: 0.2466870: 14%|█▍ | 260/1828 [09:15<55:40, 2.13s/it]
epoch: 0 loss: 0.3211006: 14%|█▍ | 260/1828 [09:17<55:40, 2.13s/it]
epoch: 0 loss: 0.3211006: 14%|█▍ | 261/1828 [09:17<55:42, 2.13s/it]
epoch: 0 loss: 0.3039247: 14%|█▍ | 261/1828 [09:19<55:42, 2.13s/it]
epoch: 0 loss: 0.3039247: 14%|█▍ | 262/1828 [09:19<55:43, 2.14s/it]
epoch: 0 loss: 0.4323672: 14%|█▍ | 262/1828 [09:21<55:43, 2.14s/it]
epoch: 0 loss: 0.4323672: 14%|█▍ | 263/1828 [09:21<55:35, 2.13s/it]
epoch: 0 loss: 0.4035657: 14%|█▍ | 263/1828 [09:23<55:35, 2.13s/it]
epoch: 0 loss: 0.4035657: 14%|█▍ | 264/1828 [09:23<54:21, 2.09s/it]
epoch: 0 loss: 0.3234578: 14%|█▍ | 264/1828 [09:26<54:21, 2.09s/it]
epoch: 0 loss: 0.3234578: 14%|█▍ | 265/1828 [09:26<54:40, 2.10s/it]
epoch: 0 loss: 0.6431109: 14%|█▍ | 265/1828 [09:28<54:40, 2.10s/it]
epoch: 0 loss: 0.6431109: 15%|█▍ | 266/1828 [09:28<54:56, 2.11s/it]
epoch: 0 loss: 0.9364270: 15%|█▍ | 266/1828 [09:30<54:56, 2.11s/it]
epoch: 0 loss: 0.9364270: 15%|█▍ | 267/1828 [09:30<55:01, 2.11s/it]
epoch: 0 loss: 0.2681694: 15%|█▍ | 267/1828 [09:32<55:01, 2.11s/it]
epoch: 0 loss: 0.2681694: 15%|█▍ | 268/1828 [09:32<55:07, 2.12s/it]
epoch: 0 loss: 0.6359509: 15%|█▍ | 268/1828 [09:34<55:07, 2.12s/it]
epoch: 0 loss: 0.6359509: 15%|█▍ | 269/1828 [09:34<55:04, 2.12s/it]
epoch: 0 loss: 0.7060709: 15%|█▍ | 269/1828 [09:36<55:04, 2.12s/it]
epoch: 0 loss: 0.7060709: 15%|█▍ | 270/1828 [09:36<55:07, 2.12s/it]
epoch: 0 loss: 0.1452857: 15%|█▍ | 270/1828 [09:38<55:07, 2.12s/it]
epoch: 0 loss: 0.1452857: 15%|█▍ | 271/1828 [09:38<55:06, 2.12s/it]
epoch: 0 loss: 0.4243963: 15%|█▍ | 271/1828 [09:40<55:06, 2.12s/it]
epoch: 0 loss: 0.4243963: 15%|█▍ | 272/1828 [09:40<55:04, 2.12s/it]
epoch: 0 loss: 0.5523804: 15%|█▍ | 272/1828 [09:43<55:04, 2.12s/it]
epoch: 0 loss: 0.5523804: 15%|█▍ | 273/1828 [09:43<55:10, 2.13s/it]
epoch: 0 loss: 0.1558693: 15%|█▍ | 273/1828 [09:45<55:10, 2.13s/it]
epoch: 0 loss: 0.1558693: 15%|█▍ | 274/1828 [09:45<55:09, 2.13s/it]
epoch: 0 loss: 0.2690632: 15%|█▍ | 274/1828 [09:47<55:09, 2.13s/it]
epoch: 0 loss: 0.2690632: 15%|█▌ | 275/1828 [09:47<55:09, 2.13s/it]
epoch: 0 loss: 0.2822823: 15%|█▌ | 275/1828 [09:49<55:09, 2.13s/it]
epoch: 0 loss: 0.2822823: 15%|█▌ | 276/1828 [09:49<55:06, 2.13s/it]
epoch: 0 loss: 0.8180482: 15%|█▌ | 276/1828 [09:51<55:06, 2.13s/it]
epoch: 0 loss: 0.8180482: 15%|█▌ | 277/1828 [09:51<55:03, 2.13s/it]
epoch: 0 loss: 0.3384075: 15%|█▌ | 277/1828 [09:53<55:03, 2.13s/it]
epoch: 0 loss: 0.3384075: 15%|█▌ | 278/1828 [09:53<55:02, 2.13s/it]
epoch: 0 loss: 0.3417062: 15%|█▌ | 278/1828 [09:55<55:02, 2.13s/it]
epoch: 0 loss: 0.3417062: 15%|█▌ | 279/1828 [09:55<55:01, 2.13s/it]
epoch: 0 loss: 0.1285317: 15%|█▌ | 279/1828 [09:57<55:01, 2.13s/it]
epoch: 0 loss: 0.1285317: 15%|█▌ | 280/1828 [09:57<55:02, 2.13s/it]
epoch: 0 loss: 0.6474587: 15%|█▌ | 280/1828 [10:00<55:02, 2.13s/it]
epoch: 0 loss: 0.6474587: 15%|█▌ | 281/1828 [10:00<54:57, 2.13s/it]
epoch: 0 loss: 0.3105499: 15%|█▌ | 281/1828 [10:02<54:57, 2.13s/it]
epoch: 0 loss: 0.3105499: 15%|█▌ | 282/1828 [10:02<54:52, 2.13s/it]
epoch: 0 loss: 0.3200988: 15%|█▌ | 282/1828 [10:04<54:52, 2.13s/it]
epoch: 0 loss: 0.3200988: 15%|█▌ | 283/1828 [10:04<54:46, 2.13s/it]
epoch: 0 loss: 0.2756557: 15%|█▌ | 283/1828 [10:06<54:46, 2.13s/it]
epoch: 0 loss: 0.2756557: 16%|█▌ | 284/1828 [10:06<54:44, 2.13s/it]
epoch: 0 loss: 0.2181560: 16%|█▌ | 284/1828 [10:08<54:44, 2.13s/it]
epoch: 0 loss: 0.2181560: 16%|█▌ | 285/1828 [10:08<54:40, 2.13s/it]
epoch: 0 loss: 0.1362952: 16%|█▌ | 285/1828 [10:10<54:40, 2.13s/it]
epoch: 0 loss: 0.1362952: 16%|█▌ | 286/1828 [10:10<54:37, 2.13s/it]
epoch: 0 loss: 0.1239334: 16%|█▌ | 286/1828 [10:12<54:37, 2.13s/it]
epoch: 0 loss: 0.1239334: 16%|█▌ | 287/1828 [10:12<54:36, 2.13s/it]
epoch: 0 loss: 0.3355779: 16%|█▌ | 287/1828 [10:14<54:36, 2.13s/it]
epoch: 0 loss: 0.3355779: 16%|█▌ | 288/1828 [10:14<54:38, 2.13s/it]
epoch: 0 loss: 0.4383239: 16%|█▌ | 288/1828 [10:17<54:38, 2.13s/it]
epoch: 0 loss: 0.4383239: 16%|█▌ | 289/1828 [10:17<54:38, 2.13s/it]
epoch: 0 loss: 0.2639011: 16%|█▌ | 289/1828 [10:19<54:38, 2.13s/it]
epoch: 0 loss: 0.2639011: 16%|█▌ | 290/1828 [10:19<54:39, 2.13s/it]
epoch: 0 loss: 0.5221723: 16%|█▌ | 290/1828 [10:21<54:39, 2.13s/it]
epoch: 0 loss: 0.5221723: 16%|█▌ | 291/1828 [10:21<54:35, 2.13s/it]
epoch: 0 loss: 0.1521265: 16%|█▌ | 291/1828 [10:23<54:35, 2.13s/it]
epoch: 0 loss: 0.1521265: 16%|█▌ | 292/1828 [10:23<54:36, 2.13s/it]
epoch: 0 loss: 0.2264468: 16%|█▌ | 292/1828 [10:25<54:36, 2.13s/it]
epoch: 0 loss: 0.2264468: 16%|█▌ | 293/1828 [10:25<54:35, 2.13s/it]
epoch: 0 loss: 0.2747345: 16%|█▌ | 293/1828 [10:27<54:35, 2.13s/it]
epoch: 0 loss: 0.2747345: 16%|█▌ | 294/1828 [10:27<54:31, 2.13s/it]
epoch: 0 loss: 0.4255839: 16%|█▌ | 294/1828 [10:29<54:31, 2.13s/it]
epoch: 0 loss: 0.4255839: 16%|█▌ | 295/1828 [10:29<54:29, 2.13s/it]
epoch: 0 loss: 0.2197859: 16%|█▌ | 295/1828 [10:31<54:29, 2.13s/it]
epoch: 0 loss: 0.2197859: 16%|█▌ | 296/1828 [10:31<53:21, 2.09s/it]
epoch: 0 loss: 0.3545854: 16%|█▌ | 296/1828 [10:34<53:21, 2.09s/it]
epoch: 0 loss: 0.3545854: 16%|█▌ | 297/1828 [10:34<53:35, 2.10s/it]
epoch: 0 loss: 0.4773168: 16%|█▌ | 297/1828 [10:36<53:35, 2.10s/it]
epoch: 0 loss: 0.4773168: 16%|█▋ | 298/1828 [10:36<53:49, 2.11s/it]
epoch: 0 loss: 0.2496186: 16%|█▋ | 298/1828 [10:38<53:49, 2.11s/it]
epoch: 0 loss: 0.2496186: 16%|█▋ | 299/1828 [10:38<53:54, 2.12s/it]
epoch: 0 loss: 0.1291211: 16%|█▋ | 299/1828 [10:40<53:54, 2.12s/it]
epoch: 0 loss: 0.1291211: 16%|█▋ | 300/1828 [10:40<52:55, 2.08s/it]
epoch: 0 loss: 0.2979057: 16%|█▋ | 300/1828 [10:42<52:55, 2.08s/it]
epoch: 0 loss: 0.2979057: 16%|█▋ | 301/1828 [10:42<53:13, 2.09s/it]
epoch: 0 loss: 0.4001083: 16%|█▋ | 301/1828 [10:44<53:13, 2.09s/it]
epoch: 0 loss: 0.4001083: 17%|█▋ | 302/1828 [10:44<53:25, 2.10s/it]
epoch: 0 loss: 0.1107873: 17%|█▋ | 302/1828 [10:46<53:25, 2.10s/it]
epoch: 0 loss: 0.1107873: 17%|█▋ | 303/1828 [10:46<53:36, 2.11s/it]
epoch: 0 loss: 0.3320691: 17%|█▋ | 303/1828 [10:48<53:36, 2.11s/it]
epoch: 0 loss: 0.3320691: 17%|█▋ | 304/1828 [10:48<53:46, 2.12s/it]
epoch: 0 loss: 0.5391124: 17%|█▋ | 304/1828 [10:50<53:46, 2.12s/it]
epoch: 0 loss: 0.5391124: 17%|█▋ | 305/1828 [10:50<53:47, 2.12s/it]
epoch: 0 loss: 0.3917314: 17%|█▋ | 305/1828 [10:53<53:47, 2.12s/it]
epoch: 0 loss: 0.3917314: 17%|█▋ | 306/1828 [10:53<53:52, 2.12s/it]
epoch: 0 loss: 0.4090514: 17%|█▋ | 306/1828 [10:55<53:52, 2.12s/it]
epoch: 0 loss: 0.4090514: 17%|█▋ | 307/1828 [10:55<53:48, 2.12s/it]
epoch: 0 loss: 0.1801630: 17%|█▋ | 307/1828 [10:57<53:48, 2.12s/it]
epoch: 0 loss: 0.1801630: 17%|█▋ | 308/1828 [10:57<53:50, 2.13s/it]
epoch: 0 loss: 0.4975915: 17%|█▋ | 308/1828 [10:59<53:50, 2.13s/it]
epoch: 0 loss: 0.4975915: 17%|█▋ | 309/1828 [10:59<53:44, 2.12s/it]
epoch: 0 loss: 0.5702341: 17%|█▋ | 309/1828 [11:01<53:44, 2.12s/it]
epoch: 0 loss: 0.5702341: 17%|█▋ | 310/1828 [11:01<53:42, 2.12s/it]
epoch: 0 loss: 0.2232314: 17%|█▋ | 310/1828 [11:03<53:42, 2.12s/it]
epoch: 0 loss: 0.2232314: 17%|█▋ | 311/1828 [11:03<53:44, 2.13s/it]
epoch: 0 loss: 0.1986854: 17%|█▋ | 311/1828 [11:05<53:44, 2.13s/it]
epoch: 0 loss: 0.1986854: 17%|█▋ | 312/1828 [11:05<53:45, 2.13s/it]
epoch: 0 loss: 0.3510034: 17%|█▋ | 312/1828 [11:07<53:45, 2.13s/it]
epoch: 0 loss: 0.3510034: 17%|█▋ | 313/1828 [11:07<53:48, 2.13s/it]
epoch: 0 loss: 0.2356694: 17%|█▋ | 313/1828 [11:10<53:48, 2.13s/it]
epoch: 0 loss: 0.2356694: 17%|█▋ | 314/1828 [11:10<53:43, 2.13s/it]
epoch: 0 loss: 0.2319398: 17%|█▋ | 314/1828 [11:12<53:43, 2.13s/it]
epoch: 0 loss: 0.2319398: 17%|█▋ | 315/1828 [11:12<53:40, 2.13s/it]
epoch: 0 loss: 0.4926760: 17%|█▋ | 315/1828 [11:14<53:40, 2.13s/it]
epoch: 0 loss: 0.4926760: 17%|█▋ | 316/1828 [11:14<53:44, 2.13s/it]
epoch: 0 loss: 0.2682504: 17%|█▋ | 316/1828 [11:16<53:44, 2.13s/it]
epoch: 0 loss: 0.2682504: 17%|█▋ | 317/1828 [11:16<53:44, 2.13s/it]
epoch: 0 loss: 0.1606586: 17%|█▋ | 317/1828 [11:18<53:44, 2.13s/it]
epoch: 0 loss: 0.1606586: 17%|█▋ | 318/1828 [11:18<53:45, 2.14s/it]
epoch: 0 loss: 0.2307937: 17%|█▋ | 318/1828 [11:20<53:45, 2.14s/it]
epoch: 0 loss: 0.2307937: 17%|█▋ | 319/1828 [11:20<53:38, 2.13s/it]
epoch: 0 loss: 0.1461570: 17%|█▋ | 319/1828 [11:22<53:38, 2.13s/it]
epoch: 0 loss: 0.1461570: 18%|█▊ | 320/1828 [11:22<53:34, 2.13s/it]
epoch: 0 loss: 0.2093841: 18%|█▊ | 320/1828 [11:25<53:34, 2.13s/it]
epoch: 0 loss: 0.2093841: 18%|█▊ | 321/1828 [11:25<53:29, 2.13s/it]
epoch: 0 loss: 0.1332726: 18%|█▊ | 321/1828 [11:27<53:29, 2.13s/it]
epoch: 0 loss: 0.1332726: 18%|█▊ | 322/1828 [11:27<53:29, 2.13s/it]
epoch: 0 loss: 0.3361726: 18%|█▊ | 322/1828 [11:29<53:29, 2.13s/it]
epoch: 0 loss: 0.3361726: 18%|█▊ | 323/1828 [11:29<53:30, 2.13s/it]
epoch: 0 loss: 0.5113770: 18%|█▊ | 323/1828 [11:31<53:30, 2.13s/it]
epoch: 0 loss: 0.5113770: 18%|█▊ | 324/1828 [11:31<53:19, 2.13s/it]
epoch: 0 loss: 0.1137714: 18%|█▊ | 324/1828 [11:33<53:19, 2.13s/it]
epoch: 0 loss: 0.1137714: 18%|█▊ | 325/1828 [11:33<53:13, 2.12s/it]
epoch: 0 loss: 0.1904896: 18%|█▊ | 325/1828 [11:35<53:13, 2.12s/it]
epoch: 0 loss: 0.1904896: 18%|█▊ | 326/1828 [11:35<53:12, 2.13s/it]
epoch: 0 loss: 0.2633573: 18%|█▊ | 326/1828 [11:37<53:12, 2.13s/it]
epoch: 0 loss: 0.2633573: 18%|█▊ | 327/1828 [11:37<53:13, 2.13s/it]
epoch: 0 loss: 0.2036604: 18%|█▊ | 327/1828 [11:39<53:13, 2.13s/it]
epoch: 0 loss: 0.2036604: 18%|█▊ | 328/1828 [11:39<53:07, 2.13s/it]
epoch: 0 loss: 0.2196550: 18%|█▊ | 328/1828 [11:42<53:07, 2.13s/it]
epoch: 0 loss: 0.2196550: 18%|█▊ | 329/1828 [11:42<53:01, 2.12s/it]
epoch: 0 loss: 0.2367932: 18%|█▊ | 329/1828 [11:44<53:01, 2.12s/it]
epoch: 0 loss: 0.2367932: 18%|█▊ | 330/1828 [11:44<53:01, 2.12s/it]
epoch: 0 loss: 0.3930167: 18%|█▊ | 330/1828 [11:46<53:01, 2.12s/it]
epoch: 0 loss: 0.3930167: 18%|█▊ | 331/1828 [11:46<53:02, 2.13s/it]
epoch: 0 loss: 0.2156489: 18%|█▊ | 331/1828 [11:48<53:02, 2.13s/it]
epoch: 0 loss: 0.2156489: 18%|█▊ | 332/1828 [11:48<52:57, 2.12s/it]
epoch: 0 loss: 0.1882576: 18%|█▊ | 332/1828 [11:50<52:57, 2.12s/it]
epoch: 0 loss: 0.1882576: 18%|█▊ | 333/1828 [11:50<52:59, 2.13s/it]
epoch: 0 loss: 0.3621215: 18%|█▊ | 333/1828 [11:52<52:59, 2.13s/it]
epoch: 0 loss: 0.3621215: 18%|█▊ | 334/1828 [11:52<52:52, 2.12s/it]
epoch: 0 loss: 0.2609291: 18%|█▊ | 334/1828 [11:54<52:52, 2.12s/it]
epoch: 0 loss: 0.2609291: 18%|█▊ | 335/1828 [11:54<52:50, 2.12s/it]
epoch: 0 loss: 0.2796804: 18%|█▊ | 335/1828 [11:56<52:50, 2.12s/it]
epoch: 0 loss: 0.2796804: 18%|█▊ | 336/1828 [11:56<52:54, 2.13s/it]
epoch: 0 loss: 0.3618945: 18%|█▊ | 336/1828 [11:59<52:54, 2.13s/it]
epoch: 0 loss: 0.3618945: 18%|█▊ | 337/1828 [11:59<52:54, 2.13s/it]
epoch: 0 loss: 0.4643139: 18%|█▊ | 337/1828 [12:01<52:54, 2.13s/it]
epoch: 0 loss: 0.4643139: 18%|█▊ | 338/1828 [12:01<52:53, 2.13s/it]
epoch: 0 loss: 0.2892395: 18%|█▊ | 338/1828 [12:03<52:53, 2.13s/it]
epoch: 0 loss: 0.2892395: 19%|█▊ | 339/1828 [12:03<52:46, 2.13s/it]
epoch: 0 loss: 0.4280899: 19%|█▊ | 339/1828 [12:05<52:46, 2.13s/it]
epoch: 0 loss: 0.4280899: 19%|█▊ | 340/1828 [12:05<52:46, 2.13s/it]
epoch: 0 loss: 0.1844694: 19%|█▊ | 340/1828 [12:07<52:46, 2.13s/it]
epoch: 0 loss: 0.1844694: 19%|█▊ | 341/1828 [12:07<52:45, 2.13s/it]
epoch: 0 loss: 0.2103485: 19%|█▊ | 341/1828 [12:09<52:45, 2.13s/it]
epoch: 0 loss: 0.2103485: 19%|█▊ | 342/1828 [12:09<52:41, 2.13s/it]
epoch: 0 loss: 0.2752577: 19%|█▊ | 342/1828 [12:11<52:41, 2.13s/it]
epoch: 0 loss: 0.2752577: 19%|█▉ | 343/1828 [12:11<52:37, 2.13s/it]
epoch: 0 loss: 0.1881800: 19%|█▉ | 343/1828 [12:13<52:37, 2.13s/it]
epoch: 0 loss: 0.1881800: 19%|█▉ | 344/1828 [12:13<52:32, 2.12s/it]
epoch: 0 loss: 0.3434016: 19%|█▉ | 344/1828 [12:16<52:32, 2.12s/it]
epoch: 0 loss: 0.3434016: 19%|█▉ | 345/1828 [12:16<52:34, 2.13s/it]
epoch: 0 loss: 0.4428032: 19%|█▉ | 345/1828 [12:18<52:34, 2.13s/it]
epoch: 0 loss: 0.4428032: 19%|█▉ | 346/1828 [12:18<52:36, 2.13s/it]
epoch: 0 loss: 0.2195939: 19%|█▉ | 346/1828 [12:20<52:36, 2.13s/it]
epoch: 0 loss: 0.2195939: 19%|█▉ | 347/1828 [12:20<52:36, 2.13s/it]
epoch: 0 loss: 0.2821806: 19%|█▉ | 347/1828 [12:22<52:36, 2.13s/it]
epoch: 0 loss: 0.2821806: 19%|█▉ | 348/1828 [12:22<52:30, 2.13s/it]
epoch: 0 loss: 0.1660236: 19%|█▉ | 348/1828 [12:24<52:30, 2.13s/it]
epoch: 0 loss: 0.1660236: 19%|█▉ | 349/1828 [12:24<52:30, 2.13s/it]
epoch: 0 loss: 0.1100354: 19%|█▉ | 349/1828 [12:26<52:30, 2.13s/it]
epoch: 0 loss: 0.1100354: 19%|█▉ | 350/1828 [12:26<52:29, 2.13s/it]
epoch: 0 loss: 0.8182057: 19%|█▉ | 350/1828 [12:28<52:29, 2.13s/it]
epoch: 0 loss: 0.8182057: 19%|█▉ | 351/1828 [12:28<52:24, 2.13s/it]
epoch: 0 loss: 0.2568128: 19%|█▉ | 351/1828 [12:30<52:24, 2.13s/it]
epoch: 0 loss: 0.2568128: 19%|█▉ | 352/1828 [12:30<52:26, 2.13s/it]
epoch: 0 loss: 0.3572868: 19%|█▉ | 352/1828 [12:33<52:26, 2.13s/it]
epoch: 0 loss: 0.3572868: 19%|█▉ | 353/1828 [12:33<52:20, 2.13s/it]
epoch: 0 loss: 0.2294697: 19%|█▉ | 353/1828 [12:35<52:20, 2.13s/it]
epoch: 0 loss: 0.2294697: 19%|█▉ | 354/1828 [12:35<52:21, 2.13s/it]
epoch: 0 loss: 0.1599403: 19%|█▉ | 354/1828 [12:37<52:21, 2.13s/it]
epoch: 0 loss: 0.1599403: 19%|█▉ | 355/1828 [12:37<52:20, 2.13s/it]
epoch: 0 loss: 0.3295975: 19%|█▉ | 355/1828 [12:39<52:20, 2.13s/it]
epoch: 0 loss: 0.3295975: 19%|█▉ | 356/1828 [12:39<52:14, 2.13s/it]
epoch: 0 loss: 0.2812515: 19%|█▉ | 356/1828 [12:41<52:14, 2.13s/it]
epoch: 0 loss: 0.2812515: 20%|█▉ | 357/1828 [12:41<52:09, 2.13s/it]
epoch: 0 loss: 0.4423675: 20%|█▉ | 357/1828 [12:43<52:09, 2.13s/it]
epoch: 0 loss: 0.4423675: 20%|█▉ | 358/1828 [12:43<52:01, 2.12s/it]
epoch: 0 loss: 0.1036854: 20%|█▉ | 358/1828 [12:45<52:01, 2.12s/it]
epoch: 0 loss: 0.1036854: 20%|█▉ | 359/1828 [12:45<52:01, 2.13s/it]
epoch: 0 loss: 0.4394960: 20%|█▉ | 359/1828 [12:47<52:01, 2.13s/it]
epoch: 0 loss: 0.4394960: 20%|█▉ | 360/1828 [12:47<52:00, 2.13s/it]
epoch: 0 loss: 0.4184482: 20%|█▉ | 360/1828 [12:50<52:00, 2.13s/it]
epoch: 0 loss: 0.4184482: 20%|█▉ | 361/1828 [12:50<51:59, 2.13s/it]
epoch: 0 loss: 0.3147155: 20%|█▉ | 361/1828 [12:52<51:59, 2.13s/it]
epoch: 0 loss: 0.3147155: 20%|█▉ | 362/1828 [12:52<52:01, 2.13s/it]
epoch: 0 loss: 0.3419936: 20%|█▉ | 362/1828 [12:54<52:01, 2.13s/it]
epoch: 0 loss: 0.3419936: 20%|█▉ | 363/1828 [12:54<52:01, 2.13s/it]
epoch: 0 loss: 0.4561570: 20%|█▉ | 363/1828 [12:56<52:01, 2.13s/it]
epoch: 0 loss: 0.4561570: 20%|█▉ | 364/1828 [12:56<52:15, 2.14s/it]
epoch: 0 loss: 0.1763853: 20%|█▉ | 364/1828 [12:58<52:15, 2.14s/it]
epoch: 0 loss: 0.1763853: 20%|█▉ | 365/1828 [12:58<52:06, 2.14s/it]
epoch: 0 loss: 0.1167289: 20%|█▉ | 365/1828 [13:00<52:06, 2.14s/it]
epoch: 0 loss: 0.1167289: 20%|██ | 366/1828 [13:00<52:05, 2.14s/it]
epoch: 0 loss: 0.2525672: 20%|██ | 366/1828 [13:02<52:05, 2.14s/it]
epoch: 0 loss: 0.2525672: 20%|██ | 367/1828 [13:02<52:15, 2.15s/it]
epoch: 0 loss: 0.2016819: 20%|██ | 367/1828 [13:05<52:15, 2.15s/it]
epoch: 0 loss: 0.2016819: 20%|██ | 368/1828 [13:05<52:08, 2.14s/it]
epoch: 0 loss: 0.4988505: 20%|██ | 368/1828 [13:07<52:08, 2.14s/it]
epoch: 0 loss: 0.4988505: 20%|██ | 369/1828 [13:07<52:09, 2.14s/it]
epoch: 0 loss: 0.1685232: 20%|██ | 369/1828 [13:09<52:09, 2.14s/it]
epoch: 0 loss: 0.1685232: 20%|██ | 370/1828 [13:09<52:00, 2.14s/it]
epoch: 0 loss: 0.2690882: 20%|██ | 370/1828 [13:11<52:00, 2.14s/it]
epoch: 0 loss: 0.2690882: 20%|██ | 371/1828 [13:11<51:52, 2.14s/it]
epoch: 0 loss: 0.2521914: 20%|██ | 371/1828 [13:13<51:52, 2.14s/it]
epoch: 0 loss: 0.2521914: 20%|██ | 372/1828 [13:13<51:43, 2.13s/it]
epoch: 0 loss: 0.2219220: 20%|██ | 372/1828 [13:15<51:43, 2.13s/it]
epoch: 0 loss: 0.2219220: 20%|██ | 373/1828 [13:15<51:45, 2.13s/it]
epoch: 0 loss: 0.1226636: 20%|██ | 373/1828 [13:17<51:45, 2.13s/it]
epoch: 0 loss: 0.1226636: 20%|██ | 374/1828 [13:17<51:46, 2.14s/it]
epoch: 0 loss: 0.1754435: 20%|██ | 374/1828 [13:20<51:46, 2.14s/it]
epoch: 0 loss: 0.1754435: 21%|██ | 375/1828 [13:20<51:44, 2.14s/it]
epoch: 0 loss: 0.2420999: 21%|██ | 375/1828 [13:22<51:44, 2.14s/it]
epoch: 0 loss: 0.2420999: 21%|██ | 376/1828 [13:22<51:38, 2.13s/it]
epoch: 0 loss: 0.1637484: 21%|██ | 376/1828 [13:24<51:38, 2.13s/it]
epoch: 0 loss: 0.1637484: 21%|██ | 377/1828 [13:24<51:33, 2.13s/it]
epoch: 0 loss: 0.5577727: 21%|██ | 377/1828 [13:26<51:33, 2.13s/it]
epoch: 0 loss: 0.5577727: 21%|██ | 378/1828 [13:26<51:32, 2.13s/it]
epoch: 0 loss: 0.2468960: 21%|██ | 378/1828 [13:28<51:32, 2.13s/it]
epoch: 0 loss: 0.2468960: 21%|██ | 379/1828 [13:28<51:27, 2.13s/it]
epoch: 0 loss: 0.5246836: 21%|██ | 379/1828 [13:30<51:27, 2.13s/it]
epoch: 0 loss: 0.5246836: 21%|██ | 380/1828 [13:30<51:23, 2.13s/it]
epoch: 0 loss: 0.1954972: 21%|██ | 380/1828 [13:32<51:23, 2.13s/it]
epoch: 0 loss: 0.1954972: 21%|██ | 381/1828 [13:32<51:16, 2.13s/it]
epoch: 0 loss: 0.3151050: 21%|██ | 381/1828 [13:34<51:16, 2.13s/it]
epoch: 0 loss: 0.3151050: 21%|██ | 382/1828 [13:34<51:17, 2.13s/it]
epoch: 0 loss: 0.1074091: 21%|██ | 382/1828 [13:37<51:17, 2.13s/it]
epoch: 0 loss: 0.1074091: 21%|██ | 383/1828 [13:37<51:23, 2.13s/it]
epoch: 0 loss: 0.2565279: 21%|██ | 383/1828 [13:39<51:23, 2.13s/it]
epoch: 0 loss: 0.2565279: 21%|██ | 384/1828 [13:39<51:19, 2.13s/it]
epoch: 0 loss: 0.2340675: 21%|██ | 384/1828 [13:41<51:19, 2.13s/it]
epoch: 0 loss: 0.2340675: 21%|██ | 385/1828 [13:41<51:15, 2.13s/it]
epoch: 0 loss: 0.1536168: 21%|██ | 385/1828 [13:43<51:15, 2.13s/it]
epoch: 0 loss: 0.1536168: 21%|██ | 386/1828 [13:43<51:13, 2.13s/it]
epoch: 0 loss: 0.3188037: 21%|██ | 386/1828 [13:45<51:13, 2.13s/it]
epoch: 0 loss: 0.3188037: 21%|██ | 387/1828 [13:45<51:21, 2.14s/it]
epoch: 0 loss: 0.1931840: 21%|██ | 387/1828 [13:47<51:21, 2.14s/it]
epoch: 0 loss: 0.1931840: 21%|██ | 388/1828 [13:47<51:18, 2.14s/it]
epoch: 0 loss: 0.3475975: 21%|██ | 388/1828 [13:49<51:18, 2.14s/it]
epoch: 0 loss: 0.3475975: 21%|██▏ | 389/1828 [13:49<51:13, 2.14s/it]
epoch: 0 loss: 0.4335420: 21%|██▏ | 389/1828 [13:52<51:13, 2.14s/it]
epoch: 0 loss: 0.4335420: 21%|██▏ | 390/1828 [13:52<51:09, 2.13s/it]
epoch: 0 loss: 0.1337750: 21%|██▏ | 390/1828 [13:54<51:09, 2.13s/it]
epoch: 0 loss: 0.1337750: 21%|██▏ | 391/1828 [13:54<51:04, 2.13s/it]
epoch: 0 loss: 0.1085044: 21%|██▏ | 391/1828 [13:56<51:04, 2.13s/it]
epoch: 0 loss: 0.1085044: 21%|██▏ | 392/1828 [13:56<51:05, 2.13s/it]
epoch: 0 loss: 0.1241815: 21%|██▏ | 392/1828 [13:58<51:05, 2.13s/it]
epoch: 0 loss: 0.1241815: 21%|██▏ | 393/1828 [13:58<51:05, 2.14s/it]
epoch: 0 loss: 0.4188871: 21%|██▏ | 393/1828 [14:00<51:05, 2.14s/it]
epoch: 0 loss: 0.4188871: 22%|██▏ | 394/1828 [14:00<50:58, 2.13s/it]
epoch: 0 loss: 0.3661775: 22%|██▏ | 394/1828 [14:02<50:58, 2.13s/it]
epoch: 0 loss: 0.3661775: 22%|██▏ | 395/1828 [14:02<50:52, 2.13s/it]
epoch: 0 loss: 0.1266283: 22%|██▏ | 395/1828 [14:04<50:52, 2.13s/it]
epoch: 0 loss: 0.1266283: 22%|██▏ | 396/1828 [14:04<50:51, 2.13s/it]
epoch: 0 loss: 0.4379943: 22%|██▏ | 396/1828 [14:06<50:51, 2.13s/it]
epoch: 0 loss: 0.4379943: 22%|██▏ | 397/1828 [14:06<50:55, 2.14s/it]
epoch: 0 loss: 0.2236344: 22%|██▏ | 397/1828 [14:09<50:55, 2.14s/it]
epoch: 0 loss: 0.2236344: 22%|██▏ | 398/1828 [14:09<50:52, 2.13s/it]
epoch: 0 loss: 0.3349766: 22%|██▏ | 398/1828 [14:11<50:52, 2.13s/it]
epoch: 0 loss: 0.3349766: 22%|██▏ | 399/1828 [14:11<50:45, 2.13s/it]
epoch: 0 loss: 0.0538106: 22%|██▏ | 399/1828 [14:13<50:45, 2.13s/it]
epoch: 0 loss: 0.0538106: 22%|██▏ | 400/1828 [14:13<50:38, 2.13s/it]
epoch: 0 loss: 0.1686780: 22%|██▏ | 400/1828 [14:15<50:38, 2.13s/it]
epoch: 0 loss: 0.1686780: 22%|██▏ | 401/1828 [14:15<50:40, 2.13s/it]
epoch: 0 loss: 0.4865437: 22%|██▏ | 401/1828 [14:17<50:40, 2.13s/it]
epoch: 0 loss: 0.4865437: 22%|██▏ | 402/1828 [14:17<50:43, 2.13s/it]
epoch: 0 loss: 0.3048713: 22%|██▏ | 402/1828 [14:19<50:43, 2.13s/it]
epoch: 0 loss: 0.3048713: 22%|██▏ | 403/1828 [14:19<50:40, 2.13s/it]
epoch: 0 loss: 0.2019655: 22%|██▏ | 403/1828 [14:21<50:40, 2.13s/it]
epoch: 0 loss: 0.2019655: 22%|██▏ | 404/1828 [14:21<50:37, 2.13s/it]
epoch: 0 loss: 0.1283737: 22%|██▏ | 404/1828 [14:24<50:37, 2.13s/it]
epoch: 0 loss: 0.1283737: 22%|██▏ | 405/1828 [14:24<50:30, 2.13s/it]
epoch: 0 loss: 0.0665901: 22%|██▏ | 405/1828 [14:26<50:30, 2.13s/it]
epoch: 0 loss: 0.0665901: 22%|██▏ | 406/1828 [14:26<50:28, 2.13s/it]
epoch: 0 loss: 0.2225803: 22%|██▏ | 406/1828 [14:28<50:28, 2.13s/it]
epoch: 0 loss: 0.2225803: 22%|██▏ | 407/1828 [14:28<50:24, 2.13s/it]
epoch: 0 loss: 0.2496744: 22%|██▏ | 407/1828 [14:30<50:24, 2.13s/it]
epoch: 0 loss: 0.2496744: 22%|██▏ | 408/1828 [14:30<50:20, 2.13s/it]
epoch: 0 loss: 0.4081229: 22%|██▏ | 408/1828 [14:32<50:20, 2.13s/it]
epoch: 0 loss: 0.4081229: 22%|██▏ | 409/1828 [14:32<50:16, 2.13s/it]
epoch: 0 loss: 0.4738132: 22%|██▏ | 409/1828 [14:34<50:16, 2.13s/it]
epoch: 0 loss: 0.4738132: 22%|██▏ | 410/1828 [14:34<50:13, 2.13s/it]
epoch: 0 loss: 0.5083668: 22%|██▏ | 410/1828 [14:36<50:13, 2.13s/it]
epoch: 0 loss: 0.5083668: 22%|██▏ | 411/1828 [14:36<50:17, 2.13s/it]
epoch: 0 loss: 0.4360587: 22%|██▏ | 411/1828 [14:38<50:17, 2.13s/it]
epoch: 0 loss: 0.4360587: 23%|██▎ | 412/1828 [14:38<50:12, 2.13s/it]
epoch: 0 loss: 0.0955140: 23%|██▎ | 412/1828 [14:41<50:12, 2.13s/it]
epoch: 0 loss: 0.0955140: 23%|██▎ | 413/1828 [14:41<50:04, 2.12s/it]
epoch: 0 loss: 0.3503150: 23%|██▎ | 413/1828 [14:43<50:04, 2.12s/it]
epoch: 0 loss: 0.3503150: 23%|██▎ | 414/1828 [14:43<50:01, 2.12s/it]
epoch: 0 loss: 0.2075382: 23%|██▎ | 414/1828 [14:45<50:01, 2.12s/it]
epoch: 0 loss: 0.2075382: 23%|██▎ | 415/1828 [14:45<50:02, 2.12s/it]
epoch: 0 loss: 0.3444858: 23%|██▎ | 415/1828 [14:47<50:02, 2.12s/it]
epoch: 0 loss: 0.3444858: 23%|██▎ | 416/1828 [14:47<50:06, 2.13s/it]
epoch: 0 loss: 0.3496541: 23%|██▎ | 416/1828 [14:49<50:06, 2.13s/it]
epoch: 0 loss: 0.3496541: 23%|██▎ | 417/1828 [14:49<50:06, 2.13s/it]
epoch: 0 loss: 0.3154039: 23%|██▎ | 417/1828 [14:51<50:06, 2.13s/it]
epoch: 0 loss: 0.3154039: 23%|██▎ | 418/1828 [14:51<49:58, 2.13s/it]
epoch: 0 loss: 0.2341327: 23%|██▎ | 418/1828 [14:53<49:58, 2.13s/it]
epoch: 0 loss: 0.2341327: 23%|██▎ | 419/1828 [14:53<49:56, 2.13s/it]
epoch: 0 loss: 0.2053914: 23%|██▎ | 419/1828 [14:55<49:56, 2.13s/it]
epoch: 0 loss: 0.2053914: 23%|██▎ | 420/1828 [14:55<49:55, 2.13s/it]
epoch: 0 loss: 0.2505538: 23%|██▎ | 420/1828 [14:58<49:55, 2.13s/it]
epoch: 0 loss: 0.2505538: 23%|██▎ | 421/1828 [14:58<49:57, 2.13s/it]
epoch: 0 loss: 0.0729388: 23%|██▎ | 421/1828 [15:00<49:57, 2.13s/it]
epoch: 0 loss: 0.0729388: 23%|██▎ | 422/1828 [15:00<49:54, 2.13s/it]
epoch: 0 loss: 0.2825767: 23%|██▎ | 422/1828 [15:02<49:54, 2.13s/it]
epoch: 0 loss: 0.2825767: 23%|██▎ | 423/1828 [15:02<49:49, 2.13s/it]
epoch: 0 loss: 0.5944701: 23%|██▎ | 423/1828 [15:04<49:49, 2.13s/it]
epoch: 0 loss: 0.5944701: 23%|██▎ | 424/1828 [15:04<49:47, 2.13s/it]
epoch: 0 loss: 0.3690287: 23%|██▎ | 424/1828 [15:06<49:47, 2.13s/it]
epoch: 0 loss: 0.3690287: 23%|██▎ | 425/1828 [15:06<49:43, 2.13s/it]
epoch: 0 loss: 0.1073913: 23%|██▎ | 425/1828 [15:08<49:43, 2.13s/it]
epoch: 0 loss: 0.1073913: 23%|██▎ | 426/1828 [15:08<49:51, 2.13s/it]
epoch: 0 loss: 0.3279747: 23%|██▎ | 426/1828 [15:10<49:51, 2.13s/it]
epoch: 0 loss: 0.3279747: 23%|██▎ | 427/1828 [15:10<49:45, 2.13s/it]
epoch: 0 loss: 0.2176772: 23%|██▎ | 427/1828 [15:12<49:45, 2.13s/it]
epoch: 0 loss: 0.2176772: 23%|██▎ | 428/1828 [15:12<49:42, 2.13s/it]
epoch: 0 loss: 0.2243467: 23%|██▎ | 428/1828 [15:15<49:42, 2.13s/it]
epoch: 0 loss: 0.2243467: 23%|██▎ | 429/1828 [15:15<49:46, 2.14s/it]
epoch: 0 loss: 0.1519326: 23%|██▎ | 429/1828 [15:17<49:46, 2.14s/it]
epoch: 0 loss: 0.1519326: 24%|██▎ | 430/1828 [15:17<49:46, 2.14s/it]
epoch: 0 loss: 0.3321648: 24%|██▎ | 430/1828 [15:19<49:46, 2.14s/it]
epoch: 0 loss: 0.3321648: 24%|██▎ | 431/1828 [15:19<49:50, 2.14s/it]
epoch: 0 loss: 0.7617782: 24%|██▎ | 431/1828 [15:21<49:50, 2.14s/it]
epoch: 0 loss: 0.7617782: 24%|██▎ | 432/1828 [15:21<49:45, 2.14s/it]