Training in progress, step 1000

added_tokens.json

@@ -98,1431 +98,5 @@
   "<extra_id_97>": 32002,
   "<extra_id_98>": 32001,
   "<extra_id_99>": 32000,
-  "<extra_id_9>": 32090,
-  "€": 32922,
-  "": 33151,
-  "‚": 33371,
-  "ƒ": 32967,
-  "ˆ": 32307,
-  "Œ": 32492,
-  " ": 33497,
-  "¡": 32642,
-  "¢": 32718,
-  "¦": 32823,
-  "§": 32576,
-  "©": 32647,
-  "ª": 33159,
-  "¬": 32451,
-  "¯": 32453,
-  "±": 33446,
-  "´": 33114,
-  "µ": 32983,
-  "¶": 33508,
-  "·": 32426,
-  "¸": 32503,
-  "¹": 32867,
-  "¼": 32733,
-  "À": 33238,
-  "Á": 33130,
-  "Â": 33170,
-  "Ã": 32493,
-  "Ä": 32407,
-  "Å": 33504,
-  "Æ": 32386,
-  "Ç": 32403,
-  "Ê": 33220,
-  "Ì": 32213,
-  "Í": 32553,
-  "Ð": 32458,
-  "Ñ": 33348,
-  "Ó": 32660,
-  "Ô": 32124,
-  "Õ": 32146,
-  "Ö": 33117,
-  "Ø": 32486,
-  "Ú": 32163,
-  "Û": 32102,
-  "Þ": 32271,
-  "ã": 32931,
-  "å": 33360,
-  "æ": 32283,
-  "ë": 33507,
-  "ì": 32882,
-  "í": 32725,
-  "ï": 32353,
-  "ð": 32952,
-  "ñ": 33095,
-  "ò": 32376,
-  "õ": 33492,
-  "ø": 32591,
-  "ú": 32300,
-  "ý": 32563,
-  "þ": 32172,
-  "Ā": 33005,
-  "ā": 32498,
-  "Ă": 32758,
-  "Ą": 33500,
-  "ą": 33197,
-  "Ć": 32154,
-  "ć": 33509,
-  "Č": 32611,
-  "č": 32267,
-  "Ď": 32619,
-  "ď": 32562,
-  "Đ": 32912,
-  "đ": 32116,
-  "Ē": 32398,
-  "ē": 32577,
-  "Ė": 32311,
-  "ė": 32834,
-  "Ę": 32240,
-  "ę": 33308,
-  "Ě": 33060,
-  "ě": 33329,
-  "Ğ": 33017,
-  "ğ": 33180,
-  "ġ": 33453,
-  "ĩ": 32115,
-  "Ī": 33312,
-  "ī": 32122,
-  "Ĭ": 32669,
-  "ĭ": 32874,
-  "İ": 32586,
-  "ı": 32405,
-  "Ł": 32786,
-  "ł": 33196,
-  "Ń": 32621,
-  "ń": 33230,
-  "Ň": 32209,
-  "ň": 33048,
-  "Ō": 32671,
-  "ō": 32212,
-  "ŏ": 32626,
-  "Ő": 32205,
-  "ő": 32349,
-  "Œ": 32930,
-  "œ": 32491,
-  "Ř": 32849,
-  "ř": 32185,
-  "Ś": 32720,
-  "ś": 33280,
-  "Ş": 32715,
-  "Š": 32557,
-  "š": 32551,
-  "Ţ": 32542,
-  "Ť": 32904,
-  "ť": 32202,
-  "ũ": 33401,
-  "Ū": 33347,
-  "ū": 33125,
-  "Ŭ": 32461,
-  "ŭ": 33498,
-  "Ů": 33126,
-  "ů": 32313,
-  "Ű": 33221,
-  "ű": 32906,
-  "Ź": 33053,
-  "ź": 32941,
-  "Ż": 32238,
-  "ż": 32666,
-  "Ž": 33240,
-  "ž": 32430,
-  "ƒ": 32936,
-  "ơ": 32603,
-  "Ư": 33006,
-  "ư": 32464,
-  "Ƶ": 32545,
-  "ǂ": 32342,
-  "ǣ": 32734,
-  "Ș": 33310,
-  "Ț": 32365,
-  "ɛ": 32755,
-  "ʹ": 32537,
-  "ʺ": 33388,
-  "ʻ": 32226,
-  "ʼ": 32929,
-  "ʾ": 32319,
-  "ʿ": 32790,
-  "ˆ": 32535,
-  "ˊ": 32670,
-  "̀": 33231,
-  "́": 32415,
-  "̂": 32570,
-  "̃": 32529,
-  "̄": 32301,
-  "̆": 32815,
-  "̇": 32698,
-  "̈": 33404,
-  "̉": 32539,
-  "̊": 33063,
-  "̋": 32850,
-  "̌": 32126,
-  "̐": 32423,
-  "̓": 33215,
-  "̕": 32971,
-  "̛": 32198,
-  "̜": 32654,
-  "̣": 32633,
-  "̤": 33501,
-  "̥": 33234,
-  "̦": 32218,
-  "̧": 32958,
-  "̨": 32320,
-  "̮": 32241,
-  "̱": 33068,
-  "̲": 32691,
-  "̳": 32984,
-  "͡": 32513,
-  "Σ": 32508,
-  "α": 32851,
-  "β": 33076,
-  "А": 33476,
-  "Б": 33167,
-  "Е": 32970,
-  "Н": 32203,
-  "П": 32817,
-  "Р": 32997,
-  "С": 32272,
-  "У": 32784,
-  "Ф": 32456,
-  "Ч": 32711,
-  "б": 33192,
-  "г": 33199,
-  "х": 32302,
-  "я": 33473,
-  "ё": 32427,
-  "і": 33093,
-  "،": 33454,
-  "أ": 32106,
-  "إ": 33247,
-  "ا": 33515,
-  "ب": 32151,
-  "ح": 32651,
-  "د": 32277,
-  "ذ": 33188,
-  "ر": 32157,
-  "ش": 33020,
-  "ص": 32333,
-  "ض": 33316,
-  "ط": 32748,
-  "ع": 33003,
-  "ق": 32316,
-  "ل": 32200,
-  "م": 32245,
-  "ن": 32795,
-  "ه": 33226,
-  "و": 32724,
-  "ي": 33344,
-  "گ": 32223,
-  "Ḍ": 32601,
-  "ḍ": 32131,
-  "ḣ": 33057,
-  "Ḥ": 32774,
-  "ḥ": 32296,
-  "Ḳ": 32206,
-  "ḳ": 33512,
-  "ḷ": 32465,
-  "ṃ": 32923,
-  "Ṅ": 32612,
-  "ṅ": 32627,
-  "ṇ": 32156,
-  "ṛ": 32798,
-  "Ṣ": 33489,
-  "ṣ": 32314,
-  "Ṭ": 33088,
-  "ṭ": 33007,
-  "Ṿ": 32648,
-  "ṿ": 33034,
-  "ẏ": 33285,
-  "Ẓ": 33373,
-  "ẓ": 33333,
-  "ạ": 33474,
-  "ả": 32379,
-  "ấ": 32541,
-  "ầ": 33113,
-  "ẩ": 32756,
-  "ậ": 33089,
-  "ắ": 32695,
-  "ặ": 32564,
-  "ẽ": 33128,
-  "ế": 32999,
-  "ề": 32978,
-  "ễ": 33236,
-  "ệ": 32527,
-  "ị": 32816,
-  "ọ": 32478,
-  "ố": 33425,
-  "ồ": 32896,
-  "ỗ": 32482,
-  "ộ": 33214,
-  "ớ": 32411,
-  "ờ": 33455,
-  "ở": 32201,
-  "ụ": 32722,
-  "ứ": 32572,
-  "ử": 33496,
-  "ữ": 33121,
-  "ỳ": 32380,
-  "‎": 32129,
-  "‏": 32304,
-  "‚": 33521,
-  "†": 33408,
-  "‡": 32607,
-  "‪": 32759,
-  "‬": 32488,
-  "⁻": 32624,
-  "™": 32171,
-  "♭": 33233,
-  "♯": 33416,
-  "　": 32257,
-  "ァ": 33355,
-  "ミ": 32522,
-  "リ": 33482,
-  "ル": 32310,
-  "ー": 33363,
-  "一": 33010,
-  "丁": 32158,
-  "万": 32372,
-  "三": 32889,
-  "上": 32990,
-  "与": 32559,
-  "世": 32331,
-  "丛": 33435,
-  "东": 33480,
-  "丝": 32351,
-  "丞": 32954,
-  "严": 33499,
-  "中": 33067,
-  "丰": 32571,
-  "丹": 33023,
-  "主": 32837,
-  "乃": 33137,
-  "久": 32299,
-  "义": 32976,
-  "之": 33390,
-  "乌": 33432,
-  "乐": 32387,
-  "乔": 32649,
-  "九": 32890,
-  "也": 32165,
-  "���": 32639,
-  "予": 32341,
-  "事": 32515,
-  "二": 32374,
-  "于": 32895,
-  "云": 32894,
-  "五": 32656,
-  "井": 33129,
-  "亚": 32318,
-  "亢": 33253,
-  "亦": 33161,
-  "亨": 32132,
-  "亮": 32945,
-  "人": 33281,
-  "什": 32274,
-  "仁": 33522,
-  "今": 32588,
-  "介": 32389,
-  "从": 33022,
-  "仑": 33448,
-  "付": 33257,
-  "仙": 32346,
-  "令": 32352,
-  "以": 33294,
-  "仪": 33042,
-  "仲": 32518,
-  "任": 33317,
-  "企": 32259,
-  "伊": 32775,
-  "休": 32538,
-  "优": 33218,
-  "会": 32824,
-  "伞": 32322,
-  "伟": 32166,
-  "传": 33483,
-  "伦": 32184,
-  "伯": 32528,
-  "但": 33246,
-  "佐": 32543,
-  "何": 32630,
-  "佘": 33212,
-  "余": 32686,
-  "作": 32861,
-  "佩": 33245,
-  "侃": 33116,
-  "來": 33194,
-  "依": 33200,
-  "侯": 32291,
-  "俄": 33103,
-  "俊": 32354,
-  "保": 33165,
-  "俞": 32117,
-  "信": 32915,
-  "修": 33409,
-  "倍": 32991,
-  "候": 32582,
-  "倦": 32315,
-  "倪": 33090,
-  "健": 33264,
-  "傅": 32694,
-  "僧": 33229,
-  "儒": 33447,
-  "元": 32211,
-  "兆": 32845,
-  "先": 33429,
-  "光": 32726,
-  "克": 33356,
-  "兑": 32105,
-  "党": 33449,
-  "全": 33096,
-  "八": 32499,
-  "公": 32593,
-  "六": 32840,
-  "兰": 32228,
-  "共": 32144,
-  "关": 33405,
-  "兴": 32616,
-  "其": 33423,
-  "兹": 32357,
-  "兼": 33525,
-  "内": 32220,
-  "再": 32519,
-  "军": 33144,
-  "农": 32673,
-  "冠": 32794,
-  "冯": 32841,
-  "冰": 32554,
-  "冲": 32707,
-  "冶": 33147,
-  "冷": 32348,
-  "凌": 33523,
-  "凡": 32652,
-  "凯": 32948,
-  "刃": 32638,
-  "列": 32697,
-  "刘": 33185,
-  "刚": 32317,
-  "创": 33049,
-  "初": 32388,
-  "利": 32195,
-  "别": 33342,
-  "制": 33169,
-  "刻": 33251,
-  "剑": 32436,
-  "剧": 33177,
-  "力": 32262,
-  "功": 32636,
-  "加": 33270,
-  "务": 33324,
-  "劢": 32996,
-  "劫": 32721,
-  "励": 33254,
-  "勃": 32236,
-  "勇": 32555,
-  "勉": 32524,
-  "勋": 33213,
-  "勒": 32797,
-  "勖": 32550,
-  "勘": 32510,
-  "包": 32246,
-  "北": 33326,
-  "匡": 32844,
-  "区": 32962,
-  "医": 33266,
-  "千": 32985,
-  "升": 33104,
-  "午": 32901,
-  "华": 33035,
-  "协": 32179,
-  "卓": 32490,
-  "南": 33296,
-  "博": 32305,
-  "卜": 33374,
-  "卞": 32289,
-  "卡": 32657,
-  "卢": 32587,
-  "卫": 33367,
-  "印": 33152,
-  "危": 33406,
-  "卿": 33115,
-  "厂": 32136,
-  "厅": 33511,
-  "厚": 32887,
-  "原": 33078,
-  "去": 33505,
-  "县": 32434,
-  "又": 32857,
-  "友": 32378,
-  "发": 32141,
-  "叔": 33438,
-  "变": 33470,
-  "口": 32260,
-  "句": 32908,
-  "另": 33261,
-  "可": 33237,
-  "史": 33414,
-  "右": 32665,
-  "叶": 33380,
-  "司": 32525,
-  "合": 32266,
-  "吉": 32676,
-  "同": 32462,
-  "后": 33450,
-  "向": 33461,
-  "吕": 32148,
-  "君": 33327,
-  "吟": 33173,
-  "启": 32123,
-  "吴": 33265,
-  "吾": 33193,
-  "告": 33397,
-  "员": 32602,
-  "周": 32435,
-  "咄": 32439,
-  "和": 32484,
-  "咎": 32139,
-  "咏": 32224,
-  "咸": 32731,
-  "哀": 32609,
-  "品": 33189,
-  "哈": 33487,
-  "哥": 32716,
-  "哲": 32940,
-  "唐": 32659,
-  "唯": 32773,
-  "善": 32663,
-  "喜": 33362,
-  "嗣": 32799,
-  "嘉": 32865,
-  "因": 32412,
-  "团": 32957,
-  "园": 33274,
-  "固": 33302,
-  "国": 32814,
-  "图": 32113,
-  "圃": 32599,
-  "土": 32899,
-  "圣": 32974,
-  "地": 33468,
-  "均": 33488,
-  "坚": 33092,
-  "坛": 33315,
-  "坤": 32140,
-  "坦": 33206,
-  "垣": 32637,
-  "埋": 32569,
-  "城": 33336,
-  "埙": 33054,
-  "培": 32514,
-  "基": 32735,
-  "堂": 32838,
-  "堃": 32808,
-  "堡": 33084,
-  "塘": 32709,
-  "塞": 33154,
-  "境": 32944,
-  "墉": 33133,
-  "增": 33012,
-  "壁": 32437,
-  "士": 32293,
-  "壮": 33176,
-  "声": 32674,
-  "处": 32643,
-  "复": 32739,
-  "夏": 33100,
-  "多": 32382,
-  "夜": 32428,
-  "大": 33072,
-  "天": 32178,
-  "太": 33451,
-  "夫": 32873,
-  "夷": 32279,
-  "奉": 33156,
-  "奎": 32483,
-  "契": 32409,
-  "奥": 32338,
-  "女": 33477,
-  "奴": 32248,
-  "如": 33415,
-  "妥": 33396,
-  "姆": 32107,
-  "委": 32450,
-  "姚": 32575,
-  "威": 32288,
-  "娄": 33320,
-  "子": 33506,
-  "孔": 32792,
-  "存": 32497,
-  "孙": 33323,
-  "孚": 33510,
-  "孝": 32356,
-  "孟": 33286,
-  "季": 32406,
-  "学": 32777,
-  "孩": 32191,
-  "宁": 32325,
-  "宇": 32868,
-  "守": 32791,
-  "安": 32449,
-  "宋": 32635,
-  "宗": 33352,
-  "官": 32466,
-  "定": 32828,
-  "宛": 33051,
-  "宜": 33198,
-  "宝": 32949,
-  "实": 33026,
-  "审": 33040,
-  "客": 32811,
-  "宣": 33081,
-  "宪": 32127,
-  "宫": 32366,
-  "宰": 32343,
-  "家": 33164,
-  "容": 32914,
-  "宾": 33107,
-  "宿": 33513,
-  "寄": 33139,
-  "寅": 33379,
-  "密": 32579,
-  "富": 33369,
-  "寒": 32770,
-  "寰": 33464,
-  "寺": 33046,
-  "导": 32592,
-  "寿": 32347,
-  "将": 33140,
-  "小": 32819,
-  "尔": 33345,
-  "尘": 32337,
-  "尚": 33340,
-  "尧": 33475,
-  "就": 32339,
-  "尹": 32500,
-  "尼": 33481,
-  "尾": 32977,
-  "局": 33009,
-  "居": 33256,
-  "屏": 32972,
-  "屠": 32966,
-  "履": 32704,
-  "屯": 32334,
-  "山": 32803,
-  "屿": 32743,
-  "岂": 32294,
-  "岑": 32807,
-  "岛": 32292,
-  "岩": 33271,
-  "岳": 32109,
-  "峥": 33276,
-  "峰": 33111,
-  "崇": 33105,
-  "崎": 32987,
-  "崔": 32153,
-  "崖": 33385,
-  "嵎": 32661,
-  "嵘": 32244,
-  "嶷": 32321,
-  "川": 33145,
-  "工": 33208,
-  "左": 33303,
-  "巨": 32363,
-  "巴": 33250,
-  "布": 32964,
-  "帆": 33411,
-  "师": 32193,
-  "希": 32859,
-  "帝": 33241,
-  "常": 32454,
-  "干": 32286,
-  "平": 33038,
-  "年": 32400,
-  "幸": 32227,
-  "广": 32495,
-  "庄": 33163,
-  "庆": 33016,
-  "序": 32502,
-  "庐": 33028,
-  "库": 32693,
-  "应": 33073,
-  "府": 32297,
-  "庞": 33172,
-  "废": 33030,
-  "庭": 32655,
-  "庵": 32420,
-  "康": 32629,
-  "廖": 32843,
-  "延": 33014,
-  "廷": 33106,
-  "建": 33160,
-  "式": 33025,
-  "弘": 33354,
-  "张": 32681,
-  "强": 33328,
-  "归": 32417,
-  "录": 32364,
-  "彦": 32207,
-  "彩": 33410,
-  "彬": 32507,
-  "彭": 33459,
-  "影": 32410,
-  "征": 32413,
-  "律": 32898,
-  "徐": 32982,
-  "徒": 32594,
-  "微": 32893,
-  "德": 33334,
-  "徽": 33287,
-  "心": 33444,
-  "忍": 33460,
-  "忏": 32853,
-  "志": 32911,
-  "忘": 32119,
-  "忙": 32933,
-  "忠": 32101,
-  "念": 32821,
-  "怀": 32883,
-  "思": 32441,
-  "性": 32264,
-  "总": 33013,
-  "恒": 32880,
-  "恩": 32309,
-  "恭": 33491,
-  "恰": 32463,
-  "恽": 32548,
-  "悟": 32708,
-  "惕": 32219,
-  "惟": 32617,
-  "惠": 32847,
-  "愁": 32481,
-  "愚": 33050,
-  "慈": 32340,
-  "慎": 33101,
-  "慕": 33366,
-  "慧": 32358,
-  "慰": 32373,
-  "懋": 32391,
-  "戈": 32261,
-  "成": 32678,
-  "我": 32295,
-  "戚": 33318,
-  "戡": 33227,
-  "戴": 33083,
-  "房": 32852,
-  "托": 32805,
-  "批": 32278,
-  "承": 32130,
-  "报": 33284,
-  "抱": 33183,
-  "拉": 33102,
-  "拜": 33162,
-  "拾": 33052,
-  "振": 32181,
-  "挺": 32255,
-  "揆": 33082,
-  "提": 33370,
-  "揖": 32230,
-  "援": 33275,
-  "搏": 33359,
-  "撒": 32806,
-  "撰": 32712,
-  "支": 33282,
-  "收": 33244,
-  "改": 33358,
-  "攻": 33190,
-  "政": 33386,
-  "敏": 33056,
-  "教": 33393,
-  "敬": 32713,
-  "敷": 33267,
-  "文": 32719,
-  "斋": 32480,
-  "斐": 33463,
-  "斗": 32620,
-  "斯": 33242,
-  "新": 32846,
-  "方": 33008,
-  "施": 32561,
-  "无": 33149,
-  "日": 33387,
-  "旧": 33479,
-  "旴": 33503,
-  "时": 33384,
-  "旷": 32303,
-  "昂": 32856,
-  "昆": 32640,
-  "昌": 33502,
-  "明": 32477,
-  "易": 32145,
-  "昔": 32942,
-  "星": 32692,
-  "映": 32950,
-  "春": 32479,
-  "昭": 33216,
-  "显": 32395,
-  "晋": 32714,
-  "晓": 33070,
-  "晨": 33248,
-  "普": 32177,
-  "景": 32801,
-  "智": 32869,
-  "暄": 32763,
-  "暹": 32152,
-  "曙": 32782,
-  "曹": 32934,
-  "曼": 33341,
-  "曾": 32827,
-  "月": 32628,
-  "有": 32501,
-  "服": 32160,
-  "朗": 32779,
-  "望": 33440,
-  "朝": 32190,
-  "木": 32598,
-  "本": 33191,
-  "札": 32604,
-  "朱": 32516,
-  "朴": 33277,
-  "权": 33255,
-  "杉": 32250,
-  "李": 32532,
-  "杏": 32438,
-  "村": 32533,
-  "杓": 32842,
-  "杜": 32359,
-  "来": 32381,
-  "杨": 32523,
-  "杰": 33108,
-  "松": 33015,
-  "林": 32813,
-  "枚": 32174,
-  "果": 32641,
-  "枢": 32308,
-  "枫": 33171,
-  "枷": 33417,
-  "柏": 32826,
-  "查": 32961,
-  "柯": 32664,
-  "柱": 32275,
-  "柳": 32937,
-  "标": 32222,
-  "栋": 32242,
-  "树": 33036,
-  "校": 32757,
-  "根": 32772,
-  "格": 32367,
-  "桂": 32820,
-  "桐": 32926,
-  "桑": 32682,
-  "桢": 32408,
-  "桥": 33313,
-  "梁": 33338,
-  "梅": 33232,
-  "梓": 32161,
-  "梦": 33119,
-  "梫": 32467,
-  "梯": 32683,
-  "棠": 32689,
-  "棣": 32578,
-  "棪": 32371,
-  "森": 33472,
-  "棱": 33426,
-  "植": 33047,
-  "楚": 32910,
-  "楞": 33186,
-  "楫": 32723,
-  "楼": 32646,
-  "槐": 32732,
-  "樊": 32764,
-  "模": 32744,
-  "樱": 33375,
-  "次": 32197,
-  "欣": 32150,
-  "欧": 33263,
-  "歌": 32234,
-  "正": 32235,
-  "武": 33032,
-  "段": 32802,
-  "殷": 33039,
-  "毅": 32687,
-  "毕": 33203,
-  "毛": 32776,
-  "氏": 33383,
-  "民": 33361,
-  "水": 32981,
-  "永": 32804,
-  "求": 32273,
-  "汉": 32596,
-  "汝": 32361,
-  "江": 33079,
-  "池": 32973,
-  "汤": 33235,
-  "汪": 32164,
-  "沃": 33289,
-  "沈": 33181,
-  "沉": 32605,
-  "沙": 32231,
-  "沧": 33291,
-  "河": 32170,
-  "治": 32854,
-  "泉": 32812,
-  "法": 32699,
-  "波": 33141,
-  "注": 32754,
-  "泯": 32955,
-  "泰": 32137,
-  "泼": 32285,
-  "泽": 33485,
-  "洁": 32471,
-  "洋": 32956,
-  "洗": 32884,
-  "洛": 32182,
-  "洤": 32459,
-  "津": 32746,
-  "洪": 33127,
-  "洲": 33322,
-  "洵": 33434,
-  "流": 32552,
-  "济": 32863,
-  "浙": 32143,
-  "浚": 32385,
-  "浦": 33148,
-  "浩": 33085,
-  "浪": 33099,
-  "浮": 32951,
-  "海": 32239,
-  "涂": 33142,
-  "涛": 32752,
-  "涟": 33431,
-  "涤": 33399,
-  "润": 32580,
-  "涵": 32204,
-  "淑": 32253,
-  "淞": 32769,
-  "淡": 32290,
-  "淦": 33413,
-  "深": 33024,
-  "淹": 32118,
-  "清": 32749,
-  "渊": 33346,
-  "渤": 32860,
-  "渥": 33428,
-  "温": 32392,
-  "渭": 32328,
-  "游": 33077,
-  "溥": 33219,
-  "溪": 32921,
-  "滋": 33249,
-  "滕": 32329,
-  "满": 33204,
-  "演": 32677,
-  "漱": 32397,
-  "潘": 32505,
-  "潮": 32111,
-  "澄": 33441,
-  "澐": 32888,
-  "澜": 32506,
-  "澹": 32875,
-  "濂": 32335,
-  "濮": 33120,
-  "瀛": 33337,
-  "灏": 32446,
-  "灵": 32903,
-  "灿": 33391,
-  "炎": 32147,
-  "炯": 32832,
-  "炳": 32120,
-  "点": 32232,
-  "烈": 32192,
-  "烩": 32138,
-  "焌": 33110,
-  "焕": 32993,
-  "焘": 32925,
-  "焚": 32600,
-  "焜": 33187,
-  "焱": 32215,
-  "然": 33098,
-  "煌": 33288,
-  "煜": 33279,
-  "煟": 32254,
-  "照": 32606,
-  "熊": 33420,
-  "熙": 33268,
-  "熬": 33134,
-  "燕": 32907,
-  "燮": 32494,
-  "爱": 33217,
-  "片": 32927,
-  "牛": 32474,
-  "物": 32701,
-  "特": 33075,
-  "狄": 33064,
-  "狐": 32684,
-  "独": 33433,
-  "玉": 32864,
-  "王": 32761,
-  "玛": 32595,
-  "玠": 32992,
-  "现": 33493,
-  "玳": 32574,
-  "玺": 33372,
-  "珂": 32504,
-  "珍": 32988,
-  "珙": 32531,
-  "珠": 32280,
-  "球": 33211,
-  "理": 33031,
-  "琛": 32995,
-  "琦": 32134,
-  "琪": 32700,
-  "琯": 32468,
-  "琴": 32870,
-  "琼": 33260,
-  "瑄": 32848,
-  "瑜": 33225,
-  "瑞": 33402,
-  "璋": 32778,
-  "璐": 32900,
-  "璜": 32650,
-  "璞": 32444,
-  "甘": 32445,
-  "生": 33166,
-  "甫": 32833,
-  "田": 32825,
-  "由": 32706,
-  "畀": 32727,
-  "畏": 32920,
-  "留": 33019,
-  "畯": 32489,
-  "白": 32536,
-  "百": 32546,
-  "皋": 32401,
-  "皓": 33398,
-  "皮": 33418,
-  "益": 32623,
-  "盛": 32470,
-  "直": 32835,
-  "相": 32960,
-  "省": 32768,
-  "眉": 32800,
-  "真": 32913,
-  "着": 32276,
-  "瞻": 32287,
-  "瞿": 32404,
-  "知": 32432,
-  "矧": 33086,
-  "石": 32634,
-  "研": 33168,
-  "硕": 32108,
-  "碗": 32618,
-  "碧": 33004,
-  "磊": 32383,
-  "礼": 32284,
-  "社": 33484,
-  "祁": 32188,
-  "祖": 32785,
-  "祜": 33184,
-  "祝": 33097,
-  "祥": 33350,
-  "福": 33462,
-  "禧": 32173,
-  "禹": 32702,
-  "禾": 32469,
-  "秀": 32114,
-  "秉": 32881,
-  "秋": 32568,
-  "科": 32196,
-  "秦": 32282,
-  "称": 32858,
-  "程": 32487,
-  "稚": 32281,
-  "稼": 32968,
-  "穆": 33524,
-  "究": 33179,
-  "立": 33514,
-  "章": 32237,
-  "童": 32963,
-  "端": 32685,
-  "竹": 33300,
-  "笃": 32566,
-  "笙": 33273,
-  "笠": 33033,
-  "符": 32872,
-  "等": 32928,
-  "筠": 32217,
-  "筱": 32251,
-  "筹": 33445,
-  "简": 33065,
-  "管": 32590,
-  "篹": 32679,
-  "籀": 33000,
-  "籣": 33381,
-  "米": 32362,
-  "籾": 32793,
-  "精": 32741,
-  "糊": 32189,
-  "素": 32625,
-  "纂": 33118,
-  "红": 32810,
-  "约": 32457,
-  "纫": 33069,
-  "纯": 33301,
-  "纲": 32133,
-  "纳": 32229,
-  "纶": 33331,
-  "绂": 32162,
-  "绍": 32866,
-  "经": 33516,
-  "绘": 32511,
-  "绥": 32836,
-  "继": 33439,
-  "绩": 33112,
-  "绮": 33243,
-  "维": 33467,
-  "编": 33262,
-  "缘": 32509,
-  "缪": 33044,
-  "罗": 32916,
-  "署": 32149,
-  "羅": 32728,
-  "羊": 32199,
-  "美": 32421,
-  "群": 32112,
-  "羹": 32829,
-  "翁": 32998,
-  "翎": 32433,
-  "翔": 33293,
-  "翟": 32475,
-  "翠": 33155,
-  "翥": 33314,
-  "翰": 32653,
-  "翼": 33519,
-  "耀": 33490,
-  "考": 33307,
-  "而": 32249,
-  "耕": 33364,
-  "耳": 32390,
-  "耶": 32946,
-  "耿": 32440,
-  "聂": 32989,
-  "联": 32214,
-  "聪": 33349,
-  "聿": 32393,
-  "肇": 32645,
-  "肖": 33394,
-  "育": 33353,
-  "胡": 32121,
-  "能": 33421,
-  "脱": 33062,
-  "腾": 32419,
-  "臣": 32180,
-  "臧": 33456,
-  "自": 32252,
-  "臬": 33295,
-  "致": 32610,
-  "舒": 33087,
-  "舜": 32167,
-  "舲": 32208,
-  "良": 33029,
-  "艾": 32104,
-  "节": 32442,
-  "芋": 32512,
-  "芝": 33378,
-  "芦": 33298,
-  "芳": 32268,
-  "芷": 33143,
-  "芸": 32399,
-  "苇": 33389,
-  "苏": 33175,
-  "苑": 32877,
-  "苓": 32377,
-  "若": 33311,
-  "英": 33299,
-  "茀": 32918,
-  "茂": 32540,
-  "范": 33292,
-  "茗": 33150,
-  "茨": 32780,
-  "荃": 33074,
-  "荣": 33400,
-  "荪": 32818,
-  "荫": 33494,
-  "荷": 33412,
-  "荻": 33283,
-  "莎": 33343,
-  "莘": 33278,
-  "莫": 32667,
-  "莱": 32176,
-  "莳": 33422,
-  "莹": 33427,
-  "菁": 33382,
-  "菊": 33335,
-  "萄": 32396,
-  "萍": 32452,
-  "萧": 33209,
-  "萨": 32965,
-  "葛": 33259,
-  "董": 32783,
-  "葵": 33269,
-  "蒋": 32103,
-  "蒙": 32183,
-  "蒲": 32932,
-  "蓉": 33061,
-  "蓝": 32750,
-  "蔚": 33332,
-  "蔡": 33182,
-  "蕃": 33252,
-  "蕉": 32762,
-  "蕙": 32336,
-  "蕻": 32613,
-  "蕾": 32186,
-  "薄": 32128,
-  "薇": 33146,
-  "薛": 32270,
-  "藏": 32142,
-  "藤": 33442,
-  "藩": 32710,
-  "蘧": 33041,
-  "虚": 33043,
-  "虞": 32905,
-  "虫": 32455,
-  "虹": 33228,
-  "蠡": 33407,
-  "行": 32256,
-  "衍": 33080,
-  "衡": 33201,
-  "补": 33158,
-  "袁": 32429,
-  "袆": 33157,
-  "裳": 32938,
-  "裴": 33403,
-  "褚": 33304,
-  "襄": 33517,
-  "襦": 32839,
-  "西": 33055,
-  "观": 32809,
-  "觉": 32402,
-  "角": 32614,
-  "言": 33045,
-  "誉": 32476,
-  "计": 32221,
-  "订": 32549,
-  "记": 32243,
-  "讲": 32306,
-  "许": 32917,
-  "论": 32891,
-  "设": 32560,
-  "诏": 32631,
-  "译": 32526,
-  "诚": 32298,
-  "询": 33011,
-  "诲": 32943,
-  "诸": 33131,
-  "诺": 32258,
-  "读": 33037,
-  "调": 33109,
-  "谊": 33305,
-  "谋": 32431,
-  "谔": 32263,
-  "谟": 32517,
-  "谢": 32644,
-  "谦": 33452,
-  "谪": 33297,
-  "谭": 32939,
-  "谷": 32370,
-  "象": 32766,
-  "豫": 33207,
-  "豹": 32369,
-  "贝": 32394,
-  "贞": 33058,
-  "财": 32422,
-  "贤": 33319,
-  "贯": 32125,
-  "贵": 33469,
-  "贺": 33123,
-  "贻": 32534,
-  "贽": 32878,
-  "贾": 32742,
-  "赖": 32573,
-  "赛": 32608,
-  "赤": 32717,
-  "赫": 32696,
-  "赵": 32924,
-  "起": 32585,
-  "超": 33136,
-  "路": 33520,
-  "蹇": 32110,
-  "身": 33239,
-  "车": 33325,
-  "轮": 32269,
-  "轶": 32583,
-  "辅": 32168,
-  "辉": 33224,
-  "辑": 32615,
-  "辛": 33195,
-  "辩": 32871,
-  "辰": 32986,
-  "边": 33223,
-  "达": 32751,
-  "迈": 33471,
-  "运": 33357,
-  "还": 32473,
-  "进": 33258,
-  "远": 32159,
-  "连": 32350,
-  "迟": 32247,
-  "迦": 32100,
-  "述": 32730,
-  "退": 33495,
-  "适": 32460,
-  "选": 33376,
-  "通": 33321,
-  "逢": 33174,
-  "逸": 32862,
-  "遇": 32187,
-  "道": 32765,
-  "遗": 32330,
-  "邓": 32581,
-  "邝": 32745,
-  "那": 33458,
-  "邦": 33124,
-  "邨": 32567,
-  "邬": 32975,
-  "邵": 32662,
-  "邹": 32155,
-  "郁": 32959,
-  "郊": 32969,
-  "郎": 32909,
-  "郑": 32384,
-  "郗": 33205,
-  "部": 33091,
-  "郭": 33330,
-  "都": 33465,
-  "鄂": 33419,
-  "酋": 32876,
-  "配": 32622,
-  "醒": 32947,
-  "采": 32980,
-  "里": 32892,
-  "重": 32225,
-  "野": 32558,
-  "金": 32485,
-  "鉴": 32368,
-  "鑫": 32885,
-  "钟": 32688,
-  "钧": 32788,
-  "钰": 33368,
-  "钱": 32324,
-  "钺": 32979,
-  "铁": 32760,
-  "铃": 32175,
-  "铎": 32332,
-  "铖": 32530,
-  "铨": 33518,
-  "铭": 33021,
-  "锋": 32822,
-  "锐": 33094,
-  "锡": 32753,
-  "锦": 32953,
-  "锴": 32565,
-  "镐": 33178,
-  "镜": 32668,
-  "长": 32312,
-  "门": 33377,
-  "闲": 32897,
-  "阀": 32556,
-  "阅": 33437,
-  "阐": 32855,
-  "阳": 33222,
-  "阿": 33443,
-  "陀": 33466,
-  "陆": 33395,
-  "陈": 32547,
-  "陛": 32632,
-  "院": 33306,
-  "陳": 32416,
-  "陵": 32375,
-  "陶": 33272,
-  "隆": 33138,
-  "随": 32789,
-  "隐": 33430,
-  "雄": 33202,
-  "雅": 32994,
-  "集": 33066,
-  "雨": 32169,
-  "雪": 32424,
-  "雯": 33153,
-  "雷": 32738,
-  "霄": 33436,
-  "霆": 32135,
-  "震": 32787,
-  "霍": 32345,
-  "霖": 32447,
-  "霞": 32658,
-  "霭": 32830,
-  "青": 33351,
-  "靖": 32879,
-  "静": 32521,
-  "非": 33309,
-  "鞠": 32448,
-  "韦": 32414,
-  "韩": 32326,
-  "音": 32418,
-  "顷": 32831,
-  "项": 32703,
-  "须": 32675,
-  "顾": 32729,
-  "顿": 32767,
-  "颂": 32597,
-  "颉": 32740,
-  "颐": 32425,
-  "颔": 32216,
-  "颖": 32680,
-  "风": 32344,
-  "飞": 33478,
-  "饭": 33059,
-  "馆": 33486,
-  "香": 32355,
-  "騵": 32690,
-  "马": 32672,
-  "驴": 32886,
-  "驹": 32796,
-  "骆": 32443,
-  "骕": 33392,
-  "骚": 32589,
-  "骥": 33001,
-  "高": 32210,
-  "魏": 33210,
-  "鲁": 33002,
-  "鲠": 33365,
-  "鲤": 32360,
-  "鲸": 32520,
-  "鸟": 32747,
-  "鸣": 32902,
-  "鸥": 32472,
-  "鸾": 32496,
-  "鸿": 32919,
-  "鹏": 32935,
-  "鹤": 33339,
-  "麒": 33424,
-  "麟": 33122,
-  "麦": 33071,
-  "黄": 33018,
-  "黎": 32736,
-  "默": 32194,
-  "鼎": 32544,
-  "鼐": 32233,
-  "齐": 32705,
-  "龄": 32584,
-  "龙": 33135,
-  "龚": 32771,
-  "龟": 33132,
-  "︠": 33290,
-  "︡": 32323,
-  "︢": 33027,
-  "（": 33457,
-  "）": 32327,
-  "，": 32265,
-  "：": 32781,
-  "�": 32737
+  "<extra_id_9>": 32090
 }

config.json

@@ -56,5 +56,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.52.3",
   "use_cache": true,
-  "vocab_size": 33526
+  "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:537e05d920112a76e9f726183737e91e9f30adffc382bab95f952c72f6d351d0
-size 244905000
+oid sha256:0c3f4a6dbde95ec9ed9f0b2959c3833472717715b841203b1ad9c4992fa481a7
+size 242041896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d01eaa9b97369635aa3dff4b509f60217545a82aaa708a5f49ab1ee1b85db2
+oid sha256:ac1380cc189c203bae91ef77cf91db50910588a8d01ee237bfebc1d47b1f4eb2
 size 5713