Training in progress, epoch 19, checkpoint

last-checkpoint/added_tokens.json

@@ -0,0 +1,927 @@
+{
+  "##ख𑀢": 106740,
+  "##ख𑁦": 106738,
+  "##चढ": 106076,
+  "##चढच": 106115,
+  "##चढ𑀢": 106219,
+  "##चलच": 106352,
+  "##चललच": 106051,
+  "##चल𑀢": 106353,
+  "##च𑀟": 106661,
+  "##च𑀟च": 106483,
+  "##च𑀟च𑀟": 106794,
+  "##च𑀟च𑀤": 106755,
+  "##च𑀟च𑀤च𑀪पच": 106510,
+  "##च𑀟च𑀪": 106769,
+  "##च𑀟त": 106363,
+  "##च𑀟त𑀢": 105978,
+  "##च𑀟त𑀢𑀟": 106373,
+  "##च𑀟त𑁦": 105988,
+  "##च𑀟पच": 106479,
+  "##च𑀟पच𑀪": 106599,
+  "##च𑀟𑀟": 106701,
+  "##च𑀟𑀟च𑀟": 106640,
+  "##च𑀟𑀟𑀢𑀟": 106298,
+  "##च𑀟𑀢": 106127,
+  "##च𑀟𑀢𑀟": 106227,
+  "##च𑀟𑀣": 106146,
+  "##च𑀟𑀣च": 106121,
+  "##च𑀟𑀳च": 106629,
+  "##च𑀟𑁦": 106272,
+  "##च𑀠": 106315,
+  "##च𑀠च": 106536,
+  "##च𑀠च𑀪": 106134,
+  "##च𑀠ढ": 106275,
+  "##च𑀠ढच": 106164,
+  "##च𑀠𑀠च": 106085,
+  "##च𑀠𑀠च𑀟": 106113,
+  "##च𑀢": 106480,
+  "##च𑀢𑀞च": 106767,
+  "##च𑀪": 106620,
+  "##च𑀪च": 106074,
+  "##च𑀪पच": 106496,
+  "##च𑀪𑀢": 106403,
+  "##च𑀪𑀢𑀟": 106062,
+  "##च𑀪𑀪": 106197,
+  "##च𑀪𑁦": 106415,
+  "##च𑀲": 106133,
+  "##च𑀲च": 106662,
+  "##च𑀲𑀢𑀟": 106791,
+  "##च𑀳": 105960,
+  "##च𑀳च": 106368,
+  "##च𑀳च𑀪": 106055,
+  "##च𑀳𑀫𑀢": 106128,
+  "##च𑀳𑀫𑀢𑀟": 106560,
+  "##च𑀳𑀫𑁦": 106412,
+  "##च𑀳𑀫𑁦𑀟": 106064,
+  "##च𑀳𑀳": 105928,
+  "##झच": 106453,
+  "##झ𑀢𑀟": 105932,
+  "##ञच": 106159,
+  "##ठ𑀦": 106730,
+  "##ठ𑀧": 106512,
+  "##ठ𑀧𑀧": 106540,
+  "##ठ𑀧𑀭": 106505,
+  "##ठ𑀯": 106011,
+  "##ढच": 106426,
+  "##ढच𑀟": 106195,
+  "##ढच𑀪": 106524,
+  "##ढन": 106163,
+  "##ढन𑀱च𑀟": 106492,
+  "##ढ𑀢": 106117,
+  "##ढ𑀢𑀟": 106015,
+  "##ढ𑁣": 106458,
+  "##ढ𑁦": 106398,
+  "##ढ𑁦𑀪": 105917,
+  "##णच": 106335,
+  "##णचणण": 106246,
+  "##णचणणन𑀟": 106673,
+  "##णच𑀟": 106507,
+  "##णच𑀪": 106443,
+  "##णण": 106144,
+  "##णणच": 106369,
+  "##णणच𑀟च": 106711,
+  "##ण𑀢": 106563,
+  "##ण𑀢𑀟": 106199,
+  "##ण𑀦": 105890,
+  "##ण𑁣": 106283,
+  "##ण𑁣ण𑀢𑀟": 106168,
+  "##ण𑁦": 106785,
+  "##ण𑁦𑀟": 105926,
+  "##तच": 106771,
+  "##तत𑁦": 105883,
+  "##त𑀞": 106364,
+  "##त𑀢": 106802,
+  "##त𑀢𑀞": 106548,
+  "##त𑀢𑀟": 106200,
+  "##त𑀫": 106301,
+  "##त𑁣": 106580,
+  "##त𑁦": 106251,
+  "##धच": 106522,
+  "##ध𑀫": 106225,
+  "##ध𑁦": 106295,
+  "##नढन": 106092,
+  "##नपच": 106569,
+  "##नपच𑀪": 106547,
+  "##नपन": 106280,
+  "##नबच": 106672,
+  "##नल": 106761,
+  "##न𑀞": 106464,
+  "##न𑀞च": 106448,
+  "##न𑀞च𑀟": 106684,
+  "##न𑀞च𑀪": 105910,
+  "##न𑀟": 106789,
+  "##न𑀟च": 106633,
+  "##न𑀟च𑀟": 106132,
+  "##न𑀟त𑀢": 105925,
+  "##न𑀟ब": 106567,
+  "##न𑀟ब𑀢णच𑀪": 106239,
+  "##न𑀟𑀢": 106215,
+  "##न𑀟𑀢𑀟": 106046,
+  "##न𑀟𑀣": 106058,
+  "##न𑀠": 105952,
+  "##न𑀠च𑀪": 106276,
+  "##न𑀣": 106255,
+  "##न𑀦": 106681,
+  "##न𑀪": 105963,
+  "##न𑀪च": 106347,
+  "##न𑀪च𑀟": 105931,
+  "##न𑀪𑀞च": 106004,
+  "##न𑀪𑀢": 106048,
+  "##न𑀪𑁦": 106758,
+  "##न𑀯": 106089,
+  "##न𑀱": 106148,
+  "##न𑀱च": 106206,
+  "##न𑀱च𑀪": 106606,
+  "##न𑀳": 105965,
+  "##पच": 106261,
+  "##पच𑀟": 105987,
+  "##पच𑀦": 106351,
+  "##पच𑀪": 105886,
+  "##पच𑀯": 106124,
+  "##पन𑀟": 105954,
+  "##पन𑀠": 105990,
+  "##पप": 106096,
+  "##पपच": 106487,
+  "##प𑀢": 106207,
+  "##प𑀢त": 105961,
+  "##प𑀢𑀟": 106278,
+  "##प𑀢𑁣𑀟": 106122,
+  "##प𑀢𑁣𑀟चल": 106574,
+  "##प𑀫": 105973,
+  "##प𑀳": 106748,
+  "##प𑀳च": 106717,
+  "##प𑁣": 106607,
+  "##प𑁣𑀟": 105994,
+  "##प𑁣𑀪": 106766,
+  "##प𑁦": 106434,
+  "##प𑁦𑀪": 106742,
+  "##बच": 106663,
+  "##बच𑀪": 106726,
+  "##बच𑀳": 106423,
+  "##ब𑀢": 105958,
+  "##ब𑀢𑀟": 106595,
+  "##ब𑁣": 106359,
+  "##ब𑁣𑀪": 106289,
+  "##ब𑁦": 106035,
+  "##ब𑁦𑀟": 106226,
+  "##र𑀦": 106478,
+  "##र𑀯": 106439,
+  "##लच": 106695,
+  "##लच𑀟𑀣": 106390,
+  "##लच𑀠": 105945,
+  "##लच𑀪": 106666,
+  "##लण": 106189,
+  "##ललच": 106700,
+  "##लल𑁣𑀟": 106615,
+  "##ल𑀢": 106086,
+  "##ल𑀢𑀟": 105983,
+  "##ल𑁣": 106557,
+  "##ल𑁣ढ": 106024,
+  "##ल𑁦": 105985,
+  "##व𑀯": 106502,
+  "##ष𑀣च": 106637,
+  "##𑀓": 106549,
+  "##𑀕": 106243,
+  "##𑀖": 106554,
+  "##𑀖𑀦": 106231,
+  "##𑀖𑀯": 106778,
+  "##𑀗": 106210,
+  "##𑀗𑀦": 106097,
+  "##𑀗𑀯": 106564,
+  "##𑀘": 106427,
+  "##𑀘च": 106068,
+  "##𑀘चल": 105984,
+  "##𑀘𑀢": 106027,
+  "##𑀘𑀢𑀟": 106521,
+  "##𑀘𑁣": 106084,
+  "##𑀘𑁦": 106800,
+  "##𑀘𑁦𑀟": 106490,
+  "##𑀘𑁦𑀪": 106350,
+  "##𑀘𑁦𑀪𑀢णच": 106589,
+  "##𑀙": 106421,
+  "##𑀙च": 106546,
+  "##𑀙च𑀪": 106699,
+  "##𑀙𑀢": 106249,
+  "##𑀙𑀢𑀟": 106400,
+  "##𑀚": 106138,
+  "##𑀛": 106208,
+  "##𑀜": 106330,
+  "##𑀜न": 106798,
+  "##𑀝": 106286,
+  "##𑀞": 106190,
+  "##𑀞च": 106597,
+  "##𑀞च𑀟": 106425,
+  "##𑀞च𑀟𑀢𑀟": 105995,
+  "##𑀞च𑀠": 106038,
+  "##𑀞च𑀠च": 106516,
+  "##𑀞च𑀢": 106555,
+  "##𑀞च𑀪": 106677,
+  "##𑀞च𑀪च": 106678,
+  "##𑀞न": 106136,
+  "##𑀞न𑀟": 106238,
+  "##𑀞𑀢": 106307,
+  "##𑀞𑀢ल": 106332,
+  "##𑀞𑀢𑀟": 106265,
+  "##𑀞𑁣": 106268,
+  "##𑀞𑁣𑀞𑀢𑀟": 106665,
+  "##𑀞𑁣𑀟": 106336,
+  "##𑀞𑁦": 106651,
+  "##𑀞𑁦𑀟": 106756,
+  "##𑀟": 106102,
+  "##𑀟च": 106183,
+  "##𑀟च𑀟": 106765,
+  "##𑀟𑀢": 106744,
+  "##𑀟𑀢𑀟": 106106,
+  "##𑀟𑁦": 106576,
+  "##𑀠": 105996,
+  "##𑀠च": 106033,
+  "##𑀠चलच": 106551,
+  "##𑀠च𑀟": 106803,
+  "##𑀠च𑀪": 106381,
+  "##𑀠𑀢": 105934,
+  "##𑀠𑀢𑀟": 106690,
+  "##𑀡": 106341,
+  "##𑀢": 106712,
+  "##𑀢च": 105897,
+  "##𑀢ढ": 106562,
+  "##𑀢ण": 106008,
+  "##𑀢णच": 106257,
+  "##𑀢णच𑀟": 106494,
+  "##𑀢णच𑀦": 106659,
+  "##𑀢णच𑀪": 106721,
+  "##𑀢णच𑀯": 106457,
+  "##𑀢णणच": 106550,
+  "##𑀢णणच𑀪": 106553,
+  "##𑀢ण𑁣": 106292,
+  "##𑀢ण𑁣ण𑀢𑀟": 106039,
+  "##𑀢ण𑁦": 106638,
+  "##𑀢त": 106611,
+  "##𑀢प": 106214,
+  "##𑀢पच": 106642,
+  "##𑀢पपच": 105936,
+  "##𑀢प𑀢𑀟": 106414,
+  "##𑀢प𑁣": 105916,
+  "##𑀢ब": 106463,
+  "##𑀢ल": 106229,
+  "##𑀢𑀞": 105980,
+  "##𑀢𑀞𑀢": 106630,
+  "##𑀢𑀞𑀢𑀟": 106327,
+  "##𑀢𑀞𑀱च": 105979,
+  "##𑀢𑀟": 106526,
+  "##𑀢𑀟च": 106023,
+  "##𑀢𑀟ब": 106378,
+  "##𑀢𑀟𑁦": 106093,
+  "##𑀢𑀠": 106586,
+  "##𑀢𑀠च": 106739,
+  "##𑀢𑀣": 106130,
+  "##𑀢𑀣च": 106078,
+  "##𑀢𑀣च𑀟": 106201,
+  "##𑀢𑀤": 106713,
+  "##𑀢𑀦": 106667,
+  "##𑀢𑀪": 106329,
+  "##𑀢𑀪च": 106617,
+  "##𑀢𑀪𑀞च": 105950,
+  "##𑀢𑀪𑀢": 106411,
+  "##𑀢𑀪𑀢𑀟": 106770,
+  "##𑀢𑀪𑁦": 106188,
+  "##𑀢𑀯": 106745,
+  "##𑀢𑀱च": 106445,
+  "##𑀢𑀳": 106533,
+  "##𑀢𑀳च": 106741,
+  "##𑀢𑀳पच𑀟": 106252,
+  "##𑀢𑀳𑀫": 105941,
+  "##𑀣": 106462,
+  "##𑀣च": 106041,
+  "##𑀣च𑀟": 106191,
+  "##𑀣च𑀪": 106180,
+  "##𑀣न": 106173,
+  "##𑀣𑀢": 105966,
+  "##𑀣𑀢𑀟": 106218,
+  "##𑀣𑀣": 106310,
+  "##𑀣𑀣च": 106783,
+  "##𑀣𑁣": 106362,
+  "##𑀣𑁣𑀟": 106634,
+  "##𑀣𑁦": 106689,
+  "##𑀤": 106372,
+  "##𑀤च": 106087,
+  "##𑀤न": 106486,
+  "##𑀥": 106724,
+  "##𑀦": 106259,
+  "##𑀧": 106107,
+  "##𑀧𑀦": 106237,
+  "##𑀧𑀧": 106514,
+  "##𑀧𑀯": 106339,
+  "##𑀨": 106100,
+  "##𑀩": 106587,
+  "##𑀪": 105911,
+  "##𑀪च": 106169,
+  "##𑀪च𑀟": 106287,
+  "##𑀪𑀢": 106537,
+  "##𑀪𑀢ल": 106402,
+  "##𑀪𑀢𑀟": 106430,
+  "##𑀪𑁣": 106175,
+  "##𑀪𑁦": 106566,
+  "##𑀫": 106236,
+  "##𑀫च": 106493,
+  "##𑀫चल": 106774,
+  "##𑀫च𑀟": 106784,
+  "##𑀫च𑀟ण𑁣ण𑀢𑀟": 106165,
+  "##𑀫च𑀢": 106703,
+  "##𑀫च𑀪": 106768,
+  "##𑀫न": 106037,
+  "##𑀫𑀢": 106509,
+  "##𑀫𑀢𑀟": 106763,
+  "##𑀫𑀢𑀠": 106405,
+  "##𑀫𑁣": 106308,
+  "##𑀫𑁦": 105885,
+  "##𑀫𑁦𑀟": 106473,
+  "##𑀬": 106036,
+  "##𑀬𑀦": 106149,
+  "##𑀬𑀯": 106718,
+  "##𑀭": 106288,
+  "##𑀭थ": 106157,
+  "##𑀭𑀦": 106222,
+  "##𑀭𑀯": 106009,
+  "##𑀮": 105969,
+  "##𑀮𑀦": 106342,
+  "##𑀮𑀯": 105923,
+  "##𑀯": 106357,
+  "##𑀰": 105905,
+  "##𑀰𑀦": 106230,
+  "##𑀰𑀯": 106590,
+  "##𑀱": 106178,
+  "##𑀱च": 106099,
+  "##𑀱च𑀟": 106184,
+  "##𑀱च𑀟𑁦": 106754,
+  "##𑀱च𑀠": 106538,
+  "##𑀱च𑀢": 105913,
+  "##𑀱च𑀦": 106095,
+  "##𑀱च𑀪": 106209,
+  "##𑀱च𑀯": 106250,
+  "##𑀱𑁣": 106012,
+  "##𑀱𑁣𑀟": 106657,
+  "##𑀱𑁦": 106176,
+  "##𑀲": 106202,
+  "##𑀲च": 106312,
+  "##𑀲च𑀪": 105956,
+  "##𑀲च𑀲": 106131,
+  "##𑀲𑀢": 106797,
+  "##𑀲𑀢𑀟": 106320,
+  "##𑀲𑁣": 106355,
+  "##𑀲𑁦": 106625,
+  "##𑀳": 106198,
+  "##𑀳च": 106258,
+  "##𑀳च𑀟": 105882,
+  "##𑀳च𑀦": 106499,
+  "##𑀳न": 106234,
+  "##𑀳प": 106670,
+  "##𑀳𑀦": 105971,
+  "##𑀳𑀫": 106680,
+  "##𑀳𑀫𑀢": 105957,
+  "##𑀳𑀫𑁦": 106147,
+  "##𑀳𑀫𑁦𑀟": 106459,
+  "##𑀳𑀯": 106476,
+  "##𑁢": 106140,
+  "##𑁢𑀦": 106019,
+  "##𑁢𑀯": 106675,
+  "##𑁣": 106192,
+  "##𑁣ल": 106440,
+  "##𑁣𑀟": 106696,
+  "##𑁣𑀟च": 106652,
+  "##𑁣𑀠": 106040,
+  "##𑁣𑀠𑀢𑀟": 106172,
+  "##𑁣𑀣च": 106182,
+  "##𑁣𑀦": 106786,
+  "##𑁣𑀪": 106467,
+  "##𑁣𑀪𑀢𑀟": 106734,
+  "##𑁣𑀫": 106519,
+  "##𑁣𑀳": 106034,
+  "##𑁤": 106267,
+  "##𑁥": 106419,
+  "##𑁥च": 106396,
+  "##𑁦": 106508,
+  "##𑁦प": 106603,
+  "##𑁦ल": 106609,
+  "##𑁦𑀟": 106057,
+  "##𑁦𑀟प": 106397,
+  "##𑁦𑀠": 106020,
+  "##𑁦𑀣": 106627,
+  "##𑁦𑀦": 106429,
+  "##𑁦𑀪": 106349,
+  "##𑁦𑀪च": 106747,
+  "##𑁦𑀪𑀳": 106762,
+  "##𑁦𑀯": 106433,
+  "##𑁦𑀳": 106108,
+  "##𑁦𑀳𑀳": 106242,
+  "चढ": 105955,
+  "चढन": 105898,
+  "चढनढन𑀱च𑀟": 106103,
+  "चढ𑀢𑀟": 106622,
+  "चढ𑁣": 106141,
+  "चणण": 105891,
+  "चणणन𑀞च𑀟": 106375,
+  "चप": 106787,
+  "चब": 106114,
+  "चलष": 105903,
+  "चल𑀙": 106160,
+  "चल𑀙च": 106655,
+  "चल𑀙न𑀠": 106671,
+  "चल𑀢": 106731,
+  "च𑀞": 106583,
+  "च𑀞च": 106704,
+  "च𑀞च𑀟": 106614,
+  "च𑀞𑀱च𑀢": 106779,
+  "च𑀞𑁦": 106447,
+  "च𑀟": 106643,
+  "च𑀟च": 106066,
+  "च𑀟𑀣": 106126,
+  "च𑀠": 106032,
+  "च𑀠न𑀪𑀞च": 106649,
+  "च𑀠𑀠च": 106750,
+  "च𑀠𑀢𑀟": 106477,
+  "च𑀠𑀲": 106271,
+  "च𑀠𑀲च𑀟𑀢": 106002,
+  "च𑀢𑀞𑀢": 106167,
+  "च𑀢𑀞𑀢𑀟": 105976,
+  "च𑀣": 106683,
+  "च𑀣च": 106010,
+  "च𑀣च𑀠": 106725,
+  "च𑀣𑀣𑀢𑀟": 106442,
+  "च𑀤": 106460,
+  "च𑀪": 106503,
+  "च𑀪𑀤": 106304,
+  "च𑀪𑁦": 106105,
+  "च𑀪𑁦𑀱च": 106285,
+  "च𑀲": 106656,
+  "च𑀲𑀢𑀪𑀞च": 106161,
+  "च𑀳": 106799,
+  "च𑀳च": 106531,
+  "झच": 106152,
+  "झच𑀪": 106455,
+  "झच𑀲च": 106579,
+  "झच𑀳च": 105981,
+  "झच𑀳च𑀪": 105943,
+  "झन𑀟ब": 106228,
+  "झन𑀟ब𑀢णच𑀪": 106079,
+  "झ𑀱च": 106162,
+  "झ𑀱चलल𑁣𑀟": 106585,
+  "झ𑀱च𑀪": 106751,
+  "ञच": 106281,
+  "ञचणच": 105912,
+  "ञच𑀟": 106565,
+  "ञ𑀢𑀟": 106498,
+  "ठ𑀧": 106444,
+  "ठ𑀧ठ": 106223,
+  "ठ𑀧ठ𑀧": 106685,
+  "ठ𑀧𑀧": 106705,
+  "ठ𑀧𑀭": 105893,
+  "ठ𑀧𑀭थ": 106306,
+  "ढच": 106098,
+  "ढचढ": 105999,
+  "ढचढढच𑀟": 106170,
+  "ढचण": 106776,
+  "ढचणच": 106715,
+  "ढचणच𑀟": 106641,
+  "ढचणच𑀟च𑀟": 106775,
+  "ढचणणच𑀟च": 106753,
+  "ढच𑀟": 106077,
+  "ढच𑀦": 105970,
+  "ढच𑀪": 106408,
+  "ढच𑀯": 106706,
+  "ढन": 106601,
+  "ढनबच": 106083,
+  "ढन𑀪": 106646,
+  "ढ𑀢": 106485,
+  "ढ𑀢ण": 106385,
+  "ढ𑀢णन": 106213,
+  "ढ𑀢𑀟": 106693,
+  "ढ𑀢𑀟त𑀢𑀞": 106376,
+  "ढ𑀢𑀪": 106014,
+  "ढ𑀢𑀪𑀟𑀢𑀟": 106796,
+  "ढ𑁣": 105906,
+  "ढ𑁦": 106067,
+  "णच": 106417,
+  "णचण𑀢𑀟": 106392,
+  "णच𑀞𑁦": 105915,
+  "णच𑀟": 105880,
+  "णच𑀟च": 106573,
+  "णच𑀟चण𑀢": 106293,
+  "णच𑀟चण𑀢𑀟": 106367,
+  "णच𑀟𑀞𑀢𑀟": 106145,
+  "णच𑀟𑀤न": 106094,
+  "णच𑀠𑀠च": 106520,
+  "णच𑀣𑀣च": 106735,
+  "णच𑀪": 106129,
+  "णच𑀱": 106091,
+  "णच𑀱च": 106465,
+  "णच𑀱च𑀟": 105904,
+  "णच𑀱च𑀟त𑀢𑀟": 105953,
+  "णन": 106450,
+  "ण𑀢": 106370,
+  "ण𑀢𑀟": 106790,
+  "तच𑀟": 105942,
+  "त𑀢": 106575,
+  "त𑀢ढ": 106404,
+  "त𑀢ढ𑀢णच𑀪": 105930,
+  "त𑀢𑀞𑀢": 106333,
+  "त𑀢𑀞𑀢𑀟": 106436,
+  "त𑀢𑀟": 106437,
+  "त𑀫": 106600,
+  "त𑁣": 106080,
+  "त𑁣𑀟": 106489,
+  "त𑁣𑀠": 106777,
+  "त𑁦": 106240,
+  "त𑁦𑀱च": 106334,
+  "धच": 106470,
+  "धच𑀪": 106030,
+  "न𑀞न": 106050,
+  "न𑀟": 106781,
+  "पच": 106217,
+  "पचढ": 106171,
+  "पचपपच": 106366,
+  "पचपपचल𑀢𑀟": 106644,
+  "पच𑀞च": 106468,
+  "पच𑀟च": 106344,
+  "पच𑀢𑀠च": 106361,
+  "पच𑀪": 106645,
+  "पच𑀪च": 105922,
+  "पच𑀪𑀢": 106692,
+  "पच𑀪𑀢𑀫𑀢": 106399,
+  "पच𑀪𑀢𑀫𑀢𑀟": 105896,
+  "पच𑀪𑁦": 106260,
+  "पच𑀱च": 105884,
+  "पच𑀲": 106475,
+  "पच𑀳": 106732,
+  "पन𑀟": 105881,
+  "पन𑀪": 105982,
+  "पन𑀪च𑀢": 106374,
+  "प𑀫𑁦": 106264,
+  "प𑀳": 106451,
+  "प𑀳च": 106070,
+  "प𑀳च𑀞": 106782,
+  "प𑀳च𑀞च𑀟𑀢𑀟": 106003,
+  "प𑀳च𑀪": 106116,
+  "प𑀳च𑀪𑀢𑀟": 106282,
+  "प𑀳𑁣𑀫": 105959,
+  "प𑁣": 106605,
+  "प𑁦": 106511,
+  "बच": 106506,
+  "बचढ": 105940,
+  "बचढच": 106393,
+  "बचढचपच𑀪": 106608,
+  "बच𑀟": 105935,
+  "बच𑀠": 106716,
+  "बच𑀠𑁦": 105962,
+  "बच𑀪": 106060,
+  "बच𑀪𑀢𑀟": 106558,
+  "बच𑀳च𑀪": 106090,
+  "बन𑀣": 106582,
+  "बन𑀣च": 105895,
+  "बन𑀣च𑀟च𑀪": 106621,
+  "बन𑀪": 106504,
+  "ब𑀢𑀣च": 105992,
+  "ब𑀢𑀣च𑀟": 106395,
+  "ब𑀢𑀪": 106059,
+  "ब𑀢𑀪𑀠च": 105944,
+  "ब𑀫": 106232,
+  "ब𑀫च𑀟च": 106000,
+  "ब𑀱च𑀠": 106616,
+  "ब𑀱च𑀠𑀟च": 106111,
+  "ब𑀱च𑀠𑀟चप𑀢": 105947,
+  "ब𑀱च𑀠𑀟चप𑀢𑀟": 105989,
+  "ब𑁣": 106382,
+  "ब𑁦": 106323,
+  "लच": 106736,
+  "लचढ": 106112,
+  "लच𑀠": 106407,
+  "लच𑀠ढच𑀪": 106610,
+  "लच𑀲": 106541,
+  "लच𑀳𑀫𑁦": 105929,
+  "ल𑀢पपच": 106204,
+  "ल𑁣": 106174,
+  "ल𑁣𑀞च": 106639,
+  "ल𑁣𑀞चत𑀢": 106788,
+  "ल𑁣𑀞चत𑀢𑀟": 106383,
+  "ल𑁦": 106571,
+  "𑀓": 105920,
+  "𑀕": 106391,
+  "𑀖": 105949,
+  "𑀗": 106527,
+  "𑀘": 105900,
+  "𑀘च": 106317,
+  "𑀘चब𑁣𑀪": 106325,
+  "𑀘च𑀟च": 106801,
+  "𑀘च𑀟च𑀢𑀪": 106256,
+  "𑀘च𑀠": 106723,
+  "𑀘च𑀠च": 106047,
+  "𑀘च𑀠च𑀙च": 106584,
+  "𑀘च𑀠𑀢": 106221,
+  "𑀘च𑀠𑀢𑀙च𑀪": 106073,
+  "𑀘च𑀪𑀢": 106110,
+  "𑀘न": 106441,
+  "𑀘𑀢": 106623,
+  "𑀘𑀢𑀟": 106296,
+  "𑀘𑀢𑀪": 106263,
+  "𑀘𑀢𑀪ब𑀢𑀟": 106420,
+  "𑀘𑀢𑀫च𑀪": 106456,
+  "𑀘𑁦𑀪": 106018,
+  "𑀘𑁦𑀪𑀢𑀟": 106045,
+  "𑀙": 106052,
+  "𑀙णच𑀟": 106577,
+  "𑀚": 105993,
+  "𑀛": 106053,
+  "𑀜": 106530,
+  "𑀝": 106674,
+  "𑀝च𑀟": 106299,
+  "𑀝𑀭थ": 106495,
+  "𑀞": 106737,
+  "𑀞च": 106697,
+  "𑀞चणच𑀟": 106338,
+  "𑀞चल": 106491,
+  "𑀞च𑀟": 106269,
+  "𑀞च𑀠": 106559,
+  "𑀞च𑀠च𑀪": 106691,
+  "𑀞च𑀠𑀠चलच": 106253,
+  "𑀞च𑀠𑀲": 106752,
+  "𑀞च𑀠𑀲च𑀟𑀢𑀟": 106515,
+  "𑀞च𑀢": 106410,
+  "𑀞च𑀪": 106709,
+  "𑀞च𑀪च": 105918,
+  "𑀞च𑀪चपन𑀟": 106042,
+  "𑀞च𑀪𑁦": 106013,
+  "𑀞च𑀲च": 106626,
+  "𑀞च𑀲𑀢𑀟": 105914,
+  "𑀞च𑀳": 106120,
+  "𑀞च𑀳च": 106719,
+  "𑀞च𑀳च𑀟त𑁦": 106151,
+  "𑀞च𑀳च𑀪": 105968,
+  "𑀞च𑀳न𑀱": 106474,
+  "𑀞च𑀳𑀫𑀢": 106025,
+  "𑀞णच": 106224,
+  "𑀞न": 105964,
+  "𑀞नलच": 105889,
+  "𑀞न𑀟": 106322,
+  "𑀞न𑀟ब𑀢णच𑀪": 106428,
+  "𑀞न𑀠च": 106154,
+  "𑀞न𑀣न": 106572,
+  "𑀞न𑀳च": 106535,
+  "𑀞न𑀳च𑀟": 106513,
+  "𑀞𑀢": 105939,
+  "𑀞𑀢𑀠": 106005,
+  "𑀞𑀢𑀪": 106694,
+  "𑀞𑀢𑀪च": 106598,
+  "𑀞𑀱": 106156,
+  "𑀞𑀱च": 106461,
+  "𑀞𑀱चलल𑁣𑀟": 105991,
+  "𑀞𑀱च𑀟": 106290,
+  "𑀞𑀱च𑀠": 106380,
+  "𑀞𑀱च𑀢𑀞𑀱च": 106592,
+  "𑀞𑀱च𑀢𑀞𑀱चण𑁣": 106728,
+  "𑀞𑁣": 106418,
+  "𑀞𑁣ब𑀢𑀟": 106792,
+  "𑀞𑁣𑀠च": 106321,
+  "𑀞𑁣𑀲𑀢𑀟": 106631,
+  "𑀞𑁦": 106698,
+  "𑀟": 106591,
+  "𑀟च": 106273,
+  "𑀟चन": 106360,
+  "𑀟च𑀘𑁦𑀪𑀢णच": 106233,
+  "𑀟च𑀘𑁦𑀪𑀢णच𑀯": 106212,
+  "𑀟च𑀟": 106387,
+  "𑀟च𑀳": 106297,
+  "𑀟च𑀳च𑀪च": 106277,
+  "𑀟न": 106632,
+  "𑀟न𑀟च": 106679,
+  "𑀟𑀢": 106764,
+  "𑀟𑁣": 106532,
+  "𑀟𑁦": 106193,
+  "𑀟𑁦𑀱": 105933,
+  "𑀠": 106523,
+  "𑀠च": 106529,
+  "𑀠चण": 106594,
+  "𑀠चप": 106356,
+  "𑀠चपच": 106542,
+  "𑀠चप𑀳च": 106143,
+  "𑀠चप𑀳चण𑀢𑀟": 106772,
+  "𑀠चब": 106109,
+  "𑀠चललच": 106101,
+  "𑀠च𑀘चल": 106185,
+  "𑀠च𑀘चल𑀢𑀳": 106528,
+  "𑀠च𑀘चल𑀢𑀳च𑀪": 106720,
+  "𑀠च𑀙": 106071,
+  "𑀠च𑀙च𑀢𑀞च": 105986,
+  "𑀠च𑀞च𑀪": 106266,
+  "𑀠च𑀞च𑀪च𑀟पच𑀪": 106648,
+  "𑀠च𑀟": 106570,
+  "𑀠च𑀟च𑀤च𑀪पच": 106248,
+  "𑀠च𑀟णच𑀟": 105921,
+  "𑀠च𑀢": 106484,
+  "𑀠च𑀤च": 106544,
+  "𑀠च𑀪": 105879,
+  "𑀠च𑀫च𑀢": 105948,
+  "𑀠च𑀲𑀢": 106707,
+  "𑀠च𑀳": 105997,
+  "𑀠च𑀳च𑀟च": 106710,
+  "𑀠च𑀳न": 106795,
+  "𑀠न": 106291,
+  "𑀠नपच𑀟": 106049,
+  "𑀠नपच𑀟𑁦": 105937,
+  "𑀠नपच𑀟𑁦𑀟": 106354,
+  "𑀠नपन": 106647,
+  "𑀠नपन𑀠": 106158,
+  "𑀠नल": 106021,
+  "𑀠नल𑀞𑀢𑀟": 105924,
+  "𑀠न𑀫चल": 106669,
+  "𑀠न𑀫चलल𑀢": 106054,
+  "𑀠न𑀳": 106682,
+  "𑀠न𑀳च𑀠𑀠च𑀟": 106300,
+  "𑀠न𑀳न": 106552,
+  "𑀠न𑀳नल": 105927,
+  "𑀠𑀢ल": 106619,
+  "𑀠𑀢���": 106722,
+  "𑀠𑁣": 106166,
+  "𑀠𑁦": 105972,
+  "𑀠𑁦𑀠": 106438,
+  "𑀡": 105974,
+  "𑀢": 106235,
+  "𑀢ढ": 106294,
+  "𑀢णच": 105899,
+  "𑀢पच": 106135,
+  "𑀢ल𑀢": 106568,
+  "𑀢ल𑀢𑀠𑀢": 106274,
+  "𑀢ल𑀢𑀠𑀢𑀟": 106319,
+  "𑀢𑀟": 106593,
+  "𑀢𑀟ब": 106153,
+  "𑀢𑀟𑀣च": 106082,
+  "𑀢𑀪𑀢𑀟": 106187,
+  "𑀢𑀳": 106452,
+  "𑀣": 106660,
+  "𑀣च": 106687,
+  "𑀣चढच𑀟": 106181,
+  "𑀣चणच": 106688,
+  "𑀣चबच": 106371,
+  "𑀣च𑀘𑀢": 106061,
+  "𑀣च𑀟": 106006,
+  "𑀣च𑀠च𑀪": 106578,
+  "𑀣च𑀢𑀣च": 106318,
+  "𑀣न": 106581,
+  "𑀣नढच": 106488,
+  "𑀣न𑀞": 106409,
+  "𑀣न𑀟": 106733,
+  "𑀣न𑀟𑀢णच": 106194,
+  "𑀣𑀢": 106618,
+  "𑀣𑀢ब": 106757,
+  "𑀣𑀢𑀟": 106525,
+  "𑀣𑀢𑀳": 106205,
+  "𑀣𑁣": 106254,
+  "𑀣𑁣𑀟": 106472,
+  "𑀣𑁦": 106539,
+  "𑀤": 106137,
+  "𑀤च": 106284,
+  "𑀤चढ": 106337,
+  "𑀤च𑀠": 106517,
+  "𑀤च𑀠च": 106324,
+  "𑀤च𑀠च𑀟": 106604,
+  "𑀤च𑀢": 106469,
+  "𑀤च𑀪": 106031,
+  "𑀤च𑁥": 106028,
+  "𑀤न𑀱च": 106454,
+  "𑀥": 106613,
+  "𑀦": 106104,
+  "𑀧": 106658,
+  "𑀨": 106016,
+  "𑀩": 106624,
+  "𑀪": 106628,
+  "𑀪च": 106432,
+  "𑀪चण": 106313,
+  "𑀪चणन𑀱च": 106186,
+  "𑀪चणन𑀱च𑀪": 106389,
+  "𑀪च𑀟च𑀪": 106340,
+  "𑀪च𑀳𑀫𑀢𑀟": 106416,
+  "𑀪न": 106142,
+  "𑀪नढन": 106377,
+  "𑀪न𑀱च": 106311,
+  "𑀪𑀢": 106388,
+  "𑀪𑁣": 106081,
+  "𑀪𑁦": 106365,
+  "𑀫": 105892,
+  "𑀫च": 106729,
+  "𑀫चझ": 106588,
+  "𑀫चञ": 105998,
+  "𑀫चञच": 105908,
+  "𑀫चल": 106179,
+  "𑀫च𑀞च": 106279,
+  "𑀫च𑀟": 106270,
+  "𑀫च𑀟णच𑀪": 106326,
+  "𑀫च𑀟𑀞च": 106069,
+  "𑀫च𑀟𑀞चल𑀢": 105888,
+  "𑀫च𑀟𑀟": 106044,
+  "𑀫च𑀟𑀟न": 106449,
+  "𑀫च𑀢": 106386,
+  "𑀫च𑀢𑀲च𑀪": 106348,
+  "𑀫च𑀢𑀲𑁦": 106556,
+  "𑀫च𑀣च": 106497,
+  "𑀫च𑀪": 106612,
+  "𑀫न": 106727,
+  "𑀫न𑀞": 106759,
+  "𑀫न𑀞न𑀠च𑀪": 106343,
+  "𑀫𑁣": 106247,
+  "𑀬": 106635,
+  "𑀭": 106203,
+  "𑀭थ": 106435,
+  "𑀭थथ": 106119,
+  "𑀭थ𑀖": 106216,
+  "𑀭थ𑀗": 106029,
+  "𑀭थ𑀬": 106668,
+  "𑀭थ𑁢": 106481,
+  "𑀭𑀗": 105907,
+  "𑀮": 106196,
+  "𑀯": 106177,
+  "𑀰": 105901,
+  "𑀱": 106482,
+  "𑀱च": 106065,
+  "𑀱चञ": 106328,
+  "𑀱चञच𑀟𑀟च𑀟": 106773,
+  "𑀱चञच𑀟𑀣च": 106466,
+  "𑀱चपच": 106500,
+  "𑀱चपच𑀟": 106345,
+  "𑀱च𑀘𑁦": 106793,
+  "𑀱च𑀘𑁦𑀟": 106471,
+  "𑀱च𑀞𑀢ल": 106007,
+  "𑀱च𑀟": 106406,
+  "𑀱च𑀟𑀟च𑀟": 106220,
+  "𑀱च𑀟𑀢": 105975,
+  "𑀱च𑀟𑀣च": 106150,
+  "𑀱च𑀳": 106561,
+  "𑀱च𑀳च": 106118,
+  "𑀱च𑀳च𑀟": 106241,
+  "𑀱च𑀳न": 105967,
+  "𑀱न𑀪": 105977,
+  "𑀱न𑀪𑀢𑀟": 106022,
+  "𑀲": 106596,
+  "𑀲च": 106545,
+  "𑀲च𑀪": 106413,
+  "𑀲च𑀪च": 106358,
+  "𑀲च𑀪𑀞𑁣": 106072,
+  "𑀲च𑀪𑀞𑁣𑀟": 106518,
+  "𑀲च𑀳च": 106001,
+  "𑀲𑀢": 106075,
+  "𑀲𑀢प𑁣": 106746,
+  "𑀲𑀢ल": 106686,
+  "𑀲𑀢𑀟च": 106262,
+  "𑀲𑀢𑀠": 106139,
+  "𑀲𑁣𑀪": 106653,
+  "𑀳": 106331,
+  "𑀳च": 106211,
+  "𑀳चढ": 106303,
+  "𑀳चढ𑁣𑀣च": 106676,
+  "𑀳चन": 106026,
+  "𑀳चन𑀪च𑀟": 106760,
+  "𑀳चल": 106534,
+  "𑀳च𑀞𑁦": 106384,
+  "𑀳च𑀟": 105909,
+  "𑀳च𑀟च": 106043,
+  "𑀳च𑀟णच": 105951,
+  "𑀳च𑀟𑀟च𑀟": 106654,
+  "𑀳च𑀟𑀢": 106401,
+  "𑀳च𑀠": 105894,
+  "𑀳च𑀠च": 106749,
+  "𑀳च𑀠च𑀪": 106302,
+  "𑀳च𑀠न": 105902,
+  "𑀳च𑀠न𑀟": 106664,
+  "𑀳च𑀠𑀢": 105887,
+  "𑀳च𑀢": 106543,
+  "𑀳च𑀪": 106743,
+  "𑀳न": 106714,
+  "𑀳न𑀞च": 106346,
+  "𑀳न𑀟": 106056,
+  "𑀳न𑀟च": 106708,
+  "𑀳न𑀟च𑀟": 106379,
+  "𑀳𑀢ण": 106780,
+  "𑀳𑀢णच𑀳च": 106602,
+  "𑀳𑀫": 106422,
+  "𑀳𑀫च": 106305,
+  "𑀳𑀫च𑀪𑀢": 105938,
+  "𑀳𑀫च𑀲": 106309,
+  "𑀳𑀫नबच": 106063,
+  "𑀳𑀫नबचढच𑀟": 106446,
+  "𑀳𑀫𑀢": 106123,
+  "𑀳𑀫𑀢बच": 106702,
+  "𑀳𑀫𑀢𑀟𑁦": 106394,
+  "𑀳𑀫𑀢𑀪": 106650,
+  "𑀳𑀫𑁦": 106088,
+  "𑀳𑀫𑁦𑀞च𑀪": 106155,
+  "𑀳𑀫𑁦𑀞च𑀪च": 106316,
+  "𑀳𑀫𑁦𑀞च𑀪च𑀪": 106314,
+  "𑀳𑀫𑁦𑀞च𑀪न": 106636,
+  "𑀳𑁣": 106244,
+  "𑀳𑁦": 105946,
+  "𑁢": 105919,
+  "𑁣": 106125,
+  "𑁣𑀞": 106017,
+  "𑁣𑀲": 106245,
+  "𑁤": 106431,
+  "𑁥": 106424,
+  "𑁦": 106501
+}

last-checkpoint/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 106804
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7b60a28934db5de15edd4b9af17a8e9a1a613be4aceb5b87391523e3de406d
+size 672306188

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fed01eb4bb307d16e1a3272e96fbd213d82ebddc8f4e6afa3d4a9bbf4c09b1d
+size 1344733434

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdeb682a8898e3848e8e66378d3969d13e44b8b0f8f6b725f583a34797210a6
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44c59300d2d7f1a454fae0e4066f6b6797dd30a81acb9effd90e8eed3ea9e7e
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,337 @@
+{
+  "best_metric": 0.827338266658216,
+  "best_model_checkpoint": "./results/checkpoint-456",
+  "epoch": 19.0,
+  "eval_steps": 500,
+  "global_step": 456,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.450119972229004,
+      "learning_rate": 9.5e-06,
+      "loss": 1.5028,
+      "step": 24
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.38772036474164134,
+      "eval_loss": 1.346899151802063,
+      "eval_runtime": 0.1331,
+      "eval_samples_per_second": 1637.312,
+      "eval_steps_per_second": 30.042,
+      "step": 24
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.728583335876465,
+      "learning_rate": 9e-06,
+      "loss": 1.2709,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.421720746842489,
+      "eval_loss": 1.1574269533157349,
+      "eval_runtime": 0.0998,
+      "eval_samples_per_second": 2183.766,
+      "eval_steps_per_second": 40.069,
+      "step": 48
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.520730018615723,
+      "learning_rate": 8.5e-06,
+      "loss": 1.0793,
+      "step": 72
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.5100182149362478,
+      "eval_loss": 0.9754979610443115,
+      "eval_runtime": 0.0959,
+      "eval_samples_per_second": 2274.042,
+      "eval_steps_per_second": 41.726,
+      "step": 72
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.030355930328369,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9111,
+      "step": 96
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6386053201801735,
+      "eval_loss": 0.8359459638595581,
+      "eval_runtime": 0.096,
+      "eval_samples_per_second": 2270.214,
+      "eval_steps_per_second": 41.655,
+      "step": 96
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.342397689819336,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7795,
+      "step": 120
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.6719327398318995,
+      "eval_loss": 0.7689192295074463,
+      "eval_runtime": 0.0959,
+      "eval_samples_per_second": 2272.996,
+      "eval_steps_per_second": 41.706,
+      "step": 120
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 7.117249488830566,
+      "learning_rate": 7e-06,
+      "loss": 0.6623,
+      "step": 144
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.7363490153785023,
+      "eval_loss": 0.6683973670005798,
+      "eval_runtime": 0.1008,
+      "eval_samples_per_second": 2163.547,
+      "eval_steps_per_second": 39.698,
+      "step": 144
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 5.1266303062438965,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 0.5661,
+      "step": 168
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.7721861083416417,
+      "eval_loss": 0.6161485314369202,
+      "eval_runtime": 0.0971,
+      "eval_samples_per_second": 2243.984,
+      "eval_steps_per_second": 41.174,
+      "step": 168
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.100093364715576,
+      "learning_rate": 6e-06,
+      "loss": 0.4879,
+      "step": 192
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1": 0.7929782861547567,
+      "eval_loss": 0.5681259632110596,
+      "eval_runtime": 0.0977,
+      "eval_samples_per_second": 2230.333,
+      "eval_steps_per_second": 40.924,
+      "step": 192
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.375860691070557,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.4076,
+      "step": 216
+    },
+    {
+      "epoch": 9.0,
+      "eval_f1": 0.7979355926308811,
+      "eval_loss": 0.5458353161811829,
+      "eval_runtime": 0.0962,
+      "eval_samples_per_second": 2265.798,
+      "eval_steps_per_second": 41.574,
+      "step": 216
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 5.850133419036865,
+      "learning_rate": 5e-06,
+      "loss": 0.359,
+      "step": 240
+    },
+    {
+      "epoch": 10.0,
+      "eval_f1": 0.8038855056192519,
+      "eval_loss": 0.5337401032447815,
+      "eval_runtime": 0.0993,
+      "eval_samples_per_second": 2194.426,
+      "eval_steps_per_second": 40.265,
+      "step": 240
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 5.326167106628418,
+      "learning_rate": 4.5e-06,
+      "loss": 0.3049,
+      "step": 264
+    },
+    {
+      "epoch": 11.0,
+      "eval_f1": 0.808985274271652,
+      "eval_loss": 0.5208148956298828,
+      "eval_runtime": 0.0986,
+      "eval_samples_per_second": 2210.709,
+      "eval_steps_per_second": 40.563,
+      "step": 264
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 4.419217109680176,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.2707,
+      "step": 288
+    },
+    {
+      "epoch": 12.0,
+      "eval_f1": 0.7915964367931138,
+      "eval_loss": 0.5140932202339172,
+      "eval_runtime": 0.1131,
+      "eval_samples_per_second": 1928.281,
+      "eval_steps_per_second": 35.381,
+      "step": 288
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 3.2652978897094727,
+      "learning_rate": 3.5e-06,
+      "loss": 0.2426,
+      "step": 312
+    },
+    {
+      "epoch": 13.0,
+      "eval_f1": 0.7960978274579872,
+      "eval_loss": 0.5064918398857117,
+      "eval_runtime": 0.0963,
+      "eval_samples_per_second": 2262.854,
+      "eval_steps_per_second": 41.52,
+      "step": 312
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 8.18807315826416,
+      "learning_rate": 3e-06,
+      "loss": 0.2111,
+      "step": 336
+    },
+    {
+      "epoch": 14.0,
+      "eval_f1": 0.8024928631739778,
+      "eval_loss": 0.5025272965431213,
+      "eval_runtime": 0.1145,
+      "eval_samples_per_second": 1904.663,
+      "eval_steps_per_second": 34.948,
+      "step": 336
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 3.970165491104126,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1919,
+      "step": 360
+    },
+    {
+      "epoch": 15.0,
+      "eval_f1": 0.8067770829812405,
+      "eval_loss": 0.5004199147224426,
+      "eval_runtime": 0.0966,
+      "eval_samples_per_second": 2257.346,
+      "eval_steps_per_second": 41.419,
+      "step": 360
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 6.731950283050537,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1764,
+      "step": 384
+    },
+    {
+      "epoch": 16.0,
+      "eval_f1": 0.8175947589100725,
+      "eval_loss": 0.4881379008293152,
+      "eval_runtime": 0.0953,
+      "eval_samples_per_second": 2287.302,
+      "eval_steps_per_second": 41.969,
+      "step": 384
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 3.039834976196289,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1694,
+      "step": 408
+    },
+    {
+      "epoch": 17.0,
+      "eval_f1": 0.8178525944285818,
+      "eval_loss": 0.49215319752693176,
+      "eval_runtime": 0.1114,
+      "eval_samples_per_second": 1956.081,
+      "eval_steps_per_second": 35.891,
+      "step": 408
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 5.969228744506836,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.155,
+      "step": 432
+    },
+    {
+      "epoch": 18.0,
+      "eval_f1": 0.8217110120593946,
+      "eval_loss": 0.4937782883644104,
+      "eval_runtime": 0.0976,
+      "eval_samples_per_second": 2232.832,
+      "eval_steps_per_second": 40.969,
+      "step": 432
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 3.987272262573242,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.147,
+      "step": 456
+    },
+    {
+      "epoch": 19.0,
+      "eval_f1": 0.827338266658216,
+      "eval_loss": 0.4907718598842621,
+      "eval_runtime": 0.096,
+      "eval_samples_per_second": 2269.814,
+      "eval_steps_per_second": 41.648,
+      "step": 456
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 711531069926808.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8de40f27c74c1baf574f62e81d0dc7e9ff066d1a50a2ab5bf7d54ee24164f8a
+size 5112