kanishka commited on
Commit
9dc51d6
·
verified ·
1 Parent(s): da74125

Model save

Browse files
Files changed (6) hide show
  1. README.md +26 -38
  2. added_tokens.json +427 -428
  3. model.safetensors +1 -1
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +0 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -2,23 +2,11 @@
2
  library_name: transformers
3
  tags:
4
  - generated_from_trainer
5
- datasets:
6
- - kanishka/babylm2-rewritten-clean-spacy
7
  metrics:
8
  - accuracy
9
  model-index:
10
  - name: opt-babylm2-rewritten-clean-spacy-earlystop-bpe_seed-42_1e-3
11
- results:
12
- - task:
13
- name: Causal Language Modeling
14
- type: text-generation
15
- dataset:
16
- name: kanishka/babylm2-rewritten-clean-spacy
17
- type: kanishka/babylm2-rewritten-clean-spacy
18
- metrics:
19
- - name: Accuracy
20
- type: accuracy
21
- value: 0.47877642614021604
22
  ---
23
 
24
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
26
 
27
  # opt-babylm2-rewritten-clean-spacy-earlystop-bpe_seed-42_1e-3
28
 
29
- This model was trained from scratch on the kanishka/babylm2-rewritten-clean-spacy dataset.
30
  It achieves the following results on the evaluation set:
31
- - Loss: 2.6820
32
- - Accuracy: 0.4788
33
 
34
  ## Model description
35
 
@@ -62,28 +50,28 @@ The following hyperparameters were used during training:
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
- | 4.101 | 1.0 | 2256 | 3.8138 | 0.3611 |
68
- | 3.445 | 2.0 | 4512 | 3.2965 | 0.4098 |
69
- | 3.1279 | 3.0 | 6768 | 3.0860 | 0.4308 |
70
- | 2.9218 | 4.0 | 9024 | 2.9823 | 0.4412 |
71
- | 2.8441 | 5.0 | 11280 | 2.9202 | 0.4473 |
72
- | 2.7865 | 6.0 | 13536 | 2.8828 | 0.4513 |
73
- | 2.7432 | 7.0 | 15792 | 2.8590 | 0.4541 |
74
- | 2.7146 | 8.0 | 18048 | 2.8378 | 0.4566 |
75
- | 2.6906 | 9.0 | 20304 | 2.8226 | 0.4583 |
76
- | 2.6681 | 10.0 | 22560 | 2.8134 | 0.4595 |
77
- | 2.6498 | 11.0 | 24816 | 2.8048 | 0.4605 |
78
- | 2.6497 | 12.0 | 27072 | 2.7970 | 0.4616 |
79
- | 2.6375 | 13.0 | 29328 | 2.7915 | 0.4621 |
80
- | 2.6278 | 14.0 | 31584 | 2.7862 | 0.4628 |
81
- | 2.6102 | 15.0 | 33840 | 2.7633 | 0.4653 |
82
- | 2.5668 | 16.0 | 36096 | 2.7394 | 0.4686 |
83
- | 2.5178 | 17.0 | 38352 | 2.7183 | 0.4717 |
84
- | 2.462 | 18.0 | 40608 | 2.6977 | 0.4748 |
85
- | 2.3974 | 19.0 | 42864 | 2.6840 | 0.4773 |
86
- | 2.3259 | 20.0 | 45120 | 2.6820 | 0.4788 |
87
 
88
 
89
  ### Framework versions
 
2
  library_name: transformers
3
  tags:
4
  - generated_from_trainer
 
 
5
  metrics:
6
  - accuracy
7
  model-index:
8
  - name: opt-babylm2-rewritten-clean-spacy-earlystop-bpe_seed-42_1e-3
9
+ results: []
 
 
 
 
 
 
 
 
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
14
 
15
  # opt-babylm2-rewritten-clean-spacy-earlystop-bpe_seed-42_1e-3
16
 
17
+ This model was trained from scratch on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.6840
20
+ - Accuracy: 0.4787
21
 
22
  ## Model description
23
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|
55
+ | 4.1044 | 1.0 | 2256 | 3.8204 | 0.3604 |
56
+ | 3.4457 | 2.0 | 4512 | 3.3046 | 0.4093 |
57
+ | 3.13 | 3.0 | 6768 | 3.0945 | 0.4299 |
58
+ | 2.9219 | 4.0 | 9024 | 2.9890 | 0.4404 |
59
+ | 2.8444 | 5.0 | 11280 | 2.9282 | 0.4466 |
60
+ | 2.7883 | 6.0 | 13536 | 2.8910 | 0.4508 |
61
+ | 2.7434 | 7.0 | 15792 | 2.8579 | 0.4545 |
62
+ | 2.7158 | 8.0 | 18048 | 2.8428 | 0.4560 |
63
+ | 2.6905 | 9.0 | 20304 | 2.8298 | 0.4573 |
64
+ | 2.6697 | 10.0 | 22560 | 2.8169 | 0.4592 |
65
+ | 2.6509 | 11.0 | 24816 | 2.8080 | 0.4601 |
66
+ | 2.6494 | 12.0 | 27072 | 2.8020 | 0.4607 |
67
+ | 2.6384 | 13.0 | 29328 | 2.7958 | 0.4616 |
68
+ | 2.6297 | 14.0 | 31584 | 2.7939 | 0.4620 |
69
+ | 2.612 | 15.0 | 33840 | 2.7649 | 0.4653 |
70
+ | 2.5667 | 16.0 | 36096 | 2.7425 | 0.4686 |
71
+ | 2.5177 | 17.0 | 38352 | 2.7206 | 0.4714 |
72
+ | 2.4607 | 18.0 | 40608 | 2.6999 | 0.4746 |
73
+ | 2.397 | 19.0 | 42864 | 2.6865 | 0.4773 |
74
+ | 2.3241 | 19.9915 | 45100 | 2.6840 | 0.4787 |
75
 
76
 
77
  ### Framework versions
added_tokens.json CHANGED
@@ -1,430 +1,429 @@
1
  {
2
- "<|endoftext|>": 16384,
3
- "Ġ000": 16506,
4
- "Ġ01": 16511,
5
- "Ġ02": 16512,
6
- "Ġ03": 16513,
7
- "Ġ04": 16574,
8
- "Ġ05": 16538,
9
- "Ġ06": 16612,
10
- "Ġ07": 16464,
11
- "Ġ08": 16475,
12
- "Ġ09": 16599,
13
- "Ġ1000000000": 16466,
14
- "Ġ1001": 16552,
15
- "Ġ102": 16472,
16
- "Ġ103": 16393,
17
- "Ġ104": 16546,
18
- "Ġ106": 16547,
19
- "Ġ1066": 16703,
20
- "Ġ107": 16444,
21
- "Ġ108": 16445,
22
- "Ġ109": 16539,
23
- "Ġ1100": 16424,
24
- "Ġ11000": 16540,
25
- "Ġ111": 16389,
26
- "Ġ112": 16446,
27
- "Ġ113": 16447,
28
- "Ġ114": 16450,
29
- "Ġ115": 16451,
30
- "Ġ116": 16499,
31
- "Ġ117": 16452,
32
- "Ġ118": 16443,
33
- "Ġ119": 16453,
34
- "Ġ12000": 16530,
35
- "Ġ120000": 16571,
36
- "Ġ121": 16414,
37
- "Ġ122": 16456,
38
- "Ġ123": 16505,
39
- "Ġ124": 16550,
40
- "Ġ1250": 16542,
41
- "Ġ126": 16488,
42
- "Ġ127": 16398,
43
- "Ġ128": 16551,
44
- "Ġ129": 16458,
45
- "Ġ1300": 16425,
46
- "Ġ13000": 16602,
47
- "Ġ131": 16410,
48
- "Ġ132": 16459,
49
- "Ġ133": 16477,
50
- "Ġ134": 16460,
51
- "Ġ135": 16396,
52
- "Ġ136": 16480,
53
- "Ġ137": 16528,
54
- "Ġ138": 16487,
55
- "Ġ139": 16533,
56
- "Ġ1400": 16426,
57
- "Ġ14000": 16554,
58
- "Ġ141": 16416,
59
- "Ġ142": 16625,
60
- "Ġ143": 16401,
61
- "Ġ144": 16522,
62
- "Ġ145": 16386,
63
- "Ġ146": 16502,
64
- "Ġ147": 16579,
65
- "Ġ148": 16507,
66
- "Ġ149": 16557,
67
- "Ġ15000": 16399,
68
- "Ġ150000": 16481,
69
- "Ġ151": 16417,
70
- "Ġ152": 16583,
71
- "Ġ153": 16390,
72
- "Ġ154": 16619,
73
- "Ġ155": 16644,
74
- "Ġ156": 16391,
75
- "Ġ157": 16683,
76
- "Ġ158": 16496,
77
- "Ġ159": 16581,
78
- "Ġ1600": 16427,
79
- "Ġ16000": 16482,
80
- "Ġ1603": 16573,
81
- "Ġ161": 16437,
82
- "Ġ162": 16575,
83
- "Ġ1620": 16730,
84
- "Ġ163": 16392,
85
- "Ġ164": 16630,
86
- "Ġ165": 16555,
87
- "Ġ166": 16678,
88
- "Ġ1660": 16566,
89
- "Ġ1666": 16634,
90
- "Ġ167": 16693,
91
- "Ġ168": 16461,
92
- "Ġ169": 16479,
93
- "Ġ1700": 16428,
94
- "Ġ17000": 16572,
95
- "Ġ1707": 16786,
96
- "Ġ171": 16504,
97
- "Ġ172": 16585,
98
- "Ġ173": 16558,
99
- "Ġ174": 16543,
100
- "Ġ1740": 16621,
101
- "Ġ1748": 16794,
102
- "Ġ1750": 16686,
103
- "Ġ1755": 16738,
104
- "Ġ1756": 16792,
105
- "Ġ1758": 16718,
106
- "Ġ1760": 16732,
107
- "Ġ1762": 16702,
108
- "Ġ1763": 16756,
109
- "Ġ1764": 16774,
110
- "Ġ1765": 16773,
111
- "Ġ1768": 16721,
112
- "Ġ1770": 16806,
113
- "Ġ1772": 16804,
114
- "Ġ1773": 16793,
115
- "Ġ1774": 16752,
116
- "Ġ1775": 16724,
117
- "Ġ1776": 16729,
118
- "Ġ1777": 16791,
119
- "Ġ1778": 16695,
120
- "Ġ1779": 16725,
121
- "Ġ1780": 16701,
122
- "Ġ1781": 16753,
123
- "Ġ1783": 16770,
124
- "Ġ1784": 16768,
125
- "Ġ1785": 16769,
126
- "Ġ1786": 16614,
127
- "Ġ1787": 16639,
128
- "Ġ1788": 16651,
129
- "Ġ1789": 16465,
130
- "Ġ1790": 16592,
131
- "Ġ1791": 16795,
132
- "Ġ1792": 16739,
133
- "Ġ1793": 16715,
134
- "Ġ1794": 16740,
135
- "Ġ1795": 16757,
136
- "Ġ1796": 16798,
137
- "Ġ1797": 16797,
138
- "Ġ1798": 16717,
139
- "Ġ1799": 16635,
140
- "Ġ18000": 16600,
141
- "Ġ1801": 16802,
142
- "Ġ1802": 16760,
143
- "Ġ1803": 16803,
144
- "Ġ1804": 16736,
145
- "Ġ1805": 16799,
146
- "Ġ1806": 16690,
147
- "Ġ1807": 16758,
148
- "Ġ1808": 16747,
149
- "Ġ1809": 16762,
150
- "Ġ181": 16420,
151
- "Ġ1810": 16805,
152
- "Ġ1811": 16707,
153
- "Ġ1812": 16626,
154
- "Ġ1813": 16713,
155
- "Ġ1814": 16610,
156
- "Ġ1815": 16704,
157
- "Ġ1816": 16735,
158
- "Ġ1817": 16759,
159
- "Ġ1818": 16705,
160
- "Ġ1819": 16637,
161
- "Ġ182": 16412,
162
- "Ġ1820": 16709,
163
- "Ġ1821": 16708,
164
- "Ġ1822": 16782,
165
- "Ġ1823": 16775,
166
- "Ġ1824": 16638,
167
- "Ġ1825": 16710,
168
- "Ġ1826": 16711,
169
- "Ġ1827": 16712,
170
- "Ġ1828": 16800,
171
- "Ġ1829": 16761,
172
- "Ġ1830": 16669,
173
- "Ġ1831": 16765,
174
- "Ġ1832": 16780,
175
- "Ġ1833": 16591,
176
- "Ġ1834": 16796,
177
- "Ġ1835": 16667,
178
- "Ġ1836": 16755,
179
- "Ġ1837": 16737,
180
- "Ġ1838": 16801,
181
- "Ġ1839": 16670,
182
- "Ġ1840": 16577,
183
- "Ġ1841": 16776,
184
- "Ġ1842": 16781,
185
- "Ġ1843": 16764,
186
- "Ġ1844": 16489,
187
- "Ġ1845": 16754,
188
- "Ġ1846": 16671,
189
- "Ġ1847": 16672,
190
- "Ġ1848": 16656,
191
- "Ġ1849": 16733,
192
- "Ġ1850": 16568,
193
- "Ġ1851": 16766,
194
- "Ġ1852": 16714,
195
- "Ġ1853": 16728,
196
- "Ġ1854": 16787,
197
- "Ġ1855": 16734,
198
- "Ġ1856": 16611,
199
- "Ġ1857": 16777,
200
- "Ġ1858": 16673,
201
- "Ġ1859": 16688,
202
- "Ġ1860": 16567,
203
- "Ġ1861": 16665,
204
- "Ġ1862": 16653,
205
- "Ġ1863": 16763,
206
- "Ġ1864": 16677,
207
- "Ġ1865": 16687,
208
- "Ġ1866": 16664,
209
- "Ġ1867": 16674,
210
- "Ġ1868": 16699,
211
- "Ġ1869": 16632,
212
- "Ġ1871": 16700,
213
- "Ġ1872": 16767,
214
- "Ġ1873": 16748,
215
- "Ġ1874": 16749,
216
- "Ġ1875": 16783,
217
- "Ġ1876": 16750,
218
- "Ġ1877": 16723,
219
- "Ġ1878": 16716,
220
- "Ġ1879": 16649,
221
- "Ġ1880": 16588,
222
- "Ġ1881": 16696,
223
- "Ġ1882": 16778,
224
- "Ġ1883": 16779,
225
- "Ġ1884": 16751,
226
- "Ġ1885": 16784,
227
- "Ġ1886": 16731,
228
- "Ġ1887": 16771,
229
- "Ġ1888": 16668,
230
- "Ġ1889": 16648,
231
- "Ġ1891": 16772,
232
- "Ġ1892": 16647,
233
- "Ġ1893": 16675,
234
- "Ġ1894": 16597,
235
- "Ġ1895": 16726,
236
- "Ġ1896": 16697,
237
- "Ġ1897": 16655,
238
- "Ġ1898": 16654,
239
- "Ġ1899": 16691,
240
- "Ġ1901": 16652,
241
- "Ġ1902": 16698,
242
- "Ġ1903": 16692,
243
- "Ġ1904": 16535,
244
- "Ġ1906": 16589,
245
- "Ġ1907": 16636,
246
- "Ġ192220": 16808,
247
- "Ġ2000000": 16490,
248
- "Ġ201920": 16810,
249
- "Ġ202021": 16811,
250
- "Ġ2025": 16645,
251
- "Ġ203": 16666,
252
- "Ġ204": 16598,
253
- "Ġ205": 16514,
254
- "Ġ206": 16400,
255
- "Ġ207": 16727,
256
- "Ġ208": 16582,
257
- "Ġ209": 16455,
258
- "Ġ210": 16484,
259
- "Ġ2100": 16553,
260
- "Ġ211": 16431,
261
- "Ġ212": 16419,
262
- "Ġ213": 16415,
263
- "Ġ214": 16516,
264
- "Ġ215": 16622,
265
- "Ġ216": 16744,
266
- "Ġ217": 16497,
267
- "Ġ218": 16418,
268
- "Ġ219": 16476,
269
- "Ġ220": 16403,
270
- "Ġ2200": 16439,
271
- "Ġ22000": 16501,
272
- "Ġ221": 16662,
273
- "Ġ222": 16434,
274
- "Ġ223": 16436,
275
- "Ġ224": 16534,
276
- "Ġ225": 16462,
277
- "Ġ226": 16531,
278
- "Ġ227": 16526,
279
- "Ġ228": 16503,
280
- "Ġ230": 16433,
281
- "Ġ2300": 16604,
282
- "Ġ231": 16603,
283
- "Ġ232": 16523,
284
- "Ġ233": 16527,
285
- "Ġ234": 16510,
286
- "Ġ235": 16565,
287
- "Ġ236": 16743,
288
- "Ġ237": 16469,
289
- "Ġ238": 16584,
290
- "Ġ239": 16745,
291
- "Ġ240": 16413,
292
- "Ġ2400": 16385,
293
- "Ġ241": 16587,
294
- "Ġ243": 16485,
295
- "Ġ244": 16498,
296
- "Ġ245": 16562,
297
- "Ġ246": 16559,
298
- "Ġ247": 16560,
299
- "Ġ248": 16563,
300
- "Ġ249": 16561,
301
- "Ġ2500": 16429,
302
- "Ġ25000": 16397,
303
- "Ġ250000": 16471,
304
- "Ġ251": 16657,
305
- "Ġ253": 16663,
306
- "Ġ254": 16617,
307
- "Ġ255": 16595,
308
- "Ġ256": 16719,
309
- "Ġ257": 16524,
310
- "Ġ258": 16627,
311
- "Ġ259": 16387,
312
- "Ġ260": 16411,
313
- "Ġ2600": 16430,
314
- "Ġ261": 16628,
315
- "Ġ262": 16421,
316
- "Ġ263": 16457,
317
- "Ġ264": 16517,
318
- "Ġ265": 16537,
319
- "Ġ266": 16629,
320
- "Ġ267": 16720,
321
- "Ġ268": 16508,
322
- "Ġ269": 16606,
323
- "Ġ270": 16521,
324
- "Ġ271": 16788,
325
- "Ġ272": 16659,
326
- "Ġ273": 16790,
327
- "Ġ275": 16509,
328
- "Ġ278": 16473,
329
- "Ġ280": 16404,
330
- "Ġ281": 16609,
331
- "Ġ282": 16624,
332
- "Ġ283": 16432,
333
- "Ġ285": 16618,
334
- "Ġ286": 16556,
335
- "Ġ287": 16661,
336
- "Ġ290": 16660,
337
- "Ġ291": 16785,
338
- "Ġ293": 16613,
339
- "Ġ294": 16640,
340
- "Ġ295": 16641,
341
- "Ġ296": 16478,
342
- "Ġ299": 16605,
343
- "Ġ300000": 16474,
344
- "Ġ3000000": 16495,
345
- "Ġ301": 16601,
346
- "Ġ302": 16642,
347
- "Ġ303": 16544,
348
- "Ġ304": 16593,
349
- "Ġ305": 16486,
350
- "Ġ306": 16491,
351
- "Ġ307": 16623,
352
- "Ġ308": 16676,
353
- "Ġ309": 16685,
354
- "Ġ310": 16689,
355
- "Ġ311": 16590,
356
- "Ġ312": 16608,
357
- "Ġ313": 16520,
358
- "Ġ314": 16679,
359
- "Ġ315": 16746,
360
- "Ġ316": 16681,
361
- "Ġ318": 16680,
362
- "Ġ319": 16682,
363
- "Ġ320": 16405,
364
- "Ġ323": 16454,
365
- "Ġ324": 16742,
366
- "Ġ325": 16515,
367
- "Ġ326": 16463,
368
- "Ġ327": 16646,
369
- "Ġ330": 16789,
370
- "Ġ333": 16694,
371
- "Ġ340": 16616,
372
- "Ġ343": 16706,
373
- "Ġ3500": 16440,
374
- "Ġ35000": 16525,
375
- "Ġ352": 16684,
376
- "Ġ355": 16529,
377
- "Ġ357": 16388,
378
- "Ġ360": 16435,
379
- "Ġ365": 16536,
380
- "Ġ370": 16494,
381
- "Ġ375": 16564,
382
- "Ġ380": 16406,
383
- "Ġ386": 16541,
384
- "Ġ395": 16576,
385
- "Ġ40000": 16395,
386
- "Ġ400000": 16483,
387
- "Ġ401": 16643,
388
- "Ġ405": 16586,
389
- "Ġ408": 16658,
390
- "Ġ410": 16580,
391
- "Ġ420": 16407,
392
- "Ġ421": 16532,
393
- "Ġ423": 16493,
394
- "Ġ430": 16569,
395
- "Ġ440": 16615,
396
- "Ġ4400": 16578,
397
- "Ġ441": 16633,
398
- "Ġ450": 16402,
399
- "Ġ4500": 16441,
400
- "Ġ45000": 16470,
401
- "Ġ460": 16620,
402
- "Ġ480": 16408,
403
- "Ġ481": 16631,
404
- "Ġ550": 16409,
405
- "Ġ60000": 16518,
406
- "Ġ600000": 16500,
407
- "Ġ650": 16422,
408
- "Ġ6500": 16549,
409
- "Ġ660": 16650,
410
- "Ġ7000": 16442,
411
- "Ġ70000": 16394,
412
- "Ġ700000": 16467,
413
- "Ġ720": 16448,
414
- "Ġ727": 16809,
415
- "Ġ737": 16807,
416
- "Ġ747": 16492,
417
- "Ġ750": 16438,
418
- "Ġ7500": 16545,
419
- "Ġ75000": 16607,
420
- "Ġ777": 16741,
421
- "Ġ8000": 16468,
422
- "Ġ80000": 16594,
423
- "Ġ800000": 16548,
424
- "Ġ850": 16449,
425
- "Ġ9000": 16519,
426
- "Ġ90000": 16596,
427
- "Ġ911": 16722,
428
- "Ġ950": 16423,
429
- "Ġ999": 16570
430
  }
 
1
  {
2
+ "01": 16510,
3
+ "02": 16511,
4
+ "03": 16512,
5
+ "04": 16573,
6
+ "05": 16537,
7
+ "06": 16611,
8
+ "07": 16464,
9
+ "08": 16475,
10
+ "09": 16598,
11
+ "1000000000": 16466,
12
+ "1001": 16551,
13
+ "102": 16472,
14
+ "103": 16393,
15
+ "104": 16545,
16
+ "106": 16546,
17
+ "1066": 16702,
18
+ "107": 16444,
19
+ "108": 16445,
20
+ "109": 16538,
21
+ "1100": 16424,
22
+ "11000": 16539,
23
+ "111": 16389,
24
+ "112": 16446,
25
+ "113": 16447,
26
+ "114": 16450,
27
+ "115": 16451,
28
+ "116": 16499,
29
+ "117": 16452,
30
+ "118": 16443,
31
+ "119": 16453,
32
+ "12000": 16529,
33
+ "120000": 16570,
34
+ "121": 16414,
35
+ "122": 16456,
36
+ "123": 16505,
37
+ "124": 16549,
38
+ "1250": 16541,
39
+ "126": 16488,
40
+ "127": 16398,
41
+ "128": 16550,
42
+ "129": 16458,
43
+ "1300": 16425,
44
+ "13000": 16601,
45
+ "131": 16410,
46
+ "132": 16459,
47
+ "133": 16477,
48
+ "134": 16460,
49
+ "135": 16396,
50
+ "136": 16480,
51
+ "137": 16527,
52
+ "138": 16487,
53
+ "139": 16532,
54
+ "1400": 16426,
55
+ "14000": 16553,
56
+ "141": 16416,
57
+ "142": 16624,
58
+ "143": 16401,
59
+ "144": 16521,
60
+ "145": 16386,
61
+ "146": 16502,
62
+ "147": 16578,
63
+ "148": 16506,
64
+ "149": 16556,
65
+ "15000": 16399,
66
+ "150000": 16481,
67
+ "151": 16417,
68
+ "152": 16582,
69
+ "153": 16390,
70
+ "154": 16618,
71
+ "155": 16643,
72
+ "156": 16391,
73
+ "157": 16682,
74
+ "158": 16496,
75
+ "159": 16580,
76
+ "1600": 16427,
77
+ "16000": 16482,
78
+ "1603": 16572,
79
+ "161": 16437,
80
+ "162": 16574,
81
+ "1620": 16729,
82
+ "163": 16392,
83
+ "164": 16629,
84
+ "165": 16554,
85
+ "166": 16677,
86
+ "1660": 16565,
87
+ "1666": 16633,
88
+ "167": 16692,
89
+ "168": 16461,
90
+ "169": 16479,
91
+ "1700": 16428,
92
+ "17000": 16571,
93
+ "1707": 16785,
94
+ "171": 16504,
95
+ "172": 16584,
96
+ "173": 16557,
97
+ "174": 16542,
98
+ "1740": 16620,
99
+ "1748": 16793,
100
+ "1750": 16685,
101
+ "1755": 16737,
102
+ "1756": 16791,
103
+ "1758": 16717,
104
+ "1760": 16731,
105
+ "1762": 16701,
106
+ "1763": 16755,
107
+ "1764": 16773,
108
+ "1765": 16772,
109
+ "1768": 16720,
110
+ "1770": 16805,
111
+ "1772": 16803,
112
+ "1773": 16792,
113
+ "1774": 16751,
114
+ "1775": 16723,
115
+ "1776": 16728,
116
+ "1777": 16790,
117
+ "1778": 16694,
118
+ "1779": 16724,
119
+ "1780": 16700,
120
+ "1781": 16752,
121
+ "1783": 16769,
122
+ "1784": 16767,
123
+ "1785": 16768,
124
+ "1786": 16613,
125
+ "1787": 16638,
126
+ "1788": 16650,
127
+ "1789": 16465,
128
+ "1790": 16591,
129
+ "1791": 16794,
130
+ "1792": 16738,
131
+ "1793": 16714,
132
+ "1794": 16739,
133
+ "1795": 16756,
134
+ "1796": 16797,
135
+ "1797": 16796,
136
+ "1798": 16716,
137
+ "1799": 16634,
138
+ "18000": 16599,
139
+ "1801": 16801,
140
+ "1802": 16759,
141
+ "1803": 16802,
142
+ "1804": 16735,
143
+ "1805": 16798,
144
+ "1806": 16689,
145
+ "1807": 16757,
146
+ "1808": 16746,
147
+ "1809": 16761,
148
+ "181": 16420,
149
+ "1810": 16804,
150
+ "1811": 16706,
151
+ "1812": 16625,
152
+ "1813": 16712,
153
+ "1814": 16609,
154
+ "1815": 16703,
155
+ "1816": 16734,
156
+ "1817": 16758,
157
+ "1818": 16704,
158
+ "1819": 16636,
159
+ "182": 16412,
160
+ "1820": 16708,
161
+ "1821": 16707,
162
+ "1822": 16781,
163
+ "1823": 16774,
164
+ "1824": 16637,
165
+ "1825": 16709,
166
+ "1826": 16710,
167
+ "1827": 16711,
168
+ "1828": 16799,
169
+ "1829": 16760,
170
+ "1830": 16668,
171
+ "1831": 16764,
172
+ "1832": 16779,
173
+ "1833": 16590,
174
+ "1834": 16795,
175
+ "1835": 16666,
176
+ "1836": 16754,
177
+ "1837": 16736,
178
+ "1838": 16800,
179
+ "1839": 16669,
180
+ "1840": 16576,
181
+ "1841": 16775,
182
+ "1842": 16780,
183
+ "1843": 16763,
184
+ "1844": 16489,
185
+ "1845": 16753,
186
+ "1846": 16670,
187
+ "1847": 16671,
188
+ "1848": 16655,
189
+ "1849": 16732,
190
+ "1850": 16567,
191
+ "1851": 16765,
192
+ "1852": 16713,
193
+ "1853": 16727,
194
+ "1854": 16786,
195
+ "1855": 16733,
196
+ "1856": 16610,
197
+ "1857": 16776,
198
+ "1858": 16672,
199
+ "1859": 16687,
200
+ "1860": 16566,
201
+ "1861": 16664,
202
+ "1862": 16652,
203
+ "1863": 16762,
204
+ "1864": 16676,
205
+ "1865": 16686,
206
+ "1866": 16663,
207
+ "1867": 16673,
208
+ "1868": 16698,
209
+ "1869": 16631,
210
+ "1871": 16699,
211
+ "1872": 16766,
212
+ "1873": 16747,
213
+ "1874": 16748,
214
+ "1875": 16782,
215
+ "1876": 16749,
216
+ "1877": 16722,
217
+ "1878": 16715,
218
+ "1879": 16648,
219
+ "1880": 16587,
220
+ "1881": 16695,
221
+ "1882": 16777,
222
+ "1883": 16778,
223
+ "1884": 16750,
224
+ "1885": 16783,
225
+ "1886": 16730,
226
+ "1887": 16770,
227
+ "1888": 16667,
228
+ "1889": 16647,
229
+ "1891": 16771,
230
+ "1892": 16646,
231
+ "1893": 16674,
232
+ "1894": 16596,
233
+ "1895": 16725,
234
+ "1896": 16696,
235
+ "1897": 16654,
236
+ "1898": 16653,
237
+ "1899": 16690,
238
+ "1901": 16651,
239
+ "1902": 16697,
240
+ "1903": 16691,
241
+ "1904": 16534,
242
+ "1906": 16588,
243
+ "1907": 16635,
244
+ "192220": 16807,
245
+ "2000000": 16490,
246
+ "201920": 16809,
247
+ "202021": 16810,
248
+ "2025": 16644,
249
+ "203": 16665,
250
+ "204": 16597,
251
+ "205": 16513,
252
+ "206": 16400,
253
+ "207": 16726,
254
+ "208": 16581,
255
+ "209": 16455,
256
+ "210": 16484,
257
+ "2100": 16552,
258
+ "211": 16431,
259
+ "212": 16419,
260
+ "213": 16415,
261
+ "214": 16515,
262
+ "215": 16621,
263
+ "216": 16743,
264
+ "217": 16497,
265
+ "218": 16418,
266
+ "219": 16476,
267
+ "220": 16403,
268
+ "2200": 16439,
269
+ "22000": 16501,
270
+ "221": 16661,
271
+ "222": 16434,
272
+ "223": 16436,
273
+ "224": 16533,
274
+ "225": 16462,
275
+ "226": 16530,
276
+ "227": 16525,
277
+ "228": 16503,
278
+ "230": 16433,
279
+ "2300": 16603,
280
+ "231": 16602,
281
+ "232": 16522,
282
+ "233": 16526,
283
+ "234": 16509,
284
+ "235": 16564,
285
+ "236": 16742,
286
+ "237": 16469,
287
+ "238": 16583,
288
+ "239": 16744,
289
+ "240": 16413,
290
+ "2400": 16385,
291
+ "241": 16586,
292
+ "243": 16485,
293
+ "244": 16498,
294
+ "245": 16561,
295
+ "246": 16558,
296
+ "247": 16559,
297
+ "248": 16562,
298
+ "249": 16560,
299
+ "2500": 16429,
300
+ "25000": 16397,
301
+ "250000": 16471,
302
+ "251": 16656,
303
+ "253": 16662,
304
+ "254": 16616,
305
+ "255": 16594,
306
+ "256": 16718,
307
+ "257": 16523,
308
+ "258": 16626,
309
+ "259": 16387,
310
+ "260": 16411,
311
+ "2600": 16430,
312
+ "261": 16627,
313
+ "262": 16421,
314
+ "263": 16457,
315
+ "264": 16516,
316
+ "265": 16536,
317
+ "266": 16628,
318
+ "267": 16719,
319
+ "268": 16507,
320
+ "269": 16605,
321
+ "270": 16520,
322
+ "271": 16787,
323
+ "272": 16658,
324
+ "273": 16789,
325
+ "275": 16508,
326
+ "278": 16473,
327
+ "280": 16404,
328
+ "281": 16608,
329
+ "282": 16623,
330
+ "283": 16432,
331
+ "285": 16617,
332
+ "286": 16555,
333
+ "287": 16660,
334
+ "290": 16659,
335
+ "291": 16784,
336
+ "293": 16612,
337
+ "294": 16639,
338
+ "295": 16640,
339
+ "296": 16478,
340
+ "299": 16604,
341
+ "300000": 16474,
342
+ "3000000": 16495,
343
+ "301": 16600,
344
+ "302": 16641,
345
+ "303": 16543,
346
+ "304": 16592,
347
+ "305": 16486,
348
+ "306": 16491,
349
+ "307": 16622,
350
+ "308": 16675,
351
+ "309": 16684,
352
+ "310": 16688,
353
+ "311": 16589,
354
+ "312": 16607,
355
+ "313": 16519,
356
+ "314": 16678,
357
+ "315": 16745,
358
+ "316": 16680,
359
+ "318": 16679,
360
+ "319": 16681,
361
+ "320": 16405,
362
+ "323": 16454,
363
+ "324": 16741,
364
+ "325": 16514,
365
+ "326": 16463,
366
+ "327": 16645,
367
+ "330": 16788,
368
+ "333": 16693,
369
+ "340": 16615,
370
+ "343": 16705,
371
+ "3500": 16440,
372
+ "35000": 16524,
373
+ "352": 16683,
374
+ "355": 16528,
375
+ "357": 16388,
376
+ "360": 16435,
377
+ "365": 16535,
378
+ "370": 16494,
379
+ "375": 16563,
380
+ "380": 16406,
381
+ "386": 16540,
382
+ "395": 16575,
383
+ "40000": 16395,
384
+ "400000": 16483,
385
+ "401": 16642,
386
+ "405": 16585,
387
+ "408": 16657,
388
+ "410": 16579,
389
+ "420": 16407,
390
+ "421": 16531,
391
+ "423": 16493,
392
+ "430": 16568,
393
+ "440": 16614,
394
+ "4400": 16577,
395
+ "441": 16632,
396
+ "450": 16402,
397
+ "4500": 16441,
398
+ "45000": 16470,
399
+ "460": 16619,
400
+ "480": 16408,
401
+ "481": 16630,
402
+ "550": 16409,
403
+ "60000": 16517,
404
+ "600000": 16500,
405
+ "650": 16422,
406
+ "6500": 16548,
407
+ "660": 16649,
408
+ "7000": 16442,
409
+ "70000": 16394,
410
+ "700000": 16467,
411
+ "720": 16448,
412
+ "727": 16808,
413
+ "737": 16806,
414
+ "747": 16492,
415
+ "750": 16438,
416
+ "7500": 16544,
417
+ "75000": 16606,
418
+ "777": 16740,
419
+ "8000": 16468,
420
+ "80000": 16593,
421
+ "800000": 16547,
422
+ "850": 16449,
423
+ "9000": 16518,
424
+ "90000": 16595,
425
+ "911": 16721,
426
+ "950": 16423,
427
+ "999": 16569,
428
+ "<|endoftext|>": 16384
 
429
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78a24b9f70ac1761212e945ed8c4d04d91c3eb638a51e917dd060936771835a3
3
  size 392682336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c150e0b350f07cf568ff48fe1eb30059ec3e50454b5b418834dc0eae576757ae
3
  size 392682336
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3256b16324f733727ac83bbf9df8ca89221d6c7f40c88ae86cf92e50b7f90b81
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f5d89d6ac20c7296ba53464c714e8bdab0613d048f74e0d7be23d39c017522
3
  size 5496