{ "_name_or_path": "/Users/shahrukh/Desktop/smole_bert_ckpts/smole-bert-mtr/guacamol_v1_train_mtr_33_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": [ 11.79173722090841, 11.791735733252384, 0.16142733236185644, -1.1338970900757865, 0.5540122744969485, 16.225004804786156, 396.5624771757886, 373.80136912196485, 396.1134686626214, 146.18284601689024, 0.000218982966933572, 0.2740248256099069, -0.42630494269048835, 0.43050527150580503, 0.2698487218946878, 1.097756745168095, 1.811554006611595, 2.4773467919623866, 27.300041530894585, 10.013533791400816, 2.2706229792311015, -2.221998676755911, 2.310731693533491, -2.3124906496480904, 6.705751478663473, 0.02838769036537712, 2.950521134456493, 1.8098238585764796, 959.1945986352539, 19.88339741193139, 15.735355475168806, 16.338591990750338, 13.40581812705491, 9.175847908179138, 9.778499910653245, 6.959070647454426, 7.648801562134866, 4.898993266684832, 5.480402292685902, 3.4352689888966146, 3.9060113407794224, -2.7150457249047597, 19.384348915624976, 8.26433842009071, 4.531898798651937, 165.13353831484594, 13.67967366656444, 9.291401675602604, 4.583452525428392, 4.415600032625782, 3.1364130627950857, 3.14916708915964, 7.838424605319413, 6.16399843449677, 2.971487393659049, 2.3455493964995275, 28.302419444717373, 41.31054470550945, 23.10033069341478, 14.860819572048287, 15.459197782667621, 23.8530746498506, 0.3856368299935323, 10.872510867046524, 3.7818028646156803, 29.291844711675488, 16.75294357342169, 57.27023750637449, 0.0, 7.48203351221471, 8.914988467282255, 6.045534311202594, 3.705783784132936, 6.582497142146744, 37.45882197069321, 11.474714466573344, 6.495022882434, 29.41743575682104, 46.04650354573215, 1.1000318533662325, 7.907948117451183, 0.0, 80.30940198607864, 10.89235226186259, 11.270609443626366, 0.049536018207520016, 15.227431568728337, 19.187725609594846, 23.48029398023669, 14.70555503418569, 17.30319935359575, 23.37786147106524, 20.151431304580427, 9.503286252126719, 15.028135819733299, 2.013004769504896, 20.229440477389073, 9.524489337420777, 2.8853750725068963, 0.11704413358043304, 11.089383000614044, 2.5087275816505867, 3.2584479470813115, 0.26021346917309446, 0.3284527402554299, 27.89175814759452, 1.6637040492806885, 6.167064961773191, 0.2918424084317963, 0.6741938094467348, 0.9660362178785311, 1.5078500633146403, 0.9717345355180851, 2.4795845988327256, 5.16056450000476, 1.5220434919214327, 7.255974426597861, 5.6044144109834235, 0.2021284192286087, 0.4408769791775761, 0.6430053984061849, 3.4456208167112568, 3.4842879718607005, 106.95390602774344, 0.06751340080547648, 0.20822899905742115, 0.18001113956831793, 0.06173891517742381, 0.028632022926564537, 1.3467119231464997, 0.12379440355704506, 0.12288276794470204, 0.09614542373204102, 0.09624063371766431, 1.088014490959812, 0.9922237244242176, 0.0178494920547267, 0.008197579762165456, 0.057059344384039, 2.065685369081509, 0.8940884119926498, 0.1524930734735459, 0.01806609477201969, 0.066877874151441, 0.12435138197294132, 0.12379440355704506, 0.010920585350991613, 0.004936637754567699, 0.011960754443926079, 0.2482005312717198, 0.14410983423941504, 0.7860084165627291, 0.03517770943816587, 0.6170463958259942, 0.4239224609877084, 0.0015376412678161685, 0.0022564766592720244, 0.0017256809894221705, 1.5067099237368016, 0.0009878036008416564, 0.8959212042158982, 2.856299568698765e-05, 0.0014662337785986993, 0.0037679351810417875, 0.13303453266178558, 0.8183655301768049, 0.04492721196599099, 0.017316316135236265, 0.6734154678142643, 0.013891136902438327, 0.030398168159876608, 0.09057563957307843, 0.029446068303643685, 4.7604992811646086e-05, 0.0003975016899772448, 0.1144804867134465, 0.07953128124077653, 0.0036465424493720903, 0.017532918852529254, 0.3037103331397397, 0.03812445849320677, 0.05170854319200998, 0.042044729651245824, 0.03360198417610039, 0.022236292142319886, 0.0008426083727661357, 0.015305005188944216, 0.013060429777875103, 0.25826422675210176, 0.09582647028020298, 0.09440784149441593, 0.005341280193466691, 0.004324913596938047, 0.12139987241861927, 0.0701197741619141, 0.02628985728023155, 0.0, 0.2347211775571022, 0.0043177728480163, 0.08424179527948891, 0.10069646104483439, 0.026180365796764766, 0.0035299102169835572, 0.011127667069722272, 0.047324123354057376, 0.00015947672591901438, 0.0572069198617551, 0.3102036541592482, 0.053655587398006306, 16.225004804786156 ], "norm_std": [ 2.450956367907171, 2.450957358490004, 0.1900694542718677, 1.585550668854749, 0.21408660245779082, 7.167756298551029, 110.38143868325362, 103.9768160504462, 110.25454925425753, 41.92446700625781, 0.015114761392606006, 0.08566396456971308, 0.07610299547961805, 0.07440580889485046, 0.07915897965410704, 0.20005517379588011, 0.2660578073294469, 0.3270457457695261, 15.643238205368789, 0.3745298835585969, 0.17032249727029578, 0.1595731293853628, 0.14602127441637475, 0.19646207097857157, 1.165741260328626, 0.2924936639075496, 0.35591926533392754, 0.44963890691205316, 358.3350806602452, 5.582530185453843, 4.600967153344112, 4.617567554729664, 3.7674115847556577, 2.8351786167897455, 2.92044496854429, 2.4182129099726115, 2.5694931718800698, 1.9215817463227578, 2.058751377138955, 1.5588279310971112, 1.6738129912367141, 1.0311367227312878, 5.9840222835220285, 3.084128127892107, 36.583867537244814, 45.5227366808627, 8.70715948623874, 8.618134414933428, 6.285577405247769, 5.673858515560443, 4.397636335931561, 6.687193262411652, 6.322651452539215, 6.0324557965672145, 5.330076373872543, 5.046112526997736, 21.807109041805635, 20.406709246001242, 14.56573922857417, 10.58673423931756, 10.494914027697359, 13.986614820847326, 1.5351065239242783, 7.973621811721162, 7.08942306197074, 25.574046418779865, 14.437564676884168, 26.099288189922394, 0.0, 8.820137844446059, 6.842194940218551, 7.245614026670348, 5.844662026785024, 9.75527215765922, 20.653481393596422, 9.264111536322721, 8.423843579831374, 22.175229148732896, 22.604609619915063, 2.77596119459279, 9.437389743854837, 0.0, 38.39255322607205, 15.074789723574137, 8.489221808525107, 0.527810624490048, 11.853179666729842, 13.634166440987086, 17.80182437479484, 15.209552748379934, 15.193632267477984, 21.06130303707713, 17.649417693703583, 8.724037460872513, 17.61720877542114, 3.6142970003153403, 13.710407134968992, 9.573917145660431, 3.1256805148338827, 1.7936151897480868, 7.002607279164903, 4.028946423062812, 3.3464293219352776, 2.2067591753870217, 0.20371763499165746, 7.8419957807268945, 1.6097240077664488, 2.5568039135211733, 0.7564394185095993, 0.8071646238806618, 1.1103683311893218, 0.9413582224291319, 0.9189417248319828, 1.1905782208843334, 2.1891341810285647, 1.3882516215092118, 2.8527781362039546, 3.4817891606665485, 0.6403934874716088, 0.6829951534922246, 0.9589865662866164, 1.3281350371365026, 1.817800813263014, 29.811516496998557, 0.28031150468530336, 0.6535994456813586, 0.6099437242988456, 0.26429580441207123, 0.1739241381223627, 1.499866896765387, 0.35956503245077653, 0.44486893089637247, 0.3281986960447466, 0.3283738128868036, 1.0710744886459551, 1.021903107242631, 0.13741495364049322, 0.09235941418055359, 0.2599074787806729, 1.6243915741585675, 0.9692005525101034, 0.4330652736152795, 0.16942001309311988, 0.26625775917228417, 0.3603252872228711, 0.35956503245077653, 0.1071544565746604, 0.07281914791660501, 0.11566822623858354, 0.9178409293056203, 0.6345547452668947, 0.9871238733924385, 0.19795531921210502, 0.8439632109002434, 0.7299173877811576, 0.04078983216108351, 0.049462768249412446, 0.04161999535203529, 0.9415591862988358, 0.031413816146489915, 1.2666473421475197, 0.0053443596288299325, 0.03826334978960425, 0.06952964247240391, 0.43025079226494517, 1.0916532717360954, 0.21494888483940283, 0.14777972493692224, 1.1770128232271766, 0.12038760981958334, 0.17723330031280918, 0.29758289879399524, 0.18714890700230555, 0.00786665268207016, 0.020980661951309387, 0.3797118834211366, 0.31268231935290575, 0.060709230514227185, 0.1401055592978817, 0.6929787825750691, 0.1992571760304207, 0.24021581743165143, 0.21592293972979806, 0.19416466992210568, 0.15419005365800725, 0.0316820984067121, 0.1281883957284432, 0.11837792354292834, 0.5730325329134964, 0.40948379288743736, 0.40698064555808344, 0.09657045000058866, 0.07471293413264501, 0.36684807642904177, 0.26126467800219405, 0.16407961325136344, 0.0, 0.4921905265324656, 0.07354132184117698, 0.29462547114662346, 0.313402437164237, 0.16366138685913564, 0.06205388707018914, 0.10616228169634329, 0.21909526869045748, 0.012998934250731066, 0.24181770922659632, 1.4594086495280145, 0.23229601666486974, 7.167756298551029 ], "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 }