{ "_name_or_path": "distributed/optimized-gpt2-1b-stable-embeddings", "activation_function": "gelu_new", "all_reduce_scores": { "0": "NON_PARTICIPATING", "1": "NON_PARTICIPATING", "10": "NON_PARTICIPATING", "100": "NON_PARTICIPATING", "101": "NON_PARTICIPATING", "102": "NON_PARTICIPATING", "103": "NON_PARTICIPATING", "104": "NON_PARTICIPATING", "105": "SUCCESS", "106": "NON_PARTICIPATING", "107": "NON_PARTICIPATING", "108": "NON_PARTICIPATING", "109": "NON_PARTICIPATING", "11": "NON_PARTICIPATING", "110": "NON_PARTICIPATING", "111": "NON_PARTICIPATING", "112": "NON_PARTICIPATING", "113": "NON_PARTICIPATING", "114": "NON_PARTICIPATING", "115": "SUCCESS", "116": "NON_PARTICIPATING", "117": "NON_PARTICIPATING", "118": "NON_PARTICIPATING", "119": "NON_PARTICIPATING", "12": "NON_PARTICIPATING", "120": "NON_PARTICIPATING", "121": "NON_PARTICIPATING", "122": "NON_PARTICIPATING", "123": "NON_PARTICIPATING", "124": "NON_PARTICIPATING", "125": "NON_PARTICIPATING", "126": "NON_PARTICIPATING", "127": "NON_PARTICIPATING", "128": "NON_PARTICIPATING", "129": "NON_PARTICIPATING", "13": "NON_PARTICIPATING", "130": "NON_PARTICIPATING", "131": "NON_PARTICIPATING", "132": "NON_PARTICIPATING", "133": "NON_PARTICIPATING", "134": "NON_PARTICIPATING", "135": "NON_PARTICIPATING", "136": "NON_PARTICIPATING", "137": "NON_PARTICIPATING", "138": "NON_PARTICIPATING", "139": "SUCCESS", "14": "NON_PARTICIPATING", "140": "NON_PARTICIPATING", "141": "NON_PARTICIPATING", "142": "NON_PARTICIPATING", "143": "NON_PARTICIPATING", "144": "NON_PARTICIPATING", "145": "NON_PARTICIPATING", "146": "SUCCESS", "147": "NON_PARTICIPATING", "148": "NON_PARTICIPATING", "149": "NON_PARTICIPATING", "15": "SUCCESS", "150": "NON_PARTICIPATING", "151": "NON_PARTICIPATING", "152": "NON_PARTICIPATING", "153": "SUCCESS", "154": "NON_PARTICIPATING", "155": "SUCCESS", "156": "NON_PARTICIPATING", "157": "NON_PARTICIPATING", "158": "NON_PARTICIPATING", "159": "NON_PARTICIPATING", "16": "SUCCESS", "160": "NON_PARTICIPATING", "161": "NON_PARTICIPATING", "162": "NON_PARTICIPATING", "163": "NON_PARTICIPATING", "164": "NON_PARTICIPATING", "165": "NON_PARTICIPATING", "166": "SUCCESS", "167": "NON_PARTICIPATING", "168": "NON_PARTICIPATING", "169": "SUCCESS", "17": "NON_PARTICIPATING", "170": "NON_PARTICIPATING", "171": "SUCCESS", "172": "NON_PARTICIPATING", "173": "NON_PARTICIPATING", "174": "NON_PARTICIPATING", "175": "NON_PARTICIPATING", "176": "NON_PARTICIPATING", "177": "NON_PARTICIPATING", "178": "NON_PARTICIPATING", "179": "NON_PARTICIPATING", "18": "NON_PARTICIPATING", "180": "NON_PARTICIPATING", "181": "NON_PARTICIPATING", "182": "NON_PARTICIPATING", "183": "NON_PARTICIPATING", "184": "NON_PARTICIPATING", "185": "NON_PARTICIPATING", "186": "NON_PARTICIPATING", "187": "NON_PARTICIPATING", "188": "NON_PARTICIPATING", "189": "NON_PARTICIPATING", "19": "NON_PARTICIPATING", "190": "NON_PARTICIPATING", "191": "NON_PARTICIPATING", "192": "NON_PARTICIPATING", "193": "NON_PARTICIPATING", "194": "NON_PARTICIPATING", "195": "NON_PARTICIPATING", "196": "NON_PARTICIPATING", "197": "SUCCESS", "198": "NON_PARTICIPATING", "199": "NON_PARTICIPATING", "2": "NON_PARTICIPATING", "20": "NON_PARTICIPATING", "200": "NON_PARTICIPATING", "201": "NON_PARTICIPATING", "202": "NON_PARTICIPATING", "203": "SUCCESS", "204": "NON_PARTICIPATING", "205": "NON_PARTICIPATING", "206": "NON_PARTICIPATING", "207": "NON_PARTICIPATING", "208": "NON_PARTICIPATING", "209": "NON_PARTICIPATING", "21": "NON_PARTICIPATING", "210": "NON_PARTICIPATING", "211": "NON_PARTICIPATING", "212": "NON_PARTICIPATING", "213": "NON_PARTICIPATING", "214": "NON_PARTICIPATING", "215": "NON_PARTICIPATING", "216": "NON_PARTICIPATING", "217": "NON_PARTICIPATING", "218": "SUCCESS", "219": "NON_PARTICIPATING", "22": "SUCCESS", "220": "NON_PARTICIPATING", "221": "NON_PARTICIPATING", "222": "NON_PARTICIPATING", "223": "NON_PARTICIPATING", "224": "NON_PARTICIPATING", "225": "NON_PARTICIPATING", "226": "NON_PARTICIPATING", "227": "NON_PARTICIPATING", "228": "NON_PARTICIPATING", "229": "NON_PARTICIPATING", "23": "NON_PARTICIPATING", "230": "NON_PARTICIPATING", "231": "NON_PARTICIPATING", "232": "NON_PARTICIPATING", "233": "NON_PARTICIPATING", "234": "NON_PARTICIPATING", "235": "NON_PARTICIPATING", "236": "NON_PARTICIPATING", "237": "NON_PARTICIPATING", "238": "NON_PARTICIPATING", "239": "NON_PARTICIPATING", "24": "NON_PARTICIPATING", "240": "NON_PARTICIPATING", "241": "SUCCESS", "242": "NON_PARTICIPATING", "243": "NON_PARTICIPATING", "244": "NON_PARTICIPATING", "245": "NON_PARTICIPATING", "246": "NON_PARTICIPATING", "247": "NON_PARTICIPATING", "248": "NON_PARTICIPATING", "249": "NON_PARTICIPATING", "25": "SUCCESS", "250": "NON_PARTICIPATING", "251": "NON_PARTICIPATING", "252": "NON_PARTICIPATING", "253": "NON_PARTICIPATING", "254": "NON_PARTICIPATING", "255": "NON_PARTICIPATING", "26": "NON_PARTICIPATING", "27": "NON_PARTICIPATING", "28": "NON_PARTICIPATING", "29": "NON_PARTICIPATING", "3": "NON_PARTICIPATING", "30": "NON_PARTICIPATING", "31": "NON_PARTICIPATING", "32": "NON_PARTICIPATING", "33": "NON_PARTICIPATING", "34": "NON_PARTICIPATING", "35": "NON_PARTICIPATING", "36": "NON_PARTICIPATING", "37": "SUCCESS", "38": "NON_PARTICIPATING", "39": "SUCCESS", "4": "SUCCESS", "40": "NON_PARTICIPATING", "41": "NON_PARTICIPATING", "42": "NON_PARTICIPATING", "43": "NON_PARTICIPATING", "44": "NON_PARTICIPATING", "45": "NON_PARTICIPATING", "46": "NON_PARTICIPATING", "47": "NON_PARTICIPATING", "48": "NON_PARTICIPATING", "49": "NON_PARTICIPATING", "5": "NON_PARTICIPATING", "50": "SUCCESS", "51": "NON_PARTICIPATING", "52": "NON_PARTICIPATING", "53": "NON_PARTICIPATING", "54": "NON_PARTICIPATING", "55": "NON_PARTICIPATING", "56": "NON_PARTICIPATING", "57": "SUCCESS", "58": "NON_PARTICIPATING", "59": "NON_PARTICIPATING", "6": "NON_PARTICIPATING", "60": "NON_PARTICIPATING", "61": "NON_PARTICIPATING", "62": "NON_PARTICIPATING", "63": "NON_PARTICIPATING", "64": "NON_PARTICIPATING", "65": "SUCCESS", "66": "NON_PARTICIPATING", "67": "NON_PARTICIPATING", "68": "SUCCESS", "69": "NON_PARTICIPATING", "7": "NON_PARTICIPATING", "70": "NON_PARTICIPATING", "71": "NON_PARTICIPATING", "72": "SUCCESS", "73": "SUCCESS", "74": "NON_PARTICIPATING", "75": "NON_PARTICIPATING", "76": "SUCCESS", "77": "NON_PARTICIPATING", "78": "NON_PARTICIPATING", "79": "NON_PARTICIPATING", "8": "NON_PARTICIPATING", "80": "SUCCESS", "81": "NON_PARTICIPATING", "82": "NON_PARTICIPATING", "83": "NON_PARTICIPATING", "84": "NON_PARTICIPATING", "85": "NON_PARTICIPATING", "86": "NON_PARTICIPATING", "87": "NON_PARTICIPATING", "88": "NON_PARTICIPATING", "89": "NON_PARTICIPATING", "9": "NON_PARTICIPATING", "90": "NON_PARTICIPATING", "91": "SUCCESS", "92": "NON_PARTICIPATING", "93": "NON_PARTICIPATING", "94": "NON_PARTICIPATING", "95": "NON_PARTICIPATING", "96": "NON_PARTICIPATING", "97": "NON_PARTICIPATING", "98": "NON_PARTICIPATING", "99": "SUCCESS" }, "architectures": [ "GPTOptim" ], "attn_pdrop": 0.1, "auto_map": { "AutoConfig": "distributed/optimized-gpt2-1b-stable-embeddings--configuration_gpt_optimized.GPTOptimConfig", "AutoModelForCausalLM": "distributed/optimized-gpt2-1b-stable-embeddings--modeling_gpt_optimized.GPTOptim" }, "block_list": [ 3852278, 3852282, 3852285, 3852290, 3852294, 3852298, 3852302, 3852305, 3852308, 3852313, 3852317, 3852321, 3852325, 3852329, 3852333, 3852337, 3852341, 3852345, 3852348, 3852353, 3852357, 3852361, 3852365, 3852369, 3852373, 3852377, 3852381, 3852385, 3852387, 3852392, 3852396, 3852399, 3852404, 3852408, 3852412, 3852416, 3852420, 3852424, 3852428, 3852432, 3852435, 3852439, 3852442, 3852447, 3852451, 3852455, 3852458, 3852462, 3852466, 3852469, 3852472, 3852477, 3852481, 3852484, 3852489, 3852493, 3852497, 3852501, 3852505, 3852508, 3852513, 3852517, 3852520, 3852524, 3852528, 3852532, 3852536, 3852540, 3852544, 3852549, 3852552, 3852555, 3852560, 3852564, 3852567, 3852572, 3852576, 3852580, 3852584, 3852588, 3852592, 3852596, 3852600, 3852605, 3852607, 3852612, 3852616, 3852621, 3852625, 3852629, 3852633, 3852637, 3852641, 3852645, 3852649, 3852652, 3852656, 3852659, 3852664, 3852669, 3852673, 3852676, 3852679, 3852684, 3852688, 3852692, 3852696, 3852700, 3852704, 3852708, 3852712, 3852716, 3852720, 3852723, 3852728, 3852732, 3852735, 3852740, 3852744, 3852748, 3852752, 3852755, 3852759, 3852763, 3852768, 3852771, 3852774, 3852778, 3852783, 3852787, 3852791, 3852795, 3852799, 3852803, 3852807, 3852811, 3852815, 3852819, 3852823, 3852827, 3852831, 3852835, 3852840, 3852843, 3852848, 3852852, 3852856, 3852859, 3852864, 3852868, 3852874, 3852880, 3852883, 3852888, 3852891, 3852895, 3852901, 3852904, 3852910, 3852916, 3852920, 3852925, 3852929, 3852934, 3852940, 3852945, 3852951, 3852956, 3852961, 3852966, 3852969, 3852975, 3852981, 3852986, 3852992, 3852996, 3853001, 3853006, 3853012, 3853018, 3853024, 3853029, 3853034, 3853040, 3853045, 3853051, 3853056, 3853067, 3853074, 3853081, 3853086, 3853090, 3853099, 3853105, 3853110, 3853122, 3853134, 3853140, 3853145, 3853151, 3853158, 3853162, 3853168, 3853175, 3853181, 3853188, 3853194, 3853200, 3853205, 3853211, 3853215, 3853220, 3853225, 3853232, 3853237, 3853243, 3853251, 3853258, 3853263, 3853271, 3853279, 3853284, 3853290, 3853295, 3853300, 3853308, 3853316, 3853329, 3853335, 3853341, 3853347, 3853352, 3853358, 3853369, 3853375, 3853379, 3853387, 3853392, 3853397, 3853401, 3853406, 3853411, 3853419, 3853424, 3853430, 3853434, 3853439, 3853445, 3853449, 3853453, 3853459, 3853464, 3853467, 3853473, 3853476, 3853481, 3853486, 3853490, 3853495, 3853499, 3853503, 3853509, 3853512, 3853518, 3853522, 3853526, 3853530, 3853534, 3853540, 3853544, 3853547, 3853552, 3853556, 3853559, 3853565, 3853569, 3853572, 3853576, 3853581, 3853584, 3853590, 3853594, 3853598, 3853602, 3853605, 3853609, 3853613, 3853616, 3853621, 3853625, 3853629, 3853633, 3853637, 3853642, 3853646, 3853650, 3853654, 3853657, 3853663, 3853666, 3853670, 3853675, 3853679, 3853682, 3853687, 3853691, 3853695, 3853698, 3853703, 3853707, 3853710, 3853715, 3853719, 3853723, 3853725, 3853729, 3853734, 3853738, 3853742, 3853747, 3853752, 3853757, 3853760, 3853764, 3853769, 3853773, 3853776, 3853781, 3853785, 3853789, 3853794, 3853798, 3853802, 3853806, 3853810, 3853815, 3853820, 3853825, 3853829, 3853833, 3853838, 3853843, 3853848, 3853853, 3853857, 3853862, 3853867, 3853873, 3853878, 3853883, 3853887, 3853893, 3853897, 3853902, 3853908, 3853913, 3853918, 3853922, 3853927, 3853933, 3853938, 3853944, 3853950, 3853955, 3853959, 3853964, 3853969, 3853974, 3853979, 3853984, 3853988, 3853995, 3853999, 3854004, 3854009, 3854018, 3854023, 3854028, 3854033, 3854037, 3854043, 3854050, 3854057, 3854063, 3854068, 3854072, 3854078, 3854086, 3854091, 3854097, 3854101, 3854108, 3854113, 3854121, 3854127, 3854133, 3854138, 3854143, 3854149, 3854155, 3854162, 3854166, 3854170, 3854176, 3854181, 3854188, 3854193, 3854198, 3854207, 3854211, 3854215, 3854220, 3854226, 3854230, 3854237, 3854241, 3854253, 3854257, 3854262, 3854267, 3854272, 3854278, 3854282, 3854287, 3854292, 3854297, 3854301, 3854305, 3854311, 3854315, 3854320, 3854323, 3854340, 3854344, 3854349, 3854352, 3854357, 3854361, 3854365, 3854370, 3854374, 3854379, 3854383, 3854387, 3854392, 3854396, 3854400, 3854404, 3854408, 3854412, 3854416, 3854419, 3854423, 3854428, 3854432, 3854437, 3854441, 3854445, 3854450, 3854454, 3854457, 3854462, 3854466, 3854471, 3854475, 3854479, 3854483, 3854487, 3854490, 3854494, 3854499, 3854504, 3854508, 3854512, 3854516, 3854521, 3854525, 3854529, 3854532, 3854537, 3854542, 3854544, 3854549, 3854554, 3854558, 3854562, 3854565, 3854570, 3854574, 3854578, 3854582, 3854586, 3854590, 3854593, 3854597, 3854603, 3854608, 3854612, 3854616, 3854620, 3854624, 3854629, 3854638, 3854642, 3854647, 3854651, 3854655, 3854660, 3854663, 3854668, 3854672, 3854676, 3854682, 3854687, 3854691, 3854696, 3854701, 3854706, 3854710, 3854715, 3854720, 3854724, 3854729, 3854734, 3854739, 3854744, 3854749, 3854753, 3854758, 3854763, 3854768, 3854774, 3854782, 3854787, 3854792, 3854797, 3854802, 3854808, 3854813, 3854817, 3854823, 3854827, 3854832, 3854839, 3854843, 3854849, 3854853, 3854858, 3854867, 3854872, 3854878, 3854883, 3854895, 3854902, 3854907, 3854913, 3854918, 3854924, 3854929, 3854933, 3854939, 3854944, 3854949, 3854956, 3854963, 3854968, 3854973, 3854978, 3854989, 3855000, 3855005, 3855010, 3855016, 3855021, 3855026, 3855031, 3855036, 3855042, 3855048, 3855054, 3855059, 3855063, 3855069, 3855073, 3855080, 3855085, 3855091, 3855095, 3855101, 3855106, 3855112, 3855118, 3855124, 3855136, 3855142, 3855146, 3855149, 3855154, 3855159, 3855163, 3855169, 3855175, 3855180, 3855185, 3855189, 3855195, 3855199, 3855208, 3855215, 3855218, 3855224, 3855227, 3855232, 3855237, 3855242, 3855247, 3855252, 3855256, 3855262, 3855265, 3855270, 3855275, 3855279, 3855284, 3855289, 3855293, 3855297, 3855300, 3855304, 3855308, 3855312, 3855317, 3855321, 3855325, 3855329, 3855332, 3855338, 3855342, 3855346, 3855350, 3855354, 3855358, 3855363, 3855367, 3855372, 3855376, 3855380, 3855383, 3855388, 3855392, 3855397, 3855402, 3855405, 3855410, 3855414, 3855418, 3855422, 3855427, 3855432, 3855436, 3855439, 3855445, 3855448, 3855454, 3855458, 3855462, 3855466, 3855471, 3855475, 3855479, 3855483, 3855487, 3855491, 3855496, 3855500, 3855505, 3855508, 3855513, 3855518, 3855521, 3855527, 3855532, 3855537, 3855541, 3855546, 3855550, 3855554, 3855557, 3855562, 3855566, 3855569, 3855574, 3855579, 3855584, 3855588, 3855594, 3855598, 3855603, 3855608, 3855612, 3855617, 3855622, 3855627, 3855632, 3855636, 3855641, 3855646, 3855653, 3855659, 3855664, 3855669, 3855674, 3855678, 3855685, 3855690, 3855696, 3855700, 3855705, 3855709, 3855715, 3855722, 3855727, 3855734, 3855738, 3855743, 3855747, 3855752, 3855758, 3855765, 3855771, 3855776, 3855780, 3855784, 3855789, 3855795, 3855801, 3855808, 3855813, 3855818, 3855823, 3855827, 3855834, 3855842, 3855848, 3855853, 3855858, 3855862, 3855867, 3855877, 3855883, 3855890, 3855896, 3855901, 3855907, 3855910, 3855916, 3855922, 3855927, 3855937, 3855944, 3855950, 3855956, 3855966, 3855972, 3855977, 3855982, 3855987, 3855993, 3855999, 3856005, 3856013, 3856024, 3856032, 3856037, 3856046, 3856051, 3856057, 3856062, 3856065, 3856071, 3856078, 3856085, 3856090, 3856103, 3856108, 3856113, 3856118, 3856123, 3856129, 3856138, 3856143, 3856147, 3856152, 3856156, 3856162, 3856167, 3856174, 3856178, 3856183, 3856189, 3856193, 3856197, 3856203, 3856207, 3856211, 3856217, 3856222, 3856226, 3856230, 3856235, 3856240, 3856244, 3856249, 3856253, 3856259, 3856263, 3856268, 3856273, 3856277, 3856282, 3856287, 3856292, 3856296, 3856301, 3856306, 3856310, 3856315, 3856319, 3856323, 3856328, 3856334, 3856339, 3856344, 3856348, 3856352, 3856358, 3856362, 3856367, 3856371, 3856374, 3856378, 3856382, 3856387, 3856392, 3856396, 3856400, 3856403, 3856408, 3856411, 3856416, 3856419, 3856424, 3856428, 3856432, 3856436, 3856441, 3856445, 3856448, 3856452, 3856456, 3856460, 3856464, 3856468, 3856472, 3856481, 3856485, 3856489, 3856493, 3856497, 3856501, 3856504, 3856509, 3856513, 3856516, 3856521, 3856526, 3856529, 3856535, 3856540, 3856547, 3856552, 3856556, 3856561, 3856565, 3856569, 3856573, 3856577, 3856582, 3856586, 3856590, 3856594, 3856598, 3856603, 3856607, 3856612, 3856615, 3856620, 3856625, 3856629, 3856634, 3856638, 3856643, 3856649, 3856657, 3856661, 3856666, 3856670, 3856675, 3856680, 3856685, 3856689, 3856692, 3856696, 3856701, 3856706, 3856711, 3856716, 3856721, 3856726, 3856730, 3856736, 3856740, 3856745, 3856749, 3856754, 3856759, 3856764, 3856769, 3856774, 3856779, 3856783, 3856788, 3856792, 3856799, 3856805, 3856809, 3856813, 3856817, 3856821, 3856827, 3856833, 3856838, 3856848, 3856852, 3856856, 3856861, 3856865, 3856874, 3856879, 3856884, 3856889, 3856894, 3856899, 3856904, 3856909, 3856915, 3856921, 3856927, 3856932, 3856937, 3856944, 3856949, 3856953, 3856958, 3856963, 3856967, 3856972, 3856977, 3856982, 3856986, 3856991, 3856997, 3857002, 3857012, 3857016, 3857021, 3857026, 3857031, 3857035, 3857039, 3857044, 3857048, 3857052, 3857057, 3857062, 3857066, 3857070, 3857074, 3857078, 3857082, 3857086, 3857090, 3857095, 3857099, 3857103, 3857107, 3857111, 3857115, 3857119, 3857122, 3857126, 3857131, 3857135, 3857141, 3857145, 3857149, 3857153, 3857157, 3857161, 3857164, 3857169, 3857173, 3857177, 3857180, 3857185, 3857189, 3857193, 3857196, 3857200, 3857205, 3857208, 3857211, 3857216, 3857220, 3857224, 3857227, 3857232, 3857235, 3857240, 3857244, 3857247, 3857251, 3857255, 3857259, 3857263, 3857267, 3857271, 3857275, 3857279, 3857283, 3857287, 3857291, 3857294, 3857298, 3857302, 3857305, 3857309, 3857313, 3857317, 3857321, 3857325, 3857329, 3857333, 3857337, 3857340, 3857344, 3857348, 3857352, 3857356, 3857360, 3857364, 3857368, 3857371, 3857375, 3857378, 3857383, 3857386, 3857390, 3857394, 3857398, 3857402, 3857407, 3857409, 3857415, 3857419, 3857422, 3857426, 3857430, 3857434, 3857438, 3857441, 3857444, 3857449, 3857453, 3857457, 3857461, 3857465, 3857468, 3857472, 3857475, 3857479, 3857484, 3857488, 3857490, 3857494, 3857499, 3857503, 3857507, 3857511, 3857515, 3857519, 3857523, 3857527, 3857531, 3857535, 3857537, 3857546, 3857551, 3857562, 3857568, 3857575, 3857593, 3857602, 3857609, 3857619, 3857625, 3857636, 3857649, 3857662, 3857669, 3857693, 3857702, 3857713, 3857729, 3857750 ], "block_size": 1024, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "inner_step": 1300, "layer_norm_epsilon": 1e-05, "model_type": "gpt_optimized", "n_embd": 1280, "n_head": 32, "n_inner": null, "n_layer": 48, "n_positions": 1024, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "torch_dtype": "float32", "transformers_version": "4.39.3", "use_cache": true, "vocab_size": 50257 }