alex-miller commited on
Commit
22dac1f
1 Parent(s): f80af53

Training in progress, epoch 1

Browse files
added_tokens.json ADDED
@@ -0,0 +1,1061 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "##_1": 106650,
3
+ "##_2": 106783,
4
+ "##ación": 106806,
5
+ "##ción": 106817,
6
+ "##án": 106617,
7
+ "##ée": 106794,
8
+ "##és": 106424,
9
+ "##ía": 106905,
10
+ "##ów": 106933,
11
+ "4liter": 106716,
12
+ "accelerate": 106281,
13
+ "accelerated": 106732,
14
+ "accelerating": 106454,
15
+ "accessibility": 106500,
16
+ "acción": 106092,
17
+ "accompagnement": 106256,
18
+ "accompagner": 106872,
19
+ "accountability": 105902,
20
+ "accountable": 106045,
21
+ "accroître": 106329,
22
+ "accès": 105914,
23
+ "acdi": 106193,
24
+ "acogida": 106834,
25
+ "acompañamiento": 106736,
26
+ "activités": 105921,
27
+ "actuación": 106792,
28
+ "adapt": 106345,
29
+ "adaptive": 106635,
30
+ "addendum": 106688,
31
+ "addresses": 106597,
32
+ "addressing": 105974,
33
+ "además": 106233,
34
+ "adequate": 106158,
35
+ "adjustment": 106502,
36
+ "admin": 105900,
37
+ "administratifs": 106470,
38
+ "administrations": 106680,
39
+ "adolescence": 106916,
40
+ "adolescents": 105975,
41
+ "advancing": 106168,
42
+ "adviser": 106497,
43
+ "advisors": 106271,
44
+ "advocacy": 105892,
45
+ "advocating": 106871,
46
+ "aecid": 106861,
47
+ "aefe": 106119,
48
+ "afdb": 105941,
49
+ "affecting": 106624,
50
+ "affectées": 106645,
51
+ "affordable": 106192,
52
+ "ageing": 106856,
53
+ "agendas": 106826,
54
+ "agri": 106287,
55
+ "agribusiness": 106443,
56
+ "agric": 106660,
57
+ "agriculteurs": 106637,
58
+ "agroforestry": 106882,
59
+ "agrícola": 106663,
60
+ "aiming": 106348,
61
+ "aligned": 106679,
62
+ "alimentación": 106421,
63
+ "alimentaire": 105912,
64
+ "alimentaires": 106661,
65
+ "alimentaria": 106018,
66
+ "alleviate": 106837,
67
+ "alleviation": 106320,
68
+ "alliances": 106266,
69
+ "allocation": 106100,
70
+ "alumnado": 106503,
71
+ "amelioration": 106928,
72
+ "amélioration": 105923,
73
+ "améliorer": 105924,
74
+ "aménagement": 106544,
75
+ "américa": 106727,
76
+ "analysed": 106476,
77
+ "analytical": 106459,
78
+ "analyze": 106613,
79
+ "andean": 106525,
80
+ "année": 106692,
81
+ "antimicrobial": 106699,
82
+ "análisis": 106501,
83
+ "apoyar": 106430,
84
+ "applying": 106892,
85
+ "apporté": 106815,
86
+ "appraisal": 106368,
87
+ "apprentissage": 106573,
88
+ "appropriation": 105969,
89
+ "approvisionnement": 106225,
90
+ "approximate": 106277,
91
+ "appuie": 106523,
92
+ "appuyer": 106124,
93
+ "aprendizaje": 106877,
94
+ "après": 106866,
95
+ "aquaculture": 106342,
96
+ "arid": 106705,
97
+ "asdb": 106353,
98
+ "asociaciones": 106585,
99
+ "asociación": 106302,
100
+ "assainissement": 105939,
101
+ "assess": 106034,
102
+ "assessed": 106272,
103
+ "assessing": 106504,
104
+ "assessments": 106157,
105
+ "assisting": 106428,
106
+ "associatifs": 106811,
107
+ "atención": 105987,
108
+ "audiovisual": 106314,
109
+ "audits": 106413,
110
+ "aulas": 106845,
111
+ "auprès": 106390,
112
+ "ausaid": 106567,
113
+ "autonomisation": 106671,
114
+ "autonomy": 106760,
115
+ "autorités": 106510,
116
+ "avian": 106796,
117
+ "ayudas": 106584,
118
+ "años": 106085,
119
+ "bamako": 106769,
120
+ "barriers": 106095,
121
+ "baseline": 106460,
122
+ "beans": 106775,
123
+ "becas": 106213,
124
+ "beneficiaries": 105993,
125
+ "beneficiarios": 106548,
126
+ "beneficiary": 106667,
127
+ "bijdrage": 106543,
128
+ "bilateral": 106056,
129
+ "biodiversité": 106614,
130
+ "biomass": 106700,
131
+ "biosphere": 106890,
132
+ "blend": 106498,
133
+ "bolivie": 106848,
134
+ "bourses": 105972,
135
+ "bridging": 106664,
136
+ "broader": 106405,
137
+ "budgeting": 106691,
138
+ "budgets": 106862,
139
+ "budgétaire": 106474,
140
+ "builds": 106354,
141
+ "básica": 106767,
142
+ "básicos": 106708,
143
+ "bénin": 106395,
144
+ "bénéficiaires": 106378,
145
+ "cacao": 106884,
146
+ "cadres": 106495,
147
+ "cambodge": 106891,
148
+ "campamentos": 106745,
149
+ "campaña": 106440,
150
+ "campesinas": 106436,
151
+ "capacidades": 105955,
152
+ "capacitación": 106052,
153
+ "capacities": 105885,
154
+ "capacité": 106070,
155
+ "capacités": 105909,
156
+ "caritas": 106310,
157
+ "carsi": 106590,
158
+ "catastrophes": 106673,
159
+ "cdcs": 106171,
160
+ "centred": 106317,
161
+ "cerp": 106473,
162
+ "cfli": 106071,
163
+ "channelcode": 106869,
164
+ "cholera": 106793,
165
+ "cida": 106086,
166
+ "ciudadana": 106636,
167
+ "ciudadanía": 106179,
168
+ "classrooms": 106194,
169
+ "clearance": 106243,
170
+ "climatique": 106491,
171
+ "climatiques": 106819,
172
+ "climático": 106840,
173
+ "clinics": 106579,
174
+ "cochabamba": 106841,
175
+ "cocoa": 106577,
176
+ "cohesion": 106279,
177
+ "colaboración": 106293,
178
+ "colectivos": 106582,
179
+ "collectivités": 106046,
180
+ "colombian": 106359,
181
+ "combating": 106227,
182
+ "comercialización": 106566,
183
+ "comité": 106580,
184
+ "comités": 106805,
185
+ "comm": 106678,
186
+ "commercialisation": 106759,
187
+ "commitments": 106212,
188
+ "commitmentsto": 106781,
189
+ "commodities": 106220,
190
+ "commodity": 105907,
191
+ "communautaire": 106099,
192
+ "communautaires": 106253,
193
+ "communauté": 106489,
194
+ "communautés": 106033,
195
+ "communicable": 106340,
196
+ "competence": 106477,
197
+ "competitiveness": 106000,
198
+ "complementary": 106432,
199
+ "compliance": 106152,
200
+ "complémentaire": 106571,
201
+ "composante": 106540,
202
+ "composantes": 106455,
203
+ "comprennent": 106389,
204
+ "compétences": 106113,
205
+ "comunicación": 106196,
206
+ "comunitaria": 106311,
207
+ "comunitarias": 106813,
208
+ "comunitario": 106437,
209
+ "comunitarios": 106908,
210
+ "conflits": 106169,
211
+ "connaissances": 106295,
212
+ "connectivity": 106410,
213
+ "conocimientos": 106545,
214
+ "consented": 106558,
215
+ "conservación": 106784,
216
+ "consolidación": 106864,
217
+ "consolidate": 106469,
218
+ "consolidating": 106920,
219
+ "consolidation": 105980,
220
+ "constituents": 106687,
221
+ "constraints": 106696,
222
+ "construcción": 105965,
223
+ "constructing": 106383,
224
+ "consultancy": 105977,
225
+ "consultants": 106355,
226
+ "consultation": 106230,
227
+ "consultations": 106328,
228
+ "contexts": 106482,
229
+ "continuation": 106032,
230
+ "continuidad": 106694,
231
+ "contractor": 106798,
232
+ "contractors": 106807,
233
+ "contractual": 106166,
234
+ "contribuer": 105999,
235
+ "contribuir": 105984,
236
+ "contributes": 105996,
237
+ "contrôle": 106322,
238
+ "convening": 106137,
239
+ "convenio": 106344,
240
+ "coop": 106172,
241
+ "cooperación": 105926,
242
+ "cooperatives": 106200,
243
+ "coopération": 105901,
244
+ "coordinación": 106519,
245
+ "coordinated": 106234,
246
+ "coordinating": 106608,
247
+ "corridors": 106868,
248
+ "counseling": 106917,
249
+ "counselling": 106569,
250
+ "covid": 105887,
251
+ "covid19": 106726,
252
+ "coûteuses": 106927,
253
+ "creación": 106129,
254
+ "crises": 106116,
255
+ "création": 106080,
256
+ "crédit": 106077,
257
+ "crédits": 106133,
258
+ "créer": 106739,
259
+ "csos": 106051,
260
+ "cultivation": 106407,
261
+ "cvca": 106336,
262
+ "côte": 106312,
263
+ "darfur": 106402,
264
+ "dcsd": 106622,
265
+ "ddhh": 106737,
266
+ "decent": 105983,
267
+ "decentralisation": 106396,
268
+ "decentralised": 106321,
269
+ "decentralization": 106162,
270
+ "decentralized": 106264,
271
+ "deepening": 106852,
272
+ "definitional": 106640,
273
+ "deforestation": 106450,
274
+ "delivering": 106269,
275
+ "demining": 106483,
276
+ "dept": 106075,
277
+ "designing": 106656,
278
+ "determinants": 106276,
279
+ "devis": 106303,
280
+ "devpt": 106803,
281
+ "devt": 106918,
282
+ "dfid": 106074,
283
+ "diagnostics": 106465,
284
+ "diakonia": 106711,
285
+ "diets": 106810,
286
+ "difusión": 106505,
287
+ "dignity": 106400,
288
+ "diplomacy": 106356,
289
+ "disabilities": 105947,
290
+ "disadvantaged": 106083,
291
+ "disasters": 106062,
292
+ "discapacidad": 106766,
293
+ "diseño": 106630,
294
+ "dispatch": 105938,
295
+ "displaced": 105929,
296
+ "displacement": 106221,
297
+ "disposal": 106222,
298
+ "disseminate": 106458,
299
+ "disseminating": 106748,
300
+ "dissemination": 106053,
301
+ "distress": 105979,
302
+ "distribución": 106728,
303
+ "diversification": 106185,
304
+ "docentes": 106833,
305
+ "donateurs": 106802,
306
+ "donneur": 106808,
307
+ "données": 106521,
308
+ "donor": 105971,
309
+ "donors": 106061,
310
+ "dotación": 106776,
311
+ "dotation": 106900,
312
+ "drafting": 106907,
313
+ "drought": 106019,
314
+ "durables": 106391,
315
+ "durée": 106772,
316
+ "duurzame": 106889,
317
+ "dvpt": 106480,
318
+ "décentralisation": 106561,
319
+ "déchets": 106747,
320
+ "défense": 106835,
321
+ "démocratique": 106296,
322
+ "département": 106780,
323
+ "dépenses": 106313,
324
+ "déplacées": 106404,
325
+ "développement": 105880,
326
+ "développer": 106346,
327
+ "ebola": 106235,
328
+ "ebrd": 106873,
329
+ "econ": 106593,
330
+ "economically": 106499,
331
+ "economies": 106331,
332
+ "economía": 106462,
333
+ "económica": 106308,
334
+ "económicas": 106902,
335
+ "económico": 106248,
336
+ "económicos": 106706,
337
+ "ecosystem": 106020,
338
+ "ecosystems": 106141,
339
+ "educ": 106238,
340
+ "educación": 105913,
341
+ "educate": 106649,
342
+ "educativa": 106208,
343
+ "educativas": 106595,
344
+ "educativo": 106257,
345
+ "educativos": 106349,
346
+ "educators": 106799,
347
+ "efficacité": 106386,
348
+ "efficiently": 106855,
349
+ "eidhr": 106326,
350
+ "ejecución": 106555,
351
+ "ejercicio": 106472,
352
+ "elaboración": 106527,
353
+ "elaboration": 106665,
354
+ "electrification": 106154,
355
+ "emergencies": 105991,
356
+ "emplois": 106538,
357
+ "employability": 106494,
358
+ "employers": 106123,
359
+ "empoderamiento": 106259,
360
+ "empower": 106089,
361
+ "empowered": 106632,
362
+ "empowering": 106014,
363
+ "empowerment": 105894,
364
+ "enables": 106375,
365
+ "enabling": 105931,
366
+ "encouraging": 106689,
367
+ "endowment": 105897,
368
+ "energies": 106730,
369
+ "engaging": 106251,
370
+ "enhance": 105891,
371
+ "enhancement": 106002,
372
+ "enhancing": 105898,
373
+ "enjeux": 106452,
374
+ "enpi": 106416,
375
+ "enseignants": 106333,
376
+ "ensuring": 106013,
377
+ "entrepreneurial": 106515,
378
+ "entrepreneurs": 106036,
379
+ "entrepreneurship": 105994,
380
+ "environmentally": 106240,
381
+ "environnementale": 106765,
382
+ "epidemic": 106224,
383
+ "equidad": 106258,
384
+ "equipamiento": 106316,
385
+ "equipping": 106309,
386
+ "equitable": 105976,
387
+ "eradication": 106252,
388
+ "escolares": 106859,
389
+ "españa": 106478,
390
+ "específico": 106744,
391
+ "essentiels": 106886,
392
+ "estrategias": 106367,
393
+ "está": 106244,
394
+ "están": 106703,
395
+ "eurasian": 106082,
396
+ "européenne": 106707,
397
+ "evaluación": 106554,
398
+ "evaluate": 106150,
399
+ "evaluating": 106911,
400
+ "evaluations": 106134,
401
+ "examine": 106715,
402
+ "exchanges": 106268,
403
+ "excluded": 106785,
404
+ "executing": 106824,
405
+ "expenditure": 105998,
406
+ "expenditures": 106684,
407
+ "expenses": 105978,
408
+ "exports": 106910,
409
+ "exposición": 106937,
410
+ "extractive": 106675,
411
+ "extremism": 106686,
412
+ "facilitating": 106126,
413
+ "facilitation": 106042,
414
+ "faciliter": 106850,
415
+ "familiale": 106618,
416
+ "faps": 106704,
417
+ "fasep": 106643,
418
+ "favoriser": 106406,
419
+ "fcil": 106003,
420
+ "feasibility": 105946,
421
+ "fellowships": 106626,
422
+ "fertilizer": 106816,
423
+ "filière": 106804,
424
+ "filières": 106587,
425
+ "financed": 106140,
426
+ "financement": 105944,
427
+ "financiers": 106646,
428
+ "financing": 105889,
429
+ "financière": 106319,
430
+ "financés": 106812,
431
+ "fishery": 106479,
432
+ "flandre": 106601,
433
+ "floods": 106181,
434
+ "flour": 106762,
435
+ "fomentar": 106516,
436
+ "fomento": 106508,
437
+ "formación": 105906,
438
+ "formulation": 106006,
439
+ "fortalecer": 106050,
440
+ "fortalecimiento": 105918,
441
+ "forums": 106723,
442
+ "fostering": 106173,
443
+ "fournir": 106186,
444
+ "fourniture": 106237,
445
+ "frameworks": 106147,
446
+ "francophonie": 106935,
447
+ "français": 105959,
448
+ "française": 106115,
449
+ "françaises": 106207,
450
+ "frontières": 106919,
451
+ "frontline": 106418,
452
+ "fspi": 106746,
453
+ "functioning": 106337,
454
+ "fundación": 106420,
455
+ "förderung": 106232,
456
+ "gaps": 106174,
457
+ "garantizar": 106361,
458
+ "gcrf": 106863,
459
+ "generación": 106627,
460
+ "generar": 106621,
461
+ "geothermal": 106753,
462
+ "gestión": 105951,
463
+ "globally": 106285,
464
+ "globaux": 106438,
465
+ "gouvernance": 105954,
466
+ "govt": 106915,
467
+ "grantee": 106035,
468
+ "grassroots": 106214,
469
+ "gratuities": 106537,
470
+ "greenhouse": 106592,
471
+ "groundwater": 106740,
472
+ "grâce": 106120,
473
+ "guarantee": 106209,
474
+ "guinée": 106408,
475
+ "género": 105945,
476
+ "général": 106197,
477
+ "générale": 106843,
478
+ "harmful": 106572,
479
+ "hazards": 106464,
480
+ "haïti": 106262,
481
+ "heating": 106563,
482
+ "herramientas": 106446,
483
+ "higiene": 106441,
484
+ "holistic": 106591,
485
+ "humanitaire": 105953,
486
+ "humanitaires": 106419,
487
+ "humanitaria": 106442,
488
+ "hydropower": 106315,
489
+ "hygiène": 106191,
490
+ "icrc": 106058,
491
+ "identifying": 106341,
492
+ "idps": 106047,
493
+ "idrc": 106122,
494
+ "ifrc": 106542,
495
+ "igualdad": 106325,
496
+ "ilea": 106801,
497
+ "illicit": 106894,
498
+ "immunization": 106467,
499
+ "implementación": 106164,
500
+ "implementing": 105922,
501
+ "improves": 106659,
502
+ "impulsar": 106906,
503
+ "impunity": 106773,
504
+ "imrs": 106327,
505
+ "incentives": 106729,
506
+ "incidence": 106456,
507
+ "incidencia": 106132,
508
+ "incl": 106365,
509
+ "inclusión": 106870,
510
+ "incomes": 106161,
511
+ "indemnities": 106556,
512
+ "indicators": 106199,
513
+ "indirect": 106429,
514
+ "indirectly": 106836,
515
+ "indígena": 106904,
516
+ "indígenas": 106110,
517
+ "inequalities": 106165,
518
+ "inequality": 106372,
519
+ "infantile": 106718,
520
+ "infectious": 106064,
521
+ "inform": 106015,
522
+ "información": 106211,
523
+ "informatiques": 106874,
524
+ "informative": 106758,
525
+ "infraestructuras": 106570,
526
+ "infrastructures": 106029,
527
+ "iniciativas": 106481,
528
+ "initiation": 106898,
529
+ "inondations": 106929,
530
+ "inputs": 106332,
531
+ "insecurity": 106215,
532
+ "insertion": 106324,
533
+ "instalación": 106893,
534
+ "institutionnel": 106135,
535
+ "insécurité": 106629,
536
+ "integración": 106616,
537
+ "integrate": 106290,
538
+ "integrating": 106364,
539
+ "intends": 106551,
540
+ "intercultural": 106267,
541
+ "internally": 106067,
542
+ "internship": 106250,
543
+ "internships": 106647,
544
+ "intervención": 106091,
545
+ "interventions": 105904,
546
+ "intégration": 106403,
547
+ "intégré": 106735,
548
+ "intégrée": 106564,
549
+ "intérieure": 106932,
550
+ "invest": 106216,
551
+ "investigación": 106160,
552
+ "investigative": 106384,
553
+ "investing": 106496,
554
+ "investissement": 106512,
555
+ "investissements": 106693,
556
+ "itsh": 106431,
557
+ "iwrm": 106619,
558
+ "jordanian": 106790,
559
+ "jordanie": 106934,
560
+ "jornadas": 106839,
561
+ "judiciary": 106602,
562
+ "juridique": 106774,
563
+ "jóvenes": 105968,
564
+ "kampala": 106888,
565
+ "kiribati": 106896,
566
+ "kits": 106301,
567
+ "kivu": 106254,
568
+ "koica": 106016,
569
+ "kyrgyz": 106488,
570
+ "kyrgyzstan": 106289,
571
+ "landscapes": 106654,
572
+ "latrines": 106423,
573
+ "lending": 106683,
574
+ "lesotho": 106334,
575
+ "leveraging": 106546,
576
+ "lgbti": 106842,
577
+ "libor": 106742,
578
+ "linkages": 106204,
579
+ "livelihood": 105943,
580
+ "livelihoods": 105899,
581
+ "liées": 106881,
582
+ "liés": 106734,
583
+ "logistical": 106524,
584
+ "logistique": 106568,
585
+ "lump": 106529,
586
+ "lycée": 106401,
587
+ "macro": 106670,
588
+ "macroeconomic": 106709,
589
+ "madres": 106858,
590
+ "mainstreaming": 106093,
591
+ "maize": 106825,
592
+ "malnutrition": 105981,
593
+ "managerial": 106463,
594
+ "manejo": 106533,
595
+ "manière": 106625,
596
+ "marché": 106210,
597
+ "marchés": 106676,
598
+ "marginalised": 106249,
599
+ "marginalized": 106038,
600
+ "maternelle": 106657,
601
+ "maternity": 106821,
602
+ "matière": 106004,
603
+ "matériel": 106658,
604
+ "mauritanie": 106818,
605
+ "mdgs": 106297,
606
+ "meaningful": 106922,
607
+ "mediation": 106283,
608
+ "medicines": 106107,
609
+ "mejora": 105936,
610
+ "mentoring": 106642,
611
+ "methodologies": 106653,
612
+ "methodology": 106373,
613
+ "mgmt": 105948,
614
+ "microfinance": 106027,
615
+ "migrant": 106145,
616
+ "migrants": 105925,
617
+ "migratory": 106895,
618
+ "ministries": 106242,
619
+ "ministère": 106048,
620
+ "minorities": 106363,
621
+ "misean": 106072,
622
+ "missionaries": 106562,
623
+ "mitigate": 106128,
624
+ "mitigating": 106763,
625
+ "mitigation": 105960,
626
+ "mobilisation": 106111,
627
+ "mobiliser": 106574,
628
+ "mobilité": 106851,
629
+ "mobilization": 106076,
630
+ "mobilizationand": 106921,
631
+ "mobilize": 106757,
632
+ "modelling": 106931,
633
+ "modernisation": 106241,
634
+ "modernization": 106049,
635
+ "monetization": 106560,
636
+ "montant": 106559,
637
+ "morbidity": 106357,
638
+ "msek": 106681,
639
+ "msmes": 106754,
640
+ "multilateral": 106078,
641
+ "multisector": 105940,
642
+ "multisectoral": 106417,
643
+ "mundus": 106682,
644
+ "mères": 106655,
645
+ "mécanismes": 106828,
646
+ "ménages": 106294,
647
+ "même": 106914,
648
+ "narcotics": 105882,
649
+ "neglected": 106800,
650
+ "negotiates": 106447,
651
+ "negotiation": 106187,
652
+ "neonatal": 106549,
653
+ "networking": 106024,
654
+ "newborn": 106040,
655
+ "ngos": 105896,
656
+ "niñas": 106011,
657
+ "niños": 105958,
658
+ "nonfat": 106814,
659
+ "norad": 106853,
660
+ "norms": 106379,
661
+ "nutricional": 106677,
662
+ "nutritional": 106121,
663
+ "nutritionnelle": 106583,
664
+ "ocha": 106229,
665
+ "oeuvre": 105963,
666
+ "ofda": 106284,
667
+ "offrent": 106849,
668
+ "offrir": 106603,
669
+ "ohchr": 106787,
670
+ "ondersteuning": 106912,
671
+ "ongd": 106936,
672
+ "opérations": 106323,
673
+ "organisational": 106273,
674
+ "organisationnelles": 106594,
675
+ "organización": 106189,
676
+ "organizational": 106023,
677
+ "orphans": 106387,
678
+ "osce": 106117,
679
+ "outputs": 106065,
680
+ "outreach": 106031,
681
+ "oversight": 106028,
682
+ "oxfam": 106190,
683
+ "p105": 106854,
684
+ "p185": 105915,
685
+ "p209": 105893,
686
+ "packages": 106475,
687
+ "pandemic": 106007,
688
+ "partenaires": 105952,
689
+ "partenariat": 106183,
690
+ "partenariats": 106741,
691
+ "participación": 105966,
692
+ "participative": 106722,
693
+ "participatory": 105986,
694
+ "particulièrement": 106557,
695
+ "partnerships": 105908,
696
+ "pauvres": 106439,
697
+ "pauvreté": 106054,
698
+ "país": 106195,
699
+ "países": 106073,
700
+ "peacebuilding": 106149,
701
+ "peacekeeping": 106846,
702
+ "peas": 106712,
703
+ "peasant": 106702,
704
+ "pepfar": 106125,
705
+ "permettra": 106755,
706
+ "perú": 106306,
707
+ "photovoltaic": 106923,
708
+ "pillar": 106860,
709
+ "pilotage": 106620,
710
+ "plaidoyer": 106752,
711
+ "planificación": 106838,
712
+ "planification": 106239,
713
+ "pnud": 106844,
714
+ "población": 105910,
715
+ "policymakers": 106539,
716
+ "polio": 106362,
717
+ "política": 106144,
718
+ "políticas": 106097,
719
+ "ponctuelles": 106879,
720
+ "poorest": 106246,
721
+ "possibilities": 106847,
722
+ "postgraduate": 106444,
723
+ "potable": 105916,
724
+ "poultry": 106751,
725
+ "practitioners": 106485,
726
+ "première": 106714,
727
+ "prep": 106832,
728
+ "preparatory": 106382,
729
+ "preparedness": 105934,
730
+ "prepositioning": 106335,
731
+ "prestation": 106633,
732
+ "prestations": 106791,
733
+ "prevalence": 106484,
734
+ "prevención": 106109,
735
+ "preventable": 106710,
736
+ "preventive": 106347,
737
+ "principled": 106925,
738
+ "priorities": 105985,
739
+ "privé": 106338,
740
+ "procurement": 105942,
741
+ "producción": 106022,
742
+ "productivas": 106733,
743
+ "productive": 105957,
744
+ "productivity": 105961,
745
+ "productivo": 106875,
746
+ "profesorado": 106638,
747
+ "prog": 105973,
748
+ "progr": 106260,
749
+ "programmatic": 106398,
750
+ "programmation": 106770,
751
+ "proj": 106094,
752
+ "promoción": 105997,
753
+ "promotes": 106175,
754
+ "promouvoir": 106131,
755
+ "promoviendo": 106820,
756
+ "prone": 106672,
757
+ "propuestas": 106651,
758
+ "prosperity": 106399,
759
+ "protección": 106084,
760
+ "protective": 106427,
761
+ "prácticas": 106178,
762
+ "préparation": 106461,
763
+ "prévention": 106057,
764
+ "prêt": 106575,
765
+ "psychosocial": 106143,
766
+ "purchases": 106509,
767
+ "pública": 106339,
768
+ "públicas": 106201,
769
+ "público": 106615,
770
+ "públicos": 106612,
771
+ "qualité": 105962,
772
+ "quotas": 106535,
773
+ "readiness": 106662,
774
+ "readjustment": 106553,
775
+ "realización": 106188,
776
+ "realization": 106720,
777
+ "receivables": 106924,
778
+ "reconciliation": 106059,
779
+ "recruitment": 106486,
780
+ "recycling": 106588,
781
+ "redacted": 106026,
782
+ "redd": 106330,
783
+ "reducción": 106611,
784
+ "referral": 106930,
785
+ "refinancement": 106867,
786
+ "reflexión": 106926,
787
+ "refuerzo": 106901,
788
+ "refugiada": 106883,
789
+ "refugiados": 106380,
790
+ "refund": 106768,
791
+ "región": 106081,
792
+ "rehab": 106282,
793
+ "rehabilitación": 106600,
794
+ "rehabilitate": 106786,
795
+ "rehabilitating": 106899,
796
+ "reinforce": 106487,
797
+ "reinforcement": 106278,
798
+ "reinforcing": 106609,
799
+ "reintegration": 106066,
800
+ "relevance": 106112,
801
+ "reliance": 106531,
802
+ "renewable": 105933,
803
+ "renewal": 106701,
804
+ "renforcement": 105888,
805
+ "renforcer": 105937,
806
+ "renforcées": 106669,
807
+ "reprod": 106138,
808
+ "reproductiva": 106913,
809
+ "reproductive": 105886,
810
+ "república": 106598,
811
+ "resettlement": 106628,
812
+ "resilience": 105890,
813
+ "resilient": 106001,
814
+ "responding": 106490,
815
+ "responsive": 106055,
816
+ "restoring": 106857,
817
+ "restructuring": 106300,
818
+ "returnees": 106247,
819
+ "robust": 106830,
820
+ "rssh": 106631,
821
+ "réalisation": 106136,
822
+ "récipiendaire": 106270,
823
+ "réduction": 106098,
824
+ "réduire": 106245,
825
+ "réforme": 106291,
826
+ "réfugiés": 106151,
827
+ "région": 105964,
828
+ "régional": 106205,
829
+ "régionale": 106586,
830
+ "régions": 106090,
831
+ "réhabilitation": 106087,
832
+ "répondre": 106492,
833
+ "réponse": 106226,
834
+ "république": 106104,
835
+ "réseau": 106043,
836
+ "réseaux": 106435,
837
+ "résilience": 106265,
838
+ "résultat": 106536,
839
+ "résultats": 106184,
840
+ "rôle": 106517,
841
+ "sadc": 106358,
842
+ "safeguarding": 106880,
843
+ "safer": 106779,
844
+ "saharan": 106041,
845
+ "saharaui": 106719,
846
+ "saharauis": 106756,
847
+ "sahel": 106105,
848
+ "saneamiento": 106142,
849
+ "sanit": 106771,
850
+ "sanitaire": 106299,
851
+ "sanitaires": 106304,
852
+ "sanitaria": 106360,
853
+ "sanitario": 106578,
854
+ "sanitary": 106218,
855
+ "sanitation": 105883,
856
+ "santé": 105884,
857
+ "scac": 105990,
858
+ "scaling": 106037,
859
+ "scholarships": 105905,
860
+ "scolaires": 106605,
861
+ "scolarisation": 106393,
862
+ "scoping": 106652,
863
+ "sdgs": 106176,
864
+ "secondment": 106146,
865
+ "secteurs": 106236,
866
+ "sectoral": 106060,
867
+ "securing": 106366,
868
+ "seekers": 106471,
869
+ "seguimiento": 106507,
870
+ "seminars": 106118,
871
+ "sensibilisation": 106068,
872
+ "sensibilización": 105982,
873
+ "sensibilizar": 106738,
874
+ "serv": 106274,
875
+ "será": 106887,
876
+ "serán": 106909,
877
+ "sewage": 106318,
878
+ "sewerage": 106170,
879
+ "sexes": 106511,
880
+ "sgbv": 106827,
881
+ "shocks": 106596,
882
+ "significatives": 106903,
883
+ "situación": 106012,
884
+ "skilled": 106721,
885
+ "slum": 106831,
886
+ "smallholder": 106044,
887
+ "smes": 106025,
888
+ "soberanía": 106589,
889
+ "socially": 106434,
890
+ "socioeconomic": 106623,
891
+ "société": 105956,
892
+ "soins": 105989,
893
+ "solidaria": 106641,
894
+ "solidaridad": 106307,
895
+ "solidarity": 106017,
896
+ "solidarité": 105970,
897
+ "somaliland": 106865,
898
+ "sostenibilidad": 106422,
899
+ "sostenible": 105992,
900
+ "sostenibles": 106797,
901
+ "soudan": 106513,
902
+ "soutenir": 106148,
903
+ "soya": 106724,
904
+ "specialists": 106506,
905
+ "spécifique": 106565,
906
+ "srhr": 106261,
907
+ "stabilisation": 106376,
908
+ "stabilization": 106411,
909
+ "stakeholder": 106203,
910
+ "stakeholders": 105928,
911
+ "stimulate": 106610,
912
+ "stratégie": 106182,
913
+ "stratégies": 106634,
914
+ "stratégique": 106449,
915
+ "strenghtening": 106409,
916
+ "strengthen": 105881,
917
+ "strengthened": 105903,
918
+ "strengthening": 105879,
919
+ "strengthens": 106466,
920
+ "stärkung": 106695,
921
+ "subdivisions": 106550,
922
+ "subprogram": 106876,
923
+ "subproject": 106778,
924
+ "subsector": 106789,
925
+ "subside": 106668,
926
+ "subsidies": 106280,
927
+ "subsidy": 106534,
928
+ "subsistance": 106451,
929
+ "subvention": 106008,
930
+ "subventions": 106493,
931
+ "sudanese": 106381,
932
+ "supp": 106674,
933
+ "supplementary": 106412,
934
+ "supportive": 106576,
935
+ "supérieur": 106155,
936
+ "surcharge": 106468,
937
+ "sustain": 106079,
938
+ "sustainability": 105917,
939
+ "sustainably": 106514,
940
+ "sustaining": 106457,
941
+ "swaziland": 106809,
942
+ "synergies": 106878,
943
+ "système": 105988,
944
+ "systèmes": 106101,
945
+ "sécurité": 105920,
946
+ "sénégal": 106153,
947
+ "tacis": 106448,
948
+ "tackling": 106644,
949
+ "tajikistan": 106114,
950
+ "también": 106180,
951
+ "tanzanie": 106788,
952
+ "targeting": 106206,
953
+ "taxation": 106292,
954
+ "taxing": 106552,
955
+ "tchad": 106231,
956
+ "tcpf": 106606,
957
+ "tempus": 106522,
958
+ "tertiary": 106795,
959
+ "thematic": 106103,
960
+ "tigray": 106731,
961
+ "timely": 106352,
962
+ "touchées": 106528,
963
+ "trainers": 106392,
964
+ "trainings": 106102,
965
+ "tranche": 106021,
966
+ "transboundary": 106666,
967
+ "transfers": 106690,
968
+ "transformación": 106581,
969
+ "transformative": 106782,
970
+ "transforming": 106648,
971
+ "transitional": 106275,
972
+ "transnational": 106750,
973
+ "transparency": 105930,
974
+ "través": 105911,
975
+ "tvet": 106433,
976
+ "twinning": 106369,
977
+ "técnica": 106106,
978
+ "técnicas": 106377,
979
+ "técnico": 106639,
980
+ "título": 105935,
981
+ "unaids": 106717,
982
+ "undergone": 106426,
983
+ "undertake": 106202,
984
+ "undp": 105932,
985
+ "unep": 106530,
986
+ "unfccc": 106822,
987
+ "unfpa": 106223,
988
+ "unhcr": 106009,
989
+ "unité": 106697,
990
+ "université": 106263,
991
+ "unrwa": 106394,
992
+ "unsafe": 106885,
993
+ "unspecified": 105919,
994
+ "unterstützung": 106604,
995
+ "upgrading": 106030,
996
+ "uptake": 106698,
997
+ "urgence": 105967,
998
+ "urgent": 106156,
999
+ "utilities": 106374,
1000
+ "utilization": 106305,
1001
+ "vaccination": 106518,
1002
+ "vaccine": 106010,
1003
+ "vaccines": 106139,
1004
+ "valorisation": 106425,
1005
+ "vegetable": 106063,
1006
+ "veloppement": 106541,
1007
+ "verification": 106088,
1008
+ "viability": 106764,
1009
+ "viable": 106228,
1010
+ "vicitms": 105995,
1011
+ "violations": 106130,
1012
+ "violences": 106599,
1013
+ "visibility": 106255,
1014
+ "vocational": 105895,
1015
+ "volet": 106286,
1016
+ "volontaires": 106217,
1017
+ "volontariat": 105950,
1018
+ "vulnerabilidad": 106414,
1019
+ "vulnerability": 106039,
1020
+ "vulnerables": 106371,
1021
+ "vulnérables": 106005,
1022
+ "vérification": 106823,
1023
+ "víctimas": 106526,
1024
+ "wastewater": 106069,
1025
+ "wellbeing": 106761,
1026
+ "wetlands": 106749,
1027
+ "womens": 106350,
1028
+ "workforce": 106351,
1029
+ "workplace": 106685,
1030
+ "youths": 106777,
1031
+ "áfrica": 106713,
1032
+ "ámbito": 106198,
1033
+ "área": 106397,
1034
+ "áreas": 106532,
1035
+ "échanges": 106288,
1036
+ "échelle": 106607,
1037
+ "école": 106298,
1038
+ "écoles": 106096,
1039
+ "écoliers": 106108,
1040
+ "économie": 106385,
1041
+ "économique": 105949,
1042
+ "économiques": 106219,
1043
+ "éducation": 105927,
1044
+ "également": 106127,
1045
+ "égalité": 106177,
1046
+ "élaboration": 106445,
1047
+ "élevage": 106743,
1048
+ "élèves": 106897,
1049
+ "énergie": 106547,
1050
+ "équipement": 106829,
1051
+ "équipements": 106725,
1052
+ "établissement": 106415,
1053
+ "établissements": 106520,
1054
+ "état": 106163,
1055
+ "étranger": 106370,
1056
+ "étude": 106388,
1057
+ "études": 106159,
1058
+ "étudiants": 106453,
1059
+ "évaluation": 106167,
1060
+ "être": 106343
1061
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alex-miller/ODABert",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "0",
14
+ "1": "1"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "0": 0,
20
+ "1": 1
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "pooler_fc_size": 768,
29
+ "pooler_num_attention_heads": 12,
30
+ "pooler_num_fc_layers": 3,
31
+ "pooler_size_per_head": 128,
32
+ "pooler_type": "first_token_transform",
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.38.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 106938
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c08058f629d627d959bff3c5aad647ab335c3f8d4f169e972f9e0bba873168f
3
+ size 672708608
runs/Mar21_17-27-27_0a46a094dd76/events.out.tfevents.1711042048.0a46a094dd76.2231.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1767dbd49e6e7c0c489997003c5d03a0840821f84e3299a73f895efb2528f528
3
+ size 5376
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0923eb43b72e66da90ce893e7759e2c46314c8cd2b23113b3bad196473d4b9
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff