{ "_name_or_path": "/Users/shahrukh/Desktop/smole_bert_ckpts/smole-bert-mtr/guacamol_v1_train_m/", "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": [ 11.78879961265325, 11.788797208559462, 0.161743306260005, -1.1315692811063311, 0.553857507652851, 16.225420435445013, 396.67377846899547, 373.906517186301, 396.22376326211344, 146.2243854390529, 0.00020579622717389938, 0.27397533012168174, -0.42619569075751296, 0.430395067609715, 0.26979931345055264, 1.0978297230672145, 1.811797453672612, 2.4777456612803634, 27.297373511547264, 10.013927309892821, 2.2705885909391057, -2.221993498354204, 2.310685266802566, -2.3124941317400713, 6.704786113625519, 0.029053546411851386, 2.9510481899052503, 1.8092407597256042, 959.3629399774176, 19.888259842310287, 15.738962804358646, 16.342765087539934, 13.409361297776742, 9.178509017278888, 9.781031913717728, 6.960772064819403, 7.650269643836828, 4.899768109960316, 5.481163654539192, 3.4355717527107705, 3.906185352370315, -2.714885743615984, 19.39068024303442, 8.268273499916912, 5.250129211450636, 165.17984316050834, 13.689998022284593, 9.316074803723536, 4.573632631781159, 4.4158152995195445, 3.1316978959444772, 3.1475899005376693, 7.8365444688313275, 6.171607431181991, 2.9705834068162282, 2.3401706686613735, 28.302697177791813, 41.3419996730726, 23.08491483824693, 14.872661089974958, 15.460703687489545, 23.871966640269605, 0.3851038562974869, 10.896161411247874, 3.782488232116172, 29.326847745603075, 16.74055030412742, 57.260832252759364, 0.0, 7.471333178473629, 8.91175093982249, 6.041776976115462, 3.696903561892062, 6.597380475443101, 37.483061243548185, 11.484073075191473, 6.500935377003061, 29.436572297903666, 46.0190707068987, 1.1107764067672086, 7.913686247777438, 0.0, 80.33889588752622, 10.907522913974908, 11.27308924719699, 0.049622794706427234, 15.22262179998044, 19.196714534306004, 23.495050107709968, 14.69896886379223, 17.316323941800068, 23.357185185607648, 20.15938033245458, 9.519507586809771, 15.016775897112439, 2.024063184343625, 20.245986605067703, 9.531171127967182, 2.8819911824014013, 0.11692336047179511, 11.082355891559102, 2.512950480176817, 3.2587894946295695, 0.2598054173379498, 0.3286261371553574, 27.898829160854103, 1.6650642838291294, 6.169583160527341, 0.29147029622089005, 0.6742096482298382, 0.9656799444507282, 1.5070606957483441, 0.9732731968480187, 2.480333892596363, 5.162941912051176, 1.5237843883924644, 7.259591518053513, 5.608242531639206, 0.20247756664027447, 0.44167326471364476, 0.6441508313539193, 3.4460138370470914, 3.4843022313496315, 106.97658736969558, 0.0672121052168558, 0.2092122874486295, 0.18132689866656612, 0.061390114240470535, 0.02878790735085272, 1.349936061782855, 0.12412104588470384, 0.12250295341150448, 0.09600001256770853, 0.09610369616307858, 1.0891961693624401, 0.993552765524262, 0.017652132111752063, 0.008457282358707538, 0.056956855056617524, 2.06690969473036, 0.8959825748721235, 0.15192631552489036, 0.018136774371928767, 0.06698274453618872, 0.12479184732747678, 0.12412104588470384, 0.010770526209956138, 0.004945393306438437, 0.012108201686586485, 0.2481823951538916, 0.14366461813017634, 0.787110872324649, 0.034873034724578665, 0.6166369754552652, 0.4245049893802863, 0.0015096959871306664, 0.0021561474946273046, 0.0017390566677977603, 1.5058848295190337, 0.000993634455629705, 0.8969604996920911, 2.9848307758046474e-05, 0.0014303623270369114, 0.0037632432228631753, 0.13374162676419207, 0.8178428470886904, 0.0451220010305521, 0.017309662054317637, 0.6755166899169275, 0.013918737196646935, 0.030101232892206765, 0.09081740376277193, 0.02967471628397994, 3.927408915532431e-05, 0.0003573942113134512, 0.11362465281705186, 0.0787147004486672, 0.0036493483643127347, 0.01761757091329538, 0.3028228644321281, 0.03790342344380349, 0.05174361246213978, 0.041843400067865626, 0.03347880455956465, 0.02212623634832661, 0.0008247558722618105, 0.015250914300795535, 0.013098694215083764, 0.25869842526612125, 0.09532764016136938, 0.09382108610137113, 0.005384477623194963, 0.004389272203999045, 0.12206229813118175, 0.07021971496437054, 0.026331705815078738, 0.0, 0.23489597079264538, 0.004157555077982631, 0.08453747690683558, 0.10048511354924657, 0.026359197677487463, 0.0034773278538124145, 0.01119939926353228, 0.04697966544759894, 0.0001704495469341075, 0.057197997964031216, 0.31014355465068055, 0.05334913722680944, 16.225420435445013 ], "norm_std": [ 2.4557450586041694, 2.455744580377551, 0.1901073412259103, 1.5837939398994312, 0.2140204835539139, 7.163352430420644, 110.37124252883991, 103.94724708282811, 110.24507857321171, 41.959360763282824, 0.014615358118186055, 0.08567380560002029, 0.07620985256921298, 0.07446761246686605, 0.07922235708746773, 0.19993954116649107, 0.26602153956973107, 0.32704134361048515, 15.627713059641515, 0.3737861594982892, 0.16970128065807558, 0.15912196564614803, 0.14528050179945476, 0.19622936556573745, 1.1645324328599111, 0.29289836148468523, 0.35572580912640833, 0.450081661911271, 358.19568896327723, 5.58516632100786, 4.604040680995728, 4.619608667697351, 3.7688930166851935, 2.837170436634257, 2.9230796797319907, 2.4191765322763215, 2.5710201479065646, 1.9207999015688948, 2.0595565417285258, 1.5581000901709552, 1.6750030761512265, 1.0314899449675925, 5.990600525015119, 3.093041429116176, 856.8649505165378, 45.533845879164865, 8.721823398756896, 8.632107693693463, 6.281047295721583, 5.682491319134954, 4.393709984185692, 6.664534480284654, 6.329666250761914, 6.0350975762603145, 5.331090335383015, 5.033238754812009, 21.780687922235597, 20.399811144341708, 14.568933118611575, 10.597285239702495, 10.508655284068706, 13.991167827590573, 1.5327257387908346, 7.980222464822894, 7.0937633795621675, 25.58650754754035, 14.428247364489906, 26.10058915784191, 0.0, 8.812798184267185, 6.850115981793158, 7.232254169264399, 5.839282733976217, 9.770108548637852, 20.672974730036653, 9.287071768188628, 8.41942718112866, 22.16609318252839, 22.599419775147982, 2.7896064158812597, 9.446327552383305, 0.0, 38.478930914153246, 15.076238963878009, 8.493696981028185, 0.5333544860135173, 11.8621258118974, 13.66309682823155, 17.819490186431942, 15.199685124398282, 15.200637820116304, 21.027598387702177, 17.652103289937063, 8.761897467133657, 17.608388797411507, 3.6343330743143096, 13.727245414380686, 9.579603715673986, 3.120179604616355, 1.781709640086731, 6.998686351805373, 4.0313107361807115, 3.347100879326076, 2.2034466221280313, 0.20375306190633777, 7.845011198538416, 1.6124574759304917, 2.5611289010997695, 0.7547619389342607, 0.8079401120375572, 1.1091285570095153, 0.941287574438209, 0.9194454569796577, 1.1909042955391855, 2.1922388970756055, 1.3908116828429344, 2.8542392945412787, 3.4917021803363664, 0.6402797341314147, 0.6837148847140367, 0.9592563423099368, 1.3269105507330647, 1.818510762759157, 29.816802920344593, 0.2790494135700369, 0.6556820384157217, 0.6128744325067826, 0.26344263872625673, 0.1741949667318314, 1.5015598717905254, 0.3597066754796728, 0.44485977583637965, 0.327287322684933, 0.32748243336484867, 1.073886022407389, 1.0245570424105435, 0.13666537358955438, 0.09392808209002645, 0.2610584184706553, 1.6264149868160163, 0.9702311384818341, 0.4330233280453187, 0.16895374444599429, 0.26662563113225124, 0.360641632049109, 0.3597066754796728, 0.10610264834046756, 0.07291652220211808, 0.11606588269547549, 0.9158423087759645, 0.6364174686814384, 0.9873875751404888, 0.19708141957511546, 0.8430467616020442, 0.7292080772794137, 0.040197180139894484, 0.04848722404467991, 0.0418350453787292, 0.9414416809467188, 0.03153122436234195, 1.2678042687955886, 0.005463278945489645, 0.037834617980830695, 0.06859881948714805, 0.4317994497087872, 1.0920572398444384, 0.21490450485434368, 0.14826374250214336, 1.1759820802559418, 0.12080458933046213, 0.17637179856764468, 0.29786944984794644, 0.18737083569796253, 0.007308297941144899, 0.019595225472568874, 0.37837107259052205, 0.3114517034148772, 0.060701980951763886, 0.14090881807826325, 0.691570542668661, 0.19875864125414572, 0.2399044125900563, 0.21579629690385252, 0.19428831720071638, 0.15404791607563412, 0.03127347245649173, 0.12754309055946822, 0.1184612880875633, 0.5726782531127644, 0.40940381168561424, 0.4067791846825119, 0.09677889753682423, 0.07558558290250689, 0.3687494220695116, 0.26131949035968716, 0.16443258686114756, 0.0, 0.49223416630062444, 0.0721047797124303, 0.2952006668799927, 0.313381735484985, 0.1643636792061654, 0.06161744361208939, 0.10642789979118751, 0.21842322996454705, 0.013351977820369445, 0.24133017412974148, 1.4776749963606077, 0.23108070589768165, 7.163352430420644 ], "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 }