Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [indobenchmark/indobert-base-p2](https://huggingface.co/indobenchmark/indobert-base-p2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.0329
-- Validation Loss: 2.2126
-- Epoch: 4
+- Train Loss: 2.1819
+- Validation Loss: 2.0387
+- Epoch: 0
 
 ## Model description
 
@@ -35,18 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 10180, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 20360, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.2803     | 2.0416          | 0     |
-| 1.6753     | 2.0023          | 1     |
-| 1.3907     | 2.0238          | 2     |
-| 1.1759     | 2.1245          | 3     |
-| 1.0329     | 2.2126          | 4     |
+| 2.1819     | 2.0387          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a7fb8d56223a9aa7c310afd909b024bf4bd7ba2e87e005c5b1f5e12017f708
+oid sha256:9d7dff97a8fc8853e05e7f855d517b6b88ae72016c0aa374ff56b9eb4f77596f
 size 495678480

tokenizer.json

@@ -29991,173 +29991,695 @@
       "untunglah": 29829,
       "ditempelkan": 29830,
       "keakuratan": 29831,
-      "##a": 29832,
-      "##n": 29833,
-      "##i": 29834,
-      "##e": 29835,
-      "##t": 29836,
-      "##r": 29837,
-      "##u": 29838,
-      "##k": 29839,
-      "##s": 29840,
-      "##m": 29841,
-      "##d": 29842,
-      "##g": 29843,
-      "##l": 29844,
-      "##p": 29845,
-      "##b": 29846,
-      "##h": 29847,
-      "##o": 29848,
-      "##y": 29849,
-      "##j": 29850,
-      "##c": 29851,
-      "##w": 29852,
-      "##f": 29853,
-      "##0": 29854,
-      "##1": 29855,
-      "##2": 29856,
-      "##v": 29857,
-      "##3": 29858,
-      "##5": 29859,
-      "##4": 29860,
-      "##9": 29861,
-      "##8": 29862,
-      "##6": 29863,
-      "##7": 29864,
-      "##z": 29865,
-      "##x": 29866,
-      "##”": 29867,
-      "##“": 29868,
-      "##q": 29869,
-      "##–": 29870,
-      "##’": 29871,
-      "##‘": 29872,
-      "##»": 29873,
-      "[UNUSED_0]": 29874,
-      "[UNUSED_1]": 29875,
-      "[UNUSED_2]": 29876,
-      "[UNUSED_3]": 29877,
-      "[UNUSED_4]": 29878,
-      "[UNUSED_5]": 29879,
-      "[UNUSED_6]": 29880,
-      "[UNUSED_7]": 29881,
-      "[UNUSED_8]": 29882,
-      "[UNUSED_9]": 29883,
-      "[UNUSED_10]": 29884,
-      "[UNUSED_11]": 29885,
-      "[UNUSED_12]": 29886,
-      "[UNUSED_13]": 29887,
-      "[UNUSED_14]": 29888,
-      "[UNUSED_15]": 29889,
-      "[UNUSED_16]": 29890,
-      "[UNUSED_17]": 29891,
-      "[UNUSED_18]": 29892,
-      "[UNUSED_19]": 29893,
-      "[UNUSED_20]": 29894,
-      "[UNUSED_21]": 29895,
-      "[UNUSED_22]": 29896,
-      "[UNUSED_23]": 29897,
-      "[UNUSED_24]": 29898,
-      "[UNUSED_25]": 29899,
-      "[UNUSED_26]": 29900,
-      "[UNUSED_27]": 29901,
-      "[UNUSED_28]": 29902,
-      "[UNUSED_29]": 29903,
-      "[UNUSED_30]": 29904,
-      "[UNUSED_31]": 29905,
-      "[UNUSED_32]": 29906,
-      "[UNUSED_33]": 29907,
-      "[UNUSED_34]": 29908,
-      "[UNUSED_35]": 29909,
-      "[UNUSED_36]": 29910,
-      "[UNUSED_37]": 29911,
-      "[UNUSED_38]": 29912,
-      "[UNUSED_39]": 29913,
-      "[UNUSED_40]": 29914,
-      "[UNUSED_41]": 29915,
-      "[UNUSED_42]": 29916,
-      "[UNUSED_43]": 29917,
-      "[UNUSED_44]": 29918,
-      "[UNUSED_45]": 29919,
-      "[UNUSED_46]": 29920,
-      "[UNUSED_47]": 29921,
-      "[UNUSED_48]": 29922,
-      "[UNUSED_49]": 29923,
-      "[UNUSED_50]": 29924,
-      "[UNUSED_51]": 29925,
-      "[UNUSED_52]": 29926,
-      "[UNUSED_53]": 29927,
-      "[UNUSED_54]": 29928,
-      "[UNUSED_55]": 29929,
-      "[UNUSED_56]": 29930,
-      "[UNUSED_57]": 29931,
-      "[UNUSED_58]": 29932,
-      "[UNUSED_59]": 29933,
-      "[UNUSED_60]": 29934,
-      "!": 29935,
-      "\"": 29936,
-      "#": 29937,
-      "$": 29938,
-      "%": 29939,
-      "&": 29940,
-      "'": 29941,
-      "(": 29942,
-      ")": 29943,
-      "*": 29944,
-      "+": 29945,
-      ",": 29946,
-      "-": 29947,
-      ".": 29948,
-      "/": 29949,
-      ":": 29950,
-      ";": 29951,
-      "<": 29952,
-      "=": 29953,
-      ">": 29954,
-      "?": 29955,
-      "@": 29956,
-      "[": 29957,
-      "\\": 29958,
-      "]": 29959,
-      "^": 29960,
-      "_": 29961,
-      "`": 29962,
-      "{": 29963,
-      "|": 29964,
-      "}": 29965,
-      "~": 29966,
-      "##!": 29967,
-      "##\"": 29968,
-      "###": 29969,
-      "##$": 29970,
-      "##%": 29971,
-      "##&": 29972,
-      "##'": 29973,
-      "##(": 29974,
-      "##)": 29975,
-      "##*": 29976,
-      "##+": 29977,
-      "##,": 29978,
-      "##-": 29979,
-      "##.": 29980,
-      "##/": 29981,
-      "##:": 29982,
-      "##;": 29983,
-      "##<": 29984,
-      "##=": 29985,
-      "##>": 29986,
-      "##?": 29987,
-      "##@": 29988,
-      "##[": 29989,
-      "##\\": 29990,
-      "##]": 29991,
-      "##^": 29992,
-      "##_": 29993,
-      "##`": 29994,
-      "##{": 29995,
-      "##|": 29996,
-      "##}": 29997,
-      "##~": 29998
+      "pocket": 29832,
+      "kejati": 29833,
+      "broadcast": 29834,
+      "gendong": 29835,
+      "##edikasi": 29836,
+      "inih": 29837,
+      "pembelajarannya": 29838,
+      "terlena": 29839,
+      "panjatkan": 29840,
+      "0853": 29841,
+      "trainee": 29842,
+      "##’”": 29843,
+      "##like": 29844,
+      "##iburan": 29845,
+      "ketatan": 29846,
+      "dibentuknya": 29847,
+      "kemendagri": 29848,
+      "bicaranya": 29849,
+      "tmm": 29850,
+      "##mulai": 29851,
+      "##terusan": 29852,
+      "keroncong": 29853,
+      "kresna": 29854,
+      "membenc": 29855,
+      "ditawari": 29856,
+      "akhiri": 29857,
+      "##ovi": 29858,
+      "practice": 29859,
+      "bermodal": 29860,
+      "##hyuk": 29861,
+      "sequ": 29862,
+      "melakoni": 29863,
+      "tergelincir": 29864,
+      "##oshima": 29865,
+      "##atm": 29866,
+      "##ongga": 29867,
+      "nani": 29868,
+      "##peralatan": 29869,
+      "kudak": 29870,
+      "months": 29871,
+      "luxor": 29872,
+      "dynamic": 29873,
+      "##angsit": 29874,
+      "managemen": 29875,
+      "##inyl": 29876,
+      "##awen": 29877,
+      "pim": 29878,
+      "irw": 29879,
+      "dhuha": 29880,
+      "kasihnya": 29881,
+      "terjemah": 29882,
+      "##siswa": 29883,
+      "##195": 29884,
+      "dikocok": 29885,
+      "demokratisasi": 29886,
+      "tempurung": 29887,
+      "##204": 29888,
+      "##icle": 29889,
+      "diajari": 29890,
+      "kesekian": 29891,
+      "##penerimaan": 29892,
+      "totalitas": 29893,
+      "pengenc": 29894,
+      "mapolres": 29895,
+      "semalaman": 29896,
+      "siram": 29897,
+      "antibiotika": 29898,
+      "ditek": 29899,
+      "terkel": 29900,
+      "menugaskan": 29901,
+      "jik": 29902,
+      "terdapatnya": 29903,
+      "crow": 29904,
+      "terhibur": 29905,
+      "jef": 29906,
+      "sng": 29907,
+      "monaco": 29908,
+      "dipilihnya": 29909,
+      "dikdas": 29910,
+      "hacking": 29911,
+      "sebar": 29912,
+      "terbentur": 29913,
+      "nadia": 29914,
+      "bermitra": 29915,
+      "silva": 29916,
+      "munkar": 29917,
+      "fine": 29918,
+      "berpe": 29919,
+      "##ising": 29920,
+      "gui": 29921,
+      "pemantau": 29922,
+      "##ewed": 29923,
+      "##ifilm": 29924,
+      "##untak": 29925,
+      "distorsi": 29926,
+      "##umin": 29927,
+      "stt": 29928,
+      "siput": 29929,
+      "seattle": 29930,
+      "intelligence": 29931,
+      "##alaikan": 29932,
+      "konj": 29933,
+      "sz": 29934,
+      "usu": 29935,
+      "diteng": 29936,
+      "triang": 29937,
+      "lengkuas": 29938,
+      "merebak": 29939,
+      "zainuddin": 29940,
+      "died": 29941,
+      "dagangannya": 29942,
+      "riasan": 29943,
+      "pembuatnya": 29944,
+      "coal": 29945,
+      "##hitung": 29946,
+      "sedim": 29947,
+      "lanka": 29948,
+      "dpw": 29949,
+      "##jus": 29950,
+      "##pajak": 29951,
+      "cakar": 29952,
+      "enkripsi": 29953,
+      "sindiran": 29954,
+      "##otok": 29955,
+      "##anamun": 29956,
+      "##jie": 29957,
+      "vintage": 29958,
+      "penjahit": 29959,
+      "##engertian": 29960,
+      "sungaisungai": 29961,
+      "inventarisasi": 29962,
+      "acces": 29963,
+      "diformulasikan": 29964,
+      "substansial": 29965,
+      "jiwaku": 29966,
+      "ibnul": 29967,
+      "septic": 29968,
+      "sutrisno": 29969,
+      "disuatu": 29970,
+      "empu": 29971,
+      "peminjam": 29972,
+      "berpergian": 29973,
+      "##sehat": 29974,
+      "luwak": 29975,
+      "##umbai": 29976,
+      "diplomat": 29977,
+      "tergeletak": 29978,
+      "##aselengkapnya": 29979,
+      "teolog": 29980,
+      "##ublish": 29981,
+      "##zair": 29982,
+      "##isensi": 29983,
+      "##untahkan": 29984,
+      "##indag": 29985,
+      "korpri": 29986,
+      "kham": 29987,
+      "rico": 29988,
+      "berdamai": 29989,
+      "berkontraksi": 29990,
+      "hajatan": 29991,
+      "menyib": 29992,
+      "##ampan": 29993,
+      "##website": 29994,
+      "damaskus": 29995,
+      "batch": 29996,
+      "steering": 29997,
+      "##aviolet": 29998,
+      "kebangk": 29999,
+      "notes": 30000,
+      "seperlunya": 30001,
+      "golok": 30002,
+      "##aine": 30003,
+      "cembung": 30004,
+      "jamil": 30005,
+      "probiotik": 30006,
+      "magazine": 30007,
+      "##ied": 30008,
+      "menkeu": 30009,
+      "menyuburkan": 30010,
+      "##kia": 30011,
+      "pasai": 30012,
+      "konsili": 30013,
+      "polio": 30014,
+      "tracking": 30015,
+      "nos": 30016,
+      "terbentuklah": 30017,
+      "pny": 30018,
+      "banyuasin": 30019,
+      "diinv": 30020,
+      "ketukan": 30021,
+      "##sejak": 30022,
+      "lagis": 30023,
+      "##unggunya": 30024,
+      "dicirikan": 30025,
+      "kelumpuhan": 30026,
+      "baka": 30027,
+      "raperda": 30028,
+      "##500000": 30029,
+      "together": 30030,
+      "shirt": 30031,
+      "##antarkan": 30032,
+      "181": 30033,
+      "karyakaryanya": 30034,
+      "##vs": 30035,
+      "cepu": 30036,
+      "siska": 30037,
+      "##onot": 30038,
+      "ketangg": 30039,
+      "restrukturisasi": 30040,
+      "pasaman": 30041,
+      "playa": 30042,
+      "306": 30043,
+      "brus": 30044,
+      "pail": 30045,
+      "klausa": 30046,
+      "strain": 30047,
+      "totalnya": 30048,
+      "gayanya": 30049,
+      "selayar": 30050,
+      "blink": 30051,
+      "songo": 30052,
+      "##nesia": 30053,
+      "karnaval": 30054,
+      "perpanjang": 30055,
+      "pemodal": 30056,
+      "tf": 30057,
+      "##eklik": 30058,
+      "inklusif": 30059,
+      "backpacker": 30060,
+      "##vania": 30061,
+      "ngangg": 30062,
+      "multikultural": 30063,
+      "tercakup": 30064,
+      "penembak": 30065,
+      "turuntemurun": 30066,
+      "sentimeter": 30067,
+      "##politik": 30068,
+      "samad": 30069,
+      "waria": 30070,
+      "ferdinand": 30071,
+      "diadili": 30072,
+      "##ekin": 30073,
+      "wav": 30074,
+      "##purukan": 30075,
+      "darmawan": 30076,
+      "ajian": 30077,
+      "##450": 30078,
+      "maskot": 30079,
+      "elegant": 30080,
+      "##tawakan": 30081,
+      "sergio": 30082,
+      "kerohanian": 30083,
+      "##yatt": 30084,
+      "yeo": 30085,
+      "prototipe": 30086,
+      "smok": 30087,
+      "dikawasan": 30088,
+      "marcel": 30089,
+      "representatif": 30090,
+      "##148": 30091,
+      "nepal": 30092,
+      "1921": 30093,
+      "nyobain": 30094,
+      "tense": 30095,
+      "gundukan": 30096,
+      "mengelak": 30097,
+      "##iak": 30098,
+      "##active": 30099,
+      "##anannya": 30100,
+      "fg": 30101,
+      "kemasannya": 30102,
+      "sitoplasma": 30103,
+      "kehatihat": 30104,
+      "lekuk": 30105,
+      "diskriminatif": 30106,
+      "##ucker": 30107,
+      "hpnya": 30108,
+      "bayan": 30109,
+      "cindy": 30110,
+      "neder": 30111,
+      "dihari": 30112,
+      "laj": 30113,
+      "words": 30114,
+      "iraq": 30115,
+      "canopy": 30116,
+      "cekung": 30117,
+      "hasi": 30118,
+      "intelegensi": 30119,
+      "menangkapnya": 30120,
+      "soem": 30121,
+      "suwar": 30122,
+      "##akers": 30123,
+      "answer": 30124,
+      "antibakteri": 30125,
+      "perry": 30126,
+      "garment": 30127,
+      "##177": 30128,
+      "##156": 30129,
+      "##tibkan": 30130,
+      "targetnya": 30131,
+      "menyiram": 30132,
+      "manokwari": 30133,
+      "maliki": 30134,
+      "pedro": 30135,
+      "##eut": 30136,
+      "menghebohkan": 30137,
+      "belajarmengajar": 30138,
+      "notepad": 30139,
+      "penghapus": 30140,
+      "##angag": 30141,
+      "bersiaplah": 30142,
+      "saba": 30143,
+      "knapa": 30144,
+      "penataran": 30145,
+      "bened": 30146,
+      "berkarat": 30147,
+      "##mag": 30148,
+      "tahunya": 30149,
+      "jacob": 30150,
+      "ortodoks": 30151,
+      "revo": 30152,
+      "memandangnya": 30153,
+      "##mia": 30154,
+      "##aptek": 30155,
+      "maap": 30156,
+      "lamin": 30157,
+      "amn": 30158,
+      "mencurigai": 30159,
+      "lalunya": 30160,
+      "limpa": 30161,
+      "projector": 30162,
+      "##ader": 30163,
+      "salemba": 30164,
+      "wikimedia": 30165,
+      "##roduk": 30166,
+      "tersiksa": 30167,
+      "rsbi": 30168,
+      "dahan": 30169,
+      "karaw": 30170,
+      "baduy": 30171,
+      "lanjuti": 30172,
+      "##empak": 30173,
+      "##iskin": 30174,
+      "fidusia": 30175,
+      "hambahamb": 30176,
+      "propinsik": 30177,
+      "perasaanku": 30178,
+      "seken": 30179,
+      "responsibility": 30180,
+      "wizard": 30181,
+      "permendiknas": 30182,
+      "dob": 30183,
+      "drh": 30184,
+      "bersepakat": 30185,
+      "mpasi": 30186,
+      "raksa": 30187,
+      "pancake": 30188,
+      "edison": 30189,
+      "fore": 30190,
+      "tersayang": 30191,
+      "pasiennya": 30192,
+      "rij": 30193,
+      "##itulah": 30194,
+      "##emonstrasikan": 30195,
+      "direnovasi": 30196,
+      "destin": 30197,
+      "terbu": 30198,
+      "penggalan": 30199,
+      "signifikansi": 30200,
+      "implementasinya": 30201,
+      "##oor": 30202,
+      "rindang": 30203,
+      "demonstran": 30204,
+      "sutar": 30205,
+      "percab": 30206,
+      "terisolasi": 30207,
+      "248": 30208,
+      "ancam": 30209,
+      "informan": 30210,
+      "##hhhhh": 30211,
+      "atlas": 30212,
+      "##ibarkan": 30213,
+      "lahiriah": 30214,
+      "ruangruang": 30215,
+      "guan": 30216,
+      "thunder": 30217,
+      "febri": 30218,
+      "ldr": 30219,
+      "tusukan": 30220,
+      "prudential": 30221,
+      "##wahy": 30222,
+      "bahtera": 30223,
+      "lempengan": 30224,
+      "adiktif": 30225,
+      "bolt": 30226,
+      "##logger": 30227,
+      "##even": 30228,
+      "##osida": 30229,
+      "mengenyam": 30230,
+      "diagnostik": 30231,
+      "##esse": 30232,
+      "berlabuh": 30233,
+      "##sbook": 30234,
+      "##uncil": 30235,
+      "sulteng": 30236,
+      "bengawan": 30237,
+      "##umandangkan": 30238,
+      "begin": 30239,
+      "##haha": 30240,
+      "nabin": 30241,
+      "dikag": 30242,
+      "ultraviolet": 30243,
+      "kelabu": 30244,
+      "diharap": 30245,
+      "##abrak": 30246,
+      "spongebob": 30247,
+      "vivan": 30248,
+      "wax": 30249,
+      "natsir": 30250,
+      "memasukkannya": 30251,
+      "”“": 30252,
+      "keamp": 30253,
+      "kesetimbangan": 30254,
+      "seluasluasnya": 30255,
+      "##caj": 30256,
+      "##test": 30257,
+      "pedagog": 30258,
+      "dilarikan": 30259,
+      "##eberapa": 30260,
+      "rumania": 30261,
+      "paska": 30262,
+      "dedaunan": 30263,
+      "arak": 30264,
+      "merevisi": 30265,
+      "keselarasan": 30266,
+      "epoxy": 30267,
+      "andika": 30268,
+      "##opus": 30269,
+      "lemparan": 30270,
+      "zal": 30271,
+      "pamrih": 30272,
+      "trigliserida": 30273,
+      "##estro": 30274,
+      "telentang": 30275,
+      "##overs": 30276,
+      "##idakt": 30277,
+      "kaliurang": 30278,
+      "pls": 30279,
+      "shalatnya": 30280,
+      "silaturahim": 30281,
+      "austin": 30282,
+      "amor": 30283,
+      "homes": 30284,
+      "tasik": 30285,
+      "korang": 30286,
+      "stam": 30287,
+      "kondisikondisi": 30288,
+      "dises": 30289,
+      "jengkol": 30290,
+      "dham": 30291,
+      "europ": 30292,
+      "persembahkan": 30293,
+      "eyel": 30294,
+      "heks": 30295,
+      "ilah": 30296,
+      "polik": 30297,
+      "temantemanku": 30298,
+      "handling": 30299,
+      "##bangsa": 30300,
+      "lipid": 30301,
+      "terobsesi": 30302,
+      "jababeka": 30303,
+      "mereview": 30304,
+      "akhiran": 30305,
+      "dirgantara": 30306,
+      "beny": 30307,
+      "bejana": 30308,
+      "tamatan": 30309,
+      "hongaria": 30310,
+      "memikirkannya": 30311,
+      "anast": 30312,
+      "menjenguk": 30313,
+      "roberto": 30314,
+      "holland": 30315,
+      "achiev": 30316,
+      "kepo": 30317,
+      "##umulih": 30318,
+      "setu": 30319,
+      "##esk": 30320,
+      "ngl": 30321,
+      "membawah": 30322,
+      "merchant": 30323,
+      "keterpurukan": 30324,
+      "diproyeksikan": 30325,
+      "kwh": 30326,
+      "##turun": 30327,
+      "barak": 30328,
+      "ppki": 30329,
+      "##ratnya": 30330,
+      "mencipta": 30331,
+      "menasehati": 30332,
+      "walatra": 30333,
+      "gugusan": 30334,
+      "327": 30335,
+      "hsd": 30336,
+      "azan": 30337,
+      "cleans": 30338,
+      "beritahukan": 30339,
+      "mempersoalkan": 30340,
+      "muncrat": 30341,
+      "##meningkatkan": 30342,
+      "disetor": 30343,
+      "##ambak": 30344,
+      "kalibata": 30345,
+      "nba": 30346,
+      "lailat": 30347,
+      "gonc": 30348,
+      "berseragam": 30349,
+      "258": 30350,
+      "1932": 30351,
+      "trem": 30352,
+      "##ucuk": 30353,
+      "##a": 30354,
+      "##n": 30355,
+      "##i": 30356,
+      "##e": 30357,
+      "##t": 30358,
+      "##r": 30359,
+      "##u": 30360,
+      "##k": 30361,
+      "##s": 30362,
+      "##m": 30363,
+      "##d": 30364,
+      "##g": 30365,
+      "##l": 30366,
+      "##p": 30367,
+      "##b": 30368,
+      "##h": 30369,
+      "##o": 30370,
+      "##y": 30371,
+      "##j": 30372,
+      "##c": 30373,
+      "##w": 30374,
+      "##f": 30375,
+      "##0": 30376,
+      "##1": 30377,
+      "##2": 30378,
+      "##v": 30379,
+      "##3": 30380,
+      "##5": 30381,
+      "##4": 30382,
+      "##9": 30383,
+      "##8": 30384,
+      "##6": 30385,
+      "##7": 30386,
+      "##z": 30387,
+      "##x": 30388,
+      "##”": 30389,
+      "##“": 30390,
+      "##q": 30391,
+      "##–": 30392,
+      "##’": 30393,
+      "##‘": 30394,
+      "##»": 30395,
+      "[UNUSED_0]": 30396,
+      "[UNUSED_1]": 30397,
+      "[UNUSED_2]": 30398,
+      "[UNUSED_3]": 30399,
+      "[UNUSED_4]": 30400,
+      "[UNUSED_5]": 30401,
+      "[UNUSED_6]": 30402,
+      "[UNUSED_7]": 30403,
+      "[UNUSED_8]": 30404,
+      "[UNUSED_9]": 30405,
+      "[UNUSED_10]": 30406,
+      "[UNUSED_11]": 30407,
+      "[UNUSED_12]": 30408,
+      "[UNUSED_13]": 30409,
+      "[UNUSED_14]": 30410,
+      "[UNUSED_15]": 30411,
+      "[UNUSED_16]": 30412,
+      "[UNUSED_17]": 30413,
+      "[UNUSED_18]": 30414,
+      "[UNUSED_19]": 30415,
+      "[UNUSED_20]": 30416,
+      "[UNUSED_21]": 30417,
+      "[UNUSED_22]": 30418,
+      "[UNUSED_23]": 30419,
+      "[UNUSED_24]": 30420,
+      "[UNUSED_25]": 30421,
+      "[UNUSED_26]": 30422,
+      "[UNUSED_27]": 30423,
+      "[UNUSED_28]": 30424,
+      "[UNUSED_29]": 30425,
+      "[UNUSED_30]": 30426,
+      "[UNUSED_31]": 30427,
+      "[UNUSED_32]": 30428,
+      "[UNUSED_33]": 30429,
+      "[UNUSED_34]": 30430,
+      "[UNUSED_35]": 30431,
+      "[UNUSED_36]": 30432,
+      "[UNUSED_37]": 30433,
+      "[UNUSED_38]": 30434,
+      "[UNUSED_39]": 30435,
+      "[UNUSED_40]": 30436,
+      "[UNUSED_41]": 30437,
+      "[UNUSED_42]": 30438,
+      "[UNUSED_43]": 30439,
+      "[UNUSED_44]": 30440,
+      "[UNUSED_45]": 30441,
+      "[UNUSED_46]": 30442,
+      "[UNUSED_47]": 30443,
+      "[UNUSED_48]": 30444,
+      "[UNUSED_49]": 30445,
+      "[UNUSED_50]": 30446,
+      "[UNUSED_51]": 30447,
+      "[UNUSED_52]": 30448,
+      "[UNUSED_53]": 30449,
+      "[UNUSED_54]": 30450,
+      "[UNUSED_55]": 30451,
+      "[UNUSED_56]": 30452,
+      "[UNUSED_57]": 30453,
+      "[UNUSED_58]": 30454,
+      "[UNUSED_59]": 30455,
+      "[UNUSED_60]": 30456,
+      "!": 30457,
+      "\"": 30458,
+      "#": 30459,
+      "$": 30460,
+      "%": 30461,
+      "&": 30462,
+      "'": 30463,
+      "(": 30464,
+      ")": 30465,
+      "*": 30466,
+      "+": 30467,
+      ",": 30468,
+      "-": 30469,
+      ".": 30470,
+      "/": 30471,
+      ":": 30472,
+      ";": 30473,
+      "<": 30474,
+      "=": 30475,
+      ">": 30476,
+      "?": 30477,
+      "@": 30478,
+      "[": 30479,
+      "\\": 30480,
+      "]": 30481,
+      "^": 30482,
+      "_": 30483,
+      "`": 30484,
+      "{": 30485,
+      "|": 30486,
+      "}": 30487,
+      "~": 30488,
+      "##!": 30489,
+      "##\"": 30490,
+      "###": 30491,
+      "##$": 30492,
+      "##%": 30493,
+      "##&": 30494,
+      "##'": 30495,
+      "##(": 30496,
+      "##)": 30497,
+      "##*": 30498,
+      "##+": 30499,
+      "##,": 30500,
+      "##-": 30501,
+      "##.": 30502,
+      "##/": 30503,
+      "##:": 30504,
+      "##;": 30505,
+      "##<": 30506,
+      "##=": 30507,
+      "##>": 30508,
+      "##?": 30509,
+      "##@": 30510,
+      "##[": 30511,
+      "##\\": 30512,
+      "##]": 30513,
+      "##^": 30514,
+      "##_": 30515,
+      "##`": 30516,
+      "##{": 30517,
+      "##|": 30518,
+      "##}": 30519,
+      "##~": 30520
     }
   }
 }

tokenizer_config.json

@@ -4,11 +4,11 @@
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "indobenchmark/indobert-lite-base-p2",
+  "name_or_path": "indobenchmark/indobert-base-p2",
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-lite-base-p2/snapshots/e65a8f16078d5e4622e1df53204c2acd12e3074f/special_tokens_map.json",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-base-p2/snapshots/94b4e0a82081fa57f227fcc2024d1ea89b57ac1f/special_tokens_map.json",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",

vocab.txt

@@ -29830,6 +29830,528 @@ pokja
 untunglah
 ditempelkan
 keakuratan
+pocket
+kejati
+broadcast
+gendong
+##edikasi
+inih
+pembelajarannya
+terlena
+panjatkan
+0853
+trainee
+##’”
+##like
+##iburan
+ketatan
+dibentuknya
+kemendagri
+bicaranya
+tmm
+##mulai
+##terusan
+keroncong
+kresna
+membenc
+ditawari
+akhiri
+##ovi
+practice
+bermodal
+##hyuk
+sequ
+melakoni
+tergelincir
+##oshima
+##atm
+##ongga
+nani
+##peralatan
+kudak
+months
+luxor
+dynamic
+##angsit
+managemen
+##inyl
+##awen
+pim
+irw
+dhuha
+kasihnya
+terjemah
+##siswa
+##195
+dikocok
+demokratisasi
+tempurung
+##204
+##icle
+diajari
+kesekian
+##penerimaan
+totalitas
+pengenc
+mapolres
+semalaman
+siram
+antibiotika
+ditek
+terkel
+menugaskan
+jik
+terdapatnya
+crow
+terhibur
+jef
+sng
+monaco
+dipilihnya
+dikdas
+hacking
+sebar
+terbentur
+nadia
+bermitra
+silva
+munkar
+fine
+berpe
+##ising
+gui
+pemantau
+##ewed
+##ifilm
+##untak
+distorsi
+##umin
+stt
+siput
+seattle
+intelligence
+##alaikan
+konj
+sz
+usu
+diteng
+triang
+lengkuas
+merebak
+zainuddin
+died
+dagangannya
+riasan
+pembuatnya
+coal
+##hitung
+sedim
+lanka
+dpw
+##jus
+##pajak
+cakar
+enkripsi
+sindiran
+##otok
+##anamun
+##jie
+vintage
+penjahit
+##engertian
+sungaisungai
+inventarisasi
+acces
+diformulasikan
+substansial
+jiwaku
+ibnul
+septic
+sutrisno
+disuatu
+empu
+peminjam
+berpergian
+##sehat
+luwak
+##umbai
+diplomat
+tergeletak
+##aselengkapnya
+teolog
+##ublish
+##zair
+##isensi
+##untahkan
+##indag
+korpri
+kham
+rico
+berdamai
+berkontraksi
+hajatan
+menyib
+##ampan
+##website
+damaskus
+batch
+steering
+##aviolet
+kebangk
+notes
+seperlunya
+golok
+##aine
+cembung
+jamil
+probiotik
+magazine
+##ied
+menkeu
+menyuburkan
+##kia
+pasai
+konsili
+polio
+tracking
+nos
+terbentuklah
+pny
+banyuasin
+diinv
+ketukan
+##sejak
+lagis
+##unggunya
+dicirikan
+kelumpuhan
+baka
+raperda
+##500000
+together
+shirt
+##antarkan
+181
+karyakaryanya
+##vs
+cepu
+siska
+##onot
+ketangg
+restrukturisasi
+pasaman
+playa
+306
+brus
+pail
+klausa
+strain
+totalnya
+gayanya
+selayar
+blink
+songo
+##nesia
+karnaval
+perpanjang
+pemodal
+tf
+##eklik
+inklusif
+backpacker
+##vania
+ngangg
+multikultural
+tercakup
+penembak
+turuntemurun
+sentimeter
+##politik
+samad
+waria
+ferdinand
+diadili
+##ekin
+wav
+##purukan
+darmawan
+ajian
+##450
+maskot
+elegant
+##tawakan
+sergio
+kerohanian
+##yatt
+yeo
+prototipe
+smok
+dikawasan
+marcel
+representatif
+##148
+nepal
+1921
+nyobain
+tense
+gundukan
+mengelak
+##iak
+##active
+##anannya
+fg
+kemasannya
+sitoplasma
+kehatihat
+lekuk
+diskriminatif
+##ucker
+hpnya
+bayan
+cindy
+neder
+dihari
+laj
+words
+iraq
+canopy
+cekung
+hasi
+intelegensi
+menangkapnya
+soem
+suwar
+##akers
+answer
+antibakteri
+perry
+garment
+##177
+##156
+##tibkan
+targetnya
+menyiram
+manokwari
+maliki
+pedro
+##eut
+menghebohkan
+belajarmengajar
+notepad
+penghapus
+##angag
+bersiaplah
+saba
+knapa
+penataran
+bened
+berkarat
+##mag
+tahunya
+jacob
+ortodoks
+revo
+memandangnya
+##mia
+##aptek
+maap
+lamin
+amn
+mencurigai
+lalunya
+limpa
+projector
+##ader
+salemba
+wikimedia
+##roduk
+tersiksa
+rsbi
+dahan
+karaw
+baduy
+lanjuti
+##empak
+##iskin
+fidusia
+hambahamb
+propinsik
+perasaanku
+seken
+responsibility
+wizard
+permendiknas
+dob
+drh
+bersepakat
+mpasi
+raksa
+pancake
+edison
+fore
+tersayang
+pasiennya
+rij
+##itulah
+##emonstrasikan
+direnovasi
+destin
+terbu
+penggalan
+signifikansi
+implementasinya
+##oor
+rindang
+demonstran
+sutar
+percab
+terisolasi
+248
+ancam
+informan
+##hhhhh
+atlas
+##ibarkan
+lahiriah
+ruangruang
+guan
+thunder
+febri
+ldr
+tusukan
+prudential
+##wahy
+bahtera
+lempengan
+adiktif
+bolt
+##logger
+##even
+##osida
+mengenyam
+diagnostik
+##esse
+berlabuh
+##sbook
+##uncil
+sulteng
+bengawan
+##umandangkan
+begin
+##haha
+nabin
+dikag
+ultraviolet
+kelabu
+diharap
+##abrak
+spongebob
+vivan
+wax
+natsir
+memasukkannya
+”“
+keamp
+kesetimbangan
+seluasluasnya
+##caj
+##test
+pedagog
+dilarikan
+##eberapa
+rumania
+paska
+dedaunan
+arak
+merevisi
+keselarasan
+epoxy
+andika
+##opus
+lemparan
+zal
+pamrih
+trigliserida
+##estro
+telentang
+##overs
+##idakt
+kaliurang
+pls
+shalatnya
+silaturahim
+austin
+amor
+homes
+tasik
+korang
+stam
+kondisikondisi
+dises
+jengkol
+dham
+europ
+persembahkan
+eyel
+heks
+ilah
+polik
+temantemanku
+handling
+##bangsa
+lipid
+terobsesi
+jababeka
+mereview
+akhiran
+dirgantara
+beny
+bejana
+tamatan
+hongaria
+memikirkannya
+anast
+menjenguk
+roberto
+holland
+achiev
+kepo
+##umulih
+setu
+##esk
+ngl
+membawah
+merchant
+keterpurukan
+diproyeksikan
+kwh
+##turun
+barak
+ppki
+##ratnya
+mencipta
+menasehati
+walatra
+gugusan
+327
+hsd
+azan
+cleans
+beritahukan
+mempersoalkan
+muncrat
+##meningkatkan
+disetor
+##ambak
+kalibata
+nba
+lailat
+gonc
+berseragam
+258
+1932
+trem
+##ucuk
 ##a
 ##n
 ##i