ykyao commited on
Commit
9215e7b
·
verified ·
1 Parent(s): 4dda761

Upload folder using huggingface_hub

Browse files
cl_hop3/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
+ }
cl_hop3/checkpoint-10000/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
+ }
cl_hop3/checkpoint-10000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "archives/levels/single/depth_aug/hop4_cont_simp/hop2_seed0_max_steps10000/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gptj",
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "resid_pdrop": 0.1,
20
+ "rotary_dim": 64,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.46.2",
24
+ "use_cache": true,
25
+ "vocab_size": 50740
26
+ }
cl_hop3/checkpoint-10000/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
+ }
cl_hop3/checkpoint-10000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cl_hop3/checkpoint-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a95c5f4622c43bafd5df382cd6ef9a5ea13a50ff22de1f1465db9906551c91
3
+ size 651965360
cl_hop3/checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4735ab298681c51d39c3f5ef054fae0718b6e19a746f4e903be019afdfdd4f
3
+ size 1303978682
cl_hop3/checkpoint-10000/output/ood_test_metrics.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "exact_match": 0.9213333333333333,
3
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
4
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
5
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
6
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
7
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
8
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
9
+ "administrator_1_administrator_1_sponsor_1_exact_match": 1.0,
10
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
11
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
12
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
13
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
14
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
15
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
16
+ "administrator_1_backer_1_patron_1_exact_match": 1.0,
17
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
18
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
19
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
20
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
21
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
22
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
23
+ }
cl_hop3/checkpoint-10000/output/ood_test_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
cl_hop3/checkpoint-10000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614c5ffbf8c73427f4a387316da4441ed677928ac24ff1850edc9e06ea6f9313
3
+ size 14960
cl_hop3/checkpoint-10000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8bb7d64010748307b670b81771765a04e56dd48ced365d776b3fed2ed3260d8
3
+ size 14960
cl_hop3/checkpoint-10000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6fc04ce2804238cd58817559f810bc8ab4e2c3cfa9966faa86f2caec26dc4a3
3
+ size 14960
cl_hop3/checkpoint-10000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a666e87839f0665ca0cc9b6b465da89cfcad71d1ba95a3139753b2474797709c
3
+ size 14960
cl_hop3/checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ebb57b09168cdbf5c71c61860fc2ee7722217ae50a194098ed9248b1bbfc51
3
+ size 1000
cl_hop3/checkpoint-10000/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
+ }
cl_hop3/checkpoint-10000/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
cl_hop3/checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 277.77777777777777,
5
+ "eval_steps": 500,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.7777777777777777,
13
+ "grad_norm": 0.17655912041664124,
14
+ "learning_rate": 5e-05,
15
+ "loss": 1.0428,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 5.555555555555555,
20
+ "grad_norm": 0.16549009084701538,
21
+ "learning_rate": 0.0001,
22
+ "loss": 0.7848,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 8.333333333333334,
27
+ "grad_norm": 0.22104553878307343,
28
+ "learning_rate": 0.00015,
29
+ "loss": 0.7735,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 11.11111111111111,
34
+ "grad_norm": 0.26575228571891785,
35
+ "learning_rate": 0.0002,
36
+ "loss": 0.7681,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 13.88888888888889,
41
+ "grad_norm": 0.19049997627735138,
42
+ "learning_rate": 0.00025,
43
+ "loss": 0.7645,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 16.666666666666668,
48
+ "grad_norm": 0.2094593495130539,
49
+ "learning_rate": 0.0003,
50
+ "loss": 0.7595,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 19.444444444444443,
55
+ "grad_norm": 0.1725180745124817,
56
+ "learning_rate": 0.00035,
57
+ "loss": 0.7538,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 22.22222222222222,
62
+ "grad_norm": 0.1677156537771225,
63
+ "learning_rate": 0.0004,
64
+ "loss": 0.7464,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 25.0,
69
+ "grad_norm": 0.305239737033844,
70
+ "learning_rate": 0.00045000000000000004,
71
+ "loss": 0.7557,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 27.77777777777778,
76
+ "grad_norm": 0.2675870954990387,
77
+ "learning_rate": 0.0005,
78
+ "loss": 0.7552,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 30.555555555555557,
83
+ "grad_norm": 0.288164883852005,
84
+ "learning_rate": 0.0004998629360792965,
85
+ "loss": 0.7373,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 33.333333333333336,
90
+ "grad_norm": 0.23344466090202332,
91
+ "learning_rate": 0.0004994519113084605,
92
+ "loss": 0.7154,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 36.111111111111114,
97
+ "grad_norm": 0.20955105125904083,
98
+ "learning_rate": 0.0004987674264578615,
99
+ "loss": 0.6976,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 38.888888888888886,
104
+ "grad_norm": 0.27504026889801025,
105
+ "learning_rate": 0.0004978103154668534,
106
+ "loss": 0.6853,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 41.666666666666664,
111
+ "grad_norm": 0.1636616587638855,
112
+ "learning_rate": 0.0004965817444277468,
113
+ "loss": 0.6754,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 44.44444444444444,
118
+ "grad_norm": 0.20831215381622314,
119
+ "learning_rate": 0.0004950832101651062,
120
+ "loss": 0.6694,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 47.22222222222222,
125
+ "grad_norm": 0.1433742344379425,
126
+ "learning_rate": 0.0004933165384120991,
127
+ "loss": 0.6663,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 50.0,
132
+ "grad_norm": 0.1756776124238968,
133
+ "learning_rate": 0.0004912838815861217,
134
+ "loss": 0.6633,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 52.77777777777778,
139
+ "grad_norm": 0.16380372643470764,
140
+ "learning_rate": 0.0004889877161664096,
141
+ "loss": 0.6621,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 55.55555555555556,
146
+ "grad_norm": 0.16083309054374695,
147
+ "learning_rate": 0.00048643083967682936,
148
+ "loss": 0.6604,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 58.333333333333336,
153
+ "grad_norm": 0.1856192797422409,
154
+ "learning_rate": 0.00048361636727752716,
155
+ "loss": 0.6595,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 61.111111111111114,
160
+ "grad_norm": 0.14920257031917572,
161
+ "learning_rate": 0.00048054772796958517,
162
+ "loss": 0.6594,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 63.888888888888886,
167
+ "grad_norm": 0.17003504931926727,
168
+ "learning_rate": 0.0004772286604173126,
169
+ "loss": 0.658,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 66.66666666666667,
174
+ "grad_norm": 0.16473492980003357,
175
+ "learning_rate": 0.00047366320839325863,
176
+ "loss": 0.6569,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 69.44444444444444,
181
+ "grad_norm": 0.17655926942825317,
182
+ "learning_rate": 0.0004698557158514987,
183
+ "loss": 0.6561,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 72.22222222222223,
188
+ "grad_norm": 0.16990351676940918,
189
+ "learning_rate": 0.00046581082163519585,
190
+ "loss": 0.6561,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 75.0,
195
+ "grad_norm": 0.16883021593093872,
196
+ "learning_rate": 0.0004615334538248844,
197
+ "loss": 0.6541,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 77.77777777777777,
202
+ "grad_norm": 0.16448619961738586,
203
+ "learning_rate": 0.00045702882373436317,
204
+ "loss": 0.6524,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 80.55555555555556,
209
+ "grad_norm": 0.15923935174942017,
210
+ "learning_rate": 0.0004523024195615124,
211
+ "loss": 0.6504,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 83.33333333333333,
216
+ "grad_norm": 0.17401619255542755,
217
+ "learning_rate": 0.00044735999970177,
218
+ "loss": 0.6476,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 86.11111111111111,
223
+ "grad_norm": 0.24677884578704834,
224
+ "learning_rate": 0.0004422075857324137,
225
+ "loss": 0.6455,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 88.88888888888889,
230
+ "grad_norm": 0.17533496022224426,
231
+ "learning_rate": 0.0004368514550761965,
232
+ "loss": 0.6419,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 91.66666666666667,
237
+ "grad_norm": 0.20539255440235138,
238
+ "learning_rate": 0.0004312981333532744,
239
+ "loss": 0.6386,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 94.44444444444444,
244
+ "grad_norm": 0.18238282203674316,
245
+ "learning_rate": 0.0004255543864307431,
246
+ "loss": 0.6339,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 97.22222222222223,
251
+ "grad_norm": 0.1727287322282791,
252
+ "learning_rate": 0.00041962721217947137,
253
+ "loss": 0.6313,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 100.0,
258
+ "grad_norm": 0.19460555911064148,
259
+ "learning_rate": 0.0004135238319482731,
260
+ "loss": 0.6284,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 102.77777777777777,
265
+ "grad_norm": 0.23844732344150543,
266
+ "learning_rate": 0.0004072516817658065,
267
+ "loss": 0.6247,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 105.55555555555556,
272
+ "grad_norm": 0.2094869464635849,
273
+ "learning_rate": 0.000400818403280918,
274
+ "loss": 0.6216,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 108.33333333333333,
279
+ "grad_norm": 0.17692449688911438,
280
+ "learning_rate": 0.00039423183445247114,
281
+ "loss": 0.6189,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 111.11111111111111,
286
+ "grad_norm": 0.2325190156698227,
287
+ "learning_rate": 0.00038750000000000004,
288
+ "loss": 0.6167,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 113.88888888888889,
293
+ "grad_norm": 0.18726158142089844,
294
+ "learning_rate": 0.0003806311016268254,
295
+ "loss": 0.6136,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 116.66666666666667,
300
+ "grad_norm": 0.16347479820251465,
301
+ "learning_rate": 0.0003736335080275424,
302
+ "loss": 0.6119,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 119.44444444444444,
307
+ "grad_norm": 0.17086496949195862,
308
+ "learning_rate": 0.0003665157446920551,
309
+ "loss": 0.6097,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 122.22222222222223,
314
+ "grad_norm": 0.20603518187999725,
315
+ "learning_rate": 0.0003592864835185802,
316
+ "loss": 0.6086,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 125.0,
321
+ "grad_norm": 0.1553768515586853,
322
+ "learning_rate": 0.0003519545322482755,
323
+ "loss": 0.6066,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 127.77777777777777,
328
+ "grad_norm": 0.1595972776412964,
329
+ "learning_rate": 0.0003445288237343632,
330
+ "loss": 0.6054,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 130.55555555555554,
335
+ "grad_norm": 0.18056078255176544,
336
+ "learning_rate": 0.0003370184050588248,
337
+ "loss": 0.6038,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 133.33333333333334,
342
+ "grad_norm": 0.16955259442329407,
343
+ "learning_rate": 0.0003294324265099252,
344
+ "loss": 0.6028,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 136.11111111111111,
349
+ "grad_norm": 0.15139202773571014,
350
+ "learning_rate": 0.0003217801304339958,
351
+ "loss": 0.6015,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 138.88888888888889,
356
+ "grad_norm": 0.2073788046836853,
357
+ "learning_rate": 0.00031407083997505935,
358
+ "loss": 0.6005,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 141.66666666666666,
363
+ "grad_norm": 0.19553761184215546,
364
+ "learning_rate": 0.0003063139477160147,
365
+ "loss": 0.5996,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 144.44444444444446,
370
+ "grad_norm": 0.16924576461315155,
371
+ "learning_rate": 0.000298518904235222,
372
+ "loss": 0.5987,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 147.22222222222223,
377
+ "grad_norm": 0.16224327683448792,
378
+ "learning_rate": 0.0002906952065924282,
379
+ "loss": 0.5979,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 150.0,
384
+ "grad_norm": 0.22193726897239685,
385
+ "learning_rate": 0.0002828523867580628,
386
+ "loss": 0.5973,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 152.77777777777777,
391
+ "grad_norm": 0.13787110149860382,
392
+ "learning_rate": 0.000275,
393
+ "loss": 0.5958,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 155.55555555555554,
398
+ "grad_norm": 0.15221582353115082,
399
+ "learning_rate": 0.0002671476132419374,
400
+ "loss": 0.5951,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 158.33333333333334,
405
+ "grad_norm": 0.16305333375930786,
406
+ "learning_rate": 0.0002593047934075718,
407
+ "loss": 0.5953,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 161.11111111111111,
412
+ "grad_norm": 0.17289704084396362,
413
+ "learning_rate": 0.000251481095764778,
414
+ "loss": 0.5948,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 163.88888888888889,
419
+ "grad_norm": 0.16018681228160858,
420
+ "learning_rate": 0.00024368605228398534,
421
+ "loss": 0.5939,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 166.66666666666666,
426
+ "grad_norm": 0.1707826554775238,
427
+ "learning_rate": 0.00023592916002494068,
428
+ "loss": 0.5929,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 169.44444444444446,
433
+ "grad_norm": 0.13028201460838318,
434
+ "learning_rate": 0.0002282198695660042,
435
+ "loss": 0.5923,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 172.22222222222223,
440
+ "grad_norm": 0.13673347234725952,
441
+ "learning_rate": 0.00022056757349007478,
442
+ "loss": 0.5923,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 175.0,
447
+ "grad_norm": 0.17910760641098022,
448
+ "learning_rate": 0.00021298159494117518,
449
+ "loss": 0.5917,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 177.77777777777777,
454
+ "grad_norm": 0.21496596932411194,
455
+ "learning_rate": 0.0002054711762656369,
456
+ "loss": 0.5905,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 180.55555555555554,
461
+ "grad_norm": 0.18710723519325256,
462
+ "learning_rate": 0.00019804546775172455,
463
+ "loss": 0.5908,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 183.33333333333334,
468
+ "grad_norm": 0.16691114008426666,
469
+ "learning_rate": 0.00019071351648141977,
470
+ "loss": 0.5892,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 186.11111111111111,
475
+ "grad_norm": 0.15617595613002777,
476
+ "learning_rate": 0.00018348425530794499,
477
+ "loss": 0.5896,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 188.88888888888889,
482
+ "grad_norm": 0.16550973057746887,
483
+ "learning_rate": 0.00017636649197245758,
484
+ "loss": 0.5887,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 191.66666666666666,
489
+ "grad_norm": 0.14558972418308258,
490
+ "learning_rate": 0.00016936889837317466,
491
+ "loss": 0.5877,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 194.44444444444446,
496
+ "grad_norm": 0.16874957084655762,
497
+ "learning_rate": 0.00016250000000000007,
498
+ "loss": 0.5884,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 197.22222222222223,
503
+ "grad_norm": 0.16562138497829437,
504
+ "learning_rate": 0.00015576816554752892,
505
+ "loss": 0.5885,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 200.0,
510
+ "grad_norm": 0.21241186559200287,
511
+ "learning_rate": 0.000149181596719082,
512
+ "loss": 0.5871,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 202.77777777777777,
517
+ "grad_norm": 0.20195314288139343,
518
+ "learning_rate": 0.0001427483182341936,
519
+ "loss": 0.5861,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 205.55555555555554,
524
+ "grad_norm": 0.1490875780582428,
525
+ "learning_rate": 0.00013647616805172693,
526
+ "loss": 0.5866,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 208.33333333333334,
531
+ "grad_norm": 0.1371557116508484,
532
+ "learning_rate": 0.00013037278782052864,
533
+ "loss": 0.5861,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 211.11111111111111,
538
+ "grad_norm": 0.16661331057548523,
539
+ "learning_rate": 0.00012444561356925697,
540
+ "loss": 0.5856,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 213.88888888888889,
545
+ "grad_norm": 0.1553059071302414,
546
+ "learning_rate": 0.00011870186664672559,
547
+ "loss": 0.5851,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 216.66666666666666,
552
+ "grad_norm": 0.1584395468235016,
553
+ "learning_rate": 0.00011314854492380354,
554
+ "loss": 0.5849,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 219.44444444444446,
559
+ "grad_norm": 0.13457843661308289,
560
+ "learning_rate": 0.00010779241426758627,
561
+ "loss": 0.5844,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 222.22222222222223,
566
+ "grad_norm": 0.16505460441112518,
567
+ "learning_rate": 0.00010264000029822998,
568
+ "loss": 0.5845,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 225.0,
573
+ "grad_norm": 0.13848286867141724,
574
+ "learning_rate": 9.76975804384876e-05,
575
+ "loss": 0.584,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 227.77777777777777,
580
+ "grad_norm": 0.15045927464962006,
581
+ "learning_rate": 9.297117626563687e-05,
582
+ "loss": 0.5832,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 230.55555555555554,
587
+ "grad_norm": 0.125036358833313,
588
+ "learning_rate": 8.846654617511564e-05,
589
+ "loss": 0.5836,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 233.33333333333334,
594
+ "grad_norm": 0.16357843577861786,
595
+ "learning_rate": 8.418917836480416e-05,
596
+ "loss": 0.583,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 236.11111111111111,
601
+ "grad_norm": 0.15839944779872894,
602
+ "learning_rate": 8.014428414850129e-05,
603
+ "loss": 0.5828,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 238.88888888888889,
608
+ "grad_norm": 0.14447073638439178,
609
+ "learning_rate": 7.633679160674144e-05,
610
+ "loss": 0.5825,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 241.66666666666666,
615
+ "grad_norm": 0.18240341544151306,
616
+ "learning_rate": 7.277133958268748e-05,
617
+ "loss": 0.5822,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 244.44444444444446,
622
+ "grad_norm": 0.1834379881620407,
623
+ "learning_rate": 6.94522720304148e-05,
624
+ "loss": 0.5817,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 247.22222222222223,
629
+ "grad_norm": 0.127864271402359,
630
+ "learning_rate": 6.638363272247286e-05,
631
+ "loss": 0.5816,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 250.0,
636
+ "grad_norm": 0.19056108593940735,
637
+ "learning_rate": 6.356916032317063e-05,
638
+ "loss": 0.5816,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 252.77777777777777,
643
+ "grad_norm": 0.1649758666753769,
644
+ "learning_rate": 6.1012283833590465e-05,
645
+ "loss": 0.5808,
646
+ "step": 9100
647
+ },
648
+ {
649
+ "epoch": 255.55555555555554,
650
+ "grad_norm": 0.12822237610816956,
651
+ "learning_rate": 5.871611841387825e-05,
652
+ "loss": 0.5813,
653
+ "step": 9200
654
+ },
655
+ {
656
+ "epoch": 258.3333333333333,
657
+ "grad_norm": 0.16172918677330017,
658
+ "learning_rate": 5.6683461587900795e-05,
659
+ "loss": 0.5804,
660
+ "step": 9300
661
+ },
662
+ {
663
+ "epoch": 261.1111111111111,
664
+ "grad_norm": 0.13213834166526794,
665
+ "learning_rate": 5.4916789834893724e-05,
666
+ "loss": 0.5812,
667
+ "step": 9400
668
+ },
669
+ {
670
+ "epoch": 263.8888888888889,
671
+ "grad_norm": 0.12903639674186707,
672
+ "learning_rate": 5.34182555722532e-05,
673
+ "loss": 0.5804,
674
+ "step": 9500
675
+ },
676
+ {
677
+ "epoch": 266.6666666666667,
678
+ "grad_norm": 0.13448406755924225,
679
+ "learning_rate": 5.2189684533146676e-05,
680
+ "loss": 0.5806,
681
+ "step": 9600
682
+ },
683
+ {
684
+ "epoch": 269.44444444444446,
685
+ "grad_norm": 0.15190230309963226,
686
+ "learning_rate": 5.123257354213851e-05,
687
+ "loss": 0.5806,
688
+ "step": 9700
689
+ },
690
+ {
691
+ "epoch": 272.22222222222223,
692
+ "grad_norm": 0.1644289195537567,
693
+ "learning_rate": 5.0548088691539564e-05,
694
+ "loss": 0.5801,
695
+ "step": 9800
696
+ },
697
+ {
698
+ "epoch": 275.0,
699
+ "grad_norm": 0.18571707606315613,
700
+ "learning_rate": 5.013706392070345e-05,
701
+ "loss": 0.5805,
702
+ "step": 9900
703
+ },
704
+ {
705
+ "epoch": 277.77777777777777,
706
+ "grad_norm": 0.16482266783714294,
707
+ "learning_rate": 5e-05,
708
+ "loss": 0.5802,
709
+ "step": 10000
710
+ }
711
+ ],
712
+ "logging_steps": 100,
713
+ "max_steps": 10000,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 278,
716
+ "save_steps": 1000,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": true
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 2.976653385798779e+17,
730
+ "train_batch_size": 512,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
cl_hop3/checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c21e3de8e40483b667273285fd147e6a6a4a7fedd375388f90c08fef047e88
3
+ size 5304
cl_hop3/checkpoint-10000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
cl_hop3/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "archives/levels/single/depth_aug/hop4_cont_simp/hop2_seed0_max_steps10000/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gptj",
14
+ "n_embd": 768,
15
+ "n_head": 12,
16
+ "n_inner": null,
17
+ "n_layer": 12,
18
+ "n_positions": 1024,
19
+ "resid_pdrop": 0.1,
20
+ "rotary_dim": 64,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.46.2",
24
+ "use_cache": true,
25
+ "vocab_size": 50740
26
+ }
cl_hop3/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
+ }
cl_hop3/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
cl_hop3/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f44abedeb5a00bada903918b03e6ab8793ceafa7d76adee820ab8fd6421a6ea
3
+ size 651965360
cl_hop3/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
+ }
cl_hop3/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
cl_hop3/validate_results.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1000": {
3
+ "exact_match": 0.12333333333333334,
4
+ "administrator_1_administrator_1_boss_1_exact_match": 0.0,
5
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
6
+ "administrator_1_administrator_1_employer_1_exact_match": 0.0,
7
+ "administrator_1_administrator_1_financier_1_exact_match": 0.0,
8
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
9
+ "administrator_1_administrator_1_ruler_1_exact_match": 0.0,
10
+ "administrator_1_administrator_1_sponsor_1_exact_match": 0.0,
11
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
12
+ "administrator_1_advisor_1_mentor_1_exact_match": 0.0,
13
+ "administrator_1_backer_1_administrator_1_exact_match": 0.0,
14
+ "administrator_1_backer_1_backer_1_exact_match": 0.0,
15
+ "administrator_1_backer_1_financier_1_exact_match": 0.0,
16
+ "administrator_1_backer_1_mentor_1_exact_match": 0.0,
17
+ "administrator_1_backer_1_patron_1_exact_match": 0.0,
18
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
19
+ "administrator_1_backer_1_teacher_1_exact_match": 0.0,
20
+ "administrator_1_boss_1_employer_1_exact_match": 0.0,
21
+ "administrator_1_boss_1_teacher_1_exact_match": 0.0,
22
+ "administrator_1_coordinator_1_administrator_1_exact_match": 0.0,
23
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
24
+ },
25
+ "2000": {
26
+ "exact_match": 0.5326666666666666,
27
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
28
+ "administrator_1_administrator_1_coordinator_1_exact_match": 0.0,
29
+ "administrator_1_administrator_1_employer_1_exact_match": 0.0,
30
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
31
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
32
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
33
+ "administrator_1_administrator_1_sponsor_1_exact_match": 0.5,
34
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
35
+ "administrator_1_advisor_1_mentor_1_exact_match": 0.0,
36
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
37
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
38
+ "administrator_1_backer_1_financier_1_exact_match": 0.0,
39
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
40
+ "administrator_1_backer_1_patron_1_exact_match": 0.0,
41
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
42
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
43
+ "administrator_1_boss_1_employer_1_exact_match": 0.0,
44
+ "administrator_1_boss_1_teacher_1_exact_match": 0.5,
45
+ "administrator_1_coordinator_1_administrator_1_exact_match": 0.0,
46
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
47
+ },
48
+ "3000": {
49
+ "exact_match": 0.6733333333333333,
50
+ "administrator_1_administrator_1_boss_1_exact_match": 0.0,
51
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
52
+ "administrator_1_administrator_1_employer_1_exact_match": 0.0,
53
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
54
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
55
+ "administrator_1_administrator_1_ruler_1_exact_match": 0.0,
56
+ "administrator_1_administrator_1_sponsor_1_exact_match": 0.0,
57
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
58
+ "administrator_1_advisor_1_mentor_1_exact_match": 0.0,
59
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
60
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
61
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
62
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
63
+ "administrator_1_backer_1_patron_1_exact_match": 0.0,
64
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
65
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
66
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
67
+ "administrator_1_boss_1_teacher_1_exact_match": 0.0,
68
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
69
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
70
+ },
71
+ "4000": {
72
+ "exact_match": 0.804,
73
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
74
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
75
+ "administrator_1_administrator_1_employer_1_exact_match": 0.0,
76
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
77
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
78
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
79
+ "administrator_1_administrator_1_sponsor_1_exact_match": 0.5,
80
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
81
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
82
+ "administrator_1_backer_1_administrator_1_exact_match": 0.0,
83
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
84
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
85
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
86
+ "administrator_1_backer_1_patron_1_exact_match": 1.0,
87
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
88
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
89
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
90
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
91
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
92
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
93
+ },
94
+ "5000": {
95
+ "exact_match": 0.8306666666666667,
96
+ "administrator_1_administrator_1_boss_1_exact_match": 0.0,
97
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
98
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
99
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
100
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
101
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
102
+ "administrator_1_administrator_1_sponsor_1_exact_match": 0.5,
103
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
104
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
105
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
106
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
107
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
108
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
109
+ "administrator_1_backer_1_patron_1_exact_match": 0.0,
110
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
111
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
112
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
113
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
114
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
115
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
116
+ },
117
+ "6000": {
118
+ "exact_match": 0.871,
119
+ "administrator_1_administrator_1_boss_1_exact_match": 0.0,
120
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
121
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
122
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
123
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
124
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
125
+ "administrator_1_administrator_1_sponsor_1_exact_match": 1.0,
126
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
127
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
128
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
129
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
130
+ "administrator_1_backer_1_financier_1_exact_match": 0.0,
131
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
132
+ "administrator_1_backer_1_patron_1_exact_match": 1.0,
133
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
134
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
135
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
136
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
137
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
138
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
139
+ },
140
+ "7000": {
141
+ "exact_match": 0.8876666666666667,
142
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
143
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
144
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
145
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
146
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
147
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
148
+ "administrator_1_administrator_1_sponsor_1_exact_match": 0.5,
149
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
150
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
151
+ "administrator_1_backer_1_administrator_1_exact_match": 0.0,
152
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
153
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
154
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
155
+ "administrator_1_backer_1_patron_1_exact_match": 1.0,
156
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
157
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
158
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
159
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
160
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
161
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
162
+ },
163
+ "8000": {
164
+ "exact_match": 0.9106666666666666,
165
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
166
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
167
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
168
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
169
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
170
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
171
+ "administrator_1_administrator_1_sponsor_1_exact_match": 1.0,
172
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
173
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
174
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
175
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
176
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
177
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
178
+ "administrator_1_backer_1_patron_1_exact_match": 1.0,
179
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
180
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
181
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
182
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
183
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
184
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
185
+ },
186
+ "9000": {
187
+ "exact_match": 0.919,
188
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
189
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
190
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
191
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
192
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
193
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
194
+ "administrator_1_administrator_1_sponsor_1_exact_match": 1.0,
195
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
196
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
197
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
198
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
199
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
200
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
201
+ "administrator_1_backer_1_patron_1_exact_match": 0.0,
202
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
203
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
204
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
205
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
206
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
207
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
208
+ },
209
+ "10000": {
210
+ "exact_match": 0.9213333333333333,
211
+ "administrator_1_administrator_1_boss_1_exact_match": 1.0,
212
+ "administrator_1_administrator_1_coordinator_1_exact_match": 1.0,
213
+ "administrator_1_administrator_1_employer_1_exact_match": 1.0,
214
+ "administrator_1_administrator_1_financier_1_exact_match": 1.0,
215
+ "administrator_1_administrator_1_patron_1_exact_match": 1.0,
216
+ "administrator_1_administrator_1_ruler_1_exact_match": 1.0,
217
+ "administrator_1_administrator_1_sponsor_1_exact_match": 1.0,
218
+ "administrator_1_administrator_1_supervisor_1_exact_match": 0.0,
219
+ "administrator_1_advisor_1_mentor_1_exact_match": 1.0,
220
+ "administrator_1_backer_1_administrator_1_exact_match": 1.0,
221
+ "administrator_1_backer_1_backer_1_exact_match": 1.0,
222
+ "administrator_1_backer_1_financier_1_exact_match": 1.0,
223
+ "administrator_1_backer_1_mentor_1_exact_match": 1.0,
224
+ "administrator_1_backer_1_patron_1_exact_match": 1.0,
225
+ "administrator_1_backer_1_sponsor_1_exact_match": 1.0,
226
+ "administrator_1_backer_1_teacher_1_exact_match": 0.5,
227
+ "administrator_1_boss_1_employer_1_exact_match": 1.0,
228
+ "administrator_1_boss_1_teacher_1_exact_match": 1.0,
229
+ "administrator_1_coordinator_1_administrator_1_exact_match": 1.0,
230
+ "administrator_1_coordinator_1_backer_1_exact_match": 1.0
231
+ }
232
+ }
cl_hop3/vocab.json ADDED
The diff for this file is too large to render. See raw diff