{ "_name_or_path": "/Users/shahrukh/Desktop/smole_bert_ckpts/smole-bert-mtr/guacamol_v1_train_mtr_66_perce/", "architectures": [ "BertModel" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 512, "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" }, "initializer_range": 0.02, "intermediate_size": 2048, "is_gpu": true, "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_22": 22, "LABEL_23": 23, "LABEL_24": 24, "LABEL_25": 25, "LABEL_26": 26, "LABEL_27": 27, "LABEL_28": 28, "LABEL_29": 29, "LABEL_3": 3, "LABEL_30": 30, "LABEL_31": 31, "LABEL_32": 32, "LABEL_33": 33, "LABEL_34": 34, "LABEL_35": 35, "LABEL_36": 36, "LABEL_37": 37, "LABEL_38": 38, "LABEL_39": 39, "LABEL_4": 4, "LABEL_40": 40, "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 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 768, "model_type": "bert", "norm_mean": [ 11.790324084662696, 11.790321185921593, 0.16161938584282315, -1.13292336671101, 0.5536361521056551, 16.230720593124513, 396.7656906746377, 373.99608313020195, 396.31595137501864, 146.26192743094896, 0.00019994096980891355, 0.27400535806187587, -0.42616876639699175, 0.430364296477931, 0.26982770351100943, 1.0978178807723786, 1.8118739067527068, 2.47790692275769, 27.287686305462106, 10.013698233060481, 2.2706462772946376, -2.2220028943831855, 2.310568622077149, -2.312568103761681, 6.704512194028279, 0.02873947351954523, 2.951373645434837, 1.8085675520339584, 959.7939152729674, 19.893550524104644, 15.74248807429742, 16.345955333528536, 13.413096174415227, 9.180837924616014, 9.783477551253876, 6.9628955303847055, 7.652515314624283, 4.901386907458127, 5.48292260766338, 3.436878902892381, 3.9076792955550634, -2.7160763538334325, 19.394948539166787, 8.26923067308588, 5.627962492668272, 165.21923217813847, 13.688199983486006, 9.315824572518897, 4.574681650249159, 4.417021609580122, 3.1360651440945713, 3.151554076353825, 7.844168789674884, 6.177575441166688, 2.974270278918946, 2.3378641324545404, 28.30988086187192, 41.34333120992818, 23.094785244035172, 14.870342985287216, 15.463435087940985, 23.87083233025909, 0.3860386557028871, 10.901341645851906, 3.788889395256489, 29.31965605023847, 16.742626563551106, 57.289597070895844, 0.0, 7.473149179975642, 8.913116310566549, 6.044056927885016, 3.695040219341257, 6.5911554553863185, 37.500157984575445, 11.491008587194926, 6.50857971562227, 29.420135695669767, 46.045861205362606, 1.1088175030143015, 7.917636374963875, 0.0, 80.37459471490043, 10.918340593380899, 11.283259798698746, 0.04956892466526578, 15.246081400428757, 19.187627213688405, 23.495614619171487, 14.705462025766934, 17.316470363470835, 23.352758450032436, 20.163296986433547, 9.517085603851411, 15.02682921721216, 2.021010590058408, 20.259385512225016, 9.534871786258725, 2.8824178556675624, 0.11554242070235834, 11.088485588243023, 2.5111690708998236, 3.258226656480657, 0.2579676238685571, 0.328583238385299, 27.906660890594207, 1.665937913568375, 6.172001599527759, 0.2909272024449924, 0.6755100874979768, 0.9664372899429692, 1.5079238510534985, 0.9730710456912721, 2.480994896744771, 5.164275309194428, 1.5242952080814236, 7.262408241376356, 5.608913082804125, 0.2018868238900896, 0.44302872485266254, 0.6449155487427521, 3.44743218668774, 3.4835483440246944, 107.00123585131973, 0.06719325722881817, 0.20943102512591522, 0.1815225980900877, 0.061487798840342375, 0.028687958793118223, 1.350159714750883, 0.12433472022545725, 0.12232459940398549, 0.09588121602193637, 0.09598475688130172, 1.089466443240567, 0.9939375041654369, 0.017749521569822242, 0.008447505974426598, 0.057159314868943455, 2.0680894212184975, 0.8963151355314145, 0.15218007064580932, 0.01830411973607792, 0.06713732136226447, 0.1249738172539536, 0.12433472022545725, 0.010653997391246395, 0.004994953870761966, 0.012059534804010244, 0.24874084794013196, 0.14365877693252468, 0.7876853024345193, 0.03486708686006988, 0.6162668640687036, 0.4242176119431406, 0.0014840856509030667, 0.0021398444268834914, 0.0017221106149612972, 1.5067491978558711, 0.000977092477459036, 0.8981253153830774, 3.4513619788443414e-05, 0.0014495720311146233, 0.003817920423494016, 0.13334396511506127, 0.8173872475745256, 0.044879606973179345, 0.017488884234178482, 0.675568403614171, 0.013798307166455618, 0.030295817425331568, 0.09080176328893375, 0.02968528339252221, 3.927411906960802e-05, 0.0003487065723453076, 0.1139842046633851, 0.07901833744323104, 0.003663204196856166, 0.017620988089230797, 0.3022964648532338, 0.03779836429244699, 0.05184659767116375, 0.0420744827717531, 0.03366387066675553, 0.022191067399148823, 0.0008330873742038065, 0.015169330959431026, 0.0130878026487418, 0.2590497091334939, 0.09513976825889499, 0.09363783073568756, 0.005353181441669602, 0.00440108158543668, 0.12246265388313926, 0.07041849549180718, 0.026439813007588235, 0.0, 0.23475212080242977, 0.004201140615627767, 0.08457860060363132, 0.10067622892288944, 0.026429101884205615, 0.003528720092163266, 0.011175272062533919, 0.04713132313317021, 0.00017613847340309052, 0.05709385800382744, 0.3098192438422942, 0.053567518161304756, 16.230720593124513 ], "norm_std": [ 2.4550058929202403, 2.4550046763307987, 0.19034657792911172, 1.5849630774382606, 0.2140692722959837, 7.174590836339799, 110.36626834000472, 103.950618403688, 110.24027308778994, 41.949924265204416, 0.014388945143235065, 0.08564699150420915, 0.0761986267952469, 0.07446668350723001, 0.07921292420192826, 0.19987252556969015, 0.26582322758105753, 0.3266560298889945, 15.610776745554308, 0.37628889840661434, 0.16992574276413358, 0.15937430142631923, 0.145475189121751, 0.19637694133546302, 1.1645579352329158, 0.2926305690140985, 0.3554823673343518, 0.4492732902876241, 358.4036248109964, 5.584742103051741, 4.602488133631476, 4.618356862258901, 3.7687068669381585, 2.836367639844321, 2.9228762179316887, 2.4191287643456727, 2.5714816225025188, 1.9213555904232145, 2.060400295889584, 1.558947686693234, 1.6765208662189428, 1.031842380148325, 5.987816608750883, 3.0872208211458707, 1054.4597945297444, 45.528260614801205, 8.716816383358164, 8.628136651890689, 6.2805444314534045, 5.683693748245157, 4.399258377219257, 6.725950334585062, 6.339190937839787, 6.03579852619268, 5.336147459976392, 5.031826964145142, 21.77658992825241, 20.396717467754833, 14.569993762705954, 10.598305342461972, 10.50199283261364, 13.995463823377126, 1.5349790778223578, 7.982659540771941, 7.110366574952326, 25.561769687205345, 14.418753535212005, 26.11241328089198, 0.0, 8.813854932750628, 6.850919038818678, 7.237980078894113, 5.8370497013503195, 9.761494995231287, 20.66584086674106, 9.286644284444607, 8.431736758432118, 22.141598091889364, 22.60923076370159, 2.785013139258897, 9.454885320645467, 0.0, 38.492079079445546, 15.068301300443434, 8.501813686220528, 0.5327255709634122, 11.879013462097667, 13.657733881276771, 17.823442471149992, 15.20244117449868, 15.197516060335087, 21.034051538384475, 17.649780963444353, 8.752159913999407, 17.6247332016268, 3.6267429238766846, 13.73412340587198, 9.57795470346257, 3.1238351178604633, 1.7782046011412973, 7.001102078817609, 4.027809303136516, 3.343922274234369, 2.20393104881796, 0.20372971586707045, 7.844672589908974, 1.6134744469069728, 2.5604574942504392, 0.7545105410238568, 0.8089594149046496, 1.110066975852158, 0.9415838803343533, 0.9189656731435103, 1.1913710114504126, 2.1912026516739704, 1.391185713443552, 2.8541715190409054, 3.4889028433422618, 0.6397641145459259, 0.6851732127182821, 0.9603618050173389, 1.3267654561924644, 1.8196689535373296, 29.814125189214675, 0.2789905968378546, 0.6554978340650328, 0.6129983463803796, 0.26364431940123295, 0.1739114989128555, 1.5020569734089357, 0.3601889857064941, 0.44452101852495135, 0.3272338420118957, 0.32742346661791805, 1.0742994550160303, 1.024595604431109, 0.13710710812304094, 0.09403549620542186, 0.2619972034489926, 1.626115256055593, 0.9702456791904546, 0.43374782629503944, 0.169941587874967, 0.26699155255659307, 0.36078509512291235, 0.3601889857064941, 0.10517492287564738, 0.07334444249450009, 0.11548805873085337, 0.9177698623706247, 0.636485536869555, 0.9879467869643126, 0.19713984839934512, 0.8424761684148383, 0.7298877621607122, 0.03986219229426135, 0.04834859576154608, 0.04160584331754362, 0.9417067812845283, 0.03128127263038684, 1.2694298902441548, 0.005874727959497218, 0.03810815229460253, 0.06920091948986301, 0.4308267850972862, 1.0907854453179529, 0.2143211833625615, 0.14926197654630616, 1.1766845048354921, 0.12025981667547037, 0.177116486587633, 0.2979896267183007, 0.1875907170612636, 0.007318064939319179, 0.019297343663800464, 0.379179104173505, 0.31233830824621117, 0.06074742279116679, 0.14114397870109588, 0.6909096009627582, 0.19852356784482253, 0.24017614826061598, 0.21620632784051327, 0.1947476326261183, 0.15423515523837159, 0.03153173504899293, 0.12645668309346972, 0.11867111861872139, 0.5734006188254458, 0.40928783631716176, 0.4067007917144585, 0.09607556687553134, 0.07576829555305392, 0.36972933122804974, 0.26159637379859746, 0.16498868013397278, 0.0, 0.4919097070776791, 0.07232427583429699, 0.29496705871385626, 0.31385480902795526, 0.1645895713672954, 0.062005989042478796, 0.10625813178598568, 0.2185930530203722, 0.013624553101225727, 0.24089526665953684, 1.473233018425206, 0.2314335314442028, 7.174590836339799 ], "num_attention_heads": 8, "num_hidden_layers": 6, "pad_token_id": 0, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.33.3", "type_vocab_size": 5, "use_cache": true, "vocab_size": 4096 }