File size: 102,329 Bytes
d83c5d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "id": "a87fe5f3",
      "metadata": {
        "id": "a87fe5f3"
      },
      "outputs": [],
      "source": [
        "import pandas as pd\n",
        "import torch\n",
        "from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments, Trainer, BitsAndBytesConfig, EarlyStoppingCallback, PreTrainedTokenizer\n",
        "from torch.utils.data import DataLoader\n",
        "import sys\n",
        "from peft import LoraConfig, get_peft_model, TaskType\n",
        "from huggingface_hub import snapshot_download\n",
        "import os\n",
        "import re\n",
        "import contextlib #helps make pip silent\n",
        "import sys\n",
        "import os\n",
        "import numpy as np\n",
        "\n",
        "with contextlib.redirect_stdout(sys.__stdout__), contextlib.redirect_stderr(sys.__stderr__):\n",
        "    %pip install datasets\n",
        "    %pip install sql_metadata\n",
        "\"\"\"\"\n",
        "with contextlib.redirect_stdout(sys.__stdout__), contextlib.redirect_stderr(sys.__stderr__):\n",
        "    %pip install datasets\n",
        "    %pip install sql_metadata\n",
        "\"\"\"\n",
        "from datasets import Dataset\n",
        "from sql_metadata import Parser"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "id": "4ec432b2",
      "metadata": {
        "id": "4ec432b2"
      },
      "outputs": [],
      "source": [
        "is_google_colab = True\n",
        "use_bnb = False"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "47577a7f",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170,
          "referenced_widgets": [
            "9200f1303f124bddaa6114cdf0f5f878",
            "17ddbb74e1764f37b8d34c311fae200c",
            "ef732739334b4ac593fd665e01cd83c1",
            "949ee3d1a9cd4060864dec5d4283ef2c",
            "b98629e053674527aacca899ab7f11a9",
            "84cc47dc70864bf3aa7599c06eb13c51",
            "5d711bb927024d8d9f9b8bb685d6f388",
            "3b80c66e0f384c45ab4187301599fab2",
            "db6a23e658a34722a8f22505c6ace7b4",
            "7751defbc4534d518d9e923b9019aa8b",
            "fe6352bce22a40e7a936e7f90313bd02"
          ]
        },
        "id": "47577a7f",
        "outputId": "999c4e88-3f89-49b1-9e21-abac91703bf3"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n",
            "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
            "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
            "You will be able to reuse this secret in all of your notebooks.\n",
            "Please note that authentication is recommended but still optional to access public models or datasets.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Fetching 37 files:   0%|          | 0/37 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "9200f1303f124bddaa6114cdf0f5f878"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "current_read_path = \"./\"\n",
        "current_write_path = \"./\"\n",
        "\n",
        "def read_path(rel_path):\n",
        "    return os.path.join(current_read_path, rel_path)\n",
        "\n",
        "def write_path(rel_path):\n",
        "    return os.path.join(current_write_path, rel_path)\n",
        "\n",
        "if is_google_colab:\n",
        "    from google.colab import drive\n",
        "    drive.mount('/content/drive')\n",
        "    current_write_path = \"/content/drive/MyDrive/sql_gen\"\n",
        "\n",
        "    hugging_face_path = snapshot_download(\n",
        "        repo_id=\"USC-Applied-NLP-Group/SQL-Generation\",\n",
        "        repo_type=\"model\",\n",
        "        allow_patterns=[\"train-data/*\", \"deepseek-coder-1.3b-instruct/*\", \"src/*\", \"nba-data/*\"],\n",
        "    )\n",
        "    sys.path.append(hugging_face_path)\n",
        "    current_read_path = hugging_face_path\n",
        "else:\n",
        "    base_path = os.getcwd()  # Use current working directory in notebooks\n",
        "    sys.path.append(os.path.abspath(os.path.join(base_path, '../..')))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "id": "10b675d0",
      "metadata": {
        "id": "10b675d0"
      },
      "outputs": [],
      "source": [
        "from src.prompts.pre_rag_prompt import input_text as input_prompt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "id": "de7c3cd3",
      "metadata": {
        "id": "de7c3cd3"
      },
      "outputs": [],
      "source": [
        "MODEL_DIR = write_path(\"dyn_rag_test\")\n",
        "VAL_OUTPUT = write_path(\"dyn_rag_test.hf\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4b7eb12a",
      "metadata": {
        "id": "4b7eb12a"
      },
      "source": [
        "## Prepare Model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "3d0c0e3b",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3d0c0e3b",
        "outputId": "a64bc20b-a33f-453e-e445-cd08109ed43b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-6-ac29fbf828da>:2: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.\n",
            "  df = df.applymap(lambda x: re.sub(r'\\s+', ' ', x) if isinstance(x, str) else x)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Total dataset examples: 1044\n"
          ]
        }
      ],
      "source": [
        "\n",
        "df = pd.read_csv(read_path(\"train-data/sql_train.tsv\"), sep='\\t')\n",
        "df = df.applymap(lambda x: re.sub(r'\\s+', ' ', x) if isinstance(x, str) else x)\n",
        "\n",
        "# Display dataset info\n",
        "print(f\"Total dataset examples: {len(df)}\")\n",
        "\n",
        "# Load tokenizer\n",
        "model_name = read_path(\"deepseek-coder-1.3b-instruct\")\n",
        "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
        "\n",
        "# Enable 8-bit quantization for lower memory usage\n",
        "bnb_config = None\n",
        "if use_bnb:\n",
        "    bnb_config = BitsAndBytesConfig(\n",
        "        load_in_8bit=True,\n",
        "        bnb_8bit_compute_dtype=torch.float16\n",
        "    )\n",
        "\n",
        "# Load model with quantization\n",
        "#device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
        "device_name = 'cuda' if torch.cuda.is_available() else 'cpu'\n",
        "device = torch.device(device_name)\n",
        "model = AutoModelForCausalLM.from_pretrained(\n",
        "    model_name,\n",
        "    quantization_config=bnb_config,\n",
        "    device_map=device\n",
        ")\n",
        "\n",
        "tokenizer.truncation_side = \"left\"\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "id": "7f8b1acf",
      "metadata": {
        "id": "7f8b1acf"
      },
      "outputs": [],
      "source": [
        "natural_query_list = df[\"natural_query\"].tolist()\n",
        "sql_query_list = df[\"sql_query\"].tolist()\n",
        "tables = [Parser(sql_query).tables for sql_query in sql_query_list]\n",
        "\n",
        "dataset_dict = {\n",
        "    \"natural_query\": natural_query_list,\n",
        "    \"tables\": tables,\n",
        "}\n",
        "\n",
        "# Create HuggingFace Dataset\n",
        "dataset = Dataset.from_dict(dataset_dict)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "id": "f385a9df",
      "metadata": {
        "id": "f385a9df"
      },
      "outputs": [],
      "source": [
        "\n",
        "def format_deepseek_chat(example, tokenizer):\n",
        "    # Manually build the prompt as one flat string\n",
        "    prompt = f\"{input_prompt}{example['natural_query']}\\n\"\n",
        "    completion = f\"Tables:\\n{example['tables']}\"\n",
        "\n",
        "    full_text = prompt + completion\n",
        "    tokenized = tokenizer(\n",
        "        full_text,\n",
        "        truncation=True,\n",
        "        padding=\"max_length\",\n",
        "        max_length=3156,  # or whatever your model can handle\n",
        "    )\n",
        "\n",
        "    # Mask out prompt tokens in the labels\n",
        "    prompt_len = len(tokenizer(prompt, truncation=True)[\"input_ids\"])\n",
        "    labels = tokenized[\"input_ids\"][:]\n",
        "    labels[:prompt_len] = [-100] * prompt_len\n",
        "    tokenized[\"labels\"] = labels\n",
        "\n",
        "    return tokenized\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "id": "43562f78",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 121,
          "referenced_widgets": [
            "68ff2fc00bd041e7b79a811e3de1e596",
            "4c41e81bcd254df7b1265206a5a6b40b",
            "1a8c093fccbb437db6e0390a920f5cc5",
            "e11d04a9d22a4229922e3eb4e3eb6466",
            "5d89a5574a3d4a8993e6dca78d406d2d",
            "dd24270dc07942a6972fbfaf58129989",
            "643903cd7a5b4a52a4687ec38eb8c4dc",
            "13ae11c314664c44ae18d35cf57a1334",
            "e68cfd05ba994a34b93107d2eab82ad3",
            "ea283e7e8b234519b881c562b7eb01d3",
            "1ec5329ea0434df4b74d0f311e016c3e"
          ]
        },
        "id": "43562f78",
        "outputId": "58e8ce3f-b7cd-4cf6-dfa4-180b4a699cf9"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/1044 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "68ff2fc00bd041e7b79a811e3de1e596"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "939\n",
            "105\n",
            "{'input_ids': [32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32013, 2042, 417, 274, 20391, 344, 2017, 3881, 4694, 12780, 10510, 523, 585, 7214, 185, 554, 7688, 276, 254, 5151, 13, 4451, 317, 254, 16135, 280, 254, 7214, 280, 254, 4892, 13, 185, 185, 5127, 440, 21598, 1, 185, 50, 577, 379, 1748, 782, 461, 8443, 9474, 13, 185, 5127, 440, 21598, 1, 207, 185, 19655, 327, 254, 2547, 11, 207, 185, 9875, 6270, 1208, 280, 254, 2547, 8507, 43, 378, 14204, 412, 9961, 8472, 185, 11972, 2942, 2547, 1208, 8507, 43, 1743, 8472, 185, 77, 767, 1523, 327, 254, 2547, 8507, 43, 9961, 8472, 185, 23861, 1064, 254, 2547, 317, 2842, 11, 185, 4968, 1064, 254, 2547, 317, 6288, 11, 185, 5456, 254, 2547, 438, 8143, 185, 477, 185, 185, 5127, 440, 14641, 1, 185, 21810, 21411, 11, 31131, 372, 440, 17, 19393, 19393, 1, 8507, 17, 16, 24, 22, 15, 1, 327, 254, 207, 16, 24, 22, 15, 4314, 8, 185, 19655, 280, 254, 1712, 2547, 11, 207, 185, 356, 26321, 335, 280, 254, 1712, 2547, 11, 185, 9875, 1208, 280, 254, 1712, 2547, 11, 185, 19464, 21411, 327, 254, 2612, 11, 185, 1984, 254, 2612, 438, 7226, 334, 19393, 19393, 12, 8213, 12, 7127, 650, 185, 1, 54, 1, 562, 254, 1712, 2547, 2103, 11, 440, 43, 1, 562, 653, 4726, 11, 185, 11695, 4054, 7226, 279, 254, 2612, 11, 185, 3267, 9054, 1396, 457, 254, 1712, 2547, 11, 185, 3267, 9054, 18012, 457, 254, 1712, 2547, 11, 185, 3267, 6206, 14986, 280, 254, 1712, 2547, 11, 185, 14565, 12, 3772, 2010, 9054, 1396, 457, 254, 1712, 2547, 11, 185, 14565, 12, 3772, 15343, 457, 254, 1712, 2547, 11, 185, 14565, 12, 3772, 2010, 6206, 14986, 280, 254, 1712, 2547, 11, 185, 6630, 8474, 1396, 457, 254, 1712, 2547, 11, 185, 6630, 8474, 18012, 457, 254, 1712, 2547, 11, 185, 6630, 5245, 14986, 280, 254, 1712, 2547, 11, 185, 2959, 4630, 11435, 5740, 457, 254, 1712, 2547, 11, 185, 1551, 4630, 11435, 5740, 457, 254, 1712, 2547, 11, 185, 11695, 11435, 5740, 457, 254, 1712, 2547, 11, 185, 468, 1923, 457, 254, 1712, 2547, 11, 185, 7537, 909, 457, 254, 1712, 2547, 11, 185, 28835, 457, 254, 1712, 2547, 11, 185, 788, 17396, 457, 254, 1712, 2547, 11, 185, 28200, 3931, 2724, 457, 254, 1712, 2547, 19555, 185, 11695, 3472, 18605, 457, 254, 1712, 2547, 11, 185, 13289, 14, 10646, 14026, 327, 254, 1712, 2547, 11, 185, 72, 35, 280, 254, 2292, 2547, 11, 185, 356, 26321, 335, 280, 254, 2292, 2547, 11, 185, 9875, 1208, 280, 254, 2292, 2547, 11, 185, 10108, 393, 4283, 473, 254, 2292, 2547, 486, 82, 12422, 11, 185, 1, 54, 1, 562, 254, 2292, 2547, 2103, 11, 440, 43, 1, 562, 653, 4726, 11, 185, 3267, 9054, 1396, 457, 254, 2292, 2547, 11, 185, 3267, 9054, 18012, 457, 254, 2292, 2547, 11, 185, 3267, 6206, 14986, 280, 254, 2292, 2547, 11, 185, 14565, 12, 3772, 2010, 9054, 1396, 457, 254, 2292, 2547, 11, 185, 14565, 12, 3772, 15343, 457, 254, 2292, 2547, 11, 185, 14565, 12, 3772, 2010, 6206, 14986, 280, 254, 2292, 2547, 11, 185, 6630, 8474, 1396, 457, 254, 2292, 2547, 11, 185, 6630, 8474, 18012, 457, 254, 2292, 2547, 11, 185, 6630, 5245, 14986, 280, 254, 2292, 2547, 11, 185, 2959, 4630, 11435, 5740, 457, 254, 2292, 2547, 11, 185, 1551, 4630, 11435, 5740, 457, 254, 2292, 2547, 11, 185, 11695, 11435, 5740, 457, 254, 2292, 2547, 11, 185, 468, 1923, 457, 254, 2292, 2547, 11, 185, 7537, 909, 457, 254, 2292, 2547, 11, 185, 28835, 457, 254, 2292, 2547, 11, 185, 788, 17396, 457, 254, 2292, 2547, 11, 185, 28200, 3931, 2724, 457, 254, 2292, 2547, 11, 185, 11695, 3472, 18605, 457, 254, 2292, 2547, 11, 185, 13289, 14, 10646, 14026, 327, 254, 2292, 2547, 11, 185, 15367, 980, 3192, 3905, 317, 2315, 334, 16, 405, 7589, 11, 207, 15, 405, 2357, 650, 185, 13388, 4314, 409, 1530, 23836, 11, 185, 477, 185, 185, 5127, 440, 1156, 62, 16204, 1, 185, 50, 577, 379, 4577, 13024, 11, 12144, 276, 254, 2612, 2365, 3752, 2612, 62, 304, 13, 185, 13403, 11866, 15787, 5787, 7449, 30862, 440, 1156, 62, 16204, 1, 334, 185, 19464, 2612, 21411, 11, 12050, 1975, 3812, 473, 2612, 2365, 185, 275, 6006, 21411, 185, 5816, 2547, 21411, 185, 5816, 2547, 31593, 335, 185, 5816, 2547, 3775, 185, 12168, 279, 254, 7416, 457, 254, 1712, 2547, 185, 9353, 5504, 3472, 457, 254, 1712, 2547, 185, 7212, 2963, 3472, 457, 254, 1712, 2547, 185, 17819, 370, 2012, 457, 254, 1712, 2547, 185, 7675, 280, 2012, 4177, 207, 185, 7675, 280, 2591, 254, 8129, 438, 16538, 185, 5816, 2547, 1936, 17396, 185, 11695, 1936, 17396, 457, 254, 1712, 2547, 185, 5816, 2547, 11435, 5740, 185, 12168, 838, 1936, 17396, 457, 254, 1712, 2547, 185, 11507, 2547, 21411, 185, 11507, 2547, 31593, 335, 185, 12168, 279, 254, 7416, 457, 254, 2292, 2547, 185, 9353, 5504, 3472, 457, 254, 2292, 2547, 185, 7212, 2963, 3472, 457, 254, 2292, 2547, 185, 17819, 370, 2012, 457, 254, 2292, 2547, 185, 11507, 2547, 1936, 17396, 185, 11695, 1936, 17396, 457, 254, 2292, 2547, 185, 11507, 2547, 11435, 5740, 185, 12168, 838, 1936, 17396, 457, 254, 2292, 2547, 185, 477, 185, 185, 185, 7605, 387, 885, 254, 4761, 280, 254, 2365, 344, 417, 4362, 276, 3495, 254, 3881, 4694, 5151, 11, 14843, 457, 929, 281, 11, 533, 441, 2816, 274, 11543, 13, 185, 185, 1459, 2194, 11, 185, 6522, 25, 185, 1, 2628, 317, 254, 1093, 3472, 254, 10851, 14204, 412, 9961, 463, 2634, 18605, 429, 1712, 1956, 185, 6522, 25, 185, 14641, 185, 185, 6522, 25, 185, 1, 15575, 9474, 417, 6288, 279, 254, 1967, 280, 8700, 1956, 185, 6231, 547, 25, 185, 21598, 185, 185, 4397, 25, 185, 1, 15575, 2547, 658, 254, 7495, 1594, 280, 2547, 1936, 17396, 279, 274, 2292, 2612, 1956, 185, 6522, 25, 185, 1156, 62, 16204, 185, 185, 4397, 25, 185, 1, 2628, 438, 254, 5126, 1594, 280, 4299, 9351, 3472, 18605, 457, 254, 10851, 14204, 412, 9961, 279, 1712, 19998, 2310, 254, 207, 17, 15, 17, 15, 4314, 1956, 185, 6522, 25, 185, 14641, 11, 746, 62, 16204, 185, 185, 4888, 317, 254, 3092, 25, 185, 2808, 1311, 3212, 3472, 1213, 254, 11738, 21915, 82, 8129, 2310, 254, 207, 16, 24, 24, 21, 4314, 30, 185, 51, 2368, 25, 185, 3204, 14641, 3676], 'attention_mask': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': [-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32014, 32013, 2042, 417, 274, 20391, 344, 2017, 3881, 4694, 12780, 10510, 523, 585, 7214, 185, 554, 7688, 276, 254, 5151, 13, 4451, 317, 254, 16135, 280, 254, 7214, 280, 254, 4892, 13, 185, 185, 5127, 440, 21598, 1, 185, 50, 577, 379, 1748, 782, 461, 8443, 9474, 13, 185, 5127, 440, 21598, 1, 207, 185, 19655, 327, 254, 2547, 11, 207, 185, 9875, 6270, 1208, 280, 254, 2547, 8507, 43, 378, 14204, 412, 9961, 8472, 185, 11972, 2942, 2547, 1208, 8507, 43, 1743, 8472, 185, 77, 767, 1523, 327, 254, 2547, 8507, 43, 9961, 8472, 185, 23861, 1064, 254, 2547, 317, 2842, 11, 185, 4968, 1064, 254, 2547, 317, 6288, 11, 185, 5456, 254, 2547, 438, 8143, 185, 477, 185, 185, 5127, 440, 14641, 1, 185, 21810, 21411, 11, 31131, 372, 440, 17, 19393, 19393, 1, 8507, 17, 16, 24, 22, 15, 1, 327, 254, 207, 16, 24, 22, 15, 4314, 8, 185, 19655, 280, 254, 1712, 2547, 11, 207, 185, 356, 26321, 335, 280, 254, 1712, 2547, 11, 185, 9875, 1208, 280, 254, 1712, 2547, 11, 185, 19464, 21411, 327, 254, 2612, 11, 185, 1984, 254, 2612, 438, 7226, 334, 19393, 19393, 12, 8213, 12, 7127, 650, 185, 1, 54, 1, 562, 254, 1712, 2547, 2103, 11, 440, 43, 1, 562, 653, 4726, 11, 185, 11695, 4054, 7226, 279, 254, 2612, 11, 185, 3267, 9054, 1396, 457, 254, 1712, 2547, 11, 185, 3267, 9054, 18012, 457, 254, 1712, 2547, 11, 185, 3267, 6206, 14986, 280, 254, 1712, 2547, 11, 185, 14565, 12, 3772, 2010, 9054, 1396, 457, 254, 1712, 2547, 11, 185, 14565, 12, 3772, 15343, 457, 254, 1712, 2547, 11, 185, 14565, 12, 3772, 2010, 6206, 14986, 280, 254, 1712, 2547, 11, 185, 6630, 8474, 1396, 457, 254, 1712, 2547, 11, 185, 6630, 8474, 18012, 457, 254, 1712, 2547, 11, 185, 6630, 5245, 14986, 280, 254, 1712, 2547, 11, 185, 2959, 4630, 11435, 5740, 457, 254, 1712, 2547, 11, 185, 1551, 4630, 11435, 5740, 457, 254, 1712, 2547, 11, 185, 11695, 11435, 5740, 457, 254, 1712, 2547, 11, 185, 468, 1923, 457, 254, 1712, 2547, 11, 185, 7537, 909, 457, 254, 1712, 2547, 11, 185, 28835, 457, 254, 1712, 2547, 11, 185, 788, 17396, 457, 254, 1712, 2547, 11, 185, 28200, 3931, 2724, 457, 254, 1712, 2547, 19555, 185, 11695, 3472, 18605, 457, 254, 1712, 2547, 11, 185, 13289, 14, 10646, 14026, 327, 254, 1712, 2547, 11, 185, 72, 35, 280, 254, 2292, 2547, 11, 185, 356, 26321, 335, 280, 254, 2292, 2547, 11, 185, 9875, 1208, 280, 254, 2292, 2547, 11, 185, 10108, 393, 4283, 473, 254, 2292, 2547, 486, 82, 12422, 11, 185, 1, 54, 1, 562, 254, 2292, 2547, 2103, 11, 440, 43, 1, 562, 653, 4726, 11, 185, 3267, 9054, 1396, 457, 254, 2292, 2547, 11, 185, 3267, 9054, 18012, 457, 254, 2292, 2547, 11, 185, 3267, 6206, 14986, 280, 254, 2292, 2547, 11, 185, 14565, 12, 3772, 2010, 9054, 1396, 457, 254, 2292, 2547, 11, 185, 14565, 12, 3772, 15343, 457, 254, 2292, 2547, 11, 185, 14565, 12, 3772, 2010, 6206, 14986, 280, 254, 2292, 2547, 11, 185, 6630, 8474, 1396, 457, 254, 2292, 2547, 11, 185, 6630, 8474, 18012, 457, 254, 2292, 2547, 11, 185, 6630, 5245, 14986, 280, 254, 2292, 2547, 11, 185, 2959, 4630, 11435, 5740, 457, 254, 2292, 2547, 11, 185, 1551, 4630, 11435, 5740, 457, 254, 2292, 2547, 11, 185, 11695, 11435, 5740, 457, 254, 2292, 2547, 11, 185, 468, 1923, 457, 254, 2292, 2547, 11, 185, 7537, 909, 457, 254, 2292, 2547, 11, 185, 28835, 457, 254, 2292, 2547, 11, 185, 788, 17396, 457, 254, 2292, 2547, 11, 185, 28200, 3931, 2724, 457, 254, 2292, 2547, 11, 185, 11695, 3472, 18605, 457, 254, 2292, 2547, 11, 185, 13289, 14, 10646, 14026, 327, 254, 2292, 2547, 11, 185, 15367, 980, 3192, 3905, 317, 2315, 334, 16, 405, 7589, 11, 207, 15, 405, 2357, 650, 185, 13388, 4314, 409, 1530, 23836, 11, 185, 477, 185, 185, 5127, 440, 1156, 62, 16204, 1, 185, 50, 577, 379, 4577, 13024, 11, 12144, 276, 254, 2612, 2365, 3752, 2612, 62, 304, 13, 185, 13403, 11866, 15787, 5787, 7449, 30862, 440, 1156, 62, 16204, 1, 334, 185, 19464, 2612, 21411, 11, 12050, 1975, 3812, 473, 2612, 2365, 185, 275, 6006, 21411, 185, 5816, 2547, 21411, 185, 5816, 2547, 31593, 335, 185, 5816, 2547, 3775, 185, 12168, 279, 254, 7416, 457, 254, 1712, 2547, 185, 9353, 5504, 3472, 457, 254, 1712, 2547, 185, 7212, 2963, 3472, 457, 254, 1712, 2547, 185, 17819, 370, 2012, 457, 254, 1712, 2547, 185, 7675, 280, 2012, 4177, 207, 185, 7675, 280, 2591, 254, 8129, 438, 16538, 185, 5816, 2547, 1936, 17396, 185, 11695, 1936, 17396, 457, 254, 1712, 2547, 185, 5816, 2547, 11435, 5740, 185, 12168, 838, 1936, 17396, 457, 254, 1712, 2547, 185, 11507, 2547, 21411, 185, 11507, 2547, 31593, 335, 185, 12168, 279, 254, 7416, 457, 254, 2292, 2547, 185, 9353, 5504, 3472, 457, 254, 2292, 2547, 185, 7212, 2963, 3472, 457, 254, 2292, 2547, 185, 17819, 370, 2012, 457, 254, 2292, 2547, 185, 11507, 2547, 1936, 17396, 185, 11695, 1936, 17396, 457, 254, 2292, 2547, 185, 11507, 2547, 11435, 5740, 185, 12168, 838, 1936, 17396, 457, 254, 2292, 2547, 185, 477, 185, 185, 185, 7605, 387, 885, 254, 4761, 280, 254, 2365, 344, 417, 4362, 276, 3495, 254, 3881, 4694, 5151, 11, 14843, 457, 929, 281, 11, 533, 441, 2816, 274, 11543, 13, 185, 185, 1459, 2194, 11, 185, 6522, 25, 185, 1, 2628, 317, 254, 1093, 3472, 254, 10851, 14204, 412, 9961, 463, 2634, 18605, 429, 1712, 1956, 185, 6522, 25, 185, 14641, 185, 185, 6522, 25, 185, 1, 15575, 9474, 417, 6288, 279, 254, 1967, 280, 8700, 1956, 185, 6231, 547, 25, 185, 21598, 185, 185, 4397, 25, 185, 1, 15575, 2547, 658, 254, 7495, 1594, 280, 2547, 1936, 17396, 279, 274, 2292, 2612, 1956, 185, 6522, 25, 185, 1156, 62, 16204, 185, 185, 4397, 25, 185, 1, 2628, 438, 254, 5126, 1594, 280, 4299, 9351, 3472, 18605, 457, 254, 10851, 14204, 412, 9961, 279, 1712, 19998, 2310, 254, 207, 17, 15, 17, 15, 4314, 1956, 185, 6522, 25, 185, 14641, 11, 746, 62, 16204, 185, 185, 4888, 317, 254, 3092, 25, 185, 2808, 1311, 3212, 3472, 1213, 254, 11738, 21915, 82, 8129, 2310, 254, 207, 16, 24, 24, 21, 4314, 30, 185, 51, 2368, 25, 185, 3204, 14641, 3676]}\n"
          ]
        }
      ],
      "source": [
        "\n",
        "\n",
        "# Apply formatting\n",
        "tokenized_dataset = dataset.map(\n",
        "    lambda x: format_deepseek_chat(x, tokenizer),\n",
        "    remove_columns=[\"natural_query\", \"tables\"]\n",
        ")\n",
        "\n",
        "# Split into train/validation\n",
        "split = int(0.9 * len(tokenized_dataset))  # 90% train, 10% validation\n",
        "train_dataset = tokenized_dataset.select(range(split))\n",
        "val_dataset = tokenized_dataset.select(range(split, len(tokenized_dataset)))\n",
        "\n",
        "print(len(train_dataset))\n",
        "print(len(val_dataset))\n",
        "\n",
        "for v in val_dataset:\n",
        "    print(v)\n",
        "    break"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "id": "8890a657",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8890a657",
        "outputId": "95b9971d-d446-432b-9faa-baa1c060d66a"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "trainable params: 14,991,360 || all params: 1,361,463,296 || trainable%: 1.1011\n"
          ]
        }
      ],
      "source": [
        "# Define LoRA configuration\n",
        "lora_config = LoraConfig(\n",
        "    r=16,  # Rank of LoRA matrices (adjust for memory vs. accuracy)\n",
        "    lora_alpha=32,  # Scaling factor\n",
        "    lora_dropout=0.0,  # Dropout for regularization\n",
        "    bias=\"none\",\n",
        "    task_type=TaskType.CAUSAL_LM,\n",
        "    target_modules=[\n",
        "        \"q_proj\",\n",
        "        \"k_proj\",\n",
        "        \"v_proj\",\n",
        "        \"o_proj\",\n",
        "        \"gate_proj\",\n",
        "        \"up_proj\",\n",
        "        \"down_proj\"\n",
        "    ]\n",
        ")\n",
        "\n",
        "# Wrap model with LoRA adapters\n",
        "model = get_peft_model(model, lora_config)\n",
        "model = model.to(device)\n",
        "model.print_trainable_parameters()  # Show trainable parameters count"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "id": "d9508451",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "d9508451",
        "outputId": "d004fa38-78a0-49ee-eed5-bbc6373ccae2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-11-319f42a4ed7b>:21: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.\n",
            "  trainer = Trainer(\n",
            "No label_names provided for model class `PeftModelForCausalLM`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.\n"
          ]
        }
      ],
      "source": [
        "training_args = TrainingArguments(\n",
        "    output_dir=MODEL_DIR,\n",
        "    eval_strategy=\"epoch\",  # Evaluate at the end of each epoch\n",
        "    save_strategy=\"epoch\",  # Save model every epoch\n",
        "    per_device_train_batch_size=1,  # LoRA allows higher batch size\n",
        "    per_device_eval_batch_size=1,\n",
        "    gradient_accumulation_steps=16,\n",
        "    num_train_epochs=10,  # Increase if needed\n",
        "    learning_rate=5e-5,  # Higher LR since we're only training LoRA layers\n",
        "    weight_decay=0.001,\n",
        "    logging_steps=50,  # Print loss every 50 steps\n",
        "    save_total_limit=2,  # Keep last 4 checkpoints\n",
        "    bf16=True if torch.cuda.is_available() else False,\n",
        "    push_to_hub=False,\n",
        "    load_best_model_at_end=True,\n",
        "    metric_for_best_model=\"eval_loss\",\n",
        "    greater_is_better=False\n",
        ")\n",
        "\n",
        "# Trainer setup\n",
        "trainer = Trainer(\n",
        "    model=model,\n",
        "    args=training_args,\n",
        "    train_dataset=train_dataset,\n",
        "    eval_dataset=val_dataset,\n",
        "    tokenizer=tokenizer,\n",
        "    callbacks=[EarlyStoppingCallback(early_stopping_patience=2)]\n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "b0ff5278",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 214
        },
        "id": "b0ff5278",
        "outputId": "07e6446f-c680-4532-caad-d62a7d3edd6d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: Using wandb-core as the SDK backend.  Please refer to https://wandb.me/wandb-core for more information.\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mlicesma\u001b[0m (\u001b[33mlicesma-usc\u001b[0m) to \u001b[32mhttps://api.wandb.ai\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "Tracking run with wandb version 0.19.9"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "Run data is saved locally in <code>/content/wandb/run-20250420_174906-5ypbflqe</code>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "Syncing run <strong><a href='https://wandb.ai/licesma-usc/huggingface/runs/5ypbflqe' target=\"_blank\">/content/drive/MyDrive/sql_gen/dyn_rag_test</a></strong> to <a href='https://wandb.ai/licesma-usc/huggingface' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              " View project at <a href='https://wandb.ai/licesma-usc/huggingface' target=\"_blank\">https://wandb.ai/licesma-usc/huggingface</a>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              " View run at <a href='https://wandb.ai/licesma-usc/huggingface/runs/5ypbflqe' target=\"_blank\">https://wandb.ai/licesma-usc/huggingface/runs/5ypbflqe</a>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='4' max='580' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [  4/580 00:11 < 54:56, 0.17 it/s, Epoch 0.05/10]\n",
              "    </div>\n",
              "    <table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              " <tr style=\"text-align: left;\">\n",
              "      <th>Epoch</th>\n",
              "      <th>Training Loss</th>\n",
              "      <th>Validation Loss</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "  </tbody>\n",
              "</table><p>"
            ]
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Run training\n",
        "trainer.train()\n",
        "\n",
        "# Merge LoRA adapters with the base model before saving\n",
        "model = model.merge_and_unload()\n",
        "model.save_pretrained(MODEL_DIR)\n",
        "tokenizer.save_pretrained(MODEL_DIR)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "# Prepare query with the same prompt\n",
        "input_text = \"How many points do the Los Angeles Lakers average at home?\"\n",
        "message = [{'role': 'user', 'content': input_prompt + input_text}]\n",
        "inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors=\"pt\").to(model.device)\n",
        "\n",
        "# Generate Tables\n",
        "outputs = model.generate(\n",
        "    inputs,\n",
        "    max_new_tokens=256,\n",
        ")\n",
        "model_output = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)\n",
        "\n",
        "print(\"Generated Tables:\", model_output)"
      ],
      "metadata": {
        "id": "J7qO7FE73i40"
      },
      "id": "J7qO7FE73i40",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import sqlite3 as sql\n",
        "\n",
        "prompt_length = len(input_prompt)\n",
        "\n",
        "print(prompt_length)\n",
        "\n",
        "# Create connection to sqlite3 database\n",
        "connection = sql.connect(read_path('nba-data/nba.sqlite'))\n",
        "cursor = connection.cursor()\n",
        "\n",
        "for v in val_dataset:\n",
        "    full_example = tokenizer.decode(v[\"input_ids\"], skip_special_tokens=True)\n",
        "    user_prompt = full_example[:prompt_length]\n",
        "    question, tables = full_example[prompt_length:].split(\"Tables:\\n\")\n",
        "    print(question)\n",
        "    print(tables)\n",
        "    break\n",
        ""
      ],
      "metadata": {
        "id": "kwHMVyQa3n89"
      },
      "id": "kwHMVyQa3n89",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def extract_tables_from_string(s):\n",
        "    keywords = {\"game\", \"team\", \"other_stats\"}\n",
        "    found = {k for k in keywords if k in s}\n",
        "    return found"
      ],
      "metadata": {
        "id": "LhiHqAaB9uE4"
      },
      "id": "LhiHqAaB9uE4",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "Kdd8nxWD9txh"
      },
      "id": "Kdd8nxWD9txh"
    },
    {
      "cell_type": "code",
      "source": [
        "def compare_table_lists(actual_tables, generated_tables):\n",
        "    actual_set = extract_tables_from_string(actual_tables)\n",
        "    generated_set = extract_tables_from_string(generated_tables)\n",
        "\n",
        "    # Check if they match\n",
        "    return generated_set == actual_set"
      ],
      "metadata": {
        "id": "KjAXaUgp4TfY"
      },
      "id": "KjAXaUgp4TfY",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "num_sql_matched = 0\n",
        "\n",
        "first_actual = []\n",
        "first_model = []\n",
        "print(\"Evaluating...\")\n",
        "for v in val_dataset:\n",
        "    full_example = tokenizer.decode(v[\"input_ids\"], skip_special_tokens=True)\n",
        "    user_prompt = full_example[:prompt_length]\n",
        "    question, training_tables = full_example[prompt_length:].split(\"Tables:\\n\")\n",
        "    #print(question)\n",
        "    #print(sql_query)\n",
        "\n",
        "    # Obtain model output\n",
        "    message = [{'role': 'user', 'content': input_prompt + question}]\n",
        "    inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors=\"pt\").to(model.device)\n",
        "\n",
        "    # Generate SQL query\n",
        "    outputs = model.generate(\n",
        "        inputs,\n",
        "        max_new_tokens=256,\n",
        "        pad_token_id=tokenizer.eos_token_id,\n",
        "    )\n",
        "    model_output = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)\n",
        "    after_last_colon = model_output.rsplit(\":\", 1)[-1]\n",
        "    tables_string = after_last_colon.replace('\\n', '').replace('\\r', '')\n",
        "    #print(\"Training tables:\", training_tables)\n",
        "    #print(\"Model tables:\", tables_string.split(\" \"))\n",
        "    first_actual = training_tables\n",
        "    first_model = tables_string\n",
        "    result = compare_table_lists(training_tables, tables_string)\n",
        "    if result:\n",
        "        num_sql_matched += 1\n",
        "\n",
        "print(\"Accuracy :\", num_sql_matched/len(val_dataset))\n",
        "\n"
      ],
      "metadata": {
        "id": "8h7bpMML6G6v"
      },
      "id": "8h7bpMML6G6v",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "num_sql_matched = 0\n",
        "\n",
        "first_actual = []\n",
        "first_model = []\n",
        "print(\"Evaluating...\")\n",
        "for v in val_dataset:\n",
        "    full_example = tokenizer.decode(v[\"input_ids\"], skip_special_tokens=True)\n",
        "    user_prompt = full_example[:prompt_length]\n",
        "    question, training_tables = full_example[prompt_length:].split(\"Tables:\\n\")\n",
        "    #print(question)\n",
        "    #print(sql_query)\n",
        "\n",
        "    # Obtain model output\n",
        "    message = [{'role': 'user', 'content': input_prompt + question}]\n",
        "    inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors=\"pt\").to(model.device)\n",
        "\n",
        "    # Generate SQL query\n",
        "    outputs = model.generate(\n",
        "        inputs,\n",
        "        max_new_tokens=256,\n",
        "        pad_token_id=tokenizer.eos_token_id,\n",
        "    )\n",
        "    model_output = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)\n",
        "    after_last_colon = model_output.rsplit(\":\", 1)[-1]\n",
        "    tables_string = after_last_colon.replace('\\n', '').replace('\\r', '')\n",
        "    #print(\"Training tables:\", training_tables)\n",
        "    #print(\"Model tables:\", tables_string.split(\" \"))\n",
        "    first_actual = training_tables\n",
        "    first_model = tables_string\n",
        "    result = compare_table_lists(training_tables, tables_string)\n",
        "    if result:\n",
        "        num_sql_matched += 1\n",
        "\n",
        "print(\"Accuracy :\", num_sql_matched/len(val_dataset))\n",
        "\n"
      ],
      "metadata": {
        "id": "CoJeZ4FoUMp_"
      },
      "execution_count": null,
      "outputs": [],
      "id": "CoJeZ4FoUMp_"
    },
    {
      "cell_type": "code",
      "source": [
        "model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype=torch.bfloat16, device_map=device)\n",
        "tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)\n"
      ],
      "metadata": {
        "id": "lNG1joS3T8DN"
      },
      "id": "lNG1joS3T8DN",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.11.11"
    },
    "colab": {
      "provenance": [],
      "gpuType": "A100"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "9200f1303f124bddaa6114cdf0f5f878": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_17ddbb74e1764f37b8d34c311fae200c",
              "IPY_MODEL_ef732739334b4ac593fd665e01cd83c1",
              "IPY_MODEL_949ee3d1a9cd4060864dec5d4283ef2c"
            ],
            "layout": "IPY_MODEL_b98629e053674527aacca899ab7f11a9"
          }
        },
        "17ddbb74e1764f37b8d34c311fae200c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_84cc47dc70864bf3aa7599c06eb13c51",
            "placeholder": "​",
            "style": "IPY_MODEL_5d711bb927024d8d9f9b8bb685d6f388",
            "value": "Fetching 37 files: 100%"
          }
        },
        "ef732739334b4ac593fd665e01cd83c1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3b80c66e0f384c45ab4187301599fab2",
            "max": 37,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_db6a23e658a34722a8f22505c6ace7b4",
            "value": 37
          }
        },
        "949ee3d1a9cd4060864dec5d4283ef2c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_7751defbc4534d518d9e923b9019aa8b",
            "placeholder": "​",
            "style": "IPY_MODEL_fe6352bce22a40e7a936e7f90313bd02",
            "value": " 37/37 [00:00&lt;00:00, 3657.54it/s]"
          }
        },
        "b98629e053674527aacca899ab7f11a9": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "84cc47dc70864bf3aa7599c06eb13c51": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "5d711bb927024d8d9f9b8bb685d6f388": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "3b80c66e0f384c45ab4187301599fab2": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "db6a23e658a34722a8f22505c6ace7b4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "7751defbc4534d518d9e923b9019aa8b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fe6352bce22a40e7a936e7f90313bd02": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "68ff2fc00bd041e7b79a811e3de1e596": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_4c41e81bcd254df7b1265206a5a6b40b",
              "IPY_MODEL_1a8c093fccbb437db6e0390a920f5cc5",
              "IPY_MODEL_e11d04a9d22a4229922e3eb4e3eb6466"
            ],
            "layout": "IPY_MODEL_5d89a5574a3d4a8993e6dca78d406d2d"
          }
        },
        "4c41e81bcd254df7b1265206a5a6b40b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_dd24270dc07942a6972fbfaf58129989",
            "placeholder": "​",
            "style": "IPY_MODEL_643903cd7a5b4a52a4687ec38eb8c4dc",
            "value": "Map: 100%"
          }
        },
        "1a8c093fccbb437db6e0390a920f5cc5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_13ae11c314664c44ae18d35cf57a1334",
            "max": 1044,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_e68cfd05ba994a34b93107d2eab82ad3",
            "value": 1044
          }
        },
        "e11d04a9d22a4229922e3eb4e3eb6466": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ea283e7e8b234519b881c562b7eb01d3",
            "placeholder": "​",
            "style": "IPY_MODEL_1ec5329ea0434df4b74d0f311e016c3e",
            "value": " 1044/1044 [00:10&lt;00:00, 43.90 examples/s]"
          }
        },
        "5d89a5574a3d4a8993e6dca78d406d2d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "dd24270dc07942a6972fbfaf58129989": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "643903cd7a5b4a52a4687ec38eb8c4dc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "13ae11c314664c44ae18d35cf57a1334": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e68cfd05ba994a34b93107d2eab82ad3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "ea283e7e8b234519b881c562b7eb01d3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1ec5329ea0434df4b74d0f311e016c3e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}