anlp-assignment1-c1-byte8-optimized / target_tokenizer.json
Anivarth's picture
Upload C1 best checkpoint and metrics
b601bbe verified
Raw History Blame Contribute Delete
25.3 kB
{
"version": 1,
"type": "byte_bpe",
"special_tokens": [
"[PAD]",
"[UNK]",
"[BOS]",
"[EOS]"
],
"max_length": 768,
"binary_chunk_size": 256,
"merges": [
[
120,
108
],
[
109,
114
],
[
260,
105
],
[
101,
114
],
[
105,
118
],
[
115,
114
],
[
105,
104
],
[
118,
105
],
[
101,
120
],
[
115,
118
],
[
105,
114
],
[
119,
120
],
[
101,
112
],
[
101,
118
],
[
115,
106
],
[
263,
104
],
[
101,
119
],
[
105,
119
],
[
261,
107
],
[
120,
115
],
[
109,
120
],
[
109,
119
],
[
115,
121
],
[
109,
103
],
[
109,
265
],
[
108,
105
],
[
118,
115
],
[
112,
105
],
[
109,
112
],
[
101,
104
],
[
101,
103
],
[
270,
120
],
[
119,
105
],
[
101,
113
],
[
112,
125
],
[
123,
276
],
[
102,
105
],
[
115,
113
],
[
106,
269
],
[
121,
118
],
[
104,
105
],
[
103,
108
],
[
115,
112
],
[
109,
118
],
[
88,
285
],
[
122,
105
],
[
109,
107
],
[
109,
113
],
[
112,
115
],
[
121,
114
],
[
122,
264
],
[
120,
264
],
[
123,
108
],
[
123,
109
],
[
120,
105
],
[
101,
125
],
[
103,
265
],
[
103,
105
],
[
268,
284
],
[
313,
260
],
[
103,
120
],
[
109,
104
],
[
101,
107
],
[
260,
268
],
[
102,
125
],
[
264,
105
],
[
121,
112
],
[
121,
119
],
[
101,
116
],
[
118,
109
],
[
115,
120
],
[
267,
119
],
[
115,
123
],
[
101,
261
],
[
105,
120
],
[
105,
112
],
[
121,
120
],
[
286,
113
],
[
282,
114
],
[
119,
121
],
[
264,
119
],
[
116,
112
],
[
103,
297
],
[
109,
271
],
[
115,
116
],
[
108,
281
],
[
121,
113
],
[
123,
325
],
[
101,
102
],
[
113,
115
],
[
119,
108
],
[
272,
112
],
[
106,
337
],
[
120,
118
],
[
77,
114
],
[
105,
113
],
[
262,
118
],
[
116,
286
],
[
114,
105
],
[
103,
112
],
[
268,
105
],
[
306,
108
],
[
101,
267
],
[
104,
109
],
[
116,
105
],
[
102,
264
],
[
273,
120
],
[
116,
115
],
[
265,
107
],
[
288,
112
],
[
283,
108
],
[
101,
111
],
[
119,
109
],
[
105,
271
],
[
268,
266
],
[
112,
109
],
[
280,
125
],
[
112,
104
],
[
117,
121
],
[
116,
264
],
[
105,
124
],
[
271,
118
],
[
269,
120
],
[
119,
115
],
[
270,
104
],
[
282,
120
],
[
107,
108
],
[
109,
277
],
[
281,
108
],
[
273,
104
],
[
101,
271
],
[
108,
289
],
[
101,
122
],
[
113,
291
],
[
113,
263
],
[
115,
104
],
[
109,
116
],
[
282,
118
],
[
101,
106
],
[
109,
263
],
[
290,
111
],
[
104,
264
],
[
115,
310
],
[
107,
105
],
[
265,
105
],
[
293,
105
],
[
282,
386
],
[
105,
273
],
[
109,
122
],
[
312,
370
],
[
338,
104
],
[
263,
120
],
[
120,
123
],
[
71,
108
],
[
361,
120
],
[
277,
119
],
[
106,
105
],
[
268,
120
],
[
114,
330
],
[
276,
119
],
[
109,
272
],
[
118,
280
],
[
290,
120
],
[
308,
123
],
[
273,
125
],
[
261,
105
],
[
115,
267
],
[
107,
118
],
[
109,
305
],
[
280,
119
],
[
101,
305
],
[
87,
120
],
[
102,
336
],
[
101,
123
],
[
116,
382
],
[
332,
114
],
[
109,
106
],
[
290,
108
],
[
269,
104
],
[
105,
122
],
[
105,
123
],
[
121,
104
],
[
106,
303
],
[
109,
101
],
[
76,
105
],
[
116,
118
],
[
283,
272
],
[
262,
303
],
[
261,
120
],
[
306,
114
],
[
105,
116
],
[
121,
116
],
[
282,
377
],
[
102,
115
],
[
104,
121
],
[
320,
284
],
[
282,
119
],
[
272,
383
],
[
103,
111
],
[
113,
264
],
[
280,
284
],
[
122,
109
],
[
120,
307
],
[
112,
275
],
[
322,
105
],
[
101,
121
],
[
269,
111
],
[
119,
103
],
[
442,
271
],
[
111,
105
],
[
120,
266
],
[
267,
105
],
[
69,
121
],
[
115,
356
],
[
112,
112
],
[
367,
119
],
[
118,
263
],
[
299,
278
],
[
297,
105
],
[
108,
264
],
[
108,
276
],
[
268,
264
],
[
119,
116
],
[
116,
366
],
[
296,
270
],
[
412,
115
],
[
121,
267
],
[
119,
264
],
[
316,
120
],
[
274,
106
],
[
101,
303
],
[
107,
121
],
[
263,
119
],
[
113,
105
],
[
108,
430
],
[
102,
118
],
[
314,
113
],
[
398,
311
],
[
350,
396
],
[
267,
103
],
[
267,
114
],
[
312,
115
],
[
116,
331
],
[
120,
119
],
[
123,
105
],
[
113,
265
],
[
270,
317
],
[
272,
294
],
[
104,
277
],
[
341,
315
],
[
115,
111
],
[
116,
108
],
[
109,
287
],
[
122,
266
],
[
88,
108
],
[
298,
113
],
[
342,
116
],
[
114,
115
],
[
102,
112
],
[
260,
281
],
[
261,
104
],
[
89,
114
],
[
104,
281
],
[
120,
299
],
[
103,
277
],
[
69,
114
],
[
261,
359
],
[
273,
111
],
[
262,
125
],
[
289,
105
],
[
462,
105
],
[
290,
105
],
[
77,
120
],
[
103,
115
],
[
109,
126
],
[
119,
284
],
[
103,
118
],
[
263,
317
],
[
103,
267
],
[
106,
106
],
[
280,
105
],
[
283,
105
],
[
318,
119
],
[
269,
260
],
[
121,
105
],
[
119,
119
],
[
103,
291
],
[
261,
279
],
[
116,
120
],
[
116,
267
],
[
125,
407
],
[
115,
103
],
[
335,
112
],
[
106,
288
],
[
113,
333
],
[
118,
265
],
[
261,
311
],
[
86,
115
],
[
101,
288
],
[
342,
113
],
[
103,
266
],
[
123,
466
],
[
349,
267
],
[
120,
125
],
[
280,
266
],
[
282,
260
],
[
327,
266
],
[
349,
271
],
[
526,
441
],
[
104,
477
],
[
348,
287
],
[
105,
310
],
[
114,
278
],
[
123,
315
],
[
283,
111
],
[
108,
307
],
[
116,
266
],
[
123,
452
],
[
69,
118
],
[
107,
263
],
[
106,
109
],
[
106,
426
],
[
106,
112
],
[
118,
406
],
[
123,
389
],
[
267,
107
],
[
276,
266
],
[
322,
333
],
[
118,
125
],
[
302,
104
],
[
277,
105
],
[
283,
263
],
[
269,
125
],
[
103,
109
],
[
106,
261
],
[
119,
364
],
[
268,
277
],
[
309,
401
],
[
320,
266
],
[
273,
301
],
[
112,
273
],
[
115,
107
],
[
102,
121
],
[
263,
125
],
[
276,
265
],
[
82,
115
],
[
70,
421
],
[
260,
406
],
[
326,
120
],
[
381,
121
],
[
281,
284
],
[
296,
103
],
[
316,
104
],
[
553,
113
],
[
83,
114
],
[
119,
285
],
[
302,
423
],
[
273,
113
],
[
104,
315
],
[
113,
261
],
[
285,
289
],
[
89,
87
],
[
102,
287
],
[
109,
105
],
[
120,
270
],
[
283,
120
],
[
118,
101
],
[
114,
266
],
[
260,
471
],
[
112,
277
],
[
358,
123
],
[
291,
119
],
[
293,
116
],
[
265,
294
],
[
276,
105
],
[
69,
459
],
[
269,
119
],
[
381,
272
],
[
472,
637
],
[
265,
104
],
[
71,
297
],
[
120,
333
],
[
103,
302
],
[
118,
266
],
[
318,
272
],
[
122,
270
],
[
262,
113
],
[
114,
346
],
[
103,
273
],
[
260,
583
],
[
119,
265
],
[
312,
512
],
[
268,
278
],
[
103,
415
],
[
119,
478
],
[
339,
102
],
[
115,
102
],
[
264,
266
],
[
82,
440
],
[
101,
126
],
[
312,
270
],
[
121,
518
],
[
69,
112
],
[
119,
101
],
[
105,
270
],
[
263,
107
],
[
312,
325
],
[
119,
278
],
[
120,
265
],
[
348,
385
],
[
112,
266
],
[
112,
119
],
[
106,
397
],
[
288,
104
],
[
372,
300
],
[
87,
108
],
[
112,
481
],
[
261,
277
],
[
86,
105
],
[
113,
365
],
[
72,
105
],
[
270,
264
],
[
264,
114
],
[
119,
299
],
[
292,
604
],
[
339,
116
],
[
123,
273
],
[
106,
120
],
[
278,
119
],
[
106,
326
],
[
106,
616
],
[
286,
116
],
[
394,
125
],
[
107,
115
],
[
268,
301
],
[
371,
105
],
[
121,
271
],
[
75,
264
],
[
121,
272
],
[
606,
388
],
[
119,
125
],
[
260,
263
],
[
286,
123
],
[
103,
338
],
[
108,
361
],
[
296,
412
],
[
705,
664
],
[
69,
106
],
[
316,
119
],
[
284,
119
],
[
109,
310
],
[
314,
293
],
[
357,
454
],
[
111,
114
],
[
101,
110
],
[
282,
116
],
[
308,
103
],
[
280,
387
],
[
119,
368
],
[
102,
346
],
[
113,
529
],
[
292,
310
],
[
91,
273
],
[
103,
299
],
[
121,
292
],
[
647,
365
],
[
113,
355
],
[
292,
612
],
[
296,
581
],
[
292,
112
],
[
499,
438
],
[
107,
309
],
[
402,
114
],
[
102,
400
],
[
353,
125
],
[
296,
278
],
[
91,
108
],
[
101,
260
],
[
106,
264
],
[
103,
328
],
[
267,
287
],
[
301,
273
],
[
263,
111
],
[
587,
271
],
[
107,
405
],
[
103,
376
],
[
263,
114
],
[
70,
105
],
[
104,
118
],
[
123,
552
],
[
69,
120
],
[
78,
115
],
[
109,
266
],
[
107,
125
],
[
109,
111
],
[
121,
424
],
[
311,
119
],
[
272,
719
],
[
417,
400
],
[
113,
109
],
[
105,
106
],
[
262,
267
],
[
488,
261
],
[
269,
377
],
[
110,
105
],
[
344,
264
],
[
102,
417
],
[
103,
420
],
[
272,
119
],
[
262,
114
],
[
301,
115
],
[
328,
263
],
[
78,
771
],
[
81,
263
],
[
105,
287
],
[
326,
273
],
[
114,
293
],
[
267,
112
],
[
635,
591
],
[
113,
125
],
[
392,
125
],
[
109,
267
],
[
113,
281
],
[
286,
545
],
[
721,
272
],
[
264,
115
],
[
261,
317
],
[
289,
104
],
[
69,
119
],
[
116,
661
],
[
267,
268
],
[
269,
113
],
[
388,
266
],
[
116,
302
],
[
104,
115
],
[
341,
290
],
[
416,
268
],
[
105,
111
],
[
122,
302
],
[
123,
373
],
[
300,
116
],
[
611,
405
],
[
305,
308
],
[
81,
315
],
[
271,
105
],
[
339,
301
],
[
109,
456
],
[
123,
421
],
[
272,
368
],
[
521,
564
],
[
453,
260
],
[
508,
449
],
[
568,
278
],
[
375,
469
],
[
112,
368
],
[
70,
115
],
[
104,
435
],
[
114,
273
],
[
461,
440
],
[
261,
119
],
[
270,
119
],
[
281,
266
],
[
283,
119
],
[
436,
283
],
[
398,
120
],
[
267,
554
],
[
328,
364
],
[
713,
435
],
[
113,
288
],
[
270,
107
],
[
363,
122
],
[
309,
120
],
[
121,
331
],
[
80,
105
],
[
118,
121
],
[
286,
289
],
[
115,
395
],
[
119,
113
],
[
332,
571
],
[
351,
266
],
[
638,
399
],
[
103,
308
],
[
267,
271
],
[
296,
579
],
[
707,
311
],
[
88,
345
],
[
120,
329
],
[
292,
120
],
[
113,
266
],
[
113,
369
],
[
82,
543
],
[
107,
732
],
[
103,
263
],
[
282,
314
],
[
74,
105
],
[
268,
428
],
[
332,
264
],
[
300,
802
],
[
103,
125
],
[
109,
115
],
[
121,
301
],
[
309,
105
],
[
262,
292
],
[
87,
314
],
[
113,
334
],
[
119,
449
],
[
104,
321
],
[
299,
301
],
[
384,
266
],
[
103,
264
],
[
103,
452
],
[
106,
410
],
[
280,
120
],
[
299,
125
],
[
353,
492
],
[
427,
715
],
[
112,
414
],
[
269,
401
],
[
367,
448
],
[
762,
121
],
[
109,
300
],
[
287,
289
],
[
491,
271
],
[
87,
450
],
[
108,
343
],
[
300,
106
],
[
496,
365
],
[
116,
273
],
[
327,
283
],
[
498,
119
],
[
550,
119
],
[
73,
114
],
[
87,
285
],
[
112,
101
],
[
335,
104
],
[
343,
119
],
[
363,
267
],
[
826,
273
],
[
883,
886
],
[
321,
291
],
[
516,
287
],
[
729,
106
],
[
71,
302
],
[
102,
340
],
[
114,
543
],
[
267,
523
],
[
111,
113
],
[
288,
125
],
[
306,
261
],
[
116,
344
],
[
475,
460
],
[
105,
390
],
[
267,
317
],
[
393,
119
],
[
697,
394
],
[
87,
105
],
[
276,
111
],
[
372,
305
],
[
119,
266
],
[
407,
294
],
[
487,
122
],
[
84,
302
],
[
104,
293
],
[
113,
270
],
[
281,
105
],
[
300,
103
],
[
663,
321
],
[
113,
694
],
[
272,
105
],
[
276,
108
],
[
371,
278
],
[
764,
320
],
[
339,
103
],
[
379,
109
],
[
119,
111
],
[
489,
283
],
[
108,
115
],
[
112,
425
],
[
293,
277
],
[
103,
402
],
[
341,
263
],
[
502,
291
],
[
71,
265
],
[
124,
120
],
[
344,
287
],
[
273,
410
],
[
303,
265
],
[
103,
438
],
[
80,
277
],
[
81,
273
],
[
116,
340
],
[
837,
351
],
[
408,
266
],
[
102,
351
],
[
465,
292
],
[
78,
263
],
[
101,
108
],
[
320,
269
],
[
358,
273
],
[
362,
101
],
[
116,
287
],
[
71,
112
],
[
269,
908
],
[
307,
105
],
[
948,
817
],
[
77,
77
],
[
102,
266
],
[
600,
403
],
[
714,
269
],
[
321,
266
],
[
329,
271
],
[
350,
332
],
[
123,
261
],
[
74,
269
],
[
116,
419
],
[
271,
360
],
[
363,
539
],
[
487,
387
],
[
279,
510
],
[
356,
114
],
[
472,
882
],
[
103,
336
],
[
107,
395
],
[
378,
289
],
[
685,
434
],
[
106,
263
],
[
114,
264
],
[
87,
565
],
[
334,
119
],
[
508,
103
],
[
772,
590
],
[
121,
102
],
[
271,
366
],
[
265,
277
],
[
84,
108
],
[
109,
102
],
[
109,
260
],
[
121,
507
],
[
741,
290
],
[
114,
332
]
]
}