liangyuant's picture
Training in progress, step 500
88c0604
{
"_name_or_path": "distilbert-base-uncased",
"activation": "gelu",
"architectures": [
"DistilBertForSequenceClassification"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10",
"11": "LABEL_11",
"12": "LABEL_12",
"13": "LABEL_13",
"14": "LABEL_14",
"15": "LABEL_15",
"16": "LABEL_16",
"17": "LABEL_17",
"18": "LABEL_18",
"19": "LABEL_19",
"20": "LABEL_20",
"21": "LABEL_21",
"22": "LABEL_22",
"23": "LABEL_23",
"24": "LABEL_24",
"25": "LABEL_25",
"26": "LABEL_26",
"27": "LABEL_27",
"28": "LABEL_28",
"29": "LABEL_29",
"30": "LABEL_30",
"31": "LABEL_31",
"32": "LABEL_32",
"33": "LABEL_33",
"34": "LABEL_34",
"35": "LABEL_35",
"36": "LABEL_36",
"37": "LABEL_37",
"38": "LABEL_38",
"39": "LABEL_39",
"40": "LABEL_40",
"41": "LABEL_41",
"42": "LABEL_42",
"43": "LABEL_43",
"44": "LABEL_44",
"45": "LABEL_45",
"46": "LABEL_46",
"47": "LABEL_47",
"48": "LABEL_48",
"49": "LABEL_49",
"50": "LABEL_50",
"51": "LABEL_51",
"52": "LABEL_52",
"53": "LABEL_53",
"54": "LABEL_54",
"55": "LABEL_55",
"56": "LABEL_56",
"57": "LABEL_57",
"58": "LABEL_58",
"59": "LABEL_59",
"60": "LABEL_60",
"61": "LABEL_61",
"62": "LABEL_62",
"63": "LABEL_63",
"64": "LABEL_64",
"65": "LABEL_65",
"66": "LABEL_66",
"67": "LABEL_67",
"68": "LABEL_68",
"69": "LABEL_69",
"70": "LABEL_70",
"71": "LABEL_71",
"72": "LABEL_72",
"73": "LABEL_73",
"74": "LABEL_74",
"75": "LABEL_75",
"76": "LABEL_76",
"77": "LABEL_77",
"78": "LABEL_78",
"79": "LABEL_79",
"80": "LABEL_80",
"81": "LABEL_81",
"82": "LABEL_82",
"83": "LABEL_83",
"84": "LABEL_84",
"85": "LABEL_85",
"86": "LABEL_86",
"87": "LABEL_87",
"88": "LABEL_88",
"89": "LABEL_89",
"90": "LABEL_90",
"91": "LABEL_91",
"92": "LABEL_92",
"93": "LABEL_93",
"94": "LABEL_94",
"95": "LABEL_95",
"96": "LABEL_96",
"97": "LABEL_97",
"98": "LABEL_98",
"99": "LABEL_99",
"100": "LABEL_100",
"101": "LABEL_101",
"102": "LABEL_102",
"103": "LABEL_103",
"104": "LABEL_104",
"105": "LABEL_105",
"106": "LABEL_106",
"107": "LABEL_107",
"108": "LABEL_108",
"109": "LABEL_109",
"110": "LABEL_110",
"111": "LABEL_111",
"112": "LABEL_112",
"113": "LABEL_113",
"114": "LABEL_114",
"115": "LABEL_115",
"116": "LABEL_116",
"117": "LABEL_117",
"118": "LABEL_118",
"119": "LABEL_119",
"120": "LABEL_120",
"121": "LABEL_121",
"122": "LABEL_122",
"123": "LABEL_123",
"124": "LABEL_124",
"125": "LABEL_125",
"126": "LABEL_126",
"127": "LABEL_127",
"128": "LABEL_128",
"129": "LABEL_129",
"130": "LABEL_130",
"131": "LABEL_131",
"132": "LABEL_132",
"133": "LABEL_133",
"134": "LABEL_134",
"135": "LABEL_135",
"136": "LABEL_136",
"137": "LABEL_137",
"138": "LABEL_138",
"139": "LABEL_139",
"140": "LABEL_140",
"141": "LABEL_141",
"142": "LABEL_142",
"143": "LABEL_143",
"144": "LABEL_144",
"145": "LABEL_145",
"146": "LABEL_146",
"147": "LABEL_147",
"148": "LABEL_148",
"149": "LABEL_149",
"150": "LABEL_150",
"151": "LABEL_151",
"152": "LABEL_152",
"153": "LABEL_153",
"154": "LABEL_154",
"155": "LABEL_155",
"156": "LABEL_156",
"157": "LABEL_157",
"158": "LABEL_158",
"159": "LABEL_159",
"160": "LABEL_160",
"161": "LABEL_161",
"162": "LABEL_162",
"163": "LABEL_163",
"164": "LABEL_164",
"165": "LABEL_165",
"166": "LABEL_166",
"167": "LABEL_167",
"168": "LABEL_168",
"169": "LABEL_169",
"170": "LABEL_170",
"171": "LABEL_171",
"172": "LABEL_172",
"173": "LABEL_173",
"174": "LABEL_174",
"175": "LABEL_175",
"176": "LABEL_176",
"177": "LABEL_177",
"178": "LABEL_178",
"179": "LABEL_179",
"180": "LABEL_180",
"181": "LABEL_181",
"182": "LABEL_182",
"183": "LABEL_183",
"184": "LABEL_184",
"185": "LABEL_185",
"186": "LABEL_186",
"187": "LABEL_187",
"188": "LABEL_188",
"189": "LABEL_189",
"190": "LABEL_190",
"191": "LABEL_191",
"192": "LABEL_192",
"193": "LABEL_193",
"194": "LABEL_194",
"195": "LABEL_195",
"196": "LABEL_196",
"197": "LABEL_197",
"198": "LABEL_198",
"199": "LABEL_199",
"200": "LABEL_200",
"201": "LABEL_201",
"202": "LABEL_202",
"203": "LABEL_203",
"204": "LABEL_204",
"205": "LABEL_205",
"206": "LABEL_206",
"207": "LABEL_207",
"208": "LABEL_208",
"209": "LABEL_209",
"210": "LABEL_210",
"211": "LABEL_211",
"212": "LABEL_212",
"213": "LABEL_213",
"214": "LABEL_214",
"215": "LABEL_215",
"216": "LABEL_216",
"217": "LABEL_217",
"218": "LABEL_218",
"219": "LABEL_219",
"220": "LABEL_220",
"221": "LABEL_221",
"222": "LABEL_222",
"223": "LABEL_223",
"224": "LABEL_224",
"225": "LABEL_225",
"226": "LABEL_226",
"227": "LABEL_227",
"228": "LABEL_228",
"229": "LABEL_229",
"230": "LABEL_230",
"231": "LABEL_231",
"232": "LABEL_232",
"233": "LABEL_233",
"234": "LABEL_234",
"235": "LABEL_235",
"236": "LABEL_236",
"237": "LABEL_237",
"238": "LABEL_238",
"239": "LABEL_239",
"240": "LABEL_240",
"241": "LABEL_241",
"242": "LABEL_242",
"243": "LABEL_243",
"244": "LABEL_244",
"245": "LABEL_245",
"246": "LABEL_246",
"247": "LABEL_247",
"248": "LABEL_248",
"249": "LABEL_249",
"250": "LABEL_250",
"251": "LABEL_251",
"252": "LABEL_252",
"253": "LABEL_253",
"254": "LABEL_254",
"255": "LABEL_255",
"256": "LABEL_256",
"257": "LABEL_257",
"258": "LABEL_258",
"259": "LABEL_259",
"260": "LABEL_260",
"261": "LABEL_261",
"262": "LABEL_262",
"263": "LABEL_263",
"264": "LABEL_264",
"265": "LABEL_265",
"266": "LABEL_266",
"267": "LABEL_267",
"268": "LABEL_268",
"269": "LABEL_269",
"270": "LABEL_270",
"271": "LABEL_271",
"272": "LABEL_272",
"273": "LABEL_273",
"274": "LABEL_274",
"275": "LABEL_275",
"276": "LABEL_276",
"277": "LABEL_277",
"278": "LABEL_278",
"279": "LABEL_279",
"280": "LABEL_280",
"281": "LABEL_281",
"282": "LABEL_282",
"283": "LABEL_283",
"284": "LABEL_284",
"285": "LABEL_285",
"286": "LABEL_286",
"287": "LABEL_287",
"288": "LABEL_288",
"289": "LABEL_289",
"290": "LABEL_290",
"291": "LABEL_291",
"292": "LABEL_292",
"293": "LABEL_293",
"294": "LABEL_294",
"295": "LABEL_295",
"296": "LABEL_296",
"297": "LABEL_297",
"298": "LABEL_298",
"299": "LABEL_299",
"300": "LABEL_300",
"301": "LABEL_301",
"302": "LABEL_302",
"303": "LABEL_303",
"304": "LABEL_304",
"305": "LABEL_305",
"306": "LABEL_306",
"307": "LABEL_307",
"308": "LABEL_308",
"309": "LABEL_309",
"310": "LABEL_310",
"311": "LABEL_311",
"312": "LABEL_312",
"313": "LABEL_313",
"314": "LABEL_314",
"315": "LABEL_315",
"316": "LABEL_316",
"317": "LABEL_317",
"318": "LABEL_318",
"319": "LABEL_319",
"320": "LABEL_320",
"321": "LABEL_321",
"322": "LABEL_322",
"323": "LABEL_323",
"324": "LABEL_324",
"325": "LABEL_325",
"326": "LABEL_326",
"327": "LABEL_327",
"328": "LABEL_328",
"329": "LABEL_329",
"330": "LABEL_330",
"331": "LABEL_331",
"332": "LABEL_332",
"333": "LABEL_333",
"334": "LABEL_334",
"335": "LABEL_335",
"336": "LABEL_336",
"337": "LABEL_337",
"338": "LABEL_338",
"339": "LABEL_339",
"340": "LABEL_340",
"341": "LABEL_341",
"342": "LABEL_342",
"343": "LABEL_343",
"344": "LABEL_344",
"345": "LABEL_345",
"346": "LABEL_346",
"347": "LABEL_347",
"348": "LABEL_348",
"349": "LABEL_349",
"350": "LABEL_350",
"351": "LABEL_351",
"352": "LABEL_352",
"353": "LABEL_353",
"354": "LABEL_354",
"355": "LABEL_355",
"356": "LABEL_356",
"357": "LABEL_357",
"358": "LABEL_358",
"359": "LABEL_359",
"360": "LABEL_360",
"361": "LABEL_361",
"362": "LABEL_362",
"363": "LABEL_363",
"364": "LABEL_364",
"365": "LABEL_365",
"366": "LABEL_366",
"367": "LABEL_367",
"368": "LABEL_368",
"369": "LABEL_369",
"370": "LABEL_370",
"371": "LABEL_371",
"372": "LABEL_372",
"373": "LABEL_373",
"374": "LABEL_374",
"375": "LABEL_375",
"376": "LABEL_376",
"377": "LABEL_377",
"378": "LABEL_378",
"379": "LABEL_379",
"380": "LABEL_380",
"381": "LABEL_381",
"382": "LABEL_382",
"383": "LABEL_383",
"384": "LABEL_384",
"385": "LABEL_385",
"386": "LABEL_386",
"387": "LABEL_387",
"388": "LABEL_388",
"389": "LABEL_389",
"390": "LABEL_390",
"391": "LABEL_391",
"392": "LABEL_392",
"393": "LABEL_393",
"394": "LABEL_394",
"395": "LABEL_395",
"396": "LABEL_396",
"397": "LABEL_397",
"398": "LABEL_398",
"399": "LABEL_399",
"400": "LABEL_400",
"401": "LABEL_401",
"402": "LABEL_402",
"403": "LABEL_403",
"404": "LABEL_404"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_10": 10,
"LABEL_100": 100,
"LABEL_101": 101,
"LABEL_102": 102,
"LABEL_103": 103,
"LABEL_104": 104,
"LABEL_105": 105,
"LABEL_106": 106,
"LABEL_107": 107,
"LABEL_108": 108,
"LABEL_109": 109,
"LABEL_11": 11,
"LABEL_110": 110,
"LABEL_111": 111,
"LABEL_112": 112,
"LABEL_113": 113,
"LABEL_114": 114,
"LABEL_115": 115,
"LABEL_116": 116,
"LABEL_117": 117,
"LABEL_118": 118,
"LABEL_119": 119,
"LABEL_12": 12,
"LABEL_120": 120,
"LABEL_121": 121,
"LABEL_122": 122,
"LABEL_123": 123,
"LABEL_124": 124,
"LABEL_125": 125,
"LABEL_126": 126,
"LABEL_127": 127,
"LABEL_128": 128,
"LABEL_129": 129,
"LABEL_13": 13,
"LABEL_130": 130,
"LABEL_131": 131,
"LABEL_132": 132,
"LABEL_133": 133,
"LABEL_134": 134,
"LABEL_135": 135,
"LABEL_136": 136,
"LABEL_137": 137,
"LABEL_138": 138,
"LABEL_139": 139,
"LABEL_14": 14,
"LABEL_140": 140,
"LABEL_141": 141,
"LABEL_142": 142,
"LABEL_143": 143,
"LABEL_144": 144,
"LABEL_145": 145,
"LABEL_146": 146,
"LABEL_147": 147,
"LABEL_148": 148,
"LABEL_149": 149,
"LABEL_15": 15,
"LABEL_150": 150,
"LABEL_151": 151,
"LABEL_152": 152,
"LABEL_153": 153,
"LABEL_154": 154,
"LABEL_155": 155,
"LABEL_156": 156,
"LABEL_157": 157,
"LABEL_158": 158,
"LABEL_159": 159,
"LABEL_16": 16,
"LABEL_160": 160,
"LABEL_161": 161,
"LABEL_162": 162,
"LABEL_163": 163,
"LABEL_164": 164,
"LABEL_165": 165,
"LABEL_166": 166,
"LABEL_167": 167,
"LABEL_168": 168,
"LABEL_169": 169,
"LABEL_17": 17,
"LABEL_170": 170,
"LABEL_171": 171,
"LABEL_172": 172,
"LABEL_173": 173,
"LABEL_174": 174,
"LABEL_175": 175,
"LABEL_176": 176,
"LABEL_177": 177,
"LABEL_178": 178,
"LABEL_179": 179,
"LABEL_18": 18,
"LABEL_180": 180,
"LABEL_181": 181,
"LABEL_182": 182,
"LABEL_183": 183,
"LABEL_184": 184,
"LABEL_185": 185,
"LABEL_186": 186,
"LABEL_187": 187,
"LABEL_188": 188,
"LABEL_189": 189,
"LABEL_19": 19,
"LABEL_190": 190,
"LABEL_191": 191,
"LABEL_192": 192,
"LABEL_193": 193,
"LABEL_194": 194,
"LABEL_195": 195,
"LABEL_196": 196,
"LABEL_197": 197,
"LABEL_198": 198,
"LABEL_199": 199,
"LABEL_2": 2,
"LABEL_20": 20,
"LABEL_200": 200,
"LABEL_201": 201,
"LABEL_202": 202,
"LABEL_203": 203,
"LABEL_204": 204,
"LABEL_205": 205,
"LABEL_206": 206,
"LABEL_207": 207,
"LABEL_208": 208,
"LABEL_209": 209,
"LABEL_21": 21,
"LABEL_210": 210,
"LABEL_211": 211,
"LABEL_212": 212,
"LABEL_213": 213,
"LABEL_214": 214,
"LABEL_215": 215,
"LABEL_216": 216,
"LABEL_217": 217,
"LABEL_218": 218,
"LABEL_219": 219,
"LABEL_22": 22,
"LABEL_220": 220,
"LABEL_221": 221,
"LABEL_222": 222,
"LABEL_223": 223,
"LABEL_224": 224,
"LABEL_225": 225,
"LABEL_226": 226,
"LABEL_227": 227,
"LABEL_228": 228,
"LABEL_229": 229,
"LABEL_23": 23,
"LABEL_230": 230,
"LABEL_231": 231,
"LABEL_232": 232,
"LABEL_233": 233,
"LABEL_234": 234,
"LABEL_235": 235,
"LABEL_236": 236,
"LABEL_237": 237,
"LABEL_238": 238,
"LABEL_239": 239,
"LABEL_24": 24,
"LABEL_240": 240,
"LABEL_241": 241,
"LABEL_242": 242,
"LABEL_243": 243,
"LABEL_244": 244,
"LABEL_245": 245,
"LABEL_246": 246,
"LABEL_247": 247,
"LABEL_248": 248,
"LABEL_249": 249,
"LABEL_25": 25,
"LABEL_250": 250,
"LABEL_251": 251,
"LABEL_252": 252,
"LABEL_253": 253,
"LABEL_254": 254,
"LABEL_255": 255,
"LABEL_256": 256,
"LABEL_257": 257,
"LABEL_258": 258,
"LABEL_259": 259,
"LABEL_26": 26,
"LABEL_260": 260,
"LABEL_261": 261,
"LABEL_262": 262,
"LABEL_263": 263,
"LABEL_264": 264,
"LABEL_265": 265,
"LABEL_266": 266,
"LABEL_267": 267,
"LABEL_268": 268,
"LABEL_269": 269,
"LABEL_27": 27,
"LABEL_270": 270,
"LABEL_271": 271,
"LABEL_272": 272,
"LABEL_273": 273,
"LABEL_274": 274,
"LABEL_275": 275,
"LABEL_276": 276,
"LABEL_277": 277,
"LABEL_278": 278,
"LABEL_279": 279,
"LABEL_28": 28,
"LABEL_280": 280,
"LABEL_281": 281,
"LABEL_282": 282,
"LABEL_283": 283,
"LABEL_284": 284,
"LABEL_285": 285,
"LABEL_286": 286,
"LABEL_287": 287,
"LABEL_288": 288,
"LABEL_289": 289,
"LABEL_29": 29,
"LABEL_290": 290,
"LABEL_291": 291,
"LABEL_292": 292,
"LABEL_293": 293,
"LABEL_294": 294,
"LABEL_295": 295,
"LABEL_296": 296,
"LABEL_297": 297,
"LABEL_298": 298,
"LABEL_299": 299,
"LABEL_3": 3,
"LABEL_30": 30,
"LABEL_300": 300,
"LABEL_301": 301,
"LABEL_302": 302,
"LABEL_303": 303,
"LABEL_304": 304,
"LABEL_305": 305,
"LABEL_306": 306,
"LABEL_307": 307,
"LABEL_308": 308,
"LABEL_309": 309,
"LABEL_31": 31,
"LABEL_310": 310,
"LABEL_311": 311,
"LABEL_312": 312,
"LABEL_313": 313,
"LABEL_314": 314,
"LABEL_315": 315,
"LABEL_316": 316,
"LABEL_317": 317,
"LABEL_318": 318,
"LABEL_319": 319,
"LABEL_32": 32,
"LABEL_320": 320,
"LABEL_321": 321,
"LABEL_322": 322,
"LABEL_323": 323,
"LABEL_324": 324,
"LABEL_325": 325,
"LABEL_326": 326,
"LABEL_327": 327,
"LABEL_328": 328,
"LABEL_329": 329,
"LABEL_33": 33,
"LABEL_330": 330,
"LABEL_331": 331,
"LABEL_332": 332,
"LABEL_333": 333,
"LABEL_334": 334,
"LABEL_335": 335,
"LABEL_336": 336,
"LABEL_337": 337,
"LABEL_338": 338,
"LABEL_339": 339,
"LABEL_34": 34,
"LABEL_340": 340,
"LABEL_341": 341,
"LABEL_342": 342,
"LABEL_343": 343,
"LABEL_344": 344,
"LABEL_345": 345,
"LABEL_346": 346,
"LABEL_347": 347,
"LABEL_348": 348,
"LABEL_349": 349,
"LABEL_35": 35,
"LABEL_350": 350,
"LABEL_351": 351,
"LABEL_352": 352,
"LABEL_353": 353,
"LABEL_354": 354,
"LABEL_355": 355,
"LABEL_356": 356,
"LABEL_357": 357,
"LABEL_358": 358,
"LABEL_359": 359,
"LABEL_36": 36,
"LABEL_360": 360,
"LABEL_361": 361,
"LABEL_362": 362,
"LABEL_363": 363,
"LABEL_364": 364,
"LABEL_365": 365,
"LABEL_366": 366,
"LABEL_367": 367,
"LABEL_368": 368,
"LABEL_369": 369,
"LABEL_37": 37,
"LABEL_370": 370,
"LABEL_371": 371,
"LABEL_372": 372,
"LABEL_373": 373,
"LABEL_374": 374,
"LABEL_375": 375,
"LABEL_376": 376,
"LABEL_377": 377,
"LABEL_378": 378,
"LABEL_379": 379,
"LABEL_38": 38,
"LABEL_380": 380,
"LABEL_381": 381,
"LABEL_382": 382,
"LABEL_383": 383,
"LABEL_384": 384,
"LABEL_385": 385,
"LABEL_386": 386,
"LABEL_387": 387,
"LABEL_388": 388,
"LABEL_389": 389,
"LABEL_39": 39,
"LABEL_390": 390,
"LABEL_391": 391,
"LABEL_392": 392,
"LABEL_393": 393,
"LABEL_394": 394,
"LABEL_395": 395,
"LABEL_396": 396,
"LABEL_397": 397,
"LABEL_398": 398,
"LABEL_399": 399,
"LABEL_4": 4,
"LABEL_40": 40,
"LABEL_400": 400,
"LABEL_401": 401,
"LABEL_402": 402,
"LABEL_403": 403,
"LABEL_404": 404,
"LABEL_41": 41,
"LABEL_42": 42,
"LABEL_43": 43,
"LABEL_44": 44,
"LABEL_45": 45,
"LABEL_46": 46,
"LABEL_47": 47,
"LABEL_48": 48,
"LABEL_49": 49,
"LABEL_5": 5,
"LABEL_50": 50,
"LABEL_51": 51,
"LABEL_52": 52,
"LABEL_53": 53,
"LABEL_54": 54,
"LABEL_55": 55,
"LABEL_56": 56,
"LABEL_57": 57,
"LABEL_58": 58,
"LABEL_59": 59,
"LABEL_6": 6,
"LABEL_60": 60,
"LABEL_61": 61,
"LABEL_62": 62,
"LABEL_63": 63,
"LABEL_64": 64,
"LABEL_65": 65,
"LABEL_66": 66,
"LABEL_67": 67,
"LABEL_68": 68,
"LABEL_69": 69,
"LABEL_7": 7,
"LABEL_70": 70,
"LABEL_71": 71,
"LABEL_72": 72,
"LABEL_73": 73,
"LABEL_74": 74,
"LABEL_75": 75,
"LABEL_76": 76,
"LABEL_77": 77,
"LABEL_78": 78,
"LABEL_79": 79,
"LABEL_8": 8,
"LABEL_80": 80,
"LABEL_81": 81,
"LABEL_82": 82,
"LABEL_83": 83,
"LABEL_84": 84,
"LABEL_85": 85,
"LABEL_86": 86,
"LABEL_87": 87,
"LABEL_88": 88,
"LABEL_89": 89,
"LABEL_9": 9,
"LABEL_90": 90,
"LABEL_91": 91,
"LABEL_92": 92,
"LABEL_93": 93,
"LABEL_94": 94,
"LABEL_95": 95,
"LABEL_96": 96,
"LABEL_97": 97,
"LABEL_98": 98,
"LABEL_99": 99
},
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"pad_token_id": 0,
"problem_type": "single_label_classification",
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"torch_dtype": "float32",
"transformers_version": "4.17.0",
"vocab_size": 30522
}