ykyao commited on
Commit
ceb61e7
·
verified ·
1 Parent(s): 080a020

Upload folder using huggingface_hub

Browse files
hop3-4000/added_tokens.json ADDED
@@ -0,0 +1,485 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Abby": 50258,
3
+ "Abel": 50257,
4
+ "Ace": 50259,
5
+ "Ada": 50260,
6
+ "Addie": 50261,
7
+ "Adele": 50262,
8
+ "Aiden": 50263,
9
+ "Aimee": 50264,
10
+ "Aisha": 50641,
11
+ "Ajay": 50265,
12
+ "Alba": 50266,
13
+ "Alec": 50267,
14
+ "Alfonso": 50642,
15
+ "Aline": 50268,
16
+ "Allegra": 50643,
17
+ "Alma": 50269,
18
+ "Alvin": 50270,
19
+ "Amber": 50271,
20
+ "Amie": 50272,
21
+ "Amir": 50273,
22
+ "Amos": 50644,
23
+ "Ana": 50274,
24
+ "Anika": 50275,
25
+ "Anita": 50276,
26
+ "Annie": 50277,
27
+ "Anson": 50645,
28
+ "Antwan": 50646,
29
+ "Anya": 50278,
30
+ "Araceli": 50647,
31
+ "Arden": 50648,
32
+ "Aria": 50279,
33
+ "Ariel": 50280,
34
+ "Arjun": 50649,
35
+ "Arlette": 50650,
36
+ "Arlo": 50281,
37
+ "Arman": 50282,
38
+ "Aron": 50283,
39
+ "Arya": 50284,
40
+ "Asa": 50285,
41
+ "Ashanti": 50651,
42
+ "Asher": 50286,
43
+ "Aston": 50287,
44
+ "Astrid": 50288,
45
+ "Aubrey": 50289,
46
+ "Aubri": 50652,
47
+ "Audra": 50290,
48
+ "Ava": 50291,
49
+ "Axel": 50292,
50
+ "Ayaan": 50293,
51
+ "Ayden": 50294,
52
+ "Bailey": 50295,
53
+ "Barb": 50296,
54
+ "Barry": 50297,
55
+ "Basil": 50653,
56
+ "Beatrix": 50654,
57
+ "Beau": 50298,
58
+ "Bella": 50299,
59
+ "Benedict": 50655,
60
+ "Benny": 50300,
61
+ "Bernadette": 50656,
62
+ "Bert": 50301,
63
+ "Beth": 50302,
64
+ "Beverly": 50303,
65
+ "Bianca": 50304,
66
+ "Bjorn": 50305,
67
+ "Blaise": 50657,
68
+ "Bobby": 50306,
69
+ "Bonita": 50658,
70
+ "Bonnie": 50307,
71
+ "Boyd": 50308,
72
+ "Brady": 50309,
73
+ "Brandy": 50310,
74
+ "Branson": 50659,
75
+ "Brenda": 50311,
76
+ "Brent": 50312,
77
+ "Brett": 50313,
78
+ "Brianna": 50314,
79
+ "Briar": 50660,
80
+ "Brice": 50315,
81
+ "Bridget": 50316,
82
+ "Britt": 50317,
83
+ "Brock": 50318,
84
+ "Brody": 50319,
85
+ "Brogan": 50661,
86
+ "Bruno": 50320,
87
+ "Bryan": 50321,
88
+ "Bryce": 50322,
89
+ "Byron": 50323,
90
+ "Cade": 50324,
91
+ "Cael": 50325,
92
+ "Cain": 50326,
93
+ "Caleb": 50327,
94
+ "Callan": 50662,
95
+ "Callie": 50328,
96
+ "Calvin": 50663,
97
+ "Cambria": 50664,
98
+ "Cameron": 50329,
99
+ "Cami": 50330,
100
+ "Candace": 50331,
101
+ "Cara": 50332,
102
+ "Carla": 50333,
103
+ "Carlton": 50334,
104
+ "Carmelo": 50665,
105
+ "Carol": 50335,
106
+ "Carrie": 50336,
107
+ "Carson": 50337,
108
+ "Carys": 50666,
109
+ "Casey": 50338,
110
+ "Cason": 50339,
111
+ "Cassius": 50667,
112
+ "Cathy": 50340,
113
+ "Cedric": 50341,
114
+ "Celeste": 50668,
115
+ "Celine": 50669,
116
+ "Cesar": 50342,
117
+ "Chad": 50343,
118
+ "Chandler": 50344,
119
+ "Charlton": 50670,
120
+ "Chase": 50345,
121
+ "Chloe": 50346,
122
+ "Cillian": 50671,
123
+ "Cindy": 50347,
124
+ "Claire": 50348,
125
+ "Claude": 50349,
126
+ "Clay": 50350,
127
+ "Cleo": 50672,
128
+ "Cliff": 50351,
129
+ "Clint": 50352,
130
+ "Clover": 50673,
131
+ "Clyde": 50353,
132
+ "Cody": 50354,
133
+ "Colby": 50355,
134
+ "Colin": 50356,
135
+ "Collette": 50674,
136
+ "Connie": 50357,
137
+ "Cooper": 50358,
138
+ "Cordelia": 50675,
139
+ "Corey": 50359,
140
+ "Cormac": 50676,
141
+ "Corwin": 50677,
142
+ "Cory": 50360,
143
+ "Curt": 50361,
144
+ "Curtis": 50362,
145
+ "Cyrus": 50363,
146
+ "Dahlia": 50678,
147
+ "Daisy": 50364,
148
+ "Dale": 50365,
149
+ "Damon": 50366,
150
+ "Dana": 50367,
151
+ "Danielle": 50368,
152
+ "Dante": 50369,
153
+ "Daphne": 50370,
154
+ "Darin": 50371,
155
+ "Darius": 50372,
156
+ "Darla": 50373,
157
+ "Darlene": 50374,
158
+ "Darnell": 50679,
159
+ "Darrel": 50375,
160
+ "Darren": 50376,
161
+ "Darryl": 50377,
162
+ "Dashiell": 50680,
163
+ "Dawn": 50378,
164
+ "Deacon": 50681,
165
+ "Debbie": 50379,
166
+ "Deborah": 50380,
167
+ "Declan": 50381,
168
+ "Delaney": 50682,
169
+ "Delia": 50382,
170
+ "Demetri": 50383,
171
+ "Demetrius": 50683,
172
+ "Demi": 50384,
173
+ "Denise": 50385,
174
+ "Dennis": 50386,
175
+ "Derek": 50387,
176
+ "Derrick": 50388,
177
+ "Deshawn": 50684,
178
+ "Devin": 50389,
179
+ "Devon": 50390,
180
+ "Dewey": 50685,
181
+ "Dexter": 50391,
182
+ "Diana": 50392,
183
+ "Diane": 50393,
184
+ "Diego": 50394,
185
+ "Dillon": 50395,
186
+ "Dina": 50396,
187
+ "Dino": 50397,
188
+ "Dior": 50686,
189
+ "Dirk": 50398,
190
+ "Dixie": 50399,
191
+ "Dolly": 50400,
192
+ "Dominic": 50401,
193
+ "Donna": 50402,
194
+ "Dorian": 50403,
195
+ "Doris": 50404,
196
+ "Douglas": 50405,
197
+ "Drake": 50406,
198
+ "Drew": 50407,
199
+ "Duke": 50408,
200
+ "Dulcie": 50687,
201
+ "Duncan": 50409,
202
+ "Dustin": 50410,
203
+ "Dusty": 50411,
204
+ "Dwayne": 50412,
205
+ "Dwight": 50413,
206
+ "Dylan": 50414,
207
+ "Eamon": 50688,
208
+ "Earl": 50415,
209
+ "Eddard": 50689,
210
+ "Eddie": 50416,
211
+ "Edgar": 50417,
212
+ "Edith": 50418,
213
+ "Edna": 50419,
214
+ "Edwin": 50420,
215
+ "Eileen": 50421,
216
+ "Elaine": 50422,
217
+ "Eldon": 50690,
218
+ "Eleanor": 50423,
219
+ "Elena": 50424,
220
+ "Eli": 50425,
221
+ "Eliana": 50426,
222
+ "Elijah": 50427,
223
+ "Elisa": 50428,
224
+ "Elise": 50429,
225
+ "Eliza": 50430,
226
+ "Ella": 50431,
227
+ "Ellen": 50432,
228
+ "Elliot": 50433,
229
+ "Eloise": 50434,
230
+ "Elowen": 50691,
231
+ "Elton": 50435,
232
+ "Elvira": 50692,
233
+ "Elvis": 50436,
234
+ "Ember": 50693,
235
+ "Emery": 50437,
236
+ "Emil": 50438,
237
+ "Emilia": 50439,
238
+ "Emiliano": 50694,
239
+ "Emma": 50440,
240
+ "Emmeline": 50695,
241
+ "Emory": 50441,
242
+ "Enid": 50442,
243
+ "Enzo": 50443,
244
+ "Ephraim": 50696,
245
+ "Erica": 50444,
246
+ "Erick": 50445,
247
+ "Erik": 50446,
248
+ "Erin": 50447,
249
+ "Ernest": 50448,
250
+ "Ernie": 50449,
251
+ "Esme": 50450,
252
+ "Esther": 50451,
253
+ "Ethan": 50452,
254
+ "Ethel": 50453,
255
+ "Eugene": 50454,
256
+ "Eulalia": 50697,
257
+ "Eunice": 50455,
258
+ "Evan": 50456,
259
+ "Evander": 50698,
260
+ "Eve": 50457,
261
+ "Evelyn": 50458,
262
+ "Everett": 50459,
263
+ "Ewan": 50460,
264
+ "Ezra": 50461,
265
+ "Fabian": 50462,
266
+ "Fanny": 50463,
267
+ "Faustino": 50699,
268
+ "Felicia": 50464,
269
+ "Felicity": 50700,
270
+ "Felix": 50465,
271
+ "Finley": 50701,
272
+ "Finn": 50467,
273
+ "Fiona": 50466,
274
+ "Flora": 50702,
275
+ "Floyd": 50468,
276
+ "Flynn": 50703,
277
+ "Forrest": 50469,
278
+ "Frances": 50470,
279
+ "Francis": 50471,
280
+ "Frankie": 50472,
281
+ "Freddie": 50473,
282
+ "Freddy": 50474,
283
+ "Frederica": 50704,
284
+ "Freya": 50475,
285
+ "Gabby": 50476,
286
+ "Gabe": 50477,
287
+ "Gabriel": 50478,
288
+ "Gael": 50705,
289
+ "Gail": 50479,
290
+ "Gale": 50480,
291
+ "Garrett": 50706,
292
+ "Garry": 50481,
293
+ "Gavin": 50482,
294
+ "Geoff": 50483,
295
+ "Gerald": 50484,
296
+ "Gerard": 50485,
297
+ "Gigi": 50486,
298
+ "Gilbert": 50487,
299
+ "Gina": 50488,
300
+ "Ginger": 50489,
301
+ "Gino": 50490,
302
+ "Giovanni": 50491,
303
+ "Gisela": 50707,
304
+ "Giselle": 50492,
305
+ "Gladys": 50493,
306
+ "Glen": 50494,
307
+ "Glenda": 50495,
308
+ "Glenn": 50496,
309
+ "Gloria": 50497,
310
+ "Grace": 50498,
311
+ "Grady": 50499,
312
+ "Gregg": 50500,
313
+ "Gregory": 50501,
314
+ "Greta": 50502,
315
+ "Gretchen": 50503,
316
+ "Griffin": 50504,
317
+ "Gus": 50505,
318
+ "Gustavo": 50708,
319
+ "Gwen": 50506,
320
+ "Hadley": 50709,
321
+ "Hailey": 50507,
322
+ "Hamza": 50710,
323
+ "Hank": 50508,
324
+ "Hanna": 50509,
325
+ "Hannah": 50510,
326
+ "Harland": 50711,
327
+ "Harley": 50511,
328
+ "Harold": 50512,
329
+ "Harvey": 50513,
330
+ "Hattie": 50712,
331
+ "Haven": 50713,
332
+ "Hazel": 50514,
333
+ "Heath": 50515,
334
+ "Heather": 50516,
335
+ "Hector": 50517,
336
+ "Heidi": 50518,
337
+ "Helen": 50519,
338
+ "Henri": 50520,
339
+ "Herb": 50521,
340
+ "Herman": 50522,
341
+ "Hilary": 50523,
342
+ "Holland": 50714,
343
+ "Holly": 50524,
344
+ "Horace": 50525,
345
+ "Hudson": 50526,
346
+ "Hugh": 50527,
347
+ "Hugo": 50528,
348
+ "Ida": 50529,
349
+ "Igor": 50530,
350
+ "Iker": 50715,
351
+ "Imogen": 50531,
352
+ "Indira": 50716,
353
+ "Ines": 50532,
354
+ "Inigo": 50717,
355
+ "Irene": 50533,
356
+ "Iris": 50534,
357
+ "Irma": 50535,
358
+ "Isaac": 50536,
359
+ "Isabel": 50537,
360
+ "Isabella": 50538,
361
+ "Isaiah": 50539,
362
+ "Isla": 50540,
363
+ "Ivan": 50541,
364
+ "Ivy": 50542,
365
+ "Jace": 50543,
366
+ "Jackie": 50544,
367
+ "Jacqueline": 50545,
368
+ "Jade": 50546,
369
+ "Jaime": 50547,
370
+ "Jalen": 50548,
371
+ "Jalil": 50718,
372
+ "Jana": 50549,
373
+ "Janet": 50550,
374
+ "Janice": 50551,
375
+ "Jared": 50552,
376
+ "Jareth": 50719,
377
+ "Jasmine": 50553,
378
+ "Jasper": 50554,
379
+ "Javier": 50555,
380
+ "Jayden": 50556,
381
+ "Jeanette": 50557,
382
+ "Jeanne": 50558,
383
+ "Jeffery": 50559,
384
+ "Jeffrey": 50560,
385
+ "Jenna": 50561,
386
+ "Jenny": 50562,
387
+ "Jensen": 50720,
388
+ "Jeremiah": 50563,
389
+ "Jermaine": 50564,
390
+ "Jerome": 50565,
391
+ "Jesse": 50566,
392
+ "Jessie": 50567,
393
+ "Jethro": 50721,
394
+ "Jill": 50568,
395
+ "Joan": 50569,
396
+ "Joanna": 50570,
397
+ "Joanne": 50571,
398
+ "Jocelyn": 50572,
399
+ "Jodi": 50573,
400
+ "Jodie": 50574,
401
+ "Joel": 50575,
402
+ "Joey": 50576,
403
+ "Jonah": 50577,
404
+ "Jorge": 50578,
405
+ "Josie": 50579,
406
+ "Jovan": 50722,
407
+ "Joyce": 50580,
408
+ "Juan": 50581,
409
+ "Juanita": 50582,
410
+ "Judith": 50583,
411
+ "Judy": 50584,
412
+ "Jules": 50585,
413
+ "Julia": 50586,
414
+ "Julian": 50587,
415
+ "Julie": 50588,
416
+ "Juliet": 50589,
417
+ "Julio": 50590,
418
+ "Julius": 50591,
419
+ "Kaden": 50592,
420
+ "Kael": 50723,
421
+ "Kai": 50593,
422
+ "Kaia": 50724,
423
+ "Kara": 50594,
424
+ "Karen": 50595,
425
+ "Kari": 50596,
426
+ "Karina": 50597,
427
+ "Katherine": 50598,
428
+ "Kathleen": 50599,
429
+ "Kathy": 50600,
430
+ "Katie": 50601,
431
+ "Kayla": 50602,
432
+ "Keira": 50603,
433
+ "Kelsey": 50604,
434
+ "Kendall": 50605,
435
+ "Kenji": 50725,
436
+ "Kennedy": 50606,
437
+ "Kenneth": 50607,
438
+ "Kenny": 50608,
439
+ "Khalid": 50609,
440
+ "Kian": 50726,
441
+ "Kimberly": 50610,
442
+ "Kip": 50727,
443
+ "Kirk": 50611,
444
+ "Kris": 50612,
445
+ "Krista": 50613,
446
+ "Kristen": 50614,
447
+ "Kristin": 50615,
448
+ "Kristina": 50616,
449
+ "Kurt": 50617,
450
+ "Lacey": 50618,
451
+ "Lachlan": 50728,
452
+ "Lana": 50619,
453
+ "Lance": 50620,
454
+ "Lara": 50621,
455
+ "Lauren": 50622,
456
+ "Laurie": 50623,
457
+ "Layla": 50624,
458
+ "Lazaro": 50729,
459
+ "Leah": 50625,
460
+ "Leandro": 50730,
461
+ "Leo": 50626,
462
+ "Leona": 50627,
463
+ "Leonard": 50628,
464
+ "Leroy": 50629,
465
+ "Leslie": 50630,
466
+ "Lester": 50631,
467
+ "Liam": 50632,
468
+ "Lincoln": 50633,
469
+ "Linda": 50634,
470
+ "Lindsay": 50635,
471
+ "Logan": 50636,
472
+ "Lola": 50637,
473
+ "Loren": 50638,
474
+ "Louise": 50639,
475
+ "Lucas": 50640,
476
+ "Lucien": 50731,
477
+ "Ludwig": 50732,
478
+ "Malik": 50733,
479
+ "Marcella": 50734,
480
+ "Maxton": 50735,
481
+ "Melina": 50736,
482
+ "Mireille": 50737,
483
+ "Mordecai": 50738,
484
+ "Talia": 50739
485
+ }
hop3-4000/checkpoint-20000/added_tokens.json ADDED
@@ -0,0 +1,485 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Abby": 50258,
3
+ "Abel": 50257,
4
+ "Ace": 50259,
5
+ "Ada": 50260,
6
+ "Addie": 50261,
7
+ "Adele": 50262,
8
+ "Aiden": 50263,
9
+ "Aimee": 50264,
10
+ "Aisha": 50641,
11
+ "Ajay": 50265,
12
+ "Alba": 50266,
13
+ "Alec": 50267,
14
+ "Alfonso": 50642,
15
+ "Aline": 50268,
16
+ "Allegra": 50643,
17
+ "Alma": 50269,
18
+ "Alvin": 50270,
19
+ "Amber": 50271,
20
+ "Amie": 50272,
21
+ "Amir": 50273,
22
+ "Amos": 50644,
23
+ "Ana": 50274,
24
+ "Anika": 50275,
25
+ "Anita": 50276,
26
+ "Annie": 50277,
27
+ "Anson": 50645,
28
+ "Antwan": 50646,
29
+ "Anya": 50278,
30
+ "Araceli": 50647,
31
+ "Arden": 50648,
32
+ "Aria": 50279,
33
+ "Ariel": 50280,
34
+ "Arjun": 50649,
35
+ "Arlette": 50650,
36
+ "Arlo": 50281,
37
+ "Arman": 50282,
38
+ "Aron": 50283,
39
+ "Arya": 50284,
40
+ "Asa": 50285,
41
+ "Ashanti": 50651,
42
+ "Asher": 50286,
43
+ "Aston": 50287,
44
+ "Astrid": 50288,
45
+ "Aubrey": 50289,
46
+ "Aubri": 50652,
47
+ "Audra": 50290,
48
+ "Ava": 50291,
49
+ "Axel": 50292,
50
+ "Ayaan": 50293,
51
+ "Ayden": 50294,
52
+ "Bailey": 50295,
53
+ "Barb": 50296,
54
+ "Barry": 50297,
55
+ "Basil": 50653,
56
+ "Beatrix": 50654,
57
+ "Beau": 50298,
58
+ "Bella": 50299,
59
+ "Benedict": 50655,
60
+ "Benny": 50300,
61
+ "Bernadette": 50656,
62
+ "Bert": 50301,
63
+ "Beth": 50302,
64
+ "Beverly": 50303,
65
+ "Bianca": 50304,
66
+ "Bjorn": 50305,
67
+ "Blaise": 50657,
68
+ "Bobby": 50306,
69
+ "Bonita": 50658,
70
+ "Bonnie": 50307,
71
+ "Boyd": 50308,
72
+ "Brady": 50309,
73
+ "Brandy": 50310,
74
+ "Branson": 50659,
75
+ "Brenda": 50311,
76
+ "Brent": 50312,
77
+ "Brett": 50313,
78
+ "Brianna": 50314,
79
+ "Briar": 50660,
80
+ "Brice": 50315,
81
+ "Bridget": 50316,
82
+ "Britt": 50317,
83
+ "Brock": 50318,
84
+ "Brody": 50319,
85
+ "Brogan": 50661,
86
+ "Bruno": 50320,
87
+ "Bryan": 50321,
88
+ "Bryce": 50322,
89
+ "Byron": 50323,
90
+ "Cade": 50324,
91
+ "Cael": 50325,
92
+ "Cain": 50326,
93
+ "Caleb": 50327,
94
+ "Callan": 50662,
95
+ "Callie": 50328,
96
+ "Calvin": 50663,
97
+ "Cambria": 50664,
98
+ "Cameron": 50329,
99
+ "Cami": 50330,
100
+ "Candace": 50331,
101
+ "Cara": 50332,
102
+ "Carla": 50333,
103
+ "Carlton": 50334,
104
+ "Carmelo": 50665,
105
+ "Carol": 50335,
106
+ "Carrie": 50336,
107
+ "Carson": 50337,
108
+ "Carys": 50666,
109
+ "Casey": 50338,
110
+ "Cason": 50339,
111
+ "Cassius": 50667,
112
+ "Cathy": 50340,
113
+ "Cedric": 50341,
114
+ "Celeste": 50668,
115
+ "Celine": 50669,
116
+ "Cesar": 50342,
117
+ "Chad": 50343,
118
+ "Chandler": 50344,
119
+ "Charlton": 50670,
120
+ "Chase": 50345,
121
+ "Chloe": 50346,
122
+ "Cillian": 50671,
123
+ "Cindy": 50347,
124
+ "Claire": 50348,
125
+ "Claude": 50349,
126
+ "Clay": 50350,
127
+ "Cleo": 50672,
128
+ "Cliff": 50351,
129
+ "Clint": 50352,
130
+ "Clover": 50673,
131
+ "Clyde": 50353,
132
+ "Cody": 50354,
133
+ "Colby": 50355,
134
+ "Colin": 50356,
135
+ "Collette": 50674,
136
+ "Connie": 50357,
137
+ "Cooper": 50358,
138
+ "Cordelia": 50675,
139
+ "Corey": 50359,
140
+ "Cormac": 50676,
141
+ "Corwin": 50677,
142
+ "Cory": 50360,
143
+ "Curt": 50361,
144
+ "Curtis": 50362,
145
+ "Cyrus": 50363,
146
+ "Dahlia": 50678,
147
+ "Daisy": 50364,
148
+ "Dale": 50365,
149
+ "Damon": 50366,
150
+ "Dana": 50367,
151
+ "Danielle": 50368,
152
+ "Dante": 50369,
153
+ "Daphne": 50370,
154
+ "Darin": 50371,
155
+ "Darius": 50372,
156
+ "Darla": 50373,
157
+ "Darlene": 50374,
158
+ "Darnell": 50679,
159
+ "Darrel": 50375,
160
+ "Darren": 50376,
161
+ "Darryl": 50377,
162
+ "Dashiell": 50680,
163
+ "Dawn": 50378,
164
+ "Deacon": 50681,
165
+ "Debbie": 50379,
166
+ "Deborah": 50380,
167
+ "Declan": 50381,
168
+ "Delaney": 50682,
169
+ "Delia": 50382,
170
+ "Demetri": 50383,
171
+ "Demetrius": 50683,
172
+ "Demi": 50384,
173
+ "Denise": 50385,
174
+ "Dennis": 50386,
175
+ "Derek": 50387,
176
+ "Derrick": 50388,
177
+ "Deshawn": 50684,
178
+ "Devin": 50389,
179
+ "Devon": 50390,
180
+ "Dewey": 50685,
181
+ "Dexter": 50391,
182
+ "Diana": 50392,
183
+ "Diane": 50393,
184
+ "Diego": 50394,
185
+ "Dillon": 50395,
186
+ "Dina": 50396,
187
+ "Dino": 50397,
188
+ "Dior": 50686,
189
+ "Dirk": 50398,
190
+ "Dixie": 50399,
191
+ "Dolly": 50400,
192
+ "Dominic": 50401,
193
+ "Donna": 50402,
194
+ "Dorian": 50403,
195
+ "Doris": 50404,
196
+ "Douglas": 50405,
197
+ "Drake": 50406,
198
+ "Drew": 50407,
199
+ "Duke": 50408,
200
+ "Dulcie": 50687,
201
+ "Duncan": 50409,
202
+ "Dustin": 50410,
203
+ "Dusty": 50411,
204
+ "Dwayne": 50412,
205
+ "Dwight": 50413,
206
+ "Dylan": 50414,
207
+ "Eamon": 50688,
208
+ "Earl": 50415,
209
+ "Eddard": 50689,
210
+ "Eddie": 50416,
211
+ "Edgar": 50417,
212
+ "Edith": 50418,
213
+ "Edna": 50419,
214
+ "Edwin": 50420,
215
+ "Eileen": 50421,
216
+ "Elaine": 50422,
217
+ "Eldon": 50690,
218
+ "Eleanor": 50423,
219
+ "Elena": 50424,
220
+ "Eli": 50425,
221
+ "Eliana": 50426,
222
+ "Elijah": 50427,
223
+ "Elisa": 50428,
224
+ "Elise": 50429,
225
+ "Eliza": 50430,
226
+ "Ella": 50431,
227
+ "Ellen": 50432,
228
+ "Elliot": 50433,
229
+ "Eloise": 50434,
230
+ "Elowen": 50691,
231
+ "Elton": 50435,
232
+ "Elvira": 50692,
233
+ "Elvis": 50436,
234
+ "Ember": 50693,
235
+ "Emery": 50437,
236
+ "Emil": 50438,
237
+ "Emilia": 50439,
238
+ "Emiliano": 50694,
239
+ "Emma": 50440,
240
+ "Emmeline": 50695,
241
+ "Emory": 50441,
242
+ "Enid": 50442,
243
+ "Enzo": 50443,
244
+ "Ephraim": 50696,
245
+ "Erica": 50444,
246
+ "Erick": 50445,
247
+ "Erik": 50446,
248
+ "Erin": 50447,
249
+ "Ernest": 50448,
250
+ "Ernie": 50449,
251
+ "Esme": 50450,
252
+ "Esther": 50451,
253
+ "Ethan": 50452,
254
+ "Ethel": 50453,
255
+ "Eugene": 50454,
256
+ "Eulalia": 50697,
257
+ "Eunice": 50455,
258
+ "Evan": 50456,
259
+ "Evander": 50698,
260
+ "Eve": 50457,
261
+ "Evelyn": 50458,
262
+ "Everett": 50459,
263
+ "Ewan": 50460,
264
+ "Ezra": 50461,
265
+ "Fabian": 50462,
266
+ "Fanny": 50463,
267
+ "Faustino": 50699,
268
+ "Felicia": 50464,
269
+ "Felicity": 50700,
270
+ "Felix": 50465,
271
+ "Finley": 50701,
272
+ "Finn": 50467,
273
+ "Fiona": 50466,
274
+ "Flora": 50702,
275
+ "Floyd": 50468,
276
+ "Flynn": 50703,
277
+ "Forrest": 50469,
278
+ "Frances": 50470,
279
+ "Francis": 50471,
280
+ "Frankie": 50472,
281
+ "Freddie": 50473,
282
+ "Freddy": 50474,
283
+ "Frederica": 50704,
284
+ "Freya": 50475,
285
+ "Gabby": 50476,
286
+ "Gabe": 50477,
287
+ "Gabriel": 50478,
288
+ "Gael": 50705,
289
+ "Gail": 50479,
290
+ "Gale": 50480,
291
+ "Garrett": 50706,
292
+ "Garry": 50481,
293
+ "Gavin": 50482,
294
+ "Geoff": 50483,
295
+ "Gerald": 50484,
296
+ "Gerard": 50485,
297
+ "Gigi": 50486,
298
+ "Gilbert": 50487,
299
+ "Gina": 50488,
300
+ "Ginger": 50489,
301
+ "Gino": 50490,
302
+ "Giovanni": 50491,
303
+ "Gisela": 50707,
304
+ "Giselle": 50492,
305
+ "Gladys": 50493,
306
+ "Glen": 50494,
307
+ "Glenda": 50495,
308
+ "Glenn": 50496,
309
+ "Gloria": 50497,
310
+ "Grace": 50498,
311
+ "Grady": 50499,
312
+ "Gregg": 50500,
313
+ "Gregory": 50501,
314
+ "Greta": 50502,
315
+ "Gretchen": 50503,
316
+ "Griffin": 50504,
317
+ "Gus": 50505,
318
+ "Gustavo": 50708,
319
+ "Gwen": 50506,
320
+ "Hadley": 50709,
321
+ "Hailey": 50507,
322
+ "Hamza": 50710,
323
+ "Hank": 50508,
324
+ "Hanna": 50509,
325
+ "Hannah": 50510,
326
+ "Harland": 50711,
327
+ "Harley": 50511,
328
+ "Harold": 50512,
329
+ "Harvey": 50513,
330
+ "Hattie": 50712,
331
+ "Haven": 50713,
332
+ "Hazel": 50514,
333
+ "Heath": 50515,
334
+ "Heather": 50516,
335
+ "Hector": 50517,
336
+ "Heidi": 50518,
337
+ "Helen": 50519,
338
+ "Henri": 50520,
339
+ "Herb": 50521,
340
+ "Herman": 50522,
341
+ "Hilary": 50523,
342
+ "Holland": 50714,
343
+ "Holly": 50524,
344
+ "Horace": 50525,
345
+ "Hudson": 50526,
346
+ "Hugh": 50527,
347
+ "Hugo": 50528,
348
+ "Ida": 50529,
349
+ "Igor": 50530,
350
+ "Iker": 50715,
351
+ "Imogen": 50531,
352
+ "Indira": 50716,
353
+ "Ines": 50532,
354
+ "Inigo": 50717,
355
+ "Irene": 50533,
356
+ "Iris": 50534,
357
+ "Irma": 50535,
358
+ "Isaac": 50536,
359
+ "Isabel": 50537,
360
+ "Isabella": 50538,
361
+ "Isaiah": 50539,
362
+ "Isla": 50540,
363
+ "Ivan": 50541,
364
+ "Ivy": 50542,
365
+ "Jace": 50543,
366
+ "Jackie": 50544,
367
+ "Jacqueline": 50545,
368
+ "Jade": 50546,
369
+ "Jaime": 50547,
370
+ "Jalen": 50548,
371
+ "Jalil": 50718,
372
+ "Jana": 50549,
373
+ "Janet": 50550,
374
+ "Janice": 50551,
375
+ "Jared": 50552,
376
+ "Jareth": 50719,
377
+ "Jasmine": 50553,
378
+ "Jasper": 50554,
379
+ "Javier": 50555,
380
+ "Jayden": 50556,
381
+ "Jeanette": 50557,
382
+ "Jeanne": 50558,
383
+ "Jeffery": 50559,
384
+ "Jeffrey": 50560,
385
+ "Jenna": 50561,
386
+ "Jenny": 50562,
387
+ "Jensen": 50720,
388
+ "Jeremiah": 50563,
389
+ "Jermaine": 50564,
390
+ "Jerome": 50565,
391
+ "Jesse": 50566,
392
+ "Jessie": 50567,
393
+ "Jethro": 50721,
394
+ "Jill": 50568,
395
+ "Joan": 50569,
396
+ "Joanna": 50570,
397
+ "Joanne": 50571,
398
+ "Jocelyn": 50572,
399
+ "Jodi": 50573,
400
+ "Jodie": 50574,
401
+ "Joel": 50575,
402
+ "Joey": 50576,
403
+ "Jonah": 50577,
404
+ "Jorge": 50578,
405
+ "Josie": 50579,
406
+ "Jovan": 50722,
407
+ "Joyce": 50580,
408
+ "Juan": 50581,
409
+ "Juanita": 50582,
410
+ "Judith": 50583,
411
+ "Judy": 50584,
412
+ "Jules": 50585,
413
+ "Julia": 50586,
414
+ "Julian": 50587,
415
+ "Julie": 50588,
416
+ "Juliet": 50589,
417
+ "Julio": 50590,
418
+ "Julius": 50591,
419
+ "Kaden": 50592,
420
+ "Kael": 50723,
421
+ "Kai": 50593,
422
+ "Kaia": 50724,
423
+ "Kara": 50594,
424
+ "Karen": 50595,
425
+ "Kari": 50596,
426
+ "Karina": 50597,
427
+ "Katherine": 50598,
428
+ "Kathleen": 50599,
429
+ "Kathy": 50600,
430
+ "Katie": 50601,
431
+ "Kayla": 50602,
432
+ "Keira": 50603,
433
+ "Kelsey": 50604,
434
+ "Kendall": 50605,
435
+ "Kenji": 50725,
436
+ "Kennedy": 50606,
437
+ "Kenneth": 50607,
438
+ "Kenny": 50608,
439
+ "Khalid": 50609,
440
+ "Kian": 50726,
441
+ "Kimberly": 50610,
442
+ "Kip": 50727,
443
+ "Kirk": 50611,
444
+ "Kris": 50612,
445
+ "Krista": 50613,
446
+ "Kristen": 50614,
447
+ "Kristin": 50615,
448
+ "Kristina": 50616,
449
+ "Kurt": 50617,
450
+ "Lacey": 50618,
451
+ "Lachlan": 50728,
452
+ "Lana": 50619,
453
+ "Lance": 50620,
454
+ "Lara": 50621,
455
+ "Lauren": 50622,
456
+ "Laurie": 50623,
457
+ "Layla": 50624,
458
+ "Lazaro": 50729,
459
+ "Leah": 50625,
460
+ "Leandro": 50730,
461
+ "Leo": 50626,
462
+ "Leona": 50627,
463
+ "Leonard": 50628,
464
+ "Leroy": 50629,
465
+ "Leslie": 50630,
466
+ "Lester": 50631,
467
+ "Liam": 50632,
468
+ "Lincoln": 50633,
469
+ "Linda": 50634,
470
+ "Lindsay": 50635,
471
+ "Logan": 50636,
472
+ "Lola": 50637,
473
+ "Loren": 50638,
474
+ "Louise": 50639,
475
+ "Lucas": 50640,
476
+ "Lucien": 50731,
477
+ "Ludwig": 50732,
478
+ "Malik": 50733,
479
+ "Marcella": 50734,
480
+ "Maxton": 50735,
481
+ "Melina": 50736,
482
+ "Mireille": 50737,
483
+ "Mordecai": 50738,
484
+ "Talia": 50739
485
+ }
hop3-4000/checkpoint-20000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTJForCausalLM"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gptj",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 1024,
18
+ "resid_pdrop": 0.1,
19
+ "rotary_dim": 64,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.46.2",
23
+ "use_cache": true,
24
+ "vocab_size": 50740
25
+ }
hop3-4000/checkpoint-20000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.2"
6
+ }
hop3-4000/checkpoint-20000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
hop3-4000/checkpoint-20000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244bae39c5b8af705f691e1cba9108d38cf52a1dc326c47d4edbde188f65ee65
3
+ size 651965360
hop3-4000/checkpoint-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69eb755b8c91f8c2cbb4a149f7d83ec01c7230299c17cad21004e402cdd777f
3
+ size 1303978682
hop3-4000/checkpoint-20000/output/ood_test_metrics.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "exact_match": 1.0,
3
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
4
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
5
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
6
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
7
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
8
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
9
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
10
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
11
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
12
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
13
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
14
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
15
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
16
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
17
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
18
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
19
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
20
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
21
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
22
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
23
+ }
hop3-4000/checkpoint-20000/output/ood_test_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
hop3-4000/checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41dabd080c5159151404148caa3a94da71e0b89be5d71c4c00d5e80f39a58622
3
+ size 14180
hop3-4000/checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26916617aa17a61e355fd0b2e58dcc69e7542afa5dfd11c9c2b137b6a32d1d14
3
+ size 1000
hop3-4000/checkpoint-20000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
hop3-4000/checkpoint-20000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
hop3-4000/checkpoint-20000/trainer_state.json ADDED
@@ -0,0 +1,1433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 102.17113665389527,
5
+ "eval_steps": 500,
6
+ "global_step": 20000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5108556832694764,
13
+ "grad_norm": 3.8150711059570312,
14
+ "learning_rate": 5e-05,
15
+ "loss": 4.2761,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 1.0217113665389528,
20
+ "grad_norm": 0.5836750864982605,
21
+ "learning_rate": 0.0001,
22
+ "loss": 1.107,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 1.5325670498084292,
27
+ "grad_norm": 0.5383573770523071,
28
+ "learning_rate": 0.00015,
29
+ "loss": 0.9188,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 2.0434227330779056,
34
+ "grad_norm": 0.41685330867767334,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.9061,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 2.554278416347382,
41
+ "grad_norm": 0.39630717039108276,
42
+ "learning_rate": 0.00025,
43
+ "loss": 0.9009,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 3.0651340996168583,
48
+ "grad_norm": 0.4555200934410095,
49
+ "learning_rate": 0.0003,
50
+ "loss": 0.8965,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 3.5759897828863347,
55
+ "grad_norm": 0.4941987097263336,
56
+ "learning_rate": 0.00035,
57
+ "loss": 0.8868,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 4.086845466155811,
62
+ "grad_norm": 0.4683818817138672,
63
+ "learning_rate": 0.0004,
64
+ "loss": 0.8831,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 4.597701149425287,
69
+ "grad_norm": 0.4812484085559845,
70
+ "learning_rate": 0.00045000000000000004,
71
+ "loss": 0.8753,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 5.108556832694764,
76
+ "grad_norm": 0.5274789929389954,
77
+ "learning_rate": 0.0005,
78
+ "loss": 0.8739,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 5.61941251596424,
83
+ "grad_norm": 0.5269874930381775,
84
+ "learning_rate": 0.0004999692436233055,
85
+ "loss": 0.8722,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 6.130268199233717,
90
+ "grad_norm": 0.415839284658432,
91
+ "learning_rate": 0.0004998769829017084,
92
+ "loss": 0.8714,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 6.641123882503193,
97
+ "grad_norm": 0.4049590826034546,
98
+ "learning_rate": 0.0004997232430583686,
99
+ "loss": 0.8698,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 7.1519795657726695,
104
+ "grad_norm": 0.5244262218475342,
105
+ "learning_rate": 0.0004995080661242243,
106
+ "loss": 0.8688,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 7.662835249042145,
111
+ "grad_norm": 0.447439968585968,
112
+ "learning_rate": 0.0004992315109265007,
113
+ "loss": 0.8675,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 8.173690932311622,
118
+ "grad_norm": 0.43550002574920654,
119
+ "learning_rate": 0.0004988936530726276,
120
+ "loss": 0.8666,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 8.684546615581098,
125
+ "grad_norm": 0.4498232305049896,
126
+ "learning_rate": 0.0004984945849295686,
127
+ "loss": 0.8658,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 9.195402298850574,
132
+ "grad_norm": 0.4852600395679474,
133
+ "learning_rate": 0.0004980344155985694,
134
+ "loss": 0.8645,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 9.706257982120052,
139
+ "grad_norm": 0.365408331155777,
140
+ "learning_rate": 0.0004975132708853304,
141
+ "loss": 0.8634,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 10.217113665389528,
146
+ "grad_norm": 0.3523465394973755,
147
+ "learning_rate": 0.0004969312932656126,
148
+ "loss": 0.8623,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 10.727969348659004,
153
+ "grad_norm": 0.46213963627815247,
154
+ "learning_rate": 0.000496288641846286,
155
+ "loss": 0.8613,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 11.23882503192848,
160
+ "grad_norm": 0.36943599581718445,
161
+ "learning_rate": 0.0004955854923218321,
162
+ "loss": 0.8603,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 11.749680715197957,
167
+ "grad_norm": 0.38349947333335876,
168
+ "learning_rate": 0.0004948220369263099,
169
+ "loss": 0.859,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 12.260536398467433,
174
+ "grad_norm": 0.3721200227737427,
175
+ "learning_rate": 0.0004939984843808013,
176
+ "loss": 0.8581,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 12.77139208173691,
181
+ "grad_norm": 0.4441462457180023,
182
+ "learning_rate": 0.0004931150598363493,
183
+ "loss": 0.8576,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 13.282247765006385,
188
+ "grad_norm": 0.4003834128379822,
189
+ "learning_rate": 0.0004921720048124034,
190
+ "loss": 0.8564,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 13.793103448275861,
195
+ "grad_norm": 0.49827203154563904,
196
+ "learning_rate": 0.0004911695771307908,
197
+ "loss": 0.856,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 14.303959131545339,
202
+ "grad_norm": 0.37891724705696106,
203
+ "learning_rate": 0.0004901080508452304,
204
+ "loss": 0.8548,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 14.814814814814815,
209
+ "grad_norm": 0.3973143696784973,
210
+ "learning_rate": 0.0004889877161664096,
211
+ "loss": 0.8545,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 15.32567049808429,
216
+ "grad_norm": 0.4246247410774231,
217
+ "learning_rate": 0.00048780887938264277,
218
+ "loss": 0.8532,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 15.836526181353767,
223
+ "grad_norm": 0.3248208165168762,
224
+ "learning_rate": 0.0004865718627761363,
225
+ "loss": 0.8533,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 16.347381864623244,
230
+ "grad_norm": 0.39810553193092346,
231
+ "learning_rate": 0.0004852770045348787,
232
+ "loss": 0.8515,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 16.85823754789272,
237
+ "grad_norm": 0.40074267983436584,
238
+ "learning_rate": 0.0004839246586601841,
239
+ "loss": 0.8516,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 17.369093231162196,
244
+ "grad_norm": 0.40132787823677063,
245
+ "learning_rate": 0.0004825151948699116,
246
+ "loss": 0.8498,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 17.879948914431672,
251
+ "grad_norm": 0.399463415145874,
252
+ "learning_rate": 0.00048104899849738794,
253
+ "loss": 0.8496,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 18.39080459770115,
258
+ "grad_norm": 0.33722564578056335,
259
+ "learning_rate": 0.00047952647038606157,
260
+ "loss": 0.8473,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 18.901660280970624,
265
+ "grad_norm": 0.3787365257740021,
266
+ "learning_rate": 0.0004779480267799158,
267
+ "loss": 0.847,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 19.412515964240104,
272
+ "grad_norm": 0.32648733258247375,
273
+ "learning_rate": 0.00047631409920967176,
274
+ "loss": 0.8443,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 19.92337164750958,
279
+ "grad_norm": 0.4032730460166931,
280
+ "learning_rate": 0.00047462513437481266,
281
+ "loss": 0.8437,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 20.434227330779056,
286
+ "grad_norm": 0.37871378660202026,
287
+ "learning_rate": 0.00047288159402146003,
288
+ "loss": 0.8396,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 20.94508301404853,
293
+ "grad_norm": 0.38903817534446716,
294
+ "learning_rate": 0.00047108395481613736,
295
+ "loss": 0.8387,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 21.455938697318008,
300
+ "grad_norm": 0.3136683404445648,
301
+ "learning_rate": 0.00046923270821545415,
302
+ "loss": 0.8319,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 21.966794380587483,
307
+ "grad_norm": 0.39562785625457764,
308
+ "learning_rate": 0.0004673283603317463,
309
+ "loss": 0.8292,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 22.47765006385696,
314
+ "grad_norm": 0.44314175844192505,
315
+ "learning_rate": 0.00046537143179471046,
316
+ "loss": 0.8157,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 22.988505747126435,
321
+ "grad_norm": 0.42985689640045166,
322
+ "learning_rate": 0.0004633624576090689,
323
+ "loss": 0.8014,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 23.499361430395915,
328
+ "grad_norm": 0.4407409727573395,
329
+ "learning_rate": 0.0004613019870083045,
330
+ "loss": 0.7601,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 24.01021711366539,
335
+ "grad_norm": 0.4977095127105713,
336
+ "learning_rate": 0.0004591905833045059,
337
+ "loss": 0.7174,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 24.521072796934867,
342
+ "grad_norm": 0.46554914116859436,
343
+ "learning_rate": 0.00045702882373436317,
344
+ "loss": 0.6907,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 25.031928480204343,
349
+ "grad_norm": 0.4139585494995117,
350
+ "learning_rate": 0.00045481729930135805,
351
+ "loss": 0.6826,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 25.54278416347382,
356
+ "grad_norm": 0.4079512655735016,
357
+ "learning_rate": 0.00045255661461418854,
358
+ "loss": 0.6781,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 26.053639846743295,
363
+ "grad_norm": 0.4325273334980011,
364
+ "learning_rate": 0.00045024738772147534,
365
+ "loss": 0.6762,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 26.56449553001277,
370
+ "grad_norm": 0.3361075222492218,
371
+ "learning_rate": 0.0004478902499427933,
372
+ "loss": 0.674,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 27.075351213282246,
377
+ "grad_norm": 0.3321281373500824,
378
+ "learning_rate": 0.00044548584569607536,
379
+ "loss": 0.6734,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 27.586206896551722,
384
+ "grad_norm": 0.3296426832675934,
385
+ "learning_rate": 0.0004430348323214347,
386
+ "loss": 0.6721,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 28.097062579821202,
391
+ "grad_norm": 0.32873860001564026,
392
+ "learning_rate": 0.00044053787990145466,
393
+ "loss": 0.6721,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 28.607918263090678,
398
+ "grad_norm": 0.32210880517959595,
399
+ "learning_rate": 0.00043799567107799504,
400
+ "loss": 0.672,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 29.118773946360154,
405
+ "grad_norm": 0.3907981514930725,
406
+ "learning_rate": 0.00043540890086556436,
407
+ "loss": 0.6709,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 29.62962962962963,
412
+ "grad_norm": 0.31113773584365845,
413
+ "learning_rate": 0.0004327782764613099,
414
+ "loss": 0.6707,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 30.140485312899106,
419
+ "grad_norm": 0.4042207896709442,
420
+ "learning_rate": 0.0004301045170516773,
421
+ "loss": 0.6707,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 30.65134099616858,
426
+ "grad_norm": 0.2873578667640686,
427
+ "learning_rate": 0.00042738835361579177,
428
+ "loss": 0.6697,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 31.162196679438058,
433
+ "grad_norm": 0.36621251702308655,
434
+ "learning_rate": 0.00042463052872561587,
435
+ "loss": 0.6701,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 31.673052362707534,
440
+ "grad_norm": 0.310585081577301,
441
+ "learning_rate": 0.00042183179634293794,
442
+ "loss": 0.67,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 32.18390804597701,
447
+ "grad_norm": 0.3390922248363495,
448
+ "learning_rate": 0.00041899292161324625,
449
+ "loss": 0.669,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 32.69476372924649,
454
+ "grad_norm": 0.2893514633178711,
455
+ "learning_rate": 0.00041611468065654586,
456
+ "loss": 0.6692,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 33.205619412515965,
461
+ "grad_norm": 0.3678007423877716,
462
+ "learning_rate": 0.0004131978603551753,
463
+ "loss": 0.6694,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 33.71647509578544,
468
+ "grad_norm": 0.3219503164291382,
469
+ "learning_rate": 0.00041024325813868065,
470
+ "loss": 0.669,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 34.22733077905492,
475
+ "grad_norm": 0.2958202064037323,
476
+ "learning_rate": 0.0004072516817658065,
477
+ "loss": 0.6684,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 34.73818646232439,
482
+ "grad_norm": 0.32199811935424805,
483
+ "learning_rate": 0.00040422394910366236,
484
+ "loss": 0.6685,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 35.24904214559387,
489
+ "grad_norm": 0.25338029861450195,
490
+ "learning_rate": 0.00040116088790412643,
491
+ "loss": 0.6685,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 35.759897828863345,
496
+ "grad_norm": 0.30959373712539673,
497
+ "learning_rate": 0.0003980633355775461,
498
+ "loss": 0.6683,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 36.27075351213282,
503
+ "grad_norm": 0.31291133165359497,
504
+ "learning_rate": 0.0003949321389637986,
505
+ "loss": 0.6682,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 36.7816091954023,
510
+ "grad_norm": 0.2806414067745209,
511
+ "learning_rate": 0.00039176815410077345,
512
+ "loss": 0.668,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 37.29246487867177,
517
+ "grad_norm": 0.33664754033088684,
518
+ "learning_rate": 0.00038857224599033987,
519
+ "loss": 0.6679,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 37.80332056194125,
524
+ "grad_norm": 0.3057114779949188,
525
+ "learning_rate": 0.0003853452883618644,
526
+ "loss": 0.6679,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 38.31417624521073,
531
+ "grad_norm": 0.2843305766582489,
532
+ "learning_rate": 0.00038208816343334156,
533
+ "loss": 0.6671,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 38.82503192848021,
538
+ "grad_norm": 0.3106359541416168,
539
+ "learning_rate": 0.0003788017616702048,
540
+ "loss": 0.6696,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 39.33588761174968,
545
+ "grad_norm": 0.30231013894081116,
546
+ "learning_rate": 0.0003754869815418815,
547
+ "loss": 0.668,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 39.84674329501916,
552
+ "grad_norm": 0.35945335030555725,
553
+ "learning_rate": 0.00037214472927616087,
554
+ "loss": 0.668,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 40.357598978288635,
559
+ "grad_norm": 0.3693214952945709,
560
+ "learning_rate": 0.00036877591861144034,
561
+ "loss": 0.667,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 40.86845466155811,
566
+ "grad_norm": 0.2945208251476288,
567
+ "learning_rate": 0.0003653814705469182,
568
+ "loss": 0.6675,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 41.37931034482759,
573
+ "grad_norm": 0.3053165376186371,
574
+ "learning_rate": 0.0003619623130908017,
575
+ "loss": 0.6678,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 41.89016602809706,
580
+ "grad_norm": 0.30423006415367126,
581
+ "learning_rate": 0.00035851938100659966,
582
+ "loss": 0.6674,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 42.40102171136654,
587
+ "grad_norm": 0.2914177179336548,
588
+ "learning_rate": 0.0003550536155575662,
589
+ "loss": 0.6676,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 42.911877394636015,
594
+ "grad_norm": 0.33945366740226746,
595
+ "learning_rate": 0.0003515659642493697,
596
+ "loss": 0.6672,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 43.42273307790549,
601
+ "grad_norm": 0.3103128969669342,
602
+ "learning_rate": 0.0003480573805710538,
603
+ "loss": 0.6671,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 43.93358876117497,
608
+ "grad_norm": 0.3014843463897705,
609
+ "learning_rate": 0.0003445288237343632,
610
+ "loss": 0.6674,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 44.44444444444444,
615
+ "grad_norm": 0.2856997549533844,
616
+ "learning_rate": 0.0003409812584115046,
617
+ "loss": 0.6673,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 44.95530012771392,
622
+ "grad_norm": 0.30553188920021057,
623
+ "learning_rate": 0.00033741565447141503,
624
+ "loss": 0.6674,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 45.466155810983395,
629
+ "grad_norm": 0.33186161518096924,
630
+ "learning_rate": 0.00033383298671460943,
631
+ "loss": 0.6677,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 45.97701149425287,
636
+ "grad_norm": 0.27859747409820557,
637
+ "learning_rate": 0.00033023423460667984,
638
+ "loss": 0.6673,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 46.48786717752235,
643
+ "grad_norm": 0.2895662784576416,
644
+ "learning_rate": 0.00032662038201051915,
645
+ "loss": 0.6674,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 46.99872286079183,
650
+ "grad_norm": 0.3233847916126251,
651
+ "learning_rate": 0.00032299241691734307,
652
+ "loss": 0.6683,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 47.509578544061306,
657
+ "grad_norm": 0.2617289125919342,
658
+ "learning_rate": 0.00031935133117658306,
659
+ "loss": 0.6672,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 48.02043422733078,
664
+ "grad_norm": 0.24173779785633087,
665
+ "learning_rate": 0.00031569812022472476,
666
+ "loss": 0.6675,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 48.53128991060026,
671
+ "grad_norm": 0.3184884488582611,
672
+ "learning_rate": 0.0003120337828131651,
673
+ "loss": 0.6677,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 49.04214559386973,
678
+ "grad_norm": 0.2559392750263214,
679
+ "learning_rate": 0.0003083593207351644,
680
+ "loss": 0.6668,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 49.55300127713921,
685
+ "grad_norm": 0.3299408555030823,
686
+ "learning_rate": 0.0003046757385519656,
687
+ "loss": 0.6667,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 50.063856960408685,
692
+ "grad_norm": 0.26693782210350037,
693
+ "learning_rate": 0.0003009840433181569,
694
+ "loss": 0.6673,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 50.57471264367816,
699
+ "grad_norm": 0.3051166534423828,
700
+ "learning_rate": 0.00029728524430635417,
701
+ "loss": 0.6672,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 51.08556832694764,
706
+ "grad_norm": 0.30509310960769653,
707
+ "learning_rate": 0.0002935803527312748,
708
+ "loss": 0.667,
709
+ "step": 10000
710
+ },
711
+ {
712
+ "epoch": 51.59642401021711,
713
+ "grad_norm": 0.32847079634666443,
714
+ "learning_rate": 0.0002898703814732824,
715
+ "loss": 0.6662,
716
+ "step": 10100
717
+ },
718
+ {
719
+ "epoch": 52.10727969348659,
720
+ "grad_norm": 0.2863231897354126,
721
+ "learning_rate": 0.000286156344801475,
722
+ "loss": 0.6675,
723
+ "step": 10200
724
+ },
725
+ {
726
+ "epoch": 52.618135376756065,
727
+ "grad_norm": 0.2994413673877716,
728
+ "learning_rate": 0.00028243925809639435,
729
+ "loss": 0.6668,
730
+ "step": 10300
731
+ },
732
+ {
733
+ "epoch": 53.12899106002554,
734
+ "grad_norm": 0.2800912857055664,
735
+ "learning_rate": 0.0002787201375724307,
736
+ "loss": 0.6659,
737
+ "step": 10400
738
+ },
739
+ {
740
+ "epoch": 53.63984674329502,
741
+ "grad_norm": 0.2775793969631195,
742
+ "learning_rate": 0.000275,
743
+ "loss": 0.6664,
744
+ "step": 10500
745
+ },
746
+ {
747
+ "epoch": 54.15070242656449,
748
+ "grad_norm": 0.2953220307826996,
749
+ "learning_rate": 0.00027127986242756933,
750
+ "loss": 0.667,
751
+ "step": 10600
752
+ },
753
+ {
754
+ "epoch": 54.66155810983397,
755
+ "grad_norm": 0.2522236704826355,
756
+ "learning_rate": 0.00026756074190360563,
757
+ "loss": 0.6662,
758
+ "step": 10700
759
+ },
760
+ {
761
+ "epoch": 55.172413793103445,
762
+ "grad_norm": 0.30071786046028137,
763
+ "learning_rate": 0.000263843655198525,
764
+ "loss": 0.6667,
765
+ "step": 10800
766
+ },
767
+ {
768
+ "epoch": 55.68326947637293,
769
+ "grad_norm": 0.30239617824554443,
770
+ "learning_rate": 0.0002601296185267177,
771
+ "loss": 0.6664,
772
+ "step": 10900
773
+ },
774
+ {
775
+ "epoch": 56.194125159642404,
776
+ "grad_norm": 0.341932088136673,
777
+ "learning_rate": 0.00025641964726872524,
778
+ "loss": 0.6661,
779
+ "step": 11000
780
+ },
781
+ {
782
+ "epoch": 56.70498084291188,
783
+ "grad_norm": 0.34843477606773376,
784
+ "learning_rate": 0.00025271475569364586,
785
+ "loss": 0.6659,
786
+ "step": 11100
787
+ },
788
+ {
789
+ "epoch": 57.215836526181356,
790
+ "grad_norm": 0.28951045870780945,
791
+ "learning_rate": 0.0002490159566818431,
792
+ "loss": 0.6662,
793
+ "step": 11200
794
+ },
795
+ {
796
+ "epoch": 57.72669220945083,
797
+ "grad_norm": 0.2758599519729614,
798
+ "learning_rate": 0.0002453242614480345,
799
+ "loss": 0.6667,
800
+ "step": 11300
801
+ },
802
+ {
803
+ "epoch": 58.23754789272031,
804
+ "grad_norm": 0.2665814161300659,
805
+ "learning_rate": 0.0002416406792648355,
806
+ "loss": 0.6663,
807
+ "step": 11400
808
+ },
809
+ {
810
+ "epoch": 58.748403575989784,
811
+ "grad_norm": 0.27837157249450684,
812
+ "learning_rate": 0.00023796621718683486,
813
+ "loss": 0.6657,
814
+ "step": 11500
815
+ },
816
+ {
817
+ "epoch": 59.25925925925926,
818
+ "grad_norm": 0.23067055642604828,
819
+ "learning_rate": 0.00023430187977527533,
820
+ "loss": 0.6655,
821
+ "step": 11600
822
+ },
823
+ {
824
+ "epoch": 59.770114942528735,
825
+ "grad_norm": 0.240305557847023,
826
+ "learning_rate": 0.00023064866882341694,
827
+ "loss": 0.6661,
828
+ "step": 11700
829
+ },
830
+ {
831
+ "epoch": 60.28097062579821,
832
+ "grad_norm": 0.28111472725868225,
833
+ "learning_rate": 0.00022700758308265702,
834
+ "loss": 0.6651,
835
+ "step": 11800
836
+ },
837
+ {
838
+ "epoch": 60.79182630906769,
839
+ "grad_norm": 0.31027185916900635,
840
+ "learning_rate": 0.0002233796179894809,
841
+ "loss": 0.6659,
842
+ "step": 11900
843
+ },
844
+ {
845
+ "epoch": 61.30268199233716,
846
+ "grad_norm": 0.3049308955669403,
847
+ "learning_rate": 0.00021976576539332022,
848
+ "loss": 0.6659,
849
+ "step": 12000
850
+ },
851
+ {
852
+ "epoch": 61.81353767560664,
853
+ "grad_norm": 0.3007783591747284,
854
+ "learning_rate": 0.00021616701328539057,
855
+ "loss": 0.6658,
856
+ "step": 12100
857
+ },
858
+ {
859
+ "epoch": 62.324393358876115,
860
+ "grad_norm": 0.25258371233940125,
861
+ "learning_rate": 0.00021258434552858503,
862
+ "loss": 0.6648,
863
+ "step": 12200
864
+ },
865
+ {
866
+ "epoch": 62.83524904214559,
867
+ "grad_norm": 0.2703670263290405,
868
+ "learning_rate": 0.0002090187415884955,
869
+ "loss": 0.666,
870
+ "step": 12300
871
+ },
872
+ {
873
+ "epoch": 63.34610472541507,
874
+ "grad_norm": 0.26429376006126404,
875
+ "learning_rate": 0.0002054711762656369,
876
+ "loss": 0.6652,
877
+ "step": 12400
878
+ },
879
+ {
880
+ "epoch": 63.85696040868454,
881
+ "grad_norm": 0.2400507777929306,
882
+ "learning_rate": 0.00020194261942894627,
883
+ "loss": 0.6651,
884
+ "step": 12500
885
+ },
886
+ {
887
+ "epoch": 64.36781609195403,
888
+ "grad_norm": 0.26643094420433044,
889
+ "learning_rate": 0.00019843403575063028,
890
+ "loss": 0.6643,
891
+ "step": 12600
892
+ },
893
+ {
894
+ "epoch": 64.8786717752235,
895
+ "grad_norm": 0.2681981027126312,
896
+ "learning_rate": 0.0001949463844424338,
897
+ "loss": 0.6654,
898
+ "step": 12700
899
+ },
900
+ {
901
+ "epoch": 65.38952745849298,
902
+ "grad_norm": 0.2941227853298187,
903
+ "learning_rate": 0.0001914806189934003,
904
+ "loss": 0.665,
905
+ "step": 12800
906
+ },
907
+ {
908
+ "epoch": 65.90038314176245,
909
+ "grad_norm": 0.28216105699539185,
910
+ "learning_rate": 0.0001880376869091983,
911
+ "loss": 0.6642,
912
+ "step": 12900
913
+ },
914
+ {
915
+ "epoch": 66.41123882503193,
916
+ "grad_norm": 0.2791600227355957,
917
+ "learning_rate": 0.00018461852945308194,
918
+ "loss": 0.6643,
919
+ "step": 13000
920
+ },
921
+ {
922
+ "epoch": 66.9220945083014,
923
+ "grad_norm": 0.24909202754497528,
924
+ "learning_rate": 0.00018122408138855972,
925
+ "loss": 0.6647,
926
+ "step": 13100
927
+ },
928
+ {
929
+ "epoch": 67.43295019157088,
930
+ "grad_norm": 0.32806509733200073,
931
+ "learning_rate": 0.0001778552707238391,
932
+ "loss": 0.6637,
933
+ "step": 13200
934
+ },
935
+ {
936
+ "epoch": 67.94380587484035,
937
+ "grad_norm": 0.2732849419116974,
938
+ "learning_rate": 0.00017451301845811858,
939
+ "loss": 0.6645,
940
+ "step": 13300
941
+ },
942
+ {
943
+ "epoch": 68.45466155810983,
944
+ "grad_norm": 0.2075076401233673,
945
+ "learning_rate": 0.00017119823832979528,
946
+ "loss": 0.6634,
947
+ "step": 13400
948
+ },
949
+ {
950
+ "epoch": 68.96551724137932,
951
+ "grad_norm": 0.2862670123577118,
952
+ "learning_rate": 0.00016791183656665845,
953
+ "loss": 0.664,
954
+ "step": 13500
955
+ },
956
+ {
957
+ "epoch": 69.47637292464879,
958
+ "grad_norm": 0.24548490345478058,
959
+ "learning_rate": 0.00016465471163813576,
960
+ "loss": 0.6628,
961
+ "step": 13600
962
+ },
963
+ {
964
+ "epoch": 69.98722860791827,
965
+ "grad_norm": 0.290222704410553,
966
+ "learning_rate": 0.00016142775400966022,
967
+ "loss": 0.6636,
968
+ "step": 13700
969
+ },
970
+ {
971
+ "epoch": 70.49808429118774,
972
+ "grad_norm": 0.28063514828681946,
973
+ "learning_rate": 0.00015823184589922667,
974
+ "loss": 0.6622,
975
+ "step": 13800
976
+ },
977
+ {
978
+ "epoch": 71.00893997445722,
979
+ "grad_norm": 0.26852983236312866,
980
+ "learning_rate": 0.00015506786103620146,
981
+ "loss": 0.6634,
982
+ "step": 13900
983
+ },
984
+ {
985
+ "epoch": 71.51979565772669,
986
+ "grad_norm": 0.29077690839767456,
987
+ "learning_rate": 0.00015193666442245402,
988
+ "loss": 0.6611,
989
+ "step": 14000
990
+ },
991
+ {
992
+ "epoch": 72.03065134099617,
993
+ "grad_norm": 0.29139581322669983,
994
+ "learning_rate": 0.00014883911209587366,
995
+ "loss": 0.6632,
996
+ "step": 14100
997
+ },
998
+ {
999
+ "epoch": 72.54150702426564,
1000
+ "grad_norm": 0.2796466648578644,
1001
+ "learning_rate": 0.00014577605089633773,
1002
+ "loss": 0.6613,
1003
+ "step": 14200
1004
+ },
1005
+ {
1006
+ "epoch": 73.05236270753512,
1007
+ "grad_norm": 0.2423846423625946,
1008
+ "learning_rate": 0.0001427483182341936,
1009
+ "loss": 0.6616,
1010
+ "step": 14300
1011
+ },
1012
+ {
1013
+ "epoch": 73.5632183908046,
1014
+ "grad_norm": 0.29155340790748596,
1015
+ "learning_rate": 0.00013975674186131936,
1016
+ "loss": 0.661,
1017
+ "step": 14400
1018
+ },
1019
+ {
1020
+ "epoch": 74.07407407407408,
1021
+ "grad_norm": 0.29103904962539673,
1022
+ "learning_rate": 0.00013680213964482475,
1023
+ "loss": 0.6613,
1024
+ "step": 14500
1025
+ },
1026
+ {
1027
+ "epoch": 74.58492975734355,
1028
+ "grad_norm": 0.30091020464897156,
1029
+ "learning_rate": 0.00013388531934345417,
1030
+ "loss": 0.6595,
1031
+ "step": 14600
1032
+ },
1033
+ {
1034
+ "epoch": 75.09578544061303,
1035
+ "grad_norm": 0.26564979553222656,
1036
+ "learning_rate": 0.00013100707838675378,
1037
+ "loss": 0.6609,
1038
+ "step": 14700
1039
+ },
1040
+ {
1041
+ "epoch": 75.6066411238825,
1042
+ "grad_norm": 0.3134582042694092,
1043
+ "learning_rate": 0.00012816820365706206,
1044
+ "loss": 0.6589,
1045
+ "step": 14800
1046
+ },
1047
+ {
1048
+ "epoch": 76.11749680715198,
1049
+ "grad_norm": 0.2349364161491394,
1050
+ "learning_rate": 0.00012536947127438414,
1051
+ "loss": 0.66,
1052
+ "step": 14900
1053
+ },
1054
+ {
1055
+ "epoch": 76.62835249042146,
1056
+ "grad_norm": 0.266669899225235,
1057
+ "learning_rate": 0.00012261164638420832,
1058
+ "loss": 0.6588,
1059
+ "step": 15000
1060
+ },
1061
+ {
1062
+ "epoch": 77.13920817369093,
1063
+ "grad_norm": 0.25405532121658325,
1064
+ "learning_rate": 0.0001198954829483227,
1065
+ "loss": 0.6592,
1066
+ "step": 15100
1067
+ },
1068
+ {
1069
+ "epoch": 77.65006385696041,
1070
+ "grad_norm": 0.2515844404697418,
1071
+ "learning_rate": 0.00011722172353869008,
1072
+ "loss": 0.6582,
1073
+ "step": 15200
1074
+ },
1075
+ {
1076
+ "epoch": 78.16091954022988,
1077
+ "grad_norm": 0.3210657238960266,
1078
+ "learning_rate": 0.00011459109913443567,
1079
+ "loss": 0.6585,
1080
+ "step": 15300
1081
+ },
1082
+ {
1083
+ "epoch": 78.67177522349937,
1084
+ "grad_norm": 0.3124668002128601,
1085
+ "learning_rate": 0.00011200432892200498,
1086
+ "loss": 0.6575,
1087
+ "step": 15400
1088
+ },
1089
+ {
1090
+ "epoch": 79.18263090676884,
1091
+ "grad_norm": 0.3148006796836853,
1092
+ "learning_rate": 0.0001094621200985454,
1093
+ "loss": 0.6573,
1094
+ "step": 15500
1095
+ },
1096
+ {
1097
+ "epoch": 79.69348659003832,
1098
+ "grad_norm": 0.28647470474243164,
1099
+ "learning_rate": 0.00010696516767856545,
1100
+ "loss": 0.6569,
1101
+ "step": 15600
1102
+ },
1103
+ {
1104
+ "epoch": 80.20434227330779,
1105
+ "grad_norm": 0.3052207827568054,
1106
+ "learning_rate": 0.00010451415430392475,
1107
+ "loss": 0.6565,
1108
+ "step": 15700
1109
+ },
1110
+ {
1111
+ "epoch": 80.71519795657727,
1112
+ "grad_norm": 0.2627497911453247,
1113
+ "learning_rate": 0.00010210975005720677,
1114
+ "loss": 0.6562,
1115
+ "step": 15800
1116
+ },
1117
+ {
1118
+ "epoch": 81.22605363984674,
1119
+ "grad_norm": 0.2958792448043823,
1120
+ "learning_rate": 9.975261227852472e-05,
1121
+ "loss": 0.6561,
1122
+ "step": 15900
1123
+ },
1124
+ {
1125
+ "epoch": 81.73690932311622,
1126
+ "grad_norm": 0.23910285532474518,
1127
+ "learning_rate": 9.744338538581147e-05,
1128
+ "loss": 0.6555,
1129
+ "step": 16000
1130
+ },
1131
+ {
1132
+ "epoch": 82.24776500638569,
1133
+ "grad_norm": 0.3099576234817505,
1134
+ "learning_rate": 9.518270069864194e-05,
1135
+ "loss": 0.6552,
1136
+ "step": 16100
1137
+ },
1138
+ {
1139
+ "epoch": 82.75862068965517,
1140
+ "grad_norm": 0.2662413716316223,
1141
+ "learning_rate": 9.297117626563687e-05,
1142
+ "loss": 0.6549,
1143
+ "step": 16200
1144
+ },
1145
+ {
1146
+ "epoch": 83.26947637292464,
1147
+ "grad_norm": 0.3181943893432617,
1148
+ "learning_rate": 9.080941669549422e-05,
1149
+ "loss": 0.654,
1150
+ "step": 16300
1151
+ },
1152
+ {
1153
+ "epoch": 83.78033205619413,
1154
+ "grad_norm": 0.3146204650402069,
1155
+ "learning_rate": 8.86980129916955e-05,
1156
+ "loss": 0.6547,
1157
+ "step": 16400
1158
+ },
1159
+ {
1160
+ "epoch": 84.2911877394636,
1161
+ "grad_norm": 0.3345377743244171,
1162
+ "learning_rate": 8.663754239093108e-05,
1163
+ "loss": 0.6529,
1164
+ "step": 16500
1165
+ },
1166
+ {
1167
+ "epoch": 84.80204342273308,
1168
+ "grad_norm": 0.2627834379673004,
1169
+ "learning_rate": 8.46285682052895e-05,
1170
+ "loss": 0.6541,
1171
+ "step": 16600
1172
+ },
1173
+ {
1174
+ "epoch": 85.31289910600256,
1175
+ "grad_norm": 0.2784910798072815,
1176
+ "learning_rate": 8.267163966825369e-05,
1177
+ "loss": 0.6529,
1178
+ "step": 16700
1179
+ },
1180
+ {
1181
+ "epoch": 85.82375478927203,
1182
+ "grad_norm": 0.3195042610168457,
1183
+ "learning_rate": 8.076729178454587e-05,
1184
+ "loss": 0.6534,
1185
+ "step": 16800
1186
+ },
1187
+ {
1188
+ "epoch": 86.33461047254151,
1189
+ "grad_norm": 0.3142065405845642,
1190
+ "learning_rate": 7.89160451838626e-05,
1191
+ "loss": 0.6515,
1192
+ "step": 16900
1193
+ },
1194
+ {
1195
+ "epoch": 86.84546615581098,
1196
+ "grad_norm": 0.3257456123828888,
1197
+ "learning_rate": 7.711840597853999e-05,
1198
+ "loss": 0.6535,
1199
+ "step": 17000
1200
+ },
1201
+ {
1202
+ "epoch": 87.35632183908046,
1203
+ "grad_norm": 0.26723408699035645,
1204
+ "learning_rate": 7.537486562518735e-05,
1205
+ "loss": 0.6511,
1206
+ "step": 17100
1207
+ },
1208
+ {
1209
+ "epoch": 87.86717752234993,
1210
+ "grad_norm": 0.251345694065094,
1211
+ "learning_rate": 7.368590079032822e-05,
1212
+ "loss": 0.6523,
1213
+ "step": 17200
1214
+ },
1215
+ {
1216
+ "epoch": 88.37803320561942,
1217
+ "grad_norm": 0.2547081410884857,
1218
+ "learning_rate": 7.205197322008425e-05,
1219
+ "loss": 0.6504,
1220
+ "step": 17300
1221
+ },
1222
+ {
1223
+ "epoch": 88.88888888888889,
1224
+ "grad_norm": 0.23923078179359436,
1225
+ "learning_rate": 7.047352961393844e-05,
1226
+ "loss": 0.6524,
1227
+ "step": 17400
1228
+ },
1229
+ {
1230
+ "epoch": 89.39974457215837,
1231
+ "grad_norm": 0.28275570273399353,
1232
+ "learning_rate": 6.895100150261207e-05,
1233
+ "loss": 0.6499,
1234
+ "step": 17500
1235
+ },
1236
+ {
1237
+ "epoch": 89.91060025542784,
1238
+ "grad_norm": 0.31541708111763,
1239
+ "learning_rate": 6.748480513008843e-05,
1240
+ "loss": 0.6518,
1241
+ "step": 17600
1242
+ },
1243
+ {
1244
+ "epoch": 90.42145593869732,
1245
+ "grad_norm": 0.2589457631111145,
1246
+ "learning_rate": 6.607534133981593e-05,
1247
+ "loss": 0.6495,
1248
+ "step": 17700
1249
+ },
1250
+ {
1251
+ "epoch": 90.93231162196679,
1252
+ "grad_norm": 0.2824679911136627,
1253
+ "learning_rate": 6.472299546512134e-05,
1254
+ "loss": 0.651,
1255
+ "step": 17800
1256
+ },
1257
+ {
1258
+ "epoch": 91.44316730523627,
1259
+ "grad_norm": 0.30694401264190674,
1260
+ "learning_rate": 6.342813722386375e-05,
1261
+ "loss": 0.6487,
1262
+ "step": 17900
1263
+ },
1264
+ {
1265
+ "epoch": 91.95402298850574,
1266
+ "grad_norm": 0.26809433102607727,
1267
+ "learning_rate": 6.219112061735721e-05,
1268
+ "loss": 0.6507,
1269
+ "step": 18000
1270
+ },
1271
+ {
1272
+ "epoch": 92.46487867177522,
1273
+ "grad_norm": 0.27633756399154663,
1274
+ "learning_rate": 6.1012283833590465e-05,
1275
+ "loss": 0.6483,
1276
+ "step": 18100
1277
+ },
1278
+ {
1279
+ "epoch": 92.9757343550447,
1280
+ "grad_norm": 0.2729721665382385,
1281
+ "learning_rate": 5.989194915476953e-05,
1282
+ "loss": 0.6506,
1283
+ "step": 18200
1284
+ },
1285
+ {
1286
+ "epoch": 93.48659003831418,
1287
+ "grad_norm": 0.2822473645210266,
1288
+ "learning_rate": 5.883042286920917e-05,
1289
+ "loss": 0.6479,
1290
+ "step": 18300
1291
+ },
1292
+ {
1293
+ "epoch": 93.99744572158366,
1294
+ "grad_norm": 0.2809203565120697,
1295
+ "learning_rate": 5.782799518759658e-05,
1296
+ "loss": 0.6502,
1297
+ "step": 18400
1298
+ },
1299
+ {
1300
+ "epoch": 94.50830140485313,
1301
+ "grad_norm": 0.25173184275627136,
1302
+ "learning_rate": 5.688494016365067e-05,
1303
+ "loss": 0.6474,
1304
+ "step": 18500
1305
+ },
1306
+ {
1307
+ "epoch": 95.01915708812261,
1308
+ "grad_norm": 0.29168185591697693,
1309
+ "learning_rate": 5.6001515619198706e-05,
1310
+ "loss": 0.6497,
1311
+ "step": 18600
1312
+ },
1313
+ {
1314
+ "epoch": 95.53001277139208,
1315
+ "grad_norm": 0.2562580406665802,
1316
+ "learning_rate": 5.517796307369017e-05,
1317
+ "loss": 0.6473,
1318
+ "step": 18700
1319
+ },
1320
+ {
1321
+ "epoch": 96.04086845466156,
1322
+ "grad_norm": 0.3017235994338989,
1323
+ "learning_rate": 5.44145076781679e-05,
1324
+ "loss": 0.6491,
1325
+ "step": 18800
1326
+ },
1327
+ {
1328
+ "epoch": 96.55172413793103,
1329
+ "grad_norm": 0.3396376967430115,
1330
+ "learning_rate": 5.3711358153713977e-05,
1331
+ "loss": 0.6471,
1332
+ "step": 18900
1333
+ },
1334
+ {
1335
+ "epoch": 97.06257982120052,
1336
+ "grad_norm": 0.26789915561676025,
1337
+ "learning_rate": 5.3068706734387484e-05,
1338
+ "loss": 0.6487,
1339
+ "step": 19000
1340
+ },
1341
+ {
1342
+ "epoch": 97.57343550446998,
1343
+ "grad_norm": 0.3137015700340271,
1344
+ "learning_rate": 5.248672911466959e-05,
1345
+ "loss": 0.6469,
1346
+ "step": 19100
1347
+ },
1348
+ {
1349
+ "epoch": 98.08429118773947,
1350
+ "grad_norm": 0.27382105588912964,
1351
+ "learning_rate": 5.196558440143059e-05,
1352
+ "loss": 0.6486,
1353
+ "step": 19200
1354
+ },
1355
+ {
1356
+ "epoch": 98.59514687100894,
1357
+ "grad_norm": 0.2740473747253418,
1358
+ "learning_rate": 5.1505415070431424e-05,
1359
+ "loss": 0.6465,
1360
+ "step": 19300
1361
+ },
1362
+ {
1363
+ "epoch": 99.10600255427842,
1364
+ "grad_norm": 0.25539904832839966,
1365
+ "learning_rate": 5.110634692737243e-05,
1366
+ "loss": 0.6482,
1367
+ "step": 19400
1368
+ },
1369
+ {
1370
+ "epoch": 99.61685823754789,
1371
+ "grad_norm": 0.3076242208480835,
1372
+ "learning_rate": 5.076848907349929e-05,
1373
+ "loss": 0.6465,
1374
+ "step": 19500
1375
+ },
1376
+ {
1377
+ "epoch": 100.12771392081737,
1378
+ "grad_norm": 0.2733049988746643,
1379
+ "learning_rate": 5.049193387577574e-05,
1380
+ "loss": 0.648,
1381
+ "step": 19600
1382
+ },
1383
+ {
1384
+ "epoch": 100.63856960408684,
1385
+ "grad_norm": 0.3100322186946869,
1386
+ "learning_rate": 5.027675694163144e-05,
1387
+ "loss": 0.6464,
1388
+ "step": 19700
1389
+ },
1390
+ {
1391
+ "epoch": 101.14942528735632,
1392
+ "grad_norm": 0.326686829328537,
1393
+ "learning_rate": 5.012301709829165e-05,
1394
+ "loss": 0.6473,
1395
+ "step": 19800
1396
+ },
1397
+ {
1398
+ "epoch": 101.66028097062579,
1399
+ "grad_norm": 0.27345895767211914,
1400
+ "learning_rate": 5.003075637669448e-05,
1401
+ "loss": 0.6461,
1402
+ "step": 19900
1403
+ },
1404
+ {
1405
+ "epoch": 102.17113665389527,
1406
+ "grad_norm": 0.2734470069408417,
1407
+ "learning_rate": 5e-05,
1408
+ "loss": 0.6471,
1409
+ "step": 20000
1410
+ }
1411
+ ],
1412
+ "logging_steps": 100,
1413
+ "max_steps": 20000,
1414
+ "num_input_tokens_seen": 0,
1415
+ "num_train_epochs": 103,
1416
+ "save_steps": 1000,
1417
+ "stateful_callbacks": {
1418
+ "TrainerControl": {
1419
+ "args": {
1420
+ "should_epoch_stop": false,
1421
+ "should_evaluate": false,
1422
+ "should_log": false,
1423
+ "should_save": true,
1424
+ "should_training_stop": true
1425
+ },
1426
+ "attributes": {}
1427
+ }
1428
+ },
1429
+ "total_flos": 6.116735726450115e+17,
1430
+ "train_batch_size": 512,
1431
+ "trial_name": null,
1432
+ "trial_params": null
1433
+ }
hop3-4000/checkpoint-20000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862dd73db63293cbb9f6d4c60cab62174986c34e99d15728fdcd968f9a339a7e
3
+ size 5240
hop3-4000/checkpoint-20000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
hop3-4000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTJForCausalLM"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gptj",
13
+ "n_embd": 768,
14
+ "n_head": 12,
15
+ "n_inner": null,
16
+ "n_layer": 12,
17
+ "n_positions": 1024,
18
+ "resid_pdrop": 0.1,
19
+ "rotary_dim": 64,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.46.2",
23
+ "use_cache": true,
24
+ "vocab_size": 50740
25
+ }
hop3-4000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.2"
6
+ }
hop3-4000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
hop3-4000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244bae39c5b8af705f691e1cba9108d38cf52a1dc326c47d4edbde188f65ee65
3
+ size 651965360
hop3-4000/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
hop3-4000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
hop3-4000/validate_results.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1000": {
3
+ "exact_match": 0.044,
4
+ "administrator_1_administrator_1_administrator_1_exact_match": 0.0,
5
+ "administrator_1_administrator_1_backer_1_exact_match": 0.0,
6
+ "administrator_1_administrator_1_leader_1_exact_match": 0.0,
7
+ "administrator_1_administrator_1_mentor_1_exact_match": 0.0,
8
+ "administrator_1_administrator_1_patron_1_exact_match": 0.0,
9
+ "administrator_1_advisor_1_advisor_1_exact_match": 0.0,
10
+ "administrator_1_advisor_1_backer_1_exact_match": 0.0,
11
+ "administrator_1_advisor_1_coordinator_1_exact_match": 0.0,
12
+ "administrator_1_advisor_1_director_1_exact_match": 0.0,
13
+ "administrator_1_advisor_1_employer_1_exact_match": 0.0,
14
+ "administrator_1_advisor_1_mentor_1_exact_match": 0.0,
15
+ "administrator_1_advisor_1_overseer_1_exact_match": 0.0,
16
+ "administrator_1_advisor_1_teacher_1_exact_match": 0.0,
17
+ "administrator_1_backer_1_boss_1_exact_match": 0.0,
18
+ "administrator_1_backer_1_manager_1_exact_match": 0.0,
19
+ "administrator_1_backer_1_mentor_1_exact_match": 0.0,
20
+ "administrator_1_backer_1_predecessor_1_exact_match": 0.0,
21
+ "administrator_1_backer_1_ruler_1_exact_match": 0.0,
22
+ "administrator_1_backer_1_sponsor_1_exact_match": 0.0,
23
+ "administrator_1_boss_1_backer_1_exact_match": 0.5
24
+ },
25
+ "2000": {
26
+ "exact_match": 0.060333333333333336,
27
+ "administrator_1_administrator_1_administrator_1_exact_match": 0.0,
28
+ "administrator_1_administrator_1_backer_1_exact_match": 0.0,
29
+ "administrator_1_administrator_1_leader_1_exact_match": 0.0,
30
+ "administrator_1_administrator_1_mentor_1_exact_match": 0.0,
31
+ "administrator_1_administrator_1_patron_1_exact_match": 0.0,
32
+ "administrator_1_advisor_1_advisor_1_exact_match": 0.0,
33
+ "administrator_1_advisor_1_backer_1_exact_match": 0.0,
34
+ "administrator_1_advisor_1_coordinator_1_exact_match": 0.0,
35
+ "administrator_1_advisor_1_director_1_exact_match": 0.0,
36
+ "administrator_1_advisor_1_employer_1_exact_match": 0.5,
37
+ "administrator_1_advisor_1_mentor_1_exact_match": 0.0,
38
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
39
+ "administrator_1_advisor_1_teacher_1_exact_match": 0.0,
40
+ "administrator_1_backer_1_boss_1_exact_match": 0.0,
41
+ "administrator_1_backer_1_manager_1_exact_match": 0.0,
42
+ "administrator_1_backer_1_mentor_1_exact_match": 0.0,
43
+ "administrator_1_backer_1_predecessor_1_exact_match": 0.0,
44
+ "administrator_1_backer_1_ruler_1_exact_match": 0.0,
45
+ "administrator_1_backer_1_sponsor_1_exact_match": 0.0,
46
+ "administrator_1_boss_1_backer_1_exact_match": 0.0
47
+ },
48
+ "3000": {
49
+ "exact_match": 0.054,
50
+ "administrator_1_administrator_1_administrator_1_exact_match": 0.0,
51
+ "administrator_1_administrator_1_backer_1_exact_match": 0.0,
52
+ "administrator_1_administrator_1_leader_1_exact_match": 0.0,
53
+ "administrator_1_administrator_1_mentor_1_exact_match": 0.0,
54
+ "administrator_1_administrator_1_patron_1_exact_match": 0.0,
55
+ "administrator_1_advisor_1_advisor_1_exact_match": 0.0,
56
+ "administrator_1_advisor_1_backer_1_exact_match": 0.0,
57
+ "administrator_1_advisor_1_coordinator_1_exact_match": 0.0,
58
+ "administrator_1_advisor_1_director_1_exact_match": 0.0,
59
+ "administrator_1_advisor_1_employer_1_exact_match": 0.0,
60
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
61
+ "administrator_1_advisor_1_overseer_1_exact_match": 0.0,
62
+ "administrator_1_advisor_1_teacher_1_exact_match": 0.0,
63
+ "administrator_1_backer_1_boss_1_exact_match": 0.0,
64
+ "administrator_1_backer_1_manager_1_exact_match": 0.0,
65
+ "administrator_1_backer_1_mentor_1_exact_match": 0.0,
66
+ "administrator_1_backer_1_predecessor_1_exact_match": 0.0,
67
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
68
+ "administrator_1_backer_1_sponsor_1_exact_match": 0.0,
69
+ "administrator_1_boss_1_backer_1_exact_match": 0.0
70
+ },
71
+ "4000": {
72
+ "exact_match": 0.08166666666666667,
73
+ "administrator_1_administrator_1_administrator_1_exact_match": 0.0,
74
+ "administrator_1_administrator_1_backer_1_exact_match": 0.0,
75
+ "administrator_1_administrator_1_leader_1_exact_match": 0.0,
76
+ "administrator_1_administrator_1_mentor_1_exact_match": 0.0,
77
+ "administrator_1_administrator_1_patron_1_exact_match": 0.0,
78
+ "administrator_1_advisor_1_advisor_1_exact_match": 0.0,
79
+ "administrator_1_advisor_1_backer_1_exact_match": 0.0,
80
+ "administrator_1_advisor_1_coordinator_1_exact_match": 0.0,
81
+ "administrator_1_advisor_1_director_1_exact_match": 0.0,
82
+ "administrator_1_advisor_1_employer_1_exact_match": 0.5,
83
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
84
+ "administrator_1_advisor_1_overseer_1_exact_match": 0.0,
85
+ "administrator_1_advisor_1_teacher_1_exact_match": 0.0,
86
+ "administrator_1_backer_1_boss_1_exact_match": 0.0,
87
+ "administrator_1_backer_1_manager_1_exact_match": 0.0,
88
+ "administrator_1_backer_1_mentor_1_exact_match": 0.0,
89
+ "administrator_1_backer_1_predecessor_1_exact_match": 0.0,
90
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
91
+ "administrator_1_backer_1_sponsor_1_exact_match": 0.0,
92
+ "administrator_1_boss_1_backer_1_exact_match": 0.0
93
+ },
94
+ "5000": {
95
+ "exact_match": 0.9976666666666667,
96
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
97
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
98
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
99
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
100
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
101
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
102
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
103
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
104
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
105
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
106
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
107
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
108
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
109
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
110
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
111
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
112
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
113
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
114
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
115
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
116
+ },
117
+ "6000": {
118
+ "exact_match": 0.9996666666666667,
119
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
120
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
121
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
122
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
123
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
124
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
125
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
126
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
127
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
128
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
129
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
130
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
131
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
132
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
133
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
134
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
135
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
136
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
137
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
138
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
139
+ },
140
+ "7000": {
141
+ "exact_match": 0.9996666666666667,
142
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
143
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
144
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
145
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
146
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
147
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
148
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
149
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
150
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
151
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
152
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
153
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
154
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
155
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
156
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
157
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
158
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
159
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
160
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
161
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
162
+ },
163
+ "8000": {
164
+ "exact_match": 1.0,
165
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
166
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
167
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
168
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
169
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
170
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
171
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
172
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
173
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
174
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
175
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
176
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
177
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
178
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
179
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
180
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
181
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
182
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
183
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
184
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
185
+ },
186
+ "9000": {
187
+ "exact_match": 1.0,
188
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
189
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
190
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
191
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
192
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
193
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
194
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
195
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
196
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
197
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
198
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
199
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
200
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
201
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
202
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
203
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
204
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
205
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
206
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
207
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
208
+ },
209
+ "10000": {
210
+ "exact_match": 0.9996666666666667,
211
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
212
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
213
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
214
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
215
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
216
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
217
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
218
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
219
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
220
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
221
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
222
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
223
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
224
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
225
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
226
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
227
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
228
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
229
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
230
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
231
+ },
232
+ "11000": {
233
+ "exact_match": 0.9996666666666667,
234
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
235
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
236
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
237
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
238
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
239
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
240
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
241
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
242
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
243
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
244
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
245
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
246
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
247
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
248
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
249
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
250
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
251
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
252
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
253
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
254
+ },
255
+ "12000": {
256
+ "exact_match": 1.0,
257
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
258
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
259
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
260
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
261
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
262
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
263
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
264
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
265
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
266
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
267
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
268
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
269
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
270
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
271
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
272
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
273
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
274
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
275
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
276
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
277
+ },
278
+ "13000": {
279
+ "exact_match": 1.0,
280
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
281
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
282
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
283
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
284
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
285
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
286
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
287
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
288
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
289
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
290
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
291
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
292
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
293
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
294
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
295
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
296
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
297
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
298
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
299
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
300
+ },
301
+ "14000": {
302
+ "exact_match": 1.0,
303
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
304
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
305
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
306
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
307
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
308
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
309
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
310
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
311
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
312
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
313
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
314
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
315
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
316
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
317
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
318
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
319
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
320
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
321
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
322
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
323
+ },
324
+ "15000": {
325
+ "exact_match": 1.0,
326
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
327
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
328
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
329
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
330
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
331
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
332
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
333
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
334
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
335
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
336
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
337
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
338
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
339
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
340
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
341
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
342
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
343
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
344
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
345
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
346
+ },
347
+ "16000": {
348
+ "exact_match": 1.0,
349
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
350
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
351
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
352
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
353
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
354
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
355
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
356
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
357
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
358
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
359
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
360
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
361
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
362
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
363
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
364
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
365
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
366
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
367
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
368
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
369
+ },
370
+ "17000": {
371
+ "exact_match": 1.0,
372
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
373
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
374
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
375
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
376
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
377
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
378
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
379
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
380
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
381
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
382
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
383
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
384
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
385
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
386
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
387
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
388
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
389
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
390
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
391
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
392
+ },
393
+ "18000": {
394
+ "exact_match": 1.0,
395
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
396
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
397
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
398
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
399
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
400
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
401
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
402
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
403
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
404
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
405
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
406
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
407
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
408
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
409
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
410
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
411
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
412
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
413
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
414
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
415
+ },
416
+ "19000": {
417
+ "exact_match": 1.0,
418
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
419
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
420
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
421
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
422
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
423
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
424
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
425
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
426
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
427
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
428
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
429
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
430
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
431
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
432
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
433
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
434
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
435
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
436
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
437
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
438
+ },
439
+ "20000": {
440
+ "exact_match": 1.0,
441
+ "administrator_1_administrator_1_administrator_1_exact_match": 1.0,
442
+ "administrator_1_administrator_1_backer_1_exact_match": 1.0,
443
+ "administrator_1_administrator_1_leader_1_exact_match": 1.0,
444
+ "administrator_1_administrator_1_mentor_1_exact_match": 1.0,
445
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
446
+ "administrator_1_advisor_1_advisor_1_exact_match": 1.0,
447
+ "administrator_1_advisor_1_backer_1_exact_match": 1.0,
448
+ "administrator_1_advisor_1_coordinator_1_exact_match": 1.0,
449
+ "administrator_1_advisor_1_director_1_exact_match": 1.0,
450
+ "administrator_1_advisor_1_employer_1_exact_match": 1.0,
451
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
452
+ "administrator_1_advisor_1_overseer_1_exact_match": 1.0,
453
+ "administrator_1_advisor_1_teacher_1_exact_match": 1.0,
454
+ "administrator_1_backer_1_boss_1_exact_match": 1.0,
455
+ "administrator_1_backer_1_manager_1_exact_match": 1.0,
456
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
457
+ "administrator_1_backer_1_predecessor_1_exact_match": 1.0,
458
+ "administrator_1_backer_1_ruler_1_exact_match": 1.0,
459
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
460
+ "administrator_1_boss_1_backer_1_exact_match": 1.0
461
+ }
462
+ }
hop3-4000/vocab.json ADDED
The diff for this file is too large to render. See raw diff