bogdanraduta commited on
Commit
0b44557
·
verified ·
1 Parent(s): 6b7d0ec

Upload eval/calibration.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. eval/calibration.json +576 -0
eval/calibration.json ADDED
@@ -0,0 +1,576 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "threshold": 0.84,
3
+ "objective": "macro_f1",
4
+ "value_on_val": 0.9308,
5
+ "default_threshold": 0.5,
6
+ "default_value_on_val": 0.9232,
7
+ "improvement": 0.0076,
8
+ "chosen_on": "validation split, never test",
9
+ "curve": [
10
+ {
11
+ "threshold": 0.02,
12
+ "macro_f1": 0.1636,
13
+ "any_label_recall": 0.9987,
14
+ "any_label_fpr": 0.0337
15
+ },
16
+ {
17
+ "threshold": 0.03,
18
+ "macro_f1": 0.2553,
19
+ "any_label_recall": 0.9987,
20
+ "any_label_fpr": 0.0273
21
+ },
22
+ {
23
+ "threshold": 0.04,
24
+ "macro_f1": 0.4666,
25
+ "any_label_recall": 0.9987,
26
+ "any_label_fpr": 0.0233
27
+ },
28
+ {
29
+ "threshold": 0.05,
30
+ "macro_f1": 0.6276,
31
+ "any_label_recall": 0.9987,
32
+ "any_label_fpr": 0.0225
33
+ },
34
+ {
35
+ "threshold": 0.06,
36
+ "macro_f1": 0.7077,
37
+ "any_label_recall": 0.9987,
38
+ "any_label_fpr": 0.0209
39
+ },
40
+ {
41
+ "threshold": 0.07,
42
+ "macro_f1": 0.7568,
43
+ "any_label_recall": 0.9987,
44
+ "any_label_fpr": 0.02
45
+ },
46
+ {
47
+ "threshold": 0.08,
48
+ "macro_f1": 0.7885,
49
+ "any_label_recall": 0.9987,
50
+ "any_label_fpr": 0.0184
51
+ },
52
+ {
53
+ "threshold": 0.09,
54
+ "macro_f1": 0.8071,
55
+ "any_label_recall": 0.9987,
56
+ "any_label_fpr": 0.0168
57
+ },
58
+ {
59
+ "threshold": 0.1,
60
+ "macro_f1": 0.8238,
61
+ "any_label_recall": 0.9987,
62
+ "any_label_fpr": 0.016
63
+ },
64
+ {
65
+ "threshold": 0.11,
66
+ "macro_f1": 0.835,
67
+ "any_label_recall": 0.9987,
68
+ "any_label_fpr": 0.0144
69
+ },
70
+ {
71
+ "threshold": 0.12,
72
+ "macro_f1": 0.8453,
73
+ "any_label_recall": 0.9987,
74
+ "any_label_fpr": 0.0136
75
+ },
76
+ {
77
+ "threshold": 0.13,
78
+ "macro_f1": 0.8529,
79
+ "any_label_recall": 0.9987,
80
+ "any_label_fpr": 0.0136
81
+ },
82
+ {
83
+ "threshold": 0.14,
84
+ "macro_f1": 0.8586,
85
+ "any_label_recall": 0.9987,
86
+ "any_label_fpr": 0.0136
87
+ },
88
+ {
89
+ "threshold": 0.15,
90
+ "macro_f1": 0.8638,
91
+ "any_label_recall": 0.9987,
92
+ "any_label_fpr": 0.0136
93
+ },
94
+ {
95
+ "threshold": 0.16,
96
+ "macro_f1": 0.869,
97
+ "any_label_recall": 0.9987,
98
+ "any_label_fpr": 0.0136
99
+ },
100
+ {
101
+ "threshold": 0.17,
102
+ "macro_f1": 0.8737,
103
+ "any_label_recall": 0.9987,
104
+ "any_label_fpr": 0.0136
105
+ },
106
+ {
107
+ "threshold": 0.18,
108
+ "macro_f1": 0.8765,
109
+ "any_label_recall": 0.9987,
110
+ "any_label_fpr": 0.0136
111
+ },
112
+ {
113
+ "threshold": 0.19,
114
+ "macro_f1": 0.88,
115
+ "any_label_recall": 0.9987,
116
+ "any_label_fpr": 0.0136
117
+ },
118
+ {
119
+ "threshold": 0.2,
120
+ "macro_f1": 0.8823,
121
+ "any_label_recall": 0.9987,
122
+ "any_label_fpr": 0.0128
123
+ },
124
+ {
125
+ "threshold": 0.21,
126
+ "macro_f1": 0.8845,
127
+ "any_label_recall": 0.9987,
128
+ "any_label_fpr": 0.0128
129
+ },
130
+ {
131
+ "threshold": 0.22,
132
+ "macro_f1": 0.8881,
133
+ "any_label_recall": 0.9987,
134
+ "any_label_fpr": 0.012
135
+ },
136
+ {
137
+ "threshold": 0.23,
138
+ "macro_f1": 0.8902,
139
+ "any_label_recall": 0.9987,
140
+ "any_label_fpr": 0.012
141
+ },
142
+ {
143
+ "threshold": 0.24,
144
+ "macro_f1": 0.8928,
145
+ "any_label_recall": 0.9987,
146
+ "any_label_fpr": 0.012
147
+ },
148
+ {
149
+ "threshold": 0.25,
150
+ "macro_f1": 0.8942,
151
+ "any_label_recall": 0.9987,
152
+ "any_label_fpr": 0.012
153
+ },
154
+ {
155
+ "threshold": 0.26,
156
+ "macro_f1": 0.896,
157
+ "any_label_recall": 0.9987,
158
+ "any_label_fpr": 0.012
159
+ },
160
+ {
161
+ "threshold": 0.27,
162
+ "macro_f1": 0.898,
163
+ "any_label_recall": 0.9987,
164
+ "any_label_fpr": 0.012
165
+ },
166
+ {
167
+ "threshold": 0.28,
168
+ "macro_f1": 0.8993,
169
+ "any_label_recall": 0.9987,
170
+ "any_label_fpr": 0.012
171
+ },
172
+ {
173
+ "threshold": 0.29,
174
+ "macro_f1": 0.8994,
175
+ "any_label_recall": 0.9987,
176
+ "any_label_fpr": 0.012
177
+ },
178
+ {
179
+ "threshold": 0.3,
180
+ "macro_f1": 0.9013,
181
+ "any_label_recall": 0.9987,
182
+ "any_label_fpr": 0.012
183
+ },
184
+ {
185
+ "threshold": 0.31,
186
+ "macro_f1": 0.9025,
187
+ "any_label_recall": 0.9987,
188
+ "any_label_fpr": 0.012
189
+ },
190
+ {
191
+ "threshold": 0.32,
192
+ "macro_f1": 0.904,
193
+ "any_label_recall": 0.9987,
194
+ "any_label_fpr": 0.012
195
+ },
196
+ {
197
+ "threshold": 0.33,
198
+ "macro_f1": 0.9048,
199
+ "any_label_recall": 0.9987,
200
+ "any_label_fpr": 0.012
201
+ },
202
+ {
203
+ "threshold": 0.34,
204
+ "macro_f1": 0.906,
205
+ "any_label_recall": 0.9987,
206
+ "any_label_fpr": 0.012
207
+ },
208
+ {
209
+ "threshold": 0.35,
210
+ "macro_f1": 0.9066,
211
+ "any_label_recall": 0.9987,
212
+ "any_label_fpr": 0.012
213
+ },
214
+ {
215
+ "threshold": 0.36,
216
+ "macro_f1": 0.9084,
217
+ "any_label_recall": 0.9987,
218
+ "any_label_fpr": 0.012
219
+ },
220
+ {
221
+ "threshold": 0.37,
222
+ "macro_f1": 0.9099,
223
+ "any_label_recall": 0.9987,
224
+ "any_label_fpr": 0.012
225
+ },
226
+ {
227
+ "threshold": 0.38,
228
+ "macro_f1": 0.9104,
229
+ "any_label_recall": 0.9987,
230
+ "any_label_fpr": 0.012
231
+ },
232
+ {
233
+ "threshold": 0.39,
234
+ "macro_f1": 0.9114,
235
+ "any_label_recall": 0.9987,
236
+ "any_label_fpr": 0.012
237
+ },
238
+ {
239
+ "threshold": 0.4,
240
+ "macro_f1": 0.9127,
241
+ "any_label_recall": 0.9987,
242
+ "any_label_fpr": 0.0112
243
+ },
244
+ {
245
+ "threshold": 0.41,
246
+ "macro_f1": 0.9143,
247
+ "any_label_recall": 0.9987,
248
+ "any_label_fpr": 0.0112
249
+ },
250
+ {
251
+ "threshold": 0.42,
252
+ "macro_f1": 0.9148,
253
+ "any_label_recall": 0.9987,
254
+ "any_label_fpr": 0.0112
255
+ },
256
+ {
257
+ "threshold": 0.43,
258
+ "macro_f1": 0.9164,
259
+ "any_label_recall": 0.9987,
260
+ "any_label_fpr": 0.0104
261
+ },
262
+ {
263
+ "threshold": 0.44,
264
+ "macro_f1": 0.9168,
265
+ "any_label_recall": 0.9987,
266
+ "any_label_fpr": 0.0104
267
+ },
268
+ {
269
+ "threshold": 0.45,
270
+ "macro_f1": 0.9183,
271
+ "any_label_recall": 0.9987,
272
+ "any_label_fpr": 0.0104
273
+ },
274
+ {
275
+ "threshold": 0.46,
276
+ "macro_f1": 0.9186,
277
+ "any_label_recall": 0.9987,
278
+ "any_label_fpr": 0.0104
279
+ },
280
+ {
281
+ "threshold": 0.47,
282
+ "macro_f1": 0.9191,
283
+ "any_label_recall": 0.9987,
284
+ "any_label_fpr": 0.0104
285
+ },
286
+ {
287
+ "threshold": 0.48,
288
+ "macro_f1": 0.9202,
289
+ "any_label_recall": 0.9987,
290
+ "any_label_fpr": 0.0104
291
+ },
292
+ {
293
+ "threshold": 0.49,
294
+ "macro_f1": 0.9221,
295
+ "any_label_recall": 0.9987,
296
+ "any_label_fpr": 0.0104
297
+ },
298
+ {
299
+ "threshold": 0.5,
300
+ "macro_f1": 0.9232,
301
+ "any_label_recall": 0.9987,
302
+ "any_label_fpr": 0.0104
303
+ },
304
+ {
305
+ "threshold": 0.51,
306
+ "macro_f1": 0.9237,
307
+ "any_label_recall": 0.9987,
308
+ "any_label_fpr": 0.0104
309
+ },
310
+ {
311
+ "threshold": 0.52,
312
+ "macro_f1": 0.9239,
313
+ "any_label_recall": 0.9987,
314
+ "any_label_fpr": 0.0104
315
+ },
316
+ {
317
+ "threshold": 0.53,
318
+ "macro_f1": 0.9248,
319
+ "any_label_recall": 0.9987,
320
+ "any_label_fpr": 0.0104
321
+ },
322
+ {
323
+ "threshold": 0.54,
324
+ "macro_f1": 0.9251,
325
+ "any_label_recall": 0.9987,
326
+ "any_label_fpr": 0.0104
327
+ },
328
+ {
329
+ "threshold": 0.55,
330
+ "macro_f1": 0.926,
331
+ "any_label_recall": 0.9974,
332
+ "any_label_fpr": 0.0104
333
+ },
334
+ {
335
+ "threshold": 0.56,
336
+ "macro_f1": 0.9265,
337
+ "any_label_recall": 0.9974,
338
+ "any_label_fpr": 0.0104
339
+ },
340
+ {
341
+ "threshold": 0.57,
342
+ "macro_f1": 0.927,
343
+ "any_label_recall": 0.9974,
344
+ "any_label_fpr": 0.0104
345
+ },
346
+ {
347
+ "threshold": 0.58,
348
+ "macro_f1": 0.9282,
349
+ "any_label_recall": 0.9974,
350
+ "any_label_fpr": 0.0104
351
+ },
352
+ {
353
+ "threshold": 0.59,
354
+ "macro_f1": 0.9284,
355
+ "any_label_recall": 0.9974,
356
+ "any_label_fpr": 0.0104
357
+ },
358
+ {
359
+ "threshold": 0.6,
360
+ "macro_f1": 0.9288,
361
+ "any_label_recall": 0.9968,
362
+ "any_label_fpr": 0.0104
363
+ },
364
+ {
365
+ "threshold": 0.61,
366
+ "macro_f1": 0.9291,
367
+ "any_label_recall": 0.9968,
368
+ "any_label_fpr": 0.0104
369
+ },
370
+ {
371
+ "threshold": 0.62,
372
+ "macro_f1": 0.9287,
373
+ "any_label_recall": 0.9968,
374
+ "any_label_fpr": 0.0104
375
+ },
376
+ {
377
+ "threshold": 0.63,
378
+ "macro_f1": 0.9283,
379
+ "any_label_recall": 0.9968,
380
+ "any_label_fpr": 0.0104
381
+ },
382
+ {
383
+ "threshold": 0.64,
384
+ "macro_f1": 0.929,
385
+ "any_label_recall": 0.9968,
386
+ "any_label_fpr": 0.0104
387
+ },
388
+ {
389
+ "threshold": 0.65,
390
+ "macro_f1": 0.9285,
391
+ "any_label_recall": 0.9968,
392
+ "any_label_fpr": 0.0104
393
+ },
394
+ {
395
+ "threshold": 0.66,
396
+ "macro_f1": 0.929,
397
+ "any_label_recall": 0.9968,
398
+ "any_label_fpr": 0.0104
399
+ },
400
+ {
401
+ "threshold": 0.67,
402
+ "macro_f1": 0.9285,
403
+ "any_label_recall": 0.9968,
404
+ "any_label_fpr": 0.0104
405
+ },
406
+ {
407
+ "threshold": 0.68,
408
+ "macro_f1": 0.9284,
409
+ "any_label_recall": 0.9968,
410
+ "any_label_fpr": 0.0104
411
+ },
412
+ {
413
+ "threshold": 0.69,
414
+ "macro_f1": 0.9289,
415
+ "any_label_recall": 0.9968,
416
+ "any_label_fpr": 0.0104
417
+ },
418
+ {
419
+ "threshold": 0.7,
420
+ "macro_f1": 0.9299,
421
+ "any_label_recall": 0.9968,
422
+ "any_label_fpr": 0.0104
423
+ },
424
+ {
425
+ "threshold": 0.71,
426
+ "macro_f1": 0.9302,
427
+ "any_label_recall": 0.9961,
428
+ "any_label_fpr": 0.0104
429
+ },
430
+ {
431
+ "threshold": 0.72,
432
+ "macro_f1": 0.9291,
433
+ "any_label_recall": 0.9955,
434
+ "any_label_fpr": 0.0104
435
+ },
436
+ {
437
+ "threshold": 0.73,
438
+ "macro_f1": 0.9297,
439
+ "any_label_recall": 0.9955,
440
+ "any_label_fpr": 0.0104
441
+ },
442
+ {
443
+ "threshold": 0.74,
444
+ "macro_f1": 0.9302,
445
+ "any_label_recall": 0.9955,
446
+ "any_label_fpr": 0.0104
447
+ },
448
+ {
449
+ "threshold": 0.75,
450
+ "macro_f1": 0.9302,
451
+ "any_label_recall": 0.9955,
452
+ "any_label_fpr": 0.0096
453
+ },
454
+ {
455
+ "threshold": 0.76,
456
+ "macro_f1": 0.9294,
457
+ "any_label_recall": 0.9942,
458
+ "any_label_fpr": 0.0096
459
+ },
460
+ {
461
+ "threshold": 0.77,
462
+ "macro_f1": 0.9281,
463
+ "any_label_recall": 0.9936,
464
+ "any_label_fpr": 0.0096
465
+ },
466
+ {
467
+ "threshold": 0.78,
468
+ "macro_f1": 0.9292,
469
+ "any_label_recall": 0.9923,
470
+ "any_label_fpr": 0.0096
471
+ },
472
+ {
473
+ "threshold": 0.79,
474
+ "macro_f1": 0.9298,
475
+ "any_label_recall": 0.9923,
476
+ "any_label_fpr": 0.0088
477
+ },
478
+ {
479
+ "threshold": 0.8,
480
+ "macro_f1": 0.9296,
481
+ "any_label_recall": 0.9923,
482
+ "any_label_fpr": 0.0088
483
+ },
484
+ {
485
+ "threshold": 0.81,
486
+ "macro_f1": 0.9299,
487
+ "any_label_recall": 0.991,
488
+ "any_label_fpr": 0.0088
489
+ },
490
+ {
491
+ "threshold": 0.82,
492
+ "macro_f1": 0.9299,
493
+ "any_label_recall": 0.9903,
494
+ "any_label_fpr": 0.008
495
+ },
496
+ {
497
+ "threshold": 0.83,
498
+ "macro_f1": 0.9307,
499
+ "any_label_recall": 0.989,
500
+ "any_label_fpr": 0.0072
501
+ },
502
+ {
503
+ "threshold": 0.84,
504
+ "macro_f1": 0.9308,
505
+ "any_label_recall": 0.9884,
506
+ "any_label_fpr": 0.0072
507
+ },
508
+ {
509
+ "threshold": 0.85,
510
+ "macro_f1": 0.9297,
511
+ "any_label_recall": 0.9884,
512
+ "any_label_fpr": 0.0072
513
+ },
514
+ {
515
+ "threshold": 0.86,
516
+ "macro_f1": 0.9301,
517
+ "any_label_recall": 0.9871,
518
+ "any_label_fpr": 0.0072
519
+ },
520
+ {
521
+ "threshold": 0.87,
522
+ "macro_f1": 0.9293,
523
+ "any_label_recall": 0.9832,
524
+ "any_label_fpr": 0.0072
525
+ },
526
+ {
527
+ "threshold": 0.88,
528
+ "macro_f1": 0.9294,
529
+ "any_label_recall": 0.982,
530
+ "any_label_fpr": 0.0072
531
+ },
532
+ {
533
+ "threshold": 0.89,
534
+ "macro_f1": 0.9296,
535
+ "any_label_recall": 0.9781,
536
+ "any_label_fpr": 0.0064
537
+ },
538
+ {
539
+ "threshold": 0.9,
540
+ "macro_f1": 0.9281,
541
+ "any_label_recall": 0.9736,
542
+ "any_label_fpr": 0.0056
543
+ },
544
+ {
545
+ "threshold": 0.91,
546
+ "macro_f1": 0.9273,
547
+ "any_label_recall": 0.9691,
548
+ "any_label_fpr": 0.0056
549
+ },
550
+ {
551
+ "threshold": 0.92,
552
+ "macro_f1": 0.9264,
553
+ "any_label_recall": 0.9652,
554
+ "any_label_fpr": 0.0048
555
+ },
556
+ {
557
+ "threshold": 0.93,
558
+ "macro_f1": 0.9254,
559
+ "any_label_recall": 0.9568,
560
+ "any_label_fpr": 0.004
561
+ },
562
+ {
563
+ "threshold": 0.94,
564
+ "macro_f1": 0.9248,
565
+ "any_label_recall": 0.9523,
566
+ "any_label_fpr": 0.0032
567
+ },
568
+ {
569
+ "threshold": 0.95,
570
+ "macro_f1": 0.9215,
571
+ "any_label_recall": 0.9362,
572
+ "any_label_fpr": 0.0032
573
+ }
574
+ ],
575
+ "notes": []
576
+ }