Hugging Face's logo

Spaces:
Rathgeberj
/
CS-UY4613Project
Runtime error

App Files Community
Jeffrey Rathgeber Jr commited on
Commit
f143154
·
unverified ·
1 Parent(s): e5de86c

Delete TrainingAlgo.ipynb

Browse files
Files changed (1) hide show
  1. TrainingAlgo.ipynb +0 -2406
TrainingAlgo.ipynb DELETED
@@ -1,2406 +0,0 @@
1
- {
2
- "nbformat": 4,
3
- "nbformat_minor": 0,
4
- "metadata": {
5
- "colab": {
6
- "provenance": []
7
- },
8
- "kernelspec": {
9
- "name": "python3",
10
- "display_name": "Python 3"
11
- },
12
- "language_info": {
13
- "name": "python"
14
- },
15
- "widgets": {
16
- "application/vnd.jupyter.widget-state+json": {
17
- "9972abac7caf4cc6b0d98071fd7b2e05": {
18
- "model_module": "@jupyter-widgets/controls",
19
- "model_name": "HBoxModel",
20
- "model_module_version": "1.5.0",
21
- "state": {
22
- "_dom_classes": [],
23
- "_model_module": "@jupyter-widgets/controls",
24
- "_model_module_version": "1.5.0",
25
- "_model_name": "HBoxModel",
26
- "_view_count": null,
27
- "_view_module": "@jupyter-widgets/controls",
28
- "_view_module_version": "1.5.0",
29
- "_view_name": "HBoxView",
30
- "box_style": "",
31
- "children": [
32
- "IPY_MODEL_b53fb6f416d8458bb0875cbace688913",
33
- "IPY_MODEL_a25b06ec34a44529bd5bd686a9a381e5",
34
- "IPY_MODEL_52da3fef70074ddf95a3b257dcf4b100"
35
- ],
36
- "layout": "IPY_MODEL_932e4324d43346e48c85af3e5d5b45c1"
37
- }
38
- },
39
- "b53fb6f416d8458bb0875cbace688913": {
40
- "model_module": "@jupyter-widgets/controls",
41
- "model_name": "HTMLModel",
42
- "model_module_version": "1.5.0",
43
- "state": {
44
- "_dom_classes": [],
45
- "_model_module": "@jupyter-widgets/controls",
46
- "_model_module_version": "1.5.0",
47
- "_model_name": "HTMLModel",
48
- "_view_count": null,
49
- "_view_module": "@jupyter-widgets/controls",
50
- "_view_module_version": "1.5.0",
51
- "_view_name": "HTMLView",
52
- "description": "",
53
- "description_tooltip": null,
54
- "layout": "IPY_MODEL_13d5e786f6294da2b6e5d90ca06c8593",
55
- "placeholder": "​",
56
- "style": "IPY_MODEL_bbfa5943bc1c41dbaf3a2ef89ac8d0b3",
57
- "value": "Downloading (…)okenizer_config.json: 100%"
58
- }
59
- },
60
- "a25b06ec34a44529bd5bd686a9a381e5": {
61
- "model_module": "@jupyter-widgets/controls",
62
- "model_name": "FloatProgressModel",
63
- "model_module_version": "1.5.0",
64
- "state": {
65
- "_dom_classes": [],
66
- "_model_module": "@jupyter-widgets/controls",
67
- "_model_module_version": "1.5.0",
68
- "_model_name": "FloatProgressModel",
69
- "_view_count": null,
70
- "_view_module": "@jupyter-widgets/controls",
71
- "_view_module_version": "1.5.0",
72
- "_view_name": "ProgressView",
73
- "bar_style": "success",
74
- "description": "",
75
- "description_tooltip": null,
76
- "layout": "IPY_MODEL_3ce089610ec446c19db3bae1baa45d7a",
77
- "max": 28,
78
- "min": 0,
79
- "orientation": "horizontal",
80
- "style": "IPY_MODEL_bcf06ca3212c43e0a5db7e7d4ea01375",
81
- "value": 28
82
- }
83
- },
84
- "52da3fef70074ddf95a3b257dcf4b100": {
85
- "model_module": "@jupyter-widgets/controls",
86
- "model_name": "HTMLModel",
87
- "model_module_version": "1.5.0",
88
- "state": {
89
- "_dom_classes": [],
90
- "_model_module": "@jupyter-widgets/controls",
91
- "_model_module_version": "1.5.0",
92
- "_model_name": "HTMLModel",
93
- "_view_count": null,
94
- "_view_module": "@jupyter-widgets/controls",
95
- "_view_module_version": "1.5.0",
96
- "_view_name": "HTMLView",
97
- "description": "",
98
- "description_tooltip": null,
99
- "layout": "IPY_MODEL_aab6a478cec84b25a29bc0ed4ee2aaac",
100
- "placeholder": "​",
101
- "style": "IPY_MODEL_3e6f987e297b4a2b8f3eb1b12b4b67af",
102
- "value": " 28.0/28.0 [00:00<00:00, 1.28kB/s]"
103
- }
104
- },
105
- "932e4324d43346e48c85af3e5d5b45c1": {
106
- "model_module": "@jupyter-widgets/base",
107
- "model_name": "LayoutModel",
108
- "model_module_version": "1.2.0",
109
- "state": {
110
- "_model_module": "@jupyter-widgets/base",
111
- "_model_module_version": "1.2.0",
112
- "_model_name": "LayoutModel",
113
- "_view_count": null,
114
- "_view_module": "@jupyter-widgets/base",
115
- "_view_module_version": "1.2.0",
116
- "_view_name": "LayoutView",
117
- "align_content": null,
118
- "align_items": null,
119
- "align_self": null,
120
- "border": null,
121
- "bottom": null,
122
- "display": null,
123
- "flex": null,
124
- "flex_flow": null,
125
- "grid_area": null,
126
- "grid_auto_columns": null,
127
- "grid_auto_flow": null,
128
- "grid_auto_rows": null,
129
- "grid_column": null,
130
- "grid_gap": null,
131
- "grid_row": null,
132
- "grid_template_areas": null,
133
- "grid_template_columns": null,
134
- "grid_template_rows": null,
135
- "height": null,
136
- "justify_content": null,
137
- "justify_items": null,
138
- "left": null,
139
- "margin": null,
140
- "max_height": null,
141
- "max_width": null,
142
- "min_height": null,
143
- "min_width": null,
144
- "object_fit": null,
145
- "object_position": null,
146
- "order": null,
147
- "overflow": null,
148
- "overflow_x": null,
149
- "overflow_y": null,
150
- "padding": null,
151
- "right": null,
152
- "top": null,
153
- "visibility": null,
154
- "width": null
155
- }
156
- },
157
- "13d5e786f6294da2b6e5d90ca06c8593": {
158
- "model_module": "@jupyter-widgets/base",
159
- "model_name": "LayoutModel",
160
- "model_module_version": "1.2.0",
161
- "state": {
162
- "_model_module": "@jupyter-widgets/base",
163
- "_model_module_version": "1.2.0",
164
- "_model_name": "LayoutModel",
165
- "_view_count": null,
166
- "_view_module": "@jupyter-widgets/base",
167
- "_view_module_version": "1.2.0",
168
- "_view_name": "LayoutView",
169
- "align_content": null,
170
- "align_items": null,
171
- "align_self": null,
172
- "border": null,
173
- "bottom": null,
174
- "display": null,
175
- "flex": null,
176
- "flex_flow": null,
177
- "grid_area": null,
178
- "grid_auto_columns": null,
179
- "grid_auto_flow": null,
180
- "grid_auto_rows": null,
181
- "grid_column": null,
182
- "grid_gap": null,
183
- "grid_row": null,
184
- "grid_template_areas": null,
185
- "grid_template_columns": null,
186
- "grid_template_rows": null,
187
- "height": null,
188
- "justify_content": null,
189
- "justify_items": null,
190
- "left": null,
191
- "margin": null,
192
- "max_height": null,
193
- "max_width": null,
194
- "min_height": null,
195
- "min_width": null,
196
- "object_fit": null,
197
- "object_position": null,
198
- "order": null,
199
- "overflow": null,
200
- "overflow_x": null,
201
- "overflow_y": null,
202
- "padding": null,
203
- "right": null,
204
- "top": null,
205
- "visibility": null,
206
- "width": null
207
- }
208
- },
209
- "bbfa5943bc1c41dbaf3a2ef89ac8d0b3": {
210
- "model_module": "@jupyter-widgets/controls",
211
- "model_name": "DescriptionStyleModel",
212
- "model_module_version": "1.5.0",
213
- "state": {
214
- "_model_module": "@jupyter-widgets/controls",
215
- "_model_module_version": "1.5.0",
216
- "_model_name": "DescriptionStyleModel",
217
- "_view_count": null,
218
- "_view_module": "@jupyter-widgets/base",
219
- "_view_module_version": "1.2.0",
220
- "_view_name": "StyleView",
221
- "description_width": ""
222
- }
223
- },
224
- "3ce089610ec446c19db3bae1baa45d7a": {
225
- "model_module": "@jupyter-widgets/base",
226
- "model_name": "LayoutModel",
227
- "model_module_version": "1.2.0",
228
- "state": {
229
- "_model_module": "@jupyter-widgets/base",
230
- "_model_module_version": "1.2.0",
231
- "_model_name": "LayoutModel",
232
- "_view_count": null,
233
- "_view_module": "@jupyter-widgets/base",
234
- "_view_module_version": "1.2.0",
235
- "_view_name": "LayoutView",
236
- "align_content": null,
237
- "align_items": null,
238
- "align_self": null,
239
- "border": null,
240
- "bottom": null,
241
- "display": null,
242
- "flex": null,
243
- "flex_flow": null,
244
- "grid_area": null,
245
- "grid_auto_columns": null,
246
- "grid_auto_flow": null,
247
- "grid_auto_rows": null,
248
- "grid_column": null,
249
- "grid_gap": null,
250
- "grid_row": null,
251
- "grid_template_areas": null,
252
- "grid_template_columns": null,
253
- "grid_template_rows": null,
254
- "height": null,
255
- "justify_content": null,
256
- "justify_items": null,
257
- "left": null,
258
- "margin": null,
259
- "max_height": null,
260
- "max_width": null,
261
- "min_height": null,
262
- "min_width": null,
263
- "object_fit": null,
264
- "object_position": null,
265
- "order": null,
266
- "overflow": null,
267
- "overflow_x": null,
268
- "overflow_y": null,
269
- "padding": null,
270
- "right": null,
271
- "top": null,
272
- "visibility": null,
273
- "width": null
274
- }
275
- },
276
- "bcf06ca3212c43e0a5db7e7d4ea01375": {
277
- "model_module": "@jupyter-widgets/controls",
278
- "model_name": "ProgressStyleModel",
279
- "model_module_version": "1.5.0",
280
- "state": {
281
- "_model_module": "@jupyter-widgets/controls",
282
- "_model_module_version": "1.5.0",
283
- "_model_name": "ProgressStyleModel",
284
- "_view_count": null,
285
- "_view_module": "@jupyter-widgets/base",
286
- "_view_module_version": "1.2.0",
287
- "_view_name": "StyleView",
288
- "bar_color": null,
289
- "description_width": ""
290
- }
291
- },
292
- "aab6a478cec84b25a29bc0ed4ee2aaac": {
293
- "model_module": "@jupyter-widgets/base",
294
- "model_name": "LayoutModel",
295
- "model_module_version": "1.2.0",
296
- "state": {
297
- "_model_module": "@jupyter-widgets/base",
298
- "_model_module_version": "1.2.0",
299
- "_model_name": "LayoutModel",
300
- "_view_count": null,
301
- "_view_module": "@jupyter-widgets/base",
302
- "_view_module_version": "1.2.0",
303
- "_view_name": "LayoutView",
304
- "align_content": null,
305
- "align_items": null,
306
- "align_self": null,
307
- "border": null,
308
- "bottom": null,
309
- "display": null,
310
- "flex": null,
311
- "flex_flow": null,
312
- "grid_area": null,
313
- "grid_auto_columns": null,
314
- "grid_auto_flow": null,
315
- "grid_auto_rows": null,
316
- "grid_column": null,
317
- "grid_gap": null,
318
- "grid_row": null,
319
- "grid_template_areas": null,
320
- "grid_template_columns": null,
321
- "grid_template_rows": null,
322
- "height": null,
323
- "justify_content": null,
324
- "justify_items": null,
325
- "left": null,
326
- "margin": null,
327
- "max_height": null,
328
- "max_width": null,
329
- "min_height": null,
330
- "min_width": null,
331
- "object_fit": null,
332
- "object_position": null,
333
- "order": null,
334
- "overflow": null,
335
- "overflow_x": null,
336
- "overflow_y": null,
337
- "padding": null,
338
- "right": null,
339
- "top": null,
340
- "visibility": null,
341
- "width": null
342
- }
343
- },
344
- "3e6f987e297b4a2b8f3eb1b12b4b67af": {
345
- "model_module": "@jupyter-widgets/controls",
346
- "model_name": "DescriptionStyleModel",
347
- "model_module_version": "1.5.0",
348
- "state": {
349
- "_model_module": "@jupyter-widgets/controls",
350
- "_model_module_version": "1.5.0",
351
- "_model_name": "DescriptionStyleModel",
352
- "_view_count": null,
353
- "_view_module": "@jupyter-widgets/base",
354
- "_view_module_version": "1.2.0",
355
- "_view_name": "StyleView",
356
- "description_width": ""
357
- }
358
- },
359
- "3a52fbc3755a4323b749da73142e5871": {
360
- "model_module": "@jupyter-widgets/controls",
361
- "model_name": "HBoxModel",
362
- "model_module_version": "1.5.0",
363
- "state": {
364
- "_dom_classes": [],
365
- "_model_module": "@jupyter-widgets/controls",
366
- "_model_module_version": "1.5.0",
367
- "_model_name": "HBoxModel",
368
- "_view_count": null,
369
- "_view_module": "@jupyter-widgets/controls",
370
- "_view_module_version": "1.5.0",
371
- "_view_name": "HBoxView",
372
- "box_style": "",
373
- "children": [
374
- "IPY_MODEL_7b2019506d154d118134985ee7e8ea43",
375
- "IPY_MODEL_3a51d4dbd7654b9ab7b69a50605d29e9",
376
- "IPY_MODEL_c5dd0d556c9c486baaedf3ca54cef54a"
377
- ],
378
- "layout": "IPY_MODEL_3b40837351f44c0f92e3e5af55da3e21"
379
- }
380
- },
381
- "7b2019506d154d118134985ee7e8ea43": {
382
- "model_module": "@jupyter-widgets/controls",
383
- "model_name": "HTMLModel",
384
- "model_module_version": "1.5.0",
385
- "state": {
386
- "_dom_classes": [],
387
- "_model_module": "@jupyter-widgets/controls",
388
- "_model_module_version": "1.5.0",
389
- "_model_name": "HTMLModel",
390
- "_view_count": null,
391
- "_view_module": "@jupyter-widgets/controls",
392
- "_view_module_version": "1.5.0",
393
- "_view_name": "HTMLView",
394
- "description": "",
395
- "description_tooltip": null,
396
- "layout": "IPY_MODEL_85a7a49bf87c4160b241a878c6b12f81",
397
- "placeholder": "​",
398
- "style": "IPY_MODEL_9510c227a23e4d829ad9366b41babae6",
399
- "value": "Downloading (…)solve/main/vocab.txt: 100%"
400
- }
401
- },
402
- "3a51d4dbd7654b9ab7b69a50605d29e9": {
403
- "model_module": "@jupyter-widgets/controls",
404
- "model_name": "FloatProgressModel",
405
- "model_module_version": "1.5.0",
406
- "state": {
407
- "_dom_classes": [],
408
- "_model_module": "@jupyter-widgets/controls",
409
- "_model_module_version": "1.5.0",
410
- "_model_name": "FloatProgressModel",
411
- "_view_count": null,
412
- "_view_module": "@jupyter-widgets/controls",
413
- "_view_module_version": "1.5.0",
414
- "_view_name": "ProgressView",
415
- "bar_style": "success",
416
- "description": "",
417
- "description_tooltip": null,
418
- "layout": "IPY_MODEL_b78852da0af54675a3a1b65729eed99f",
419
- "max": 231508,
420
- "min": 0,
421
- "orientation": "horizontal",
422
- "style": "IPY_MODEL_5638394766b640cdaf9208a8794636d2",
423
- "value": 231508
424
- }
425
- },
426
- "c5dd0d556c9c486baaedf3ca54cef54a": {
427
- "model_module": "@jupyter-widgets/controls",
428
- "model_name": "HTMLModel",
429
- "model_module_version": "1.5.0",
430
- "state": {
431
- "_dom_classes": [],
432
- "_model_module": "@jupyter-widgets/controls",
433
- "_model_module_version": "1.5.0",
434
- "_model_name": "HTMLModel",
435
- "_view_count": null,
436
- "_view_module": "@jupyter-widgets/controls",
437
- "_view_module_version": "1.5.0",
438
- "_view_name": "HTMLView",
439
- "description": "",
440
- "description_tooltip": null,
441
- "layout": "IPY_MODEL_67535c820a3b407bb801873d788ba535",
442
- "placeholder": "​",
443
- "style": "IPY_MODEL_365db64fb2c847a5a41b5d057d77600c",
444
- "value": " 232k/232k [00:00<00:00, 6.66MB/s]"
445
- }
446
- },
447
- "3b40837351f44c0f92e3e5af55da3e21": {
448
- "model_module": "@jupyter-widgets/base",
449
- "model_name": "LayoutModel",
450
- "model_module_version": "1.2.0",
451
- "state": {
452
- "_model_module": "@jupyter-widgets/base",
453
- "_model_module_version": "1.2.0",
454
- "_model_name": "LayoutModel",
455
- "_view_count": null,
456
- "_view_module": "@jupyter-widgets/base",
457
- "_view_module_version": "1.2.0",
458
- "_view_name": "LayoutView",
459
- "align_content": null,
460
- "align_items": null,
461
- "align_self": null,
462
- "border": null,
463
- "bottom": null,
464
- "display": null,
465
- "flex": null,
466
- "flex_flow": null,
467
- "grid_area": null,
468
- "grid_auto_columns": null,
469
- "grid_auto_flow": null,
470
- "grid_auto_rows": null,
471
- "grid_column": null,
472
- "grid_gap": null,
473
- "grid_row": null,
474
- "grid_template_areas": null,
475
- "grid_template_columns": null,
476
- "grid_template_rows": null,
477
- "height": null,
478
- "justify_content": null,
479
- "justify_items": null,
480
- "left": null,
481
- "margin": null,
482
- "max_height": null,
483
- "max_width": null,
484
- "min_height": null,
485
- "min_width": null,
486
- "object_fit": null,
487
- "object_position": null,
488
- "order": null,
489
- "overflow": null,
490
- "overflow_x": null,
491
- "overflow_y": null,
492
- "padding": null,
493
- "right": null,
494
- "top": null,
495
- "visibility": null,
496
- "width": null
497
- }
498
- },
499
- "85a7a49bf87c4160b241a878c6b12f81": {
500
- "model_module": "@jupyter-widgets/base",
501
- "model_name": "LayoutModel",
502
- "model_module_version": "1.2.0",
503
- "state": {
504
- "_model_module": "@jupyter-widgets/base",
505
- "_model_module_version": "1.2.0",
506
- "_model_name": "LayoutModel",
507
- "_view_count": null,
508
- "_view_module": "@jupyter-widgets/base",
509
- "_view_module_version": "1.2.0",
510
- "_view_name": "LayoutView",
511
- "align_content": null,
512
- "align_items": null,
513
- "align_self": null,
514
- "border": null,
515
- "bottom": null,
516
- "display": null,
517
- "flex": null,
518
- "flex_flow": null,
519
- "grid_area": null,
520
- "grid_auto_columns": null,
521
- "grid_auto_flow": null,
522
- "grid_auto_rows": null,
523
- "grid_column": null,
524
- "grid_gap": null,
525
- "grid_row": null,
526
- "grid_template_areas": null,
527
- "grid_template_columns": null,
528
- "grid_template_rows": null,
529
- "height": null,
530
- "justify_content": null,
531
- "justify_items": null,
532
- "left": null,
533
- "margin": null,
534
- "max_height": null,
535
- "max_width": null,
536
- "min_height": null,
537
- "min_width": null,
538
- "object_fit": null,
539
- "object_position": null,
540
- "order": null,
541
- "overflow": null,
542
- "overflow_x": null,
543
- "overflow_y": null,
544
- "padding": null,
545
- "right": null,
546
- "top": null,
547
- "visibility": null,
548
- "width": null
549
- }
550
- },
551
- "9510c227a23e4d829ad9366b41babae6": {
552
- "model_module": "@jupyter-widgets/controls",
553
- "model_name": "DescriptionStyleModel",
554
- "model_module_version": "1.5.0",
555
- "state": {
556
- "_model_module": "@jupyter-widgets/controls",
557
- "_model_module_version": "1.5.0",
558
- "_model_name": "DescriptionStyleModel",
559
- "_view_count": null,
560
- "_view_module": "@jupyter-widgets/base",
561
- "_view_module_version": "1.2.0",
562
- "_view_name": "StyleView",
563
- "description_width": ""
564
- }
565
- },
566
- "b78852da0af54675a3a1b65729eed99f": {
567
- "model_module": "@jupyter-widgets/base",
568
- "model_name": "LayoutModel",
569
- "model_module_version": "1.2.0",
570
- "state": {
571
- "_model_module": "@jupyter-widgets/base",
572
- "_model_module_version": "1.2.0",
573
- "_model_name": "LayoutModel",
574
- "_view_count": null,
575
- "_view_module": "@jupyter-widgets/base",
576
- "_view_module_version": "1.2.0",
577
- "_view_name": "LayoutView",
578
- "align_content": null,
579
- "align_items": null,
580
- "align_self": null,
581
- "border": null,
582
- "bottom": null,
583
- "display": null,
584
- "flex": null,
585
- "flex_flow": null,
586
- "grid_area": null,
587
- "grid_auto_columns": null,
588
- "grid_auto_flow": null,
589
- "grid_auto_rows": null,
590
- "grid_column": null,
591
- "grid_gap": null,
592
- "grid_row": null,
593
- "grid_template_areas": null,
594
- "grid_template_columns": null,
595
- "grid_template_rows": null,
596
- "height": null,
597
- "justify_content": null,
598
- "justify_items": null,
599
- "left": null,
600
- "margin": null,
601
- "max_height": null,
602
- "max_width": null,
603
- "min_height": null,
604
- "min_width": null,
605
- "object_fit": null,
606
- "object_position": null,
607
- "order": null,
608
- "overflow": null,
609
- "overflow_x": null,
610
- "overflow_y": null,
611
- "padding": null,
612
- "right": null,
613
- "top": null,
614
- "visibility": null,
615
- "width": null
616
- }
617
- },
618
- "5638394766b640cdaf9208a8794636d2": {
619
- "model_module": "@jupyter-widgets/controls",
620
- "model_name": "ProgressStyleModel",
621
- "model_module_version": "1.5.0",
622
- "state": {
623
- "_model_module": "@jupyter-widgets/controls",
624
- "_model_module_version": "1.5.0",
625
- "_model_name": "ProgressStyleModel",
626
- "_view_count": null,
627
- "_view_module": "@jupyter-widgets/base",
628
- "_view_module_version": "1.2.0",
629
- "_view_name": "StyleView",
630
- "bar_color": null,
631
- "description_width": ""
632
- }
633
- },
634
- "67535c820a3b407bb801873d788ba535": {
635
- "model_module": "@jupyter-widgets/base",
636
- "model_name": "LayoutModel",
637
- "model_module_version": "1.2.0",
638
- "state": {
639
- "_model_module": "@jupyter-widgets/base",
640
- "_model_module_version": "1.2.0",
641
- "_model_name": "LayoutModel",
642
- "_view_count": null,
643
- "_view_module": "@jupyter-widgets/base",
644
- "_view_module_version": "1.2.0",
645
- "_view_name": "LayoutView",
646
- "align_content": null,
647
- "align_items": null,
648
- "align_self": null,
649
- "border": null,
650
- "bottom": null,
651
- "display": null,
652
- "flex": null,
653
- "flex_flow": null,
654
- "grid_area": null,
655
- "grid_auto_columns": null,
656
- "grid_auto_flow": null,
657
- "grid_auto_rows": null,
658
- "grid_column": null,
659
- "grid_gap": null,
660
- "grid_row": null,
661
- "grid_template_areas": null,
662
- "grid_template_columns": null,
663
- "grid_template_rows": null,
664
- "height": null,
665
- "justify_content": null,
666
- "justify_items": null,
667
- "left": null,
668
- "margin": null,
669
- "max_height": null,
670
- "max_width": null,
671
- "min_height": null,
672
- "min_width": null,
673
- "object_fit": null,
674
- "object_position": null,
675
- "order": null,
676
- "overflow": null,
677
- "overflow_x": null,
678
- "overflow_y": null,
679
- "padding": null,
680
- "right": null,
681
- "top": null,
682
- "visibility": null,
683
- "width": null
684
- }
685
- },
686
- "365db64fb2c847a5a41b5d057d77600c": {
687
- "model_module": "@jupyter-widgets/controls",
688
- "model_name": "DescriptionStyleModel",
689
- "model_module_version": "1.5.0",
690
- "state": {
691
- "_model_module": "@jupyter-widgets/controls",
692
- "_model_module_version": "1.5.0",
693
- "_model_name": "DescriptionStyleModel",
694
- "_view_count": null,
695
- "_view_module": "@jupyter-widgets/base",
696
- "_view_module_version": "1.2.0",
697
- "_view_name": "StyleView",
698
- "description_width": ""
699
- }
700
- },
701
- "d0334d8257ce422597da3d29ac22cd4f": {
702
- "model_module": "@jupyter-widgets/controls",
703
- "model_name": "HBoxModel",
704
- "model_module_version": "1.5.0",
705
- "state": {
706
- "_dom_classes": [],
707
- "_model_module": "@jupyter-widgets/controls",
708
- "_model_module_version": "1.5.0",
709
- "_model_name": "HBoxModel",
710
- "_view_count": null,
711
- "_view_module": "@jupyter-widgets/controls",
712
- "_view_module_version": "1.5.0",
713
- "_view_name": "HBoxView",
714
- "box_style": "",
715
- "children": [
716
- "IPY_MODEL_eae4e7789fe54a7b98bfda99d20360bd",
717
- "IPY_MODEL_5f48726592fe446ea43b7bdec668919b",
718
- "IPY_MODEL_3edcc888477a440d81e8b6df174966cd"
719
- ],
720
- "layout": "IPY_MODEL_9a23d53c1e7a448282c1aaa36d26c4ec"
721
- }
722
- },
723
- "eae4e7789fe54a7b98bfda99d20360bd": {
724
- "model_module": "@jupyter-widgets/controls",
725
- "model_name": "HTMLModel",
726
- "model_module_version": "1.5.0",
727
- "state": {
728
- "_dom_classes": [],
729
- "_model_module": "@jupyter-widgets/controls",
730
- "_model_module_version": "1.5.0",
731
- "_model_name": "HTMLModel",
732
- "_view_count": null,
733
- "_view_module": "@jupyter-widgets/controls",
734
- "_view_module_version": "1.5.0",
735
- "_view_name": "HTMLView",
736
- "description": "",
737
- "description_tooltip": null,
738
- "layout": "IPY_MODEL_e8e2739386c045078bf2cc3987534a93",
739
- "placeholder": "​",
740
- "style": "IPY_MODEL_bb14cd687abb432b8e2a01cd58e7c550",
741
- "value": "Downloading (…)/main/tokenizer.json: 100%"
742
- }
743
- },
744
- "5f48726592fe446ea43b7bdec668919b": {
745
- "model_module": "@jupyter-widgets/controls",
746
- "model_name": "FloatProgressModel",
747
- "model_module_version": "1.5.0",
748
- "state": {
749
- "_dom_classes": [],
750
- "_model_module": "@jupyter-widgets/controls",
751
- "_model_module_version": "1.5.0",
752
- "_model_name": "FloatProgressModel",
753
- "_view_count": null,
754
- "_view_module": "@jupyter-widgets/controls",
755
- "_view_module_version": "1.5.0",
756
- "_view_name": "ProgressView",
757
- "bar_style": "success",
758
- "description": "",
759
- "description_tooltip": null,
760
- "layout": "IPY_MODEL_c5c6159f813949a3851fb158a992a65c",
761
- "max": 466062,
762
- "min": 0,
763
- "orientation": "horizontal",
764
- "style": "IPY_MODEL_03337be3fcd94f388ae2650078269a55",
765
- "value": 466062
766
- }
767
- },
768
- "3edcc888477a440d81e8b6df174966cd": {
769
- "model_module": "@jupyter-widgets/controls",
770
- "model_name": "HTMLModel",
771
- "model_module_version": "1.5.0",
772
- "state": {
773
- "_dom_classes": [],
774
- "_model_module": "@jupyter-widgets/controls",
775
- "_model_module_version": "1.5.0",
776
- "_model_name": "HTMLModel",
777
- "_view_count": null,
778
- "_view_module": "@jupyter-widgets/controls",
779
- "_view_module_version": "1.5.0",
780
- "_view_name": "HTMLView",
781
- "description": "",
782
- "description_tooltip": null,
783
- "layout": "IPY_MODEL_ff28b23c163240dc9b543f340b9d2d52",
784
- "placeholder": "​",
785
- "style": "IPY_MODEL_110e8e19d5f242829cc4cafdb9a10cb2",
786
- "value": " 466k/466k [00:00<00:00, 15.5MB/s]"
787
- }
788
- },
789
- "9a23d53c1e7a448282c1aaa36d26c4ec": {
790
- "model_module": "@jupyter-widgets/base",
791
- "model_name": "LayoutModel",
792
- "model_module_version": "1.2.0",
793
- "state": {
794
- "_model_module": "@jupyter-widgets/base",
795
- "_model_module_version": "1.2.0",
796
- "_model_name": "LayoutModel",
797
- "_view_count": null,
798
- "_view_module": "@jupyter-widgets/base",
799
- "_view_module_version": "1.2.0",
800
- "_view_name": "LayoutView",
801
- "align_content": null,
802
- "align_items": null,
803
- "align_self": null,
804
- "border": null,
805
- "bottom": null,
806
- "display": null,
807
- "flex": null,
808
- "flex_flow": null,
809
- "grid_area": null,
810
- "grid_auto_columns": null,
811
- "grid_auto_flow": null,
812
- "grid_auto_rows": null,
813
- "grid_column": null,
814
- "grid_gap": null,
815
- "grid_row": null,
816
- "grid_template_areas": null,
817
- "grid_template_columns": null,
818
- "grid_template_rows": null,
819
- "height": null,
820
- "justify_content": null,
821
- "justify_items": null,
822
- "left": null,
823
- "margin": null,
824
- "max_height": null,
825
- "max_width": null,
826
- "min_height": null,
827
- "min_width": null,
828
- "object_fit": null,
829
- "object_position": null,
830
- "order": null,
831
- "overflow": null,
832
- "overflow_x": null,
833
- "overflow_y": null,
834
- "padding": null,
835
- "right": null,
836
- "top": null,
837
- "visibility": null,
838
- "width": null
839
- }
840
- },
841
- "e8e2739386c045078bf2cc3987534a93": {
842
- "model_module": "@jupyter-widgets/base",
843
- "model_name": "LayoutModel",
844
- "model_module_version": "1.2.0",
845
- "state": {
846
- "_model_module": "@jupyter-widgets/base",
847
- "_model_module_version": "1.2.0",
848
- "_model_name": "LayoutModel",
849
- "_view_count": null,
850
- "_view_module": "@jupyter-widgets/base",
851
- "_view_module_version": "1.2.0",
852
- "_view_name": "LayoutView",
853
- "align_content": null,
854
- "align_items": null,
855
- "align_self": null,
856
- "border": null,
857
- "bottom": null,
858
- "display": null,
859
- "flex": null,
860
- "flex_flow": null,
861
- "grid_area": null,
862
- "grid_auto_columns": null,
863
- "grid_auto_flow": null,
864
- "grid_auto_rows": null,
865
- "grid_column": null,
866
- "grid_gap": null,
867
- "grid_row": null,
868
- "grid_template_areas": null,
869
- "grid_template_columns": null,
870
- "grid_template_rows": null,
871
- "height": null,
872
- "justify_content": null,
873
- "justify_items": null,
874
- "left": null,
875
- "margin": null,
876
- "max_height": null,
877
- "max_width": null,
878
- "min_height": null,
879
- "min_width": null,
880
- "object_fit": null,
881
- "object_position": null,
882
- "order": null,
883
- "overflow": null,
884
- "overflow_x": null,
885
- "overflow_y": null,
886
- "padding": null,
887
- "right": null,
888
- "top": null,
889
- "visibility": null,
890
- "width": null
891
- }
892
- },
893
- "bb14cd687abb432b8e2a01cd58e7c550": {
894
- "model_module": "@jupyter-widgets/controls",
895
- "model_name": "DescriptionStyleModel",
896
- "model_module_version": "1.5.0",
897
- "state": {
898
- "_model_module": "@jupyter-widgets/controls",
899
- "_model_module_version": "1.5.0",
900
- "_model_name": "DescriptionStyleModel",
901
- "_view_count": null,
902
- "_view_module": "@jupyter-widgets/base",
903
- "_view_module_version": "1.2.0",
904
- "_view_name": "StyleView",
905
- "description_width": ""
906
- }
907
- },
908
- "c5c6159f813949a3851fb158a992a65c": {
909
- "model_module": "@jupyter-widgets/base",
910
- "model_name": "LayoutModel",
911
- "model_module_version": "1.2.0",
912
- "state": {
913
- "_model_module": "@jupyter-widgets/base",
914
- "_model_module_version": "1.2.0",
915
- "_model_name": "LayoutModel",
916
- "_view_count": null,
917
- "_view_module": "@jupyter-widgets/base",
918
- "_view_module_version": "1.2.0",
919
- "_view_name": "LayoutView",
920
- "align_content": null,
921
- "align_items": null,
922
- "align_self": null,
923
- "border": null,
924
- "bottom": null,
925
- "display": null,
926
- "flex": null,
927
- "flex_flow": null,
928
- "grid_area": null,
929
- "grid_auto_columns": null,
930
- "grid_auto_flow": null,
931
- "grid_auto_rows": null,
932
- "grid_column": null,
933
- "grid_gap": null,
934
- "grid_row": null,
935
- "grid_template_areas": null,
936
- "grid_template_columns": null,
937
- "grid_template_rows": null,
938
- "height": null,
939
- "justify_content": null,
940
- "justify_items": null,
941
- "left": null,
942
- "margin": null,
943
- "max_height": null,
944
- "max_width": null,
945
- "min_height": null,
946
- "min_width": null,
947
- "object_fit": null,
948
- "object_position": null,
949
- "order": null,
950
- "overflow": null,
951
- "overflow_x": null,
952
- "overflow_y": null,
953
- "padding": null,
954
- "right": null,
955
- "top": null,
956
- "visibility": null,
957
- "width": null
958
- }
959
- },
960
- "03337be3fcd94f388ae2650078269a55": {
961
- "model_module": "@jupyter-widgets/controls",
962
- "model_name": "ProgressStyleModel",
963
- "model_module_version": "1.5.0",
964
- "state": {
965
- "_model_module": "@jupyter-widgets/controls",
966
- "_model_module_version": "1.5.0",
967
- "_model_name": "ProgressStyleModel",
968
- "_view_count": null,
969
- "_view_module": "@jupyter-widgets/base",
970
- "_view_module_version": "1.2.0",
971
- "_view_name": "StyleView",
972
- "bar_color": null,
973
- "description_width": ""
974
- }
975
- },
976
- "ff28b23c163240dc9b543f340b9d2d52": {
977
- "model_module": "@jupyter-widgets/base",
978
- "model_name": "LayoutModel",
979
- "model_module_version": "1.2.0",
980
- "state": {
981
- "_model_module": "@jupyter-widgets/base",
982
- "_model_module_version": "1.2.0",
983
- "_model_name": "LayoutModel",
984
- "_view_count": null,
985
- "_view_module": "@jupyter-widgets/base",
986
- "_view_module_version": "1.2.0",
987
- "_view_name": "LayoutView",
988
- "align_content": null,
989
- "align_items": null,
990
- "align_self": null,
991
- "border": null,
992
- "bottom": null,
993
- "display": null,
994
- "flex": null,
995
- "flex_flow": null,
996
- "grid_area": null,
997
- "grid_auto_columns": null,
998
- "grid_auto_flow": null,
999
- "grid_auto_rows": null,
1000
- "grid_column": null,
1001
- "grid_gap": null,
1002
- "grid_row": null,
1003
- "grid_template_areas": null,
1004
- "grid_template_columns": null,
1005
- "grid_template_rows": null,
1006
- "height": null,
1007
- "justify_content": null,
1008
- "justify_items": null,
1009
- "left": null,
1010
- "margin": null,
1011
- "max_height": null,
1012
- "max_width": null,
1013
- "min_height": null,
1014
- "min_width": null,
1015
- "object_fit": null,
1016
- "object_position": null,
1017
- "order": null,
1018
- "overflow": null,
1019
- "overflow_x": null,
1020
- "overflow_y": null,
1021
- "padding": null,
1022
- "right": null,
1023
- "top": null,
1024
- "visibility": null,
1025
- "width": null
1026
- }
1027
- },
1028
- "110e8e19d5f242829cc4cafdb9a10cb2": {
1029
- "model_module": "@jupyter-widgets/controls",
1030
- "model_name": "DescriptionStyleModel",
1031
- "model_module_version": "1.5.0",
1032
- "state": {
1033
- "_model_module": "@jupyter-widgets/controls",
1034
- "_model_module_version": "1.5.0",
1035
- "_model_name": "DescriptionStyleModel",
1036
- "_view_count": null,
1037
- "_view_module": "@jupyter-widgets/base",
1038
- "_view_module_version": "1.2.0",
1039
- "_view_name": "StyleView",
1040
- "description_width": ""
1041
- }
1042
- },
1043
- "ee6313a98fd041c9b755be6b6a94ebff": {
1044
- "model_module": "@jupyter-widgets/controls",
1045
- "model_name": "HBoxModel",
1046
- "model_module_version": "1.5.0",
1047
- "state": {
1048
- "_dom_classes": [],
1049
- "_model_module": "@jupyter-widgets/controls",
1050
- "_model_module_version": "1.5.0",
1051
- "_model_name": "HBoxModel",
1052
- "_view_count": null,
1053
- "_view_module": "@jupyter-widgets/controls",
1054
- "_view_module_version": "1.5.0",
1055
- "_view_name": "HBoxView",
1056
- "box_style": "",
1057
- "children": [
1058
- "IPY_MODEL_40f2cc2506fd49dd9e284c1891312785",
1059
- "IPY_MODEL_719e9ba1b98d4170a6acff418ada38fa",
1060
- "IPY_MODEL_1e532190fe2b49a08a97211e3f1c60d0"
1061
- ],
1062
- "layout": "IPY_MODEL_e0ac88aa562e4354b15e182164990a79"
1063
- }
1064
- },
1065
- "40f2cc2506fd49dd9e284c1891312785": {
1066
- "model_module": "@jupyter-widgets/controls",
1067
- "model_name": "HTMLModel",
1068
- "model_module_version": "1.5.0",
1069
- "state": {
1070
- "_dom_classes": [],
1071
- "_model_module": "@jupyter-widgets/controls",
1072
- "_model_module_version": "1.5.0",
1073
- "_model_name": "HTMLModel",
1074
- "_view_count": null,
1075
- "_view_module": "@jupyter-widgets/controls",
1076
- "_view_module_version": "1.5.0",
1077
- "_view_name": "HTMLView",
1078
- "description": "",
1079
- "description_tooltip": null,
1080
- "layout": "IPY_MODEL_5e6bd272a50b4734a8a4dd4cb683d4e2",
1081
- "placeholder": "​",
1082
- "style": "IPY_MODEL_9fd8ea0a806e4641ae945dc59baa0505",
1083
- "value": "Downloading (…)lve/main/config.json: 100%"
1084
- }
1085
- },
1086
- "719e9ba1b98d4170a6acff418ada38fa": {
1087
- "model_module": "@jupyter-widgets/controls",
1088
- "model_name": "FloatProgressModel",
1089
- "model_module_version": "1.5.0",
1090
- "state": {
1091
- "_dom_classes": [],
1092
- "_model_module": "@jupyter-widgets/controls",
1093
- "_model_module_version": "1.5.0",
1094
- "_model_name": "FloatProgressModel",
1095
- "_view_count": null,
1096
- "_view_module": "@jupyter-widgets/controls",
1097
- "_view_module_version": "1.5.0",
1098
- "_view_name": "ProgressView",
1099
- "bar_style": "success",
1100
- "description": "",
1101
- "description_tooltip": null,
1102
- "layout": "IPY_MODEL_941fcfabb72940a59c7fa76e3506385d",
1103
- "max": 483,
1104
- "min": 0,
1105
- "orientation": "horizontal",
1106
- "style": "IPY_MODEL_23bc61b5726942169123eca1f60bd883",
1107
- "value": 483
1108
- }
1109
- },
1110
- "1e532190fe2b49a08a97211e3f1c60d0": {
1111
- "model_module": "@jupyter-widgets/controls",
1112
- "model_name": "HTMLModel",
1113
- "model_module_version": "1.5.0",
1114
- "state": {
1115
- "_dom_classes": [],
1116
- "_model_module": "@jupyter-widgets/controls",
1117
- "_model_module_version": "1.5.0",
1118
- "_model_name": "HTMLModel",
1119
- "_view_count": null,
1120
- "_view_module": "@jupyter-widgets/controls",
1121
- "_view_module_version": "1.5.0",
1122
- "_view_name": "HTMLView",
1123
- "description": "",
1124
- "description_tooltip": null,
1125
- "layout": "IPY_MODEL_b9ebd383be484f5d8fabafd4a130d6ae",
1126
- "placeholder": "​",
1127
- "style": "IPY_MODEL_afdf7f80c04848fb8978d2634ee86526",
1128
- "value": " 483/483 [00:00<00:00, 30.4kB/s]"
1129
- }
1130
- },
1131
- "e0ac88aa562e4354b15e182164990a79": {
1132
- "model_module": "@jupyter-widgets/base",
1133
- "model_name": "LayoutModel",
1134
- "model_module_version": "1.2.0",
1135
- "state": {
1136
- "_model_module": "@jupyter-widgets/base",
1137
- "_model_module_version": "1.2.0",
1138
- "_model_name": "LayoutModel",
1139
- "_view_count": null,
1140
- "_view_module": "@jupyter-widgets/base",
1141
- "_view_module_version": "1.2.0",
1142
- "_view_name": "LayoutView",
1143
- "align_content": null,
1144
- "align_items": null,
1145
- "align_self": null,
1146
- "border": null,
1147
- "bottom": null,
1148
- "display": null,
1149
- "flex": null,
1150
- "flex_flow": null,
1151
- "grid_area": null,
1152
- "grid_auto_columns": null,
1153
- "grid_auto_flow": null,
1154
- "grid_auto_rows": null,
1155
- "grid_column": null,
1156
- "grid_gap": null,
1157
- "grid_row": null,
1158
- "grid_template_areas": null,
1159
- "grid_template_columns": null,
1160
- "grid_template_rows": null,
1161
- "height": null,
1162
- "justify_content": null,
1163
- "justify_items": null,
1164
- "left": null,
1165
- "margin": null,
1166
- "max_height": null,
1167
- "max_width": null,
1168
- "min_height": null,
1169
- "min_width": null,
1170
- "object_fit": null,
1171
- "object_position": null,
1172
- "order": null,
1173
- "overflow": null,
1174
- "overflow_x": null,
1175
- "overflow_y": null,
1176
- "padding": null,
1177
- "right": null,
1178
- "top": null,
1179
- "visibility": null,
1180
- "width": null
1181
- }
1182
- },
1183
- "5e6bd272a50b4734a8a4dd4cb683d4e2": {
1184
- "model_module": "@jupyter-widgets/base",
1185
- "model_name": "LayoutModel",
1186
- "model_module_version": "1.2.0",
1187
- "state": {
1188
- "_model_module": "@jupyter-widgets/base",
1189
- "_model_module_version": "1.2.0",
1190
- "_model_name": "LayoutModel",
1191
- "_view_count": null,
1192
- "_view_module": "@jupyter-widgets/base",
1193
- "_view_module_version": "1.2.0",
1194
- "_view_name": "LayoutView",
1195
- "align_content": null,
1196
- "align_items": null,
1197
- "align_self": null,
1198
- "border": null,
1199
- "bottom": null,
1200
- "display": null,
1201
- "flex": null,
1202
- "flex_flow": null,
1203
- "grid_area": null,
1204
- "grid_auto_columns": null,
1205
- "grid_auto_flow": null,
1206
- "grid_auto_rows": null,
1207
- "grid_column": null,
1208
- "grid_gap": null,
1209
- "grid_row": null,
1210
- "grid_template_areas": null,
1211
- "grid_template_columns": null,
1212
- "grid_template_rows": null,
1213
- "height": null,
1214
- "justify_content": null,
1215
- "justify_items": null,
1216
- "left": null,
1217
- "margin": null,
1218
- "max_height": null,
1219
- "max_width": null,
1220
- "min_height": null,
1221
- "min_width": null,
1222
- "object_fit": null,
1223
- "object_position": null,
1224
- "order": null,
1225
- "overflow": null,
1226
- "overflow_x": null,
1227
- "overflow_y": null,
1228
- "padding": null,
1229
- "right": null,
1230
- "top": null,
1231
- "visibility": null,
1232
- "width": null
1233
- }
1234
- },
1235
- "9fd8ea0a806e4641ae945dc59baa0505": {
1236
- "model_module": "@jupyter-widgets/controls",
1237
- "model_name": "DescriptionStyleModel",
1238
- "model_module_version": "1.5.0",
1239
- "state": {
1240
- "_model_module": "@jupyter-widgets/controls",
1241
- "_model_module_version": "1.5.0",
1242
- "_model_name": "DescriptionStyleModel",
1243
- "_view_count": null,
1244
- "_view_module": "@jupyter-widgets/base",
1245
- "_view_module_version": "1.2.0",
1246
- "_view_name": "StyleView",
1247
- "description_width": ""
1248
- }
1249
- },
1250
- "941fcfabb72940a59c7fa76e3506385d": {
1251
- "model_module": "@jupyter-widgets/base",
1252
- "model_name": "LayoutModel",
1253
- "model_module_version": "1.2.0",
1254
- "state": {
1255
- "_model_module": "@jupyter-widgets/base",
1256
- "_model_module_version": "1.2.0",
1257
- "_model_name": "LayoutModel",
1258
- "_view_count": null,
1259
- "_view_module": "@jupyter-widgets/base",
1260
- "_view_module_version": "1.2.0",
1261
- "_view_name": "LayoutView",
1262
- "align_content": null,
1263
- "align_items": null,
1264
- "align_self": null,
1265
- "border": null,
1266
- "bottom": null,
1267
- "display": null,
1268
- "flex": null,
1269
- "flex_flow": null,
1270
- "grid_area": null,
1271
- "grid_auto_columns": null,
1272
- "grid_auto_flow": null,
1273
- "grid_auto_rows": null,
1274
- "grid_column": null,
1275
- "grid_gap": null,
1276
- "grid_row": null,
1277
- "grid_template_areas": null,
1278
- "grid_template_columns": null,
1279
- "grid_template_rows": null,
1280
- "height": null,
1281
- "justify_content": null,
1282
- "justify_items": null,
1283
- "left": null,
1284
- "margin": null,
1285
- "max_height": null,
1286
- "max_width": null,
1287
- "min_height": null,
1288
- "min_width": null,
1289
- "object_fit": null,
1290
- "object_position": null,
1291
- "order": null,
1292
- "overflow": null,
1293
- "overflow_x": null,
1294
- "overflow_y": null,
1295
- "padding": null,
1296
- "right": null,
1297
- "top": null,
1298
- "visibility": null,
1299
- "width": null
1300
- }
1301
- },
1302
- "23bc61b5726942169123eca1f60bd883": {
1303
- "model_module": "@jupyter-widgets/controls",
1304
- "model_name": "ProgressStyleModel",
1305
- "model_module_version": "1.5.0",
1306
- "state": {
1307
- "_model_module": "@jupyter-widgets/controls",
1308
- "_model_module_version": "1.5.0",
1309
- "_model_name": "ProgressStyleModel",
1310
- "_view_count": null,
1311
- "_view_module": "@jupyter-widgets/base",
1312
- "_view_module_version": "1.2.0",
1313
- "_view_name": "StyleView",
1314
- "bar_color": null,
1315
- "description_width": ""
1316
- }
1317
- },
1318
- "b9ebd383be484f5d8fabafd4a130d6ae": {
1319
- "model_module": "@jupyter-widgets/base",
1320
- "model_name": "LayoutModel",
1321
- "model_module_version": "1.2.0",
1322
- "state": {
1323
- "_model_module": "@jupyter-widgets/base",
1324
- "_model_module_version": "1.2.0",
1325
- "_model_name": "LayoutModel",
1326
- "_view_count": null,
1327
- "_view_module": "@jupyter-widgets/base",
1328
- "_view_module_version": "1.2.0",
1329
- "_view_name": "LayoutView",
1330
- "align_content": null,
1331
- "align_items": null,
1332
- "align_self": null,
1333
- "border": null,
1334
- "bottom": null,
1335
- "display": null,
1336
- "flex": null,
1337
- "flex_flow": null,
1338
- "grid_area": null,
1339
- "grid_auto_columns": null,
1340
- "grid_auto_flow": null,
1341
- "grid_auto_rows": null,
1342
- "grid_column": null,
1343
- "grid_gap": null,
1344
- "grid_row": null,
1345
- "grid_template_areas": null,
1346
- "grid_template_columns": null,
1347
- "grid_template_rows": null,
1348
- "height": null,
1349
- "justify_content": null,
1350
- "justify_items": null,
1351
- "left": null,
1352
- "margin": null,
1353
- "max_height": null,
1354
- "max_width": null,
1355
- "min_height": null,
1356
- "min_width": null,
1357
- "object_fit": null,
1358
- "object_position": null,
1359
- "order": null,
1360
- "overflow": null,
1361
- "overflow_x": null,
1362
- "overflow_y": null,
1363
- "padding": null,
1364
- "right": null,
1365
- "top": null,
1366
- "visibility": null,
1367
- "width": null
1368
- }
1369
- },
1370
- "afdf7f80c04848fb8978d2634ee86526": {
1371
- "model_module": "@jupyter-widgets/controls",
1372
- "model_name": "DescriptionStyleModel",
1373
- "model_module_version": "1.5.0",
1374
- "state": {
1375
- "_model_module": "@jupyter-widgets/controls",
1376
- "_model_module_version": "1.5.0",
1377
- "_model_name": "DescriptionStyleModel",
1378
- "_view_count": null,
1379
- "_view_module": "@jupyter-widgets/base",
1380
- "_view_module_version": "1.2.0",
1381
- "_view_name": "StyleView",
1382
- "description_width": ""
1383
- }
1384
- },
1385
- "a828e2eb329548568ea23df75056ce46": {
1386
- "model_module": "@jupyter-widgets/controls",
1387
- "model_name": "HBoxModel",
1388
- "model_module_version": "1.5.0",
1389
- "state": {
1390
- "_dom_classes": [],
1391
- "_model_module": "@jupyter-widgets/controls",
1392
- "_model_module_version": "1.5.0",
1393
- "_model_name": "HBoxModel",
1394
- "_view_count": null,
1395
- "_view_module": "@jupyter-widgets/controls",
1396
- "_view_module_version": "1.5.0",
1397
- "_view_name": "HBoxView",
1398
- "box_style": "",
1399
- "children": [
1400
- "IPY_MODEL_94f47a73ba5b402b84717807b4f127d9",
1401
- "IPY_MODEL_66f521247f4c4a608e4a79933ca8b499",
1402
- "IPY_MODEL_9012d483dc42427189bea7c35c6a9f21"
1403
- ],
1404
- "layout": "IPY_MODEL_342182d835634efd9e8dcc16c753602b"
1405
- }
1406
- },
1407
- "94f47a73ba5b402b84717807b4f127d9": {
1408
- "model_module": "@jupyter-widgets/controls",
1409
- "model_name": "HTMLModel",
1410
- "model_module_version": "1.5.0",
1411
- "state": {
1412
- "_dom_classes": [],
1413
- "_model_module": "@jupyter-widgets/controls",
1414
- "_model_module_version": "1.5.0",
1415
- "_model_name": "HTMLModel",
1416
- "_view_count": null,
1417
- "_view_module": "@jupyter-widgets/controls",
1418
- "_view_module_version": "1.5.0",
1419
- "_view_name": "HTMLView",
1420
- "description": "",
1421
- "description_tooltip": null,
1422
- "layout": "IPY_MODEL_a8c8ad17737448748e212de8bba42b5f",
1423
- "placeholder": "​",
1424
- "style": "IPY_MODEL_e414907cc96e4e3d879a6759124fd8fe",
1425
- "value": "Downloading pytorch_model.bin: 100%"
1426
- }
1427
- },
1428
- "66f521247f4c4a608e4a79933ca8b499": {
1429
- "model_module": "@jupyter-widgets/controls",
1430
- "model_name": "FloatProgressModel",
1431
- "model_module_version": "1.5.0",
1432
- "state": {
1433
- "_dom_classes": [],
1434
- "_model_module": "@jupyter-widgets/controls",
1435
- "_model_module_version": "1.5.0",
1436
- "_model_name": "FloatProgressModel",
1437
- "_view_count": null,
1438
- "_view_module": "@jupyter-widgets/controls",
1439
- "_view_module_version": "1.5.0",
1440
- "_view_name": "ProgressView",
1441
- "bar_style": "success",
1442
- "description": "",
1443
- "description_tooltip": null,
1444
- "layout": "IPY_MODEL_a464bcc2342841588e7384b4c2f10a42",
1445
- "max": 267967963,
1446
- "min": 0,
1447
- "orientation": "horizontal",
1448
- "style": "IPY_MODEL_6cc18dcc7a7d4361a5aac3271d47347a",
1449
- "value": 267967963
1450
- }
1451
- },
1452
- "9012d483dc42427189bea7c35c6a9f21": {
1453
- "model_module": "@jupyter-widgets/controls",
1454
- "model_name": "HTMLModel",
1455
- "model_module_version": "1.5.0",
1456
- "state": {
1457
- "_dom_classes": [],
1458
- "_model_module": "@jupyter-widgets/controls",
1459
- "_model_module_version": "1.5.0",
1460
- "_model_name": "HTMLModel",
1461
- "_view_count": null,
1462
- "_view_module": "@jupyter-widgets/controls",
1463
- "_view_module_version": "1.5.0",
1464
- "_view_name": "HTMLView",
1465
- "description": "",
1466
- "description_tooltip": null,
1467
- "layout": "IPY_MODEL_cb8c4e778a994ba7bb57f279614ebfe8",
1468
- "placeholder": "​",
1469
- "style": "IPY_MODEL_739f16b75f3248489495a606ab3650ab",
1470
- "value": " 268M/268M [00:00<00:00, 372MB/s]"
1471
- }
1472
- },
1473
- "342182d835634efd9e8dcc16c753602b": {
1474
- "model_module": "@jupyter-widgets/base",
1475
- "model_name": "LayoutModel",
1476
- "model_module_version": "1.2.0",
1477
- "state": {
1478
- "_model_module": "@jupyter-widgets/base",
1479
- "_model_module_version": "1.2.0",
1480
- "_model_name": "LayoutModel",
1481
- "_view_count": null,
1482
- "_view_module": "@jupyter-widgets/base",
1483
- "_view_module_version": "1.2.0",
1484
- "_view_name": "LayoutView",
1485
- "align_content": null,
1486
- "align_items": null,
1487
- "align_self": null,
1488
- "border": null,
1489
- "bottom": null,
1490
- "display": null,
1491
- "flex": null,
1492
- "flex_flow": null,
1493
- "grid_area": null,
1494
- "grid_auto_columns": null,
1495
- "grid_auto_flow": null,
1496
- "grid_auto_rows": null,
1497
- "grid_column": null,
1498
- "grid_gap": null,
1499
- "grid_row": null,
1500
- "grid_template_areas": null,
1501
- "grid_template_columns": null,
1502
- "grid_template_rows": null,
1503
- "height": null,
1504
- "justify_content": null,
1505
- "justify_items": null,
1506
- "left": null,
1507
- "margin": null,
1508
- "max_height": null,
1509
- "max_width": null,
1510
- "min_height": null,
1511
- "min_width": null,
1512
- "object_fit": null,
1513
- "object_position": null,
1514
- "order": null,
1515
- "overflow": null,
1516
- "overflow_x": null,
1517
- "overflow_y": null,
1518
- "padding": null,
1519
- "right": null,
1520
- "top": null,
1521
- "visibility": null,
1522
- "width": null
1523
- }
1524
- },
1525
- "a8c8ad17737448748e212de8bba42b5f": {
1526
- "model_module": "@jupyter-widgets/base",
1527
- "model_name": "LayoutModel",
1528
- "model_module_version": "1.2.0",
1529
- "state": {
1530
- "_model_module": "@jupyter-widgets/base",
1531
- "_model_module_version": "1.2.0",
1532
- "_model_name": "LayoutModel",
1533
- "_view_count": null,
1534
- "_view_module": "@jupyter-widgets/base",
1535
- "_view_module_version": "1.2.0",
1536
- "_view_name": "LayoutView",
1537
- "align_content": null,
1538
- "align_items": null,
1539
- "align_self": null,
1540
- "border": null,
1541
- "bottom": null,
1542
- "display": null,
1543
- "flex": null,
1544
- "flex_flow": null,
1545
- "grid_area": null,
1546
- "grid_auto_columns": null,
1547
- "grid_auto_flow": null,
1548
- "grid_auto_rows": null,
1549
- "grid_column": null,
1550
- "grid_gap": null,
1551
- "grid_row": null,
1552
- "grid_template_areas": null,
1553
- "grid_template_columns": null,
1554
- "grid_template_rows": null,
1555
- "height": null,
1556
- "justify_content": null,
1557
- "justify_items": null,
1558
- "left": null,
1559
- "margin": null,
1560
- "max_height": null,
1561
- "max_width": null,
1562
- "min_height": null,
1563
- "min_width": null,
1564
- "object_fit": null,
1565
- "object_position": null,
1566
- "order": null,
1567
- "overflow": null,
1568
- "overflow_x": null,
1569
- "overflow_y": null,
1570
- "padding": null,
1571
- "right": null,
1572
- "top": null,
1573
- "visibility": null,
1574
- "width": null
1575
- }
1576
- },
1577
- "e414907cc96e4e3d879a6759124fd8fe": {
1578
- "model_module": "@jupyter-widgets/controls",
1579
- "model_name": "DescriptionStyleModel",
1580
- "model_module_version": "1.5.0",
1581
- "state": {
1582
- "_model_module": "@jupyter-widgets/controls",
1583
- "_model_module_version": "1.5.0",
1584
- "_model_name": "DescriptionStyleModel",
1585
- "_view_count": null,
1586
- "_view_module": "@jupyter-widgets/base",
1587
- "_view_module_version": "1.2.0",
1588
- "_view_name": "StyleView",
1589
- "description_width": ""
1590
- }
1591
- },
1592
- "a464bcc2342841588e7384b4c2f10a42": {
1593
- "model_module": "@jupyter-widgets/base",
1594
- "model_name": "LayoutModel",
1595
- "model_module_version": "1.2.0",
1596
- "state": {
1597
- "_model_module": "@jupyter-widgets/base",
1598
- "_model_module_version": "1.2.0",
1599
- "_model_name": "LayoutModel",
1600
- "_view_count": null,
1601
- "_view_module": "@jupyter-widgets/base",
1602
- "_view_module_version": "1.2.0",
1603
- "_view_name": "LayoutView",
1604
- "align_content": null,
1605
- "align_items": null,
1606
- "align_self": null,
1607
- "border": null,
1608
- "bottom": null,
1609
- "display": null,
1610
- "flex": null,
1611
- "flex_flow": null,
1612
- "grid_area": null,
1613
- "grid_auto_columns": null,
1614
- "grid_auto_flow": null,
1615
- "grid_auto_rows": null,
1616
- "grid_column": null,
1617
- "grid_gap": null,
1618
- "grid_row": null,
1619
- "grid_template_areas": null,
1620
- "grid_template_columns": null,
1621
- "grid_template_rows": null,
1622
- "height": null,
1623
- "justify_content": null,
1624
- "justify_items": null,
1625
- "left": null,
1626
- "margin": null,
1627
- "max_height": null,
1628
- "max_width": null,
1629
- "min_height": null,
1630
- "min_width": null,
1631
- "object_fit": null,
1632
- "object_position": null,
1633
- "order": null,
1634
- "overflow": null,
1635
- "overflow_x": null,
1636
- "overflow_y": null,
1637
- "padding": null,
1638
- "right": null,
1639
- "top": null,
1640
- "visibility": null,
1641
- "width": null
1642
- }
1643
- },
1644
- "6cc18dcc7a7d4361a5aac3271d47347a": {
1645
- "model_module": "@jupyter-widgets/controls",
1646
- "model_name": "ProgressStyleModel",
1647
- "model_module_version": "1.5.0",
1648
- "state": {
1649
- "_model_module": "@jupyter-widgets/controls",
1650
- "_model_module_version": "1.5.0",
1651
- "_model_name": "ProgressStyleModel",
1652
- "_view_count": null,
1653
- "_view_module": "@jupyter-widgets/base",
1654
- "_view_module_version": "1.2.0",
1655
- "_view_name": "StyleView",
1656
- "bar_color": null,
1657
- "description_width": ""
1658
- }
1659
- },
1660
- "cb8c4e778a994ba7bb57f279614ebfe8": {
1661
- "model_module": "@jupyter-widgets/base",
1662
- "model_name": "LayoutModel",
1663
- "model_module_version": "1.2.0",
1664
- "state": {
1665
- "_model_module": "@jupyter-widgets/base",
1666
- "_model_module_version": "1.2.0",
1667
- "_model_name": "LayoutModel",
1668
- "_view_count": null,
1669
- "_view_module": "@jupyter-widgets/base",
1670
- "_view_module_version": "1.2.0",
1671
- "_view_name": "LayoutView",
1672
- "align_content": null,
1673
- "align_items": null,
1674
- "align_self": null,
1675
- "border": null,
1676
- "bottom": null,
1677
- "display": null,
1678
- "flex": null,
1679
- "flex_flow": null,
1680
- "grid_area": null,
1681
- "grid_auto_columns": null,
1682
- "grid_auto_flow": null,
1683
- "grid_auto_rows": null,
1684
- "grid_column": null,
1685
- "grid_gap": null,
1686
- "grid_row": null,
1687
- "grid_template_areas": null,
1688
- "grid_template_columns": null,
1689
- "grid_template_rows": null,
1690
- "height": null,
1691
- "justify_content": null,
1692
- "justify_items": null,
1693
- "left": null,
1694
- "margin": null,
1695
- "max_height": null,
1696
- "max_width": null,
1697
- "min_height": null,
1698
- "min_width": null,
1699
- "object_fit": null,
1700
- "object_position": null,
1701
- "order": null,
1702
- "overflow": null,
1703
- "overflow_x": null,
1704
- "overflow_y": null,
1705
- "padding": null,
1706
- "right": null,
1707
- "top": null,
1708
- "visibility": null,
1709
- "width": null
1710
- }
1711
- },
1712
- "739f16b75f3248489495a606ab3650ab": {
1713
- "model_module": "@jupyter-widgets/controls",
1714
- "model_name": "DescriptionStyleModel",
1715
- "model_module_version": "1.5.0",
1716
- "state": {
1717
- "_model_module": "@jupyter-widgets/controls",
1718
- "_model_module_version": "1.5.0",
1719
- "_model_name": "DescriptionStyleModel",
1720
- "_view_count": null,
1721
- "_view_module": "@jupyter-widgets/base",
1722
- "_view_module_version": "1.2.0",
1723
- "_view_name": "StyleView",
1724
- "description_width": ""
1725
- }
1726
- }
1727
- }
1728
- }
1729
- },
1730
- "cells": [
1731
- {
1732
- "cell_type": "code",
1733
- "source": [
1734
- "from pathlib import Path\n",
1735
- "from sklearn.model_selection import train_test_split\n",
1736
- "import torch\n",
1737
- "from torch.utils.data import Dataset\n",
1738
- "from transformers import DistilBertTokenizerFast, DistilBertForSequenceClassification\n",
1739
- "from transformers import Trainer, TrainingArguments\n",
1740
- "from torch.utils.data import DataLoader\n",
1741
- "from transformers import AdamW\n",
1742
- "import pandas as pd\n",
1743
- "from huggingface_hub import notebook_login"
1744
- ],
1745
- "metadata": {
1746
- "id": "Bu9ttXsprt9w"
1747
- },
1748
- "execution_count": null,
1749
- "outputs": []
1750
- },
1751
- {
1752
- "cell_type": "code",
1753
- "execution_count": null,
1754
- "metadata": {
1755
- "id": "UCoa8JqwrVXU",
1756
- "colab": {
1757
- "base_uri": "https://localhost:8080/",
1758
- "height": 144,
1759
- "referenced_widgets": [
1760
- "9972abac7caf4cc6b0d98071fd7b2e05",
1761
- "b53fb6f416d8458bb0875cbace688913",
1762
- "a25b06ec34a44529bd5bd686a9a381e5",
1763
- "52da3fef70074ddf95a3b257dcf4b100",
1764
- "932e4324d43346e48c85af3e5d5b45c1",
1765
- "13d5e786f6294da2b6e5d90ca06c8593",
1766
- "bbfa5943bc1c41dbaf3a2ef89ac8d0b3",
1767
- "3ce089610ec446c19db3bae1baa45d7a",
1768
- "bcf06ca3212c43e0a5db7e7d4ea01375",
1769
- "aab6a478cec84b25a29bc0ed4ee2aaac",
1770
- "3e6f987e297b4a2b8f3eb1b12b4b67af",
1771
- "3a52fbc3755a4323b749da73142e5871",
1772
- "7b2019506d154d118134985ee7e8ea43",
1773
- "3a51d4dbd7654b9ab7b69a50605d29e9",
1774
- "c5dd0d556c9c486baaedf3ca54cef54a",
1775
- "3b40837351f44c0f92e3e5af55da3e21",
1776
- "85a7a49bf87c4160b241a878c6b12f81",
1777
- "9510c227a23e4d829ad9366b41babae6",
1778
- "b78852da0af54675a3a1b65729eed99f",
1779
- "5638394766b640cdaf9208a8794636d2",
1780
- "67535c820a3b407bb801873d788ba535",
1781
- "365db64fb2c847a5a41b5d057d77600c",
1782
- "d0334d8257ce422597da3d29ac22cd4f",
1783
- "eae4e7789fe54a7b98bfda99d20360bd",
1784
- "5f48726592fe446ea43b7bdec668919b",
1785
- "3edcc888477a440d81e8b6df174966cd",
1786
- "9a23d53c1e7a448282c1aaa36d26c4ec",
1787
- "e8e2739386c045078bf2cc3987534a93",
1788
- "bb14cd687abb432b8e2a01cd58e7c550",
1789
- "c5c6159f813949a3851fb158a992a65c",
1790
- "03337be3fcd94f388ae2650078269a55",
1791
- "ff28b23c163240dc9b543f340b9d2d52",
1792
- "110e8e19d5f242829cc4cafdb9a10cb2",
1793
- "ee6313a98fd041c9b755be6b6a94ebff",
1794
- "40f2cc2506fd49dd9e284c1891312785",
1795
- "719e9ba1b98d4170a6acff418ada38fa",
1796
- "1e532190fe2b49a08a97211e3f1c60d0",
1797
- "e0ac88aa562e4354b15e182164990a79",
1798
- "5e6bd272a50b4734a8a4dd4cb683d4e2",
1799
- "9fd8ea0a806e4641ae945dc59baa0505",
1800
- "941fcfabb72940a59c7fa76e3506385d",
1801
- "23bc61b5726942169123eca1f60bd883",
1802
- "b9ebd383be484f5d8fabafd4a130d6ae",
1803
- "afdf7f80c04848fb8978d2634ee86526"
1804
- ]
1805
- },
1806
- "outputId": "8feba0de-40f9-42eb-b903-68ea33e1e5ee"
1807
- },
1808
- "outputs": [
1809
- {
1810
- "output_type": "display_data",
1811
- "data": {
1812
- "text/plain": [
1813
- "Downloading (…)okenizer_config.json: 0%| | 0.00/28.0 [00:00<?, ?B/s]"
1814
- ],
1815
- "application/vnd.jupyter.widget-view+json": {
1816
- "version_major": 2,
1817
- "version_minor": 0,
1818
- "model_id": "9972abac7caf4cc6b0d98071fd7b2e05"
1819
- }
1820
- },
1821
- "metadata": {}
1822
- },
1823
- {
1824
- "output_type": "display_data",
1825
- "data": {
1826
- "text/plain": [
1827
- "Downloading (…)solve/main/vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]"
1828
- ],
1829
- "application/vnd.jupyter.widget-view+json": {
1830
- "version_major": 2,
1831
- "version_minor": 0,
1832
- "model_id": "3a52fbc3755a4323b749da73142e5871"
1833
- }
1834
- },
1835
- "metadata": {}
1836
- },
1837
- {
1838
- "output_type": "display_data",
1839
- "data": {
1840
- "text/plain": [
1841
- "Downloading (…)/main/tokenizer.json: 0%| | 0.00/466k [00:00<?, ?B/s]"
1842
- ],
1843
- "application/vnd.jupyter.widget-view+json": {
1844
- "version_major": 2,
1845
- "version_minor": 0,
1846
- "model_id": "d0334d8257ce422597da3d29ac22cd4f"
1847
- }
1848
- },
1849
- "metadata": {}
1850
- },
1851
- {
1852
- "output_type": "display_data",
1853
- "data": {
1854
- "text/plain": [
1855
- "Downloading (…)lve/main/config.json: 0%| | 0.00/483 [00:00<?, ?B/s]"
1856
- ],
1857
- "application/vnd.jupyter.widget-view+json": {
1858
- "version_major": 2,
1859
- "version_minor": 0,
1860
- "model_id": "ee6313a98fd041c9b755be6b6a94ebff"
1861
- }
1862
- },
1863
- "metadata": {}
1864
- }
1865
- ],
1866
- "source": [
1867
- "df_train = pd.read_csv('train.csv')\n",
1868
- "df_test = pd.read_csv('test.csv')\n",
1869
- "df_test_labels = pd.read_csv('test_labels.csv')\n",
1870
- "\n",
1871
- "model_name = \"distilbert-base-uncased\"\n",
1872
- "\n",
1873
- "def read_file(f):\n",
1874
- " texts = f['comment_text'].tolist()\n",
1875
- " labels = []\n",
1876
- " for i in range(len(f)):\n",
1877
- " temp = []\n",
1878
- " temp.append(f['toxic'][i])\n",
1879
- " temp.append(f['severe_toxic'][i])\n",
1880
- " temp.append(f['obscene'][i])\n",
1881
- " temp.append(f['threat'][i])\n",
1882
- " temp.append(f['insult'][i])\n",
1883
- " temp.append(f['identity_hate'][i])\n",
1884
- " labels.append(temp)\n",
1885
- " return texts, labels\n",
1886
- "\n",
1887
- "train_texts, train_labels = read_file(df_train)\n",
1888
- "test_texts = df_test['comment_text'].tolist()\n",
1889
- "test_labels = []\n",
1890
- "for i in range(len(df_test_labels)):\n",
1891
- " temp = []\n",
1892
- " temp.append(df_test_labels['toxic'][i])\n",
1893
- " temp.append(df_test_labels['severe_toxic'][i])\n",
1894
- " temp.append(df_test_labels['obscene'][i])\n",
1895
- " temp.append(df_test_labels['threat'][i])\n",
1896
- " temp.append(df_test_labels['insult'][i])\n",
1897
- " temp.append(df_test_labels['identity_hate'][i])\n",
1898
- " test_labels.append(temp)\n",
1899
- "\n",
1900
- "train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=.2)\n",
1901
- "\n",
1902
- "tokenizer = DistilBertTokenizerFast.from_pretrained(model_name)\n",
1903
- "\n",
1904
- "ind = 0\n",
1905
- "train_encodings = {'input_ids': [], 'attention_mask': []}\n",
1906
- "\n",
1907
- "for i in range(len(train_texts)//16):\n",
1908
- " temp = tokenizer(train_texts[ind:ind+16], truncation=True, padding=True)\n",
1909
- " train_encodings['input_ids'] += temp['input_ids']\n",
1910
- " train_encodings['attention_mask'] += temp['attention_mask']\n",
1911
- " ind += 16\n",
1912
- "\n",
1913
- "ind = 0\n",
1914
- "val_encodings = {'input_ids': [], 'attention_mask': []}\n",
1915
- "\n",
1916
- "for i in range(len(val_texts)//16):\n",
1917
- " temp = tokenizer(val_texts[ind:ind+16], truncation=True, padding=True)\n",
1918
- " val_encodings['input_ids'] += temp['input_ids']\n",
1919
- " val_encodings['attention_mask'] += temp['attention_mask']\n",
1920
- " ind += 16\n",
1921
- "\n",
1922
- "ind = 0\n",
1923
- "test_encodings = {'input_ids': [], 'attention_mask': []}\n",
1924
- "\n",
1925
- "for i in range(len(test_texts)//16):\n",
1926
- " temp = tokenizer(test_texts[ind:ind+16], truncation=True, padding=True)\n",
1927
- " test_encodings['input_ids'] += temp['input_ids']\n",
1928
- " test_encodings['attention_mask'] += temp['attention_mask']\n",
1929
- " ind += 16\n",
1930
- "\n",
1931
- "while True:\n",
1932
- " if len(train_labels) > len(train_encodings):\n",
1933
- " train_labels.pop()\n",
1934
- " else:\n",
1935
- " break\n",
1936
- " \n",
1937
- "while True:\n",
1938
- " if len(val_labels) > len(val_encodings):\n",
1939
- " val_labels.pop()\n",
1940
- " else:\n",
1941
- " break\n",
1942
- "\n",
1943
- "while True:\n",
1944
- " if len(test_labels) > len(test_encodings):\n",
1945
- " test_labels.pop()\n",
1946
- " else:\n",
1947
- " break\n",
1948
- "\n",
1949
- "class dataset(Dataset):\n",
1950
- " def __init__(self, encodings, labels):\n",
1951
- " self.encodings = encodings\n",
1952
- " self.labels = labels\n",
1953
- " \n",
1954
- " def __getitem__(self, idx):\n",
1955
- " item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}\n",
1956
- " item['labels'] = torch.tensor(self.labels[idx])\n",
1957
- " return item\n",
1958
- " \n",
1959
- " def __len__(self):\n",
1960
- " return(len(self.labels))\n",
1961
- "\n",
1962
- "train_dataset_list = [[], [], [], [], [], []]\n",
1963
- "for i in train_labels:\n",
1964
- " for j in range(6):\n",
1965
- " train_dataset_list[j].append(i[j])\n",
1966
- " \n",
1967
- "val_dataset_list = [[], [], [], [], [], []]\n",
1968
- "for i in val_labels:\n",
1969
- " for j in range(6):\n",
1970
- " val_dataset_list[j].append(i[j])\n",
1971
- "\n",
1972
- "train_dataset_0 = dataset(train_encodings, train_dataset_list[0])\n",
1973
- "train_dataset_1 = dataset(train_encodings, train_dataset_list[1])\n",
1974
- "train_dataset_2 = dataset(train_encodings, train_dataset_list[2])\n",
1975
- "train_dataset_3 = dataset(train_encodings, train_dataset_list[3])\n",
1976
- "train_dataset_4 = dataset(train_encodings, train_dataset_list[4])\n",
1977
- "train_dataset_5 = dataset(train_encodings, train_dataset_list[5])\n",
1978
- "\n",
1979
- "val_dataset_0 = dataset(val_encodings, val_dataset_list[0])\n",
1980
- "val_dataset_1 = dataset(val_encodings, val_dataset_list[1])\n",
1981
- "val_dataset_2 = dataset(val_encodings, val_dataset_list[2])\n",
1982
- "val_dataset_3 = dataset(val_encodings, val_dataset_list[3])\n",
1983
- "val_dataset_4 = dataset(val_encodings, val_dataset_list[4])\n",
1984
- "val_dataset_5 = dataset(val_encodings, val_dataset_list[5])"
1985
- ]
1986
- },
1987
- {
1988
- "cell_type": "code",
1989
- "source": [
1990
- "# save tokenizer\n",
1991
- "tokenizer.save_pretrained(\"tokenizer.json\")"
1992
- ],
1993
- "metadata": {
1994
- "colab": {
1995
- "base_uri": "https://localhost:8080/"
1996
- },
1997
- "id": "dc8jvgisXLhE",
1998
- "outputId": "876334df-a494-41fd-bd50-70cdab7936ad"
1999
- },
2000
- "execution_count": null,
2001
- "outputs": [
2002
- {
2003
- "output_type": "execute_result",
2004
- "data": {
2005
- "text/plain": [
2006
- "('tokenizer.json/tokenizer_config.json',\n",
2007
- " 'tokenizer.json/special_tokens_map.json',\n",
2008
- " 'tokenizer.json/vocab.txt',\n",
2009
- " 'tokenizer.json/added_tokens.json',\n",
2010
- " 'tokenizer.json/tokenizer.json')"
2011
- ]
2012
- },
2013
- "metadata": {},
2014
- "execution_count": 9
2015
- }
2016
- ]
2017
- },
2018
- {
2019
- "cell_type": "code",
2020
- "source": [
2021
- "# training_args = TrainingArguments(output_dir='Rathgeberj/milestone3_fine_tuned', \n",
2022
- "# push_to_hub=True, \n",
2023
- "# num_train_epochs=2, \n",
2024
- "# per_device_train_batch_size=16, \n",
2025
- "# per_device_eval_batch_size=64, \n",
2026
- "# warmup_steps=500, learning_rate=5e-5, \n",
2027
- "# weight_decay=.01, logging_dir='./logs', \n",
2028
- "# logging_steps=10)\n",
2029
- "# /Users/jeffreyrathgeber\n",
2030
- "\n",
2031
- "training_args = TrainingArguments(output_dir='results', \n",
2032
- " num_train_epochs=2, \n",
2033
- " per_device_train_batch_size=16, \n",
2034
- " per_device_eval_batch_size=64, \n",
2035
- " warmup_steps=500, learning_rate=5e-5, \n",
2036
- " weight_decay=.01, logging_dir='./logs', \n",
2037
- " logging_steps=10)\n",
2038
- "\n",
2039
- "model_0 = DistilBertForSequenceClassification.from_pretrained(model_name)\n",
2040
- "model_1 = DistilBertForSequenceClassification.from_pretrained(model_name)\n",
2041
- "model_2 = DistilBertForSequenceClassification.from_pretrained(model_name)\n",
2042
- "model_3 = DistilBertForSequenceClassification.from_pretrained(model_name)\n",
2043
- "model_4 = DistilBertForSequenceClassification.from_pretrained(model_name)\n",
2044
- "model_5 = DistilBertForSequenceClassification.from_pretrained(model_name)"
2045
- ],
2046
- "metadata": {
2047
- "colab": {
2048
- "base_uri": "https://localhost:8080/",
2049
- "height": 563,
2050
- "referenced_widgets": [
2051
- "a828e2eb329548568ea23df75056ce46",
2052
- "94f47a73ba5b402b84717807b4f127d9",
2053
- "66f521247f4c4a608e4a79933ca8b499",
2054
- "9012d483dc42427189bea7c35c6a9f21",
2055
- "342182d835634efd9e8dcc16c753602b",
2056
- "a8c8ad17737448748e212de8bba42b5f",
2057
- "e414907cc96e4e3d879a6759124fd8fe",
2058
- "a464bcc2342841588e7384b4c2f10a42",
2059
- "6cc18dcc7a7d4361a5aac3271d47347a",
2060
- "cb8c4e778a994ba7bb57f279614ebfe8",
2061
- "739f16b75f3248489495a606ab3650ab"
2062
- ]
2063
- },
2064
- "id": "1FrCJtT23YVX",
2065
- "outputId": "5311555b-7789-4bd5-8931-4abc9b70360e"
2066
- },
2067
- "execution_count": null,
2068
- "outputs": [
2069
- {
2070
- "output_type": "display_data",
2071
- "data": {
2072
- "text/plain": [
2073
- "Downloading pytorch_model.bin: 0%| | 0.00/268M [00:00<?, ?B/s]"
2074
- ],
2075
- "application/vnd.jupyter.widget-view+json": {
2076
- "version_major": 2,
2077
- "version_minor": 0,
2078
- "model_id": "a828e2eb329548568ea23df75056ce46"
2079
- }
2080
- },
2081
- "metadata": {}
2082
- },
2083
- {
2084
- "output_type": "stream",
2085
- "name": "stderr",
2086
- "text": [
2087
- "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_projector.weight']\n",
2088
- "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
2089
- "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
2090
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
2091
- "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
2092
- "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_projector.weight']\n",
2093
- "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
2094
- "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
2095
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
2096
- "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
2097
- "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_projector.weight']\n",
2098
- "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
2099
- "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
2100
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
2101
- "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
2102
- "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_projector.weight']\n",
2103
- "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
2104
- "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
2105
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
2106
- "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
2107
- "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_projector.weight']\n",
2108
- "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
2109
- "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
2110
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
2111
- "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
2112
- "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_transform.weight', 'vocab_layer_norm.weight', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_projector.bias', 'vocab_projector.weight']\n",
2113
- "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
2114
- "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
2115
- "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.bias', 'classifier.bias', 'pre_classifier.weight']\n",
2116
- "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
2117
- ]
2118
- }
2119
- ]
2120
- },
2121
- {
2122
- "cell_type": "code",
2123
- "source": [
2124
- "trainer_0 = Trainer(model=model_0, args=training_args, train_dataset=train_dataset_0, eval_dataset=val_dataset_0)\n",
2125
- "trainer_0.train()\n",
2126
- "trainer_0.save_model(output_dir='NEW')"
2127
- ],
2128
- "metadata": {
2129
- "colab": {
2130
- "base_uri": "https://localhost:8080/",
2131
- "height": 127
2132
- },
2133
- "id": "_iaP4g715FZl",
2134
- "outputId": "feab2bf7-e30a-4282-8f34-4d45bf2baf55"
2135
- },
2136
- "execution_count": null,
2137
- "outputs": [
2138
- {
2139
- "output_type": "stream",
2140
- "name": "stderr",
2141
- "text": [
2142
- "/usr/local/lib/python3.9/dist-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
2143
- " warnings.warn(\n"
2144
- ]
2145
- },
2146
- {
2147
- "output_type": "display_data",
2148
- "data": {
2149
- "text/plain": [
2150
- "<IPython.core.display.HTML object>"
2151
- ],
2152
- "text/html": [
2153
- "\n",
2154
- " <div>\n",
2155
- " \n",
2156
- " <progress value='2' max='2' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2157
- " [2/2 00:04, Epoch 2/2]\n",
2158
- " </div>\n",
2159
- " <table border=\"1\" class=\"dataframe\">\n",
2160
- " <thead>\n",
2161
- " <tr style=\"text-align: left;\">\n",
2162
- " <th>Step</th>\n",
2163
- " <th>Training Loss</th>\n",
2164
- " </tr>\n",
2165
- " </thead>\n",
2166
- " <tbody>\n",
2167
- " </tbody>\n",
2168
- "</table><p>"
2169
- ]
2170
- },
2171
- "metadata": {}
2172
- }
2173
- ]
2174
- },
2175
- {
2176
- "cell_type": "code",
2177
- "source": [
2178
- "trainer_1 = Trainer(model=model_1, args=training_args, train_dataset=train_dataset_1, eval_dataset=val_dataset_1)\n",
2179
- "trainer_1.train()\n",
2180
- "trainer_1.save_model(output_dir='UPDATED_1')"
2181
- ],
2182
- "metadata": {
2183
- "colab": {
2184
- "base_uri": "https://localhost:8080/",
2185
- "height": 74
2186
- },
2187
- "id": "q6hRKNNgGrVB",
2188
- "outputId": "8dddc83c-4292-424c-8534-61d8125ecac5"
2189
- },
2190
- "execution_count": null,
2191
- "outputs": [
2192
- {
2193
- "output_type": "display_data",
2194
- "data": {
2195
- "text/plain": [
2196
- "<IPython.core.display.HTML object>"
2197
- ],
2198
- "text/html": [
2199
- "\n",
2200
- " <div>\n",
2201
- " \n",
2202
- " <progress value='2' max='2' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2203
- " [2/2 00:09, Epoch 2/2]\n",
2204
- " </div>\n",
2205
- " <table border=\"1\" class=\"dataframe\">\n",
2206
- " <thead>\n",
2207
- " <tr style=\"text-align: left;\">\n",
2208
- " <th>Step</th>\n",
2209
- " <th>Training Loss</th>\n",
2210
- " </tr>\n",
2211
- " </thead>\n",
2212
- " <tbody>\n",
2213
- " </tbody>\n",
2214
- "</table><p>"
2215
- ]
2216
- },
2217
- "metadata": {}
2218
- }
2219
- ]
2220
- },
2221
- {
2222
- "cell_type": "code",
2223
- "source": [
2224
- "trainer_2 = Trainer(model=model_2, args=training_args, train_dataset=train_dataset_2, eval_dataset=val_dataset_2)\n",
2225
- "trainer_2.train()\n",
2226
- "trainer_2.save_model(output_dir='UPDATED_2')\n"
2227
- ],
2228
- "metadata": {
2229
- "colab": {
2230
- "base_uri": "https://localhost:8080/",
2231
- "height": 74
2232
- },
2233
- "id": "UwuqSkNdGrgk",
2234
- "outputId": "ecc6c398-36d1-40c3-a7ca-0ad99cf0369e"
2235
- },
2236
- "execution_count": null,
2237
- "outputs": [
2238
- {
2239
- "output_type": "display_data",
2240
- "data": {
2241
- "text/plain": [
2242
- "<IPython.core.display.HTML object>"
2243
- ],
2244
- "text/html": [
2245
- "\n",
2246
- " <div>\n",
2247
- " \n",
2248
- " <progress value='2' max='2' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2249
- " [2/2 00:03, Epoch 2/2]\n",
2250
- " </div>\n",
2251
- " <table border=\"1\" class=\"dataframe\">\n",
2252
- " <thead>\n",
2253
- " <tr style=\"text-align: left;\">\n",
2254
- " <th>Step</th>\n",
2255
- " <th>Training Loss</th>\n",
2256
- " </tr>\n",
2257
- " </thead>\n",
2258
- " <tbody>\n",
2259
- " </tbody>\n",
2260
- "</table><p>"
2261
- ]
2262
- },
2263
- "metadata": {}
2264
- }
2265
- ]
2266
- },
2267
- {
2268
- "cell_type": "code",
2269
- "source": [
2270
- "trainer_3 = Trainer(model=model_3, args=training_args, train_dataset=train_dataset_3, eval_dataset=val_dataset_3)\n",
2271
- "trainer_3.train()\n",
2272
- "trainer_3.save_model(output_dir='UPDATED_3')"
2273
- ],
2274
- "metadata": {
2275
- "colab": {
2276
- "base_uri": "https://localhost:8080/",
2277
- "height": 74
2278
- },
2279
- "id": "TbysKTvgGrqJ",
2280
- "outputId": "e8f04274-92f8-439e-b567-75d589eaaa1b"
2281
- },
2282
- "execution_count": null,
2283
- "outputs": [
2284
- {
2285
- "output_type": "display_data",
2286
- "data": {
2287
- "text/plain": [
2288
- "<IPython.core.display.HTML object>"
2289
- ],
2290
- "text/html": [
2291
- "\n",
2292
- " <div>\n",
2293
- " \n",
2294
- " <progress value='2' max='2' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2295
- " [2/2 00:03, Epoch 2/2]\n",
2296
- " </div>\n",
2297
- " <table border=\"1\" class=\"dataframe\">\n",
2298
- " <thead>\n",
2299
- " <tr style=\"text-align: left;\">\n",
2300
- " <th>Step</th>\n",
2301
- " <th>Training Loss</th>\n",
2302
- " </tr>\n",
2303
- " </thead>\n",
2304
- " <tbody>\n",
2305
- " </tbody>\n",
2306
- "</table><p>"
2307
- ]
2308
- },
2309
- "metadata": {}
2310
- }
2311
- ]
2312
- },
2313
- {
2314
- "cell_type": "code",
2315
- "source": [
2316
- "trainer_4 = Trainer(model=model_4, args=training_args, train_dataset=train_dataset_4, eval_dataset=val_dataset_4)\n",
2317
- "trainer_4.train()\n",
2318
- "trainer_4.save_model(output_dir='UPDATED_4')"
2319
- ],
2320
- "metadata": {
2321
- "id": "VTJ-4cENGr05",
2322
- "colab": {
2323
- "base_uri": "https://localhost:8080/",
2324
- "height": 74
2325
- },
2326
- "outputId": "54cc3a64-c511-4484-c09f-f8ffe2ff65d7"
2327
- },
2328
- "execution_count": null,
2329
- "outputs": [
2330
- {
2331
- "output_type": "display_data",
2332
- "data": {
2333
- "text/plain": [
2334
- "<IPython.core.display.HTML object>"
2335
- ],
2336
- "text/html": [
2337
- "\n",
2338
- " <div>\n",
2339
- " \n",
2340
- " <progress value='2' max='2' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2341
- " [2/2 00:03, Epoch 2/2]\n",
2342
- " </div>\n",
2343
- " <table border=\"1\" class=\"dataframe\">\n",
2344
- " <thead>\n",
2345
- " <tr style=\"text-align: left;\">\n",
2346
- " <th>Step</th>\n",
2347
- " <th>Training Loss</th>\n",
2348
- " </tr>\n",
2349
- " </thead>\n",
2350
- " <tbody>\n",
2351
- " </tbody>\n",
2352
- "</table><p>"
2353
- ]
2354
- },
2355
- "metadata": {}
2356
- }
2357
- ]
2358
- },
2359
- {
2360
- "cell_type": "code",
2361
- "source": [
2362
- "trainer_5 = Trainer(model=model_5, args=training_args, train_dataset=train_dataset_5, eval_dataset=val_dataset_5)\n",
2363
- "trainer_5.train()\n",
2364
- "trainer_5.save_model(output_dir='UPDATED_5')"
2365
- ],
2366
- "metadata": {
2367
- "id": "mgIWDFQ2HtXL",
2368
- "colab": {
2369
- "base_uri": "https://localhost:8080/",
2370
- "height": 74
2371
- },
2372
- "outputId": "7cddb662-1c2f-4923-c747-866ec6f3297d"
2373
- },
2374
- "execution_count": null,
2375
- "outputs": [
2376
- {
2377
- "output_type": "display_data",
2378
- "data": {
2379
- "text/plain": [
2380
- "<IPython.core.display.HTML object>"
2381
- ],
2382
- "text/html": [
2383
- "\n",
2384
- " <div>\n",
2385
- " \n",
2386
- " <progress value='2' max='2' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
2387
- " [2/2 00:03, Epoch 2/2]\n",
2388
- " </div>\n",
2389
- " <table border=\"1\" class=\"dataframe\">\n",
2390
- " <thead>\n",
2391
- " <tr style=\"text-align: left;\">\n",
2392
- " <th>Step</th>\n",
2393
- " <th>Training Loss</th>\n",
2394
- " </tr>\n",
2395
- " </thead>\n",
2396
- " <tbody>\n",
2397
- " </tbody>\n",
2398
- "</table><p>"
2399
- ]
2400
- },
2401
- "metadata": {}
2402
- }
2403
- ]
2404
- }
2405
- ]
2406
- }