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
schema: '2.0'
stages:
prepare:
cmd: python -m scripts.prepare
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: scripts/prepare.py
md5: 20524be787ecc0bd3158a7a4cdaf20a7
size: 477
params:
params.yaml:
basic:
vocab_size: 50000
min_freq: 3
outs:
- path: outputs/config.json
md5: b475a25ba02680cc35f445c7f4b571e9
size: 85
- path: outputs/vocab.plk
md5: d1d7dd5445ea139f986675be21f6a4f9
size: 872687
inference@mlp:
cmd: python -m scripts.inference mlp
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/config.json
md5: b475a25ba02680cc35f445c7f4b571e9
size: 85
- path: outputs/mlp_checkpoint.pth
md5: 126d8aebdce4e616ce585b0055e1cd8a
size: 26921107
- path: scripts/inference.py
md5: 6009800af49693dcf5ea45a0415b071b
size: 1970
outs:
- path: outputs/mlp_submission.csv
md5: cfff14d87841c7c5d44ca2ae6578ac47
size: 330570
inference@lstm:
cmd: python -m scripts.inference lstm
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/config.json
md5: b475a25ba02680cc35f445c7f4b571e9
size: 85
- path: outputs/lstm_checkpoint.pth
md5: fdc05da24348e77beda95b0cc2d0ffce
size: 69723667
- path: scripts/inference.py
md5: 6009800af49693dcf5ea45a0415b071b
size: 1970
outs:
- path: outputs/lstm_submission.csv
md5: 98bbc0400205ae607e65f8c302a7c1ee
size: 330692
inference@cnn:
cmd: python -m scripts.inference cnn
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/cnn_checkpoint.pth
md5: 3f1690058c3c432329453ef733de978b
size: 25602311
- path: outputs/config.json
md5: cdb8221e0e5eb1a11d5f25ff535fcc38
size: 85
- path: scripts/inference.py
md5: 3824553fe72926fced071bd91ad71d90
size: 1980
outs:
- path: outputs/cnn_submission.csv
md5: 5ec4bc3440cd7a2887bba1a08e29fcd8
size: 258587
validate@mlp:
cmd: python -m scripts.validate mlp
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: outputs/config.json
md5: 833365f54b55ee1829588de2567d1bf7
size: 85
- path: outputs/vocab.plk
md5: 23ba90394b758ae7f60257b9bc7d5506
size: 1494895
- path: scripts/validate.py
md5: 06be09580d4ce344e850a0c5aa8121b8
size: 2769
params:
params.yaml:
mlp:
embed_dim: 128
use_bag: true
hidden_size: 512
dropout: 0.1
validate:
batch_size: 256
shuffle: true
epochs: 5
kfold: 10
early_stops: 3
optimizer:
lr: 0.0001
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/mlp_validate_plots.csv
md5: cbc3bc78748e4f1cd5dba7747fa2684e
size: 279
- path: outputs/mlp_validate_results.json
md5: eb090e4414bdf9f238e8d215ed7601f6
size: 155
validate@cnn:
cmd: python -m scripts.validate cnn
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: outputs/config.json
md5: cdb8221e0e5eb1a11d5f25ff535fcc38
size: 85
- path: outputs/vocab.plk
md5: 14284264890cd690d7bad61190b39ce0
size: 966319
- path: scripts/validate.py
md5: 0e3aa787e0e2ae0f08dd8aa491d696d0
size: 3588
params:
params.yaml:
cnn:
embed_dim: 128
use_bag: false
hidden_size: 512
kernel_size: 3
n_layers: 4
dropout: 0.33
max_len: 512
validate:
batch_size: 64
shuffle: true
epochs: 10
kfold: 10
early_stops: 3
optimizer:
lr: 0.001
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 1e-06
outs:
- path: outputs/cnn_validate_plots.csv
md5: 048c5d6e8f768602d6c2261687507772
size: 3839
- path: outputs/cnn_validate_results.json
md5: d1a11ca141476d800617b31736d666f8
size: 127
validate_bert@basic:
cmd: python -m scripts.validate_bert basic
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: scripts/validate_bert.py
md5: b8d7c28900ead5fc89eb87b5c55d6f16
size: 2429
params:
params.yaml:
bert.basic:
pretrained_model: bert-base-uncased
hidden_size: 768
dropout: 0.1
bert.max_len: 128
validate:
batch_size: 32
shuffle: true
epochs: 4
kfold: 10
early_stops: 3
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/bert-basic_validate_plots.csv
md5: 261b5f5d6626b9760f6eb3a7731959a4
size: 232
- path: outputs/bert-basic_validate_results.json
md5: 83e3f47932d2cc95584327703d8fb775
size: 154
validate_bert@lstm:
cmd: python -m scripts.validate_bert lstm
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: scripts/validate_bert.py
md5: b8d7c28900ead5fc89eb87b5c55d6f16
size: 2429
params:
params.yaml:
bert.lstm:
pretrained_model: bert-base-uncased
bert_hidden_size: 768
hidden_size: 512
dropout: 0.1
n_layers: 2
attention_method: concat
bert.max_len: 128
validate:
batch_size: 32
shuffle: true
epochs: 4
kfold: 10
early_stops: 3
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/bert-lstm_validate_plots.csv
md5: d83ef3404423476ecedefd9019213112
size: 234
- path: outputs/bert-lstm_validate_results.json
md5: f1f0542a879a1862dcf82eb17790e629
size: 153
train_bert@lstm:
cmd: python -m scripts.train_bert bert lstm
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: scripts/train_bert.py
md5: 28fb5beb554be9c9253586dab639ec0f
size: 1943
params:
params.yaml:
bert.lstm:
bert_hidden_size: 768
hidden_size: 512
dropout: 0.1
n_layers: 2
attention_method: concat
bert.max_len: 128
bert.pretrained_model: bert-base-uncased
train:
batch_size: 32
shuffle: true
epochs: 4
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/bert-lstm_checkpoint.pth
md5: 2adea24bf1a1c5648c0a12bf852433ce
size: 530373919
- path: outputs/bert-lstm_plots.csv
md5: 5a2f68ca26ced5e3b82c52a23f736a27
size: 171
- path: outputs/bert-lstm_results.json
md5: f0227ac6257fb301b759ab0b619cbbb0
size: 156
inference_bert@lstm:
cmd: python -m scripts.inference_bert bert lstm
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/bert-lstm_checkpoint.pth
md5: 2adea24bf1a1c5648c0a12bf852433ce
size: 530373919
- path: scripts/inference_bert.py
md5: 4253ac549774d38db305a9097228c108
size: 1898
outs:
- path: outputs/bert-lstm_submission.csv
md5: 9d080c140238e6adbeb7ef78c54ede21
size: 419729
validate_xlnet@basic:
cmd: python -m scripts.validate_bert xlnet basic
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: scripts/validate_bert.py
md5: e162b3b5f8716c7dabfbb413c67652d3
size: 2719
params:
params.yaml:
validate:
batch_size: 32
shuffle: true
epochs: 4
kfold: 10
early_stops: 3
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
xlnet.basic:
hidden_size: 768
dropout: 0.1
xlnet.max_len: 128
xlnet.pretrained_model: xlnet-base-cased
outs:
- path: outputs/xlnet-basic_validate_plots.csv
md5: 078516f43a751c7149d4e1b2b3200a5d
size: 232
- path: outputs/xlnet-basic_validate_results.json
md5: 011b99a5eaf6ec1ad0d3b649e7bd8c63
size: 154
validate_bert@bert-base-uncased_basic:
cmd: python -m scripts.validate_bert bert bert-base-uncased basic
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: model/bert/basic.py
md5: 7e5f25a5a50a46ea6c93949ce3fb861d
size: 1324
- path: scripts/validate_bert.py
md5: 20660b0b12c7342e4f7368d4ee146275
size: 2789
params:
params.yaml:
bert.basic:
dropout: 0.1
bert.do_lower_case: true
bert.max_len: 128
validate:
batch_size: 32
shuffle: true
epochs: 4
kfold: 10
early_stops: 3
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/bert-bert-base-uncased-basic_validate_plots.csv
md5: 195596b5c128026c2d7d1deddca5842c
size: 230
- path: outputs/bert-bert-base-uncased-basic_validate_results.json
md5: b929aa837f251b320db1660e94b8d723
size: 153
validate_bert@bert-large-uncased_basic:
cmd: python -m scripts.validate_bert bert bert-large-uncased basic
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: model/bert/basic.py
md5: 7e5f25a5a50a46ea6c93949ce3fb861d
size: 1324
- path: scripts/validate_bert.py
md5: 20660b0b12c7342e4f7368d4ee146275
size: 2789
params:
params.yaml:
bert.basic:
dropout: 0.1
bert.do_lower_case: true
bert.max_len: 128
validate:
batch_size: 16
shuffle: true
epochs: 4
kfold: 10
early_stops: 3
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/bert-bert-large-uncased-basic_validate_plots.csv
md5: af3870c50430090aa4e8f776cf9fb0ec
size: 229
- path: outputs/bert-bert-large-uncased-basic_validate_results.json
md5: 7df7cd93c728bd527170a51f6e34618c
size: 156
validate_bert@bert-base-uncased_lstm:
cmd: python -m scripts.validate_bert bert bert-base-uncased lstm
deps:
- path: data/train.csv
md5: d0d12f53a232828404431f2416df09fe
size: 33430132
- path: model/bert/lstm.py
md5: 09610a8fecd1493281715631401a86a2
size: 1897
- path: scripts/validate_bert.py
md5: 20660b0b12c7342e4f7368d4ee146275
size: 2789
params:
params.yaml:
bert.do_lower_case: true
bert.lstm:
hidden_size: 768
dropout: 0.1
n_layers: 2
attention_method: concat
bert.max_len: 128
validate:
batch_size: 32
shuffle: true
epochs: 4
kfold: 10
early_stops: 3
optimizer:
lr: 2e-05
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0
outs:
- path: outputs/bert-bert-base-uncased-lstm_validate_plots.csv
md5: aeea9348fc6e16aa332767a1bc5598be
size: 228
- path: outputs/bert-bert-base-uncased-lstm_validate_results.json
md5: 1810c78d585d2b3f8faf5e555232dfe1
size: 153
train@mlp:
cmd: python -m scripts.train mlp
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: outputs/config.json
md5: b475a25ba02680cc35f445c7f4b571e9
size: 85
- path: outputs/vocab.plk
md5: d1d7dd5445ea139f986675be21f6a4f9
size: 872687
- path: scripts/train.py
md5: e24786983fccaa1a2d5a88a8f68d4256
size: 2261
params:
params.yaml:
mlp:
embed_dim: 128
use_bag: true
hidden_size: 512
dropout: 0.1
train:
batch_size: 128
shuffle: true
epochs: 10
optimizer:
lr: 0.001
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0.0001
outs:
- path: outputs/mlp_checkpoint.pth
md5: 126d8aebdce4e616ce585b0055e1cd8a
size: 26921107
- path: outputs/mlp_plots.csv
md5: 7edeb8e35a8cee099176ff800fba77f0
size: 359
- path: outputs/mlp_results.json
md5: b200ed1aa1a6dec2c005d05bf4dc5013
size: 156
train@lstm:
cmd: python -m scripts.train lstm
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: outputs/config.json
md5: b475a25ba02680cc35f445c7f4b571e9
size: 85
- path: outputs/vocab.plk
md5: d1d7dd5445ea139f986675be21f6a4f9
size: 872687
- path: scripts/train.py
md5: e24786983fccaa1a2d5a88a8f68d4256
size: 2261
params:
params.yaml:
lstm:
embed_dim: 128
use_bag: false
use_eos: true
attention_method: concat
hidden_size: 512
n_layers: 2
dropout: 0.1
max_len: 256
train:
batch_size: 128
shuffle: true
epochs: 5
optimizer:
lr: 0.0001
step_lr: 2.0
gamma: 0.5
clip: 1.0
weight_decay: 0.0001
outs:
- path: outputs/lstm_checkpoint.pth
md5: fdc05da24348e77beda95b0cc2d0ffce
size: 69723667
- path: outputs/lstm_plots.csv
md5: 7b6bcef6350556128ebdcbae5bb28713
size: 200
- path: outputs/lstm_results.json
md5: bbc7a3f6830727f4cfe44364dfef671a
size: 153
train_bert@bert-large-uncased_basic:
cmd: python -m scripts.train_bert bert bert-large-uncased basic
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/bert/basic.py
md5: 7e5f25a5a50a46ea6c93949ce3fb861d
size: 1324
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
bert.basic:
dropout: 0.1
bert.do_lower_case: true
bert.max_len: 128
train:
batch_size: 16
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
outs:
- path: outputs/bert-bert-large-uncased-basic_checkpoint.pth
md5: 75275b0a961a2bd92cdb993950f1bde4
size: 1344932329
- path: outputs/bert-bert-large-uncased-basic_plots.csv
md5: 002f5ca93ac087d9599c08cf9dc08fc7
size: 311
- path: outputs/bert-bert-large-uncased-basic_results.json
md5: a9dbe5b64885bc0435757c23e412ee5c
size: 157
inference_bert@bert-large-uncased_basic:
cmd: python -m scripts.inference_bert bert bert-large-uncased basic
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/bert-bert-large-uncased-basic_checkpoint.pth
md5: 75275b0a961a2bd92cdb993950f1bde4
size: 1344932329
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
outs:
- path: outputs/bert-bert-large-uncased-basic_submission.csv
md5: 65246e6c1ce04f64e8e10f3f4de06600
size: 229245
train_roberta@roberta-large_basic:
cmd: python -m scripts.train_bert roberta roberta-large basic
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/roberta/basic.py
md5: 2c8632ca917584d6f8799ebe1483cb92
size: 1330
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
roberta.basic:
dropout: 0.1
roberta.do_lower_case: true
roberta.max_len: 128
train:
batch_size: 16
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
outs:
- path: outputs/roberta-roberta-large-basic_checkpoint.pth
md5: 32746b7a10b19bb892ec3a032da549f0
size: 1425803817
- path: outputs/roberta-roberta-large-basic_plots.csv
md5: 4cc8f9cf64e867b116dac693ad45d686
size: 312
- path: outputs/roberta-roberta-large-basic_results.json
md5: 40b071c1cdcd5956174a353ff6184fb3
size: 153
inference_roberta@roberta-large_basic:
cmd: python -m scripts.inference_bert roberta roberta-large basic
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/roberta-roberta-large-basic_checkpoint.pth
md5: 32746b7a10b19bb892ec3a032da549f0
size: 1425803817
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
params:
params.yaml:
roberta.eval_max_len: 128
outs:
- path: outputs/roberta-roberta-large-basic_submission.csv
md5: eeb427d0f74d71bdfd9ec76dc54a3f84
size: 229245
train_xlnet@xlnet-large-cased_basic:
cmd: python -m scripts.train_bert xlnet xlnet-large-cased basic
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/xlnet/basic.py
md5: 7c902712cffc82cf7005db19912dbf65
size: 1518
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
train:
batch_size: 8
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
xlnet.basic:
dropout: 0.1
xlnet.do_lower_case: true
xlnet.max_len: 128
outs:
- path: outputs/xlnet-xlnet-large-cased-basic_checkpoint.pth
md5: 99ac993f83fb9e03f20c72b61ebe5e0b
size: 1445421701
- path: outputs/xlnet-xlnet-large-cased-basic_plots.csv
md5: 2c110acac84dca78d4b82994f551b24d
size: 310
- path: outputs/xlnet-xlnet-large-cased-basic_results.json
md5: dab15eda010dacdd9eec534795aa467a
size: 154
inference_xlnet@xlnet-large-cased_basic:
cmd: python -m scripts.inference_bert xlnet xlnet-large-cased basic
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/xlnet-xlnet-large-cased-basic_checkpoint.pth
md5: 99ac993f83fb9e03f20c72b61ebe5e0b
size: 1445421701
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
outs:
- path: outputs/xlnet-xlnet-large-cased-basic_submission.csv
md5: 0bed9eb6bb98e18658641303f5059919
size: 229245
ensemble:
cmd: python -m scripts.ensemble
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/bert-bert-large-uncased-basic_checkpoint.pth
md5: 75275b0a961a2bd92cdb993950f1bde4
size: 1344932329
- path: outputs/roberta-roberta-large-basic_checkpoint.pth
md5: 32746b7a10b19bb892ec3a032da549f0
size: 1425803817
- path: outputs/xlnet-xlnet-large-cased-basic_checkpoint.pth
md5: 99ac993f83fb9e03f20c72b61ebe5e0b
size: 1445421701
- path: scripts/ensemble.py
md5: 75c167d8c71730b367a538b95b6a851c
size: 2504
params:
params.yaml:
evaluate:
batch_size: 128
outs:
- path: outputs/ensemble.csv
md5: e638fc8a4eed6d2e166ffd6c74f7f04f
size: 1212474
train_bert@bert-large-uncased_cnn:
cmd: python -m scripts.train_bert bert bert-large-uncased cnn
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/bert/cnn.py
md5: 2a4916dc588b10bd42d80426aeed5ef6
size: 1557
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
bert.cnn:
dropout: 0.1
hidden_size: 1024
kernel_size: 3
bert.do_lower_case: true
bert.max_len: 128
train:
batch_size: 16
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
outs:
- path: outputs/bert-bert-large-uncased-cnn_checkpoint.pth
md5: ba8c3a240efebf084505c94052a6c8dc
size: 1353338847
- path: outputs/bert-bert-large-uncased-cnn_plots.csv
md5: 636957460dc5962c9f81547eddbeec21
size: 314
- path: outputs/bert-bert-large-uncased-cnn_results.json
md5: 4821e83b3639908f49d7c24f90682249
size: 157
inference_bert@bert-large-uncased_cnn:
cmd: python -m scripts.inference_bert bert bert-large-uncased cnn
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/bert-bert-large-uncased-cnn_checkpoint.pth
md5: ba8c3a240efebf084505c94052a6c8dc
size: 1353338847
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
outs:
- path: outputs/bert-bert-large-uncased-cnn_submission.csv
md5: 0f5dd6d5a9df18e0f9d3abbe416057fb
size: 229245
train_roberta@roberta-large_cnn:
cmd: python -m scripts.train_bert roberta roberta-large cnn
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/roberta/cnn.py
md5: f0f2fd60d086d2744c9214bbb72c29f2
size: 1599
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
roberta.cnn:
dropout: 0.1
hidden_size: 1024
kernel_size: 3
roberta.do_lower_case: true
roberta.max_len: 128
train:
batch_size: 16
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
outs:
- path: outputs/roberta-roberta-large-cnn_checkpoint.pth
md5: 355a7f2bfc0ad163c0b191d5d52d525e
size: 1434210335
- path: outputs/roberta-roberta-large-cnn_plots.csv
md5: 5a085b9e3b2ab5ef223b86d16476026a
size: 312
- path: outputs/roberta-roberta-large-cnn_results.json
md5: 1e2e9bfed37c190d25f587df9cd26640
size: 157
inference_roberta@roberta-large_cnn:
cmd: python -m scripts.inference_bert roberta roberta-large cnn
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/roberta-roberta-large-cnn_checkpoint.pth
md5: 355a7f2bfc0ad163c0b191d5d52d525e
size: 1434210335
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
params:
params.yaml:
roberta.eval_max_len: 128
outs:
- path: outputs/roberta-roberta-large-cnn_submission.csv
md5: 89cf8c60730f6d3ba63f4aec4a82838b
size: 229245
train_xlnet@xlnet-large-cased_cnn:
cmd: python -m scripts.train_bert xlnet xlnet-large-cased cnn
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/xlnet/cnn.py
md5: 8b84a28dd591bfe84ab1171c5d053708
size: 1559
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
train:
batch_size: 8
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
xlnet.cnn:
dropout: 0.1
hidden_size: 1024
kernel_size: 3
xlnet.do_lower_case: true
xlnet.max_len: 128
outs:
- path: outputs/xlnet-xlnet-large-cased-cnn_checkpoint.pth
md5: d68d28074ee53c79be038367b79050b4
size: 1453828347
- path: outputs/xlnet-xlnet-large-cased-cnn_plots.csv
md5: 317f320e8fd70396656d321a560fb7a5
size: 312
- path: outputs/xlnet-xlnet-large-cased-cnn_results.json
md5: f76ee3e885f7c6570f47a76f6856ab7e
size: 155
inference_xlnet@xlnet-large-cased_cnn:
cmd: python -m scripts.inference_bert xlnet xlnet-large-cased cnn
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/xlnet-xlnet-large-cased-cnn_checkpoint.pth
md5: d68d28074ee53c79be038367b79050b4
size: 1453828347
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
outs:
- path: outputs/xlnet-xlnet-large-cased-cnn_submission.csv
md5: d315f9b5c206f15d7bb913ac662a6b8f
size: 229245
train_albert@albert-xlarge-v2_cnn:
cmd: python -m scripts.train_bert albert albert-xlarge-v2 cnn
deps:
- path: data/all.csv
md5: a79bcf8affd28ae57eee3fd38f872faa
size: 128402973
- path: model/albert/cnn.py
md5: 0d74b0e337e36b9d1773c96be4075d16
size: 1561
- path: scripts/train_bert.py
md5: 4cfa4bacc4a848148004d0bf3e63e0be
size: 2590
params:
params.yaml:
albert.cnn:
dropout: 0
hidden_size: 2048
kernel_size: 3
albert.do_lower_case: true
albert.max_len: 128
train:
batch_size: 8
shuffle: true
epochs: 6
early_stops: 2
optimizer:
lr: 2e-05
step_lr: 500
gamma: 0.5
clip: 1.0
weight_decay: 1e-05
outs:
- path: outputs/albert-albert-xlarge-v2-cnn_checkpoint.pth
md5: 351b134909cefa5683a452ff6ee2694a
size: 285297404
- path: outputs/albert-albert-xlarge-v2-cnn_plots.csv
md5: ce868bde9f81e2987d7bce4ee5e5af46
size: 312
- path: outputs/albert-albert-xlarge-v2-cnn_results.json
md5: f31adfa1ca3bfc022eda51deeff20f30
size: 156
inference_albert@albert-xlarge-v2_cnn:
cmd: python -m scripts.inference_bert albert albert-xlarge-v2 cnn
deps:
- path: data/test.csv
md5: 8ba62e41af40f5b5f9e9ed83e5ee3f2a
size: 33708755
- path: outputs/albert-albert-xlarge-v2-cnn_checkpoint.pth
md5: 351b134909cefa5683a452ff6ee2694a
size: 285297404
- path: scripts/inference_bert.py
md5: dd331f744ebee45890ca3a8106bf48dd
size: 2254
params:
params.yaml:
albert.eval_max_len: 128
outs:
- path: outputs/albert-albert-xlarge-v2-cnn_submission.csv
md5: 58c5a4fcc43a194b2cbbfe015f540387
size: 229245
Tip!
Press p or n or
Models
Annotations
Connect to our Discord channel