{ "best_metric": 0.84970489436635, "best_model_checkpoint": "checkpoints/multicse-bert-large-uncased", "epoch": 3.0, "global_step": 2706, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03, "eval_avg_sts": 0.7624996022459282, "eval_sickr_spearman": 0.7306625637849724, "eval_stsb_spearman": 0.7943366407068839, "step": 25 }, { "epoch": 0.06, "eval_avg_sts": 0.8071313365516628, "eval_sickr_spearman": 0.7781768986027124, "eval_stsb_spearman": 0.8360857745006132, "step": 50 }, { "epoch": 0.08, "eval_avg_sts": 0.8149248188031465, "eval_sickr_spearman": 0.7874237501893749, "eval_stsb_spearman": 0.842425887416918, "step": 75 }, { "epoch": 0.11, "eval_avg_sts": 0.8218597211542165, "eval_sickr_spearman": 0.7970756000233636, "eval_stsb_spearman": 0.8466438422850692, "step": 100 }, { "epoch": 0.14, "eval_avg_sts": 0.8222996516785348, "eval_sickr_spearman": 0.7976810320569911, "eval_stsb_spearman": 0.8469182713000784, "step": 125 }, { "epoch": 0.17, "eval_avg_sts": 0.8296571369885761, "eval_sickr_spearman": 0.806694500521766, "eval_stsb_spearman": 0.8526197734553864, "step": 150 }, { "epoch": 0.19, "eval_avg_sts": 0.8336126250309825, "eval_sickr_spearman": 0.8114649014854978, "eval_stsb_spearman": 0.8557603485764674, "step": 175 }, { "epoch": 0.22, "eval_avg_sts": 0.8353162227426572, "eval_sickr_spearman": 0.8118504471367415, "eval_stsb_spearman": 0.8587819983485729, "step": 200 }, { "epoch": 0.25, "eval_avg_sts": 0.8300942602644428, "eval_sickr_spearman": 0.8061713937960034, "eval_stsb_spearman": 0.8540171267328822, "step": 225 }, { "epoch": 0.28, "eval_avg_sts": 0.8347835912873767, "eval_sickr_spearman": 0.8143648272659254, "eval_stsb_spearman": 0.855202355308828, "step": 250 }, { "epoch": 0.3, "eval_avg_sts": 0.8319994856438386, "eval_sickr_spearman": 0.8115708100641689, "eval_stsb_spearman": 0.8524281612235085, "step": 275 }, { "epoch": 0.33, "eval_avg_sts": 0.8368355138029437, "eval_sickr_spearman": 0.8189529021685982, "eval_stsb_spearman": 0.8547181254372894, "step": 300 }, { "epoch": 0.36, "eval_avg_sts": 0.8374901642309274, "eval_sickr_spearman": 0.8199181832142, "eval_stsb_spearman": 0.8550621452476548, "step": 325 }, { "epoch": 0.39, "eval_avg_sts": 0.835477792488754, "eval_sickr_spearman": 0.814654118589887, "eval_stsb_spearman": 0.8563014663876211, "step": 350 }, { "epoch": 0.42, "eval_avg_sts": 0.839369517546883, "eval_sickr_spearman": 0.8205669393013246, "eval_stsb_spearman": 0.8581720957924415, "step": 375 }, { "epoch": 0.44, "eval_avg_sts": 0.8380452297674821, "eval_sickr_spearman": 0.8173899220967006, "eval_stsb_spearman": 0.8587005374382635, "step": 400 }, { "epoch": 0.47, "eval_avg_sts": 0.8416927413750428, "eval_sickr_spearman": 0.8239470800339302, "eval_stsb_spearman": 0.8594384027161553, "step": 425 }, { "epoch": 0.5, "eval_avg_sts": 0.8319043646289148, "eval_sickr_spearman": 0.8098517769436988, "eval_stsb_spearman": 0.8539569523141309, "step": 450 }, { "epoch": 0.53, "eval_avg_sts": 0.8327259954986015, "eval_sickr_spearman": 0.8118681706131722, "eval_stsb_spearman": 0.8535838203840307, "step": 475 }, { "epoch": 0.55, "learning_rate": 8.152254249815226e-06, "loss": 0.4849, "step": 500 }, { "epoch": 0.55, "eval_avg_sts": 0.8398049341434459, "eval_sickr_spearman": 0.8219116180171858, "eval_stsb_spearman": 0.857698250269706, "step": 500 }, { "epoch": 0.58, "eval_avg_sts": 0.8399287988815654, "eval_sickr_spearman": 0.8219933669518336, "eval_stsb_spearman": 0.8578642308112973, "step": 525 }, { "epoch": 0.61, "eval_avg_sts": 0.8372186514713016, "eval_sickr_spearman": 0.8191553052300584, "eval_stsb_spearman": 0.8552819977125447, "step": 550 }, { "epoch": 0.64, "eval_avg_sts": 0.8397984072854183, "eval_sickr_spearman": 0.8222581624140619, "eval_stsb_spearman": 0.8573386521567748, "step": 575 }, { "epoch": 0.67, "eval_avg_sts": 0.8424072290367514, "eval_sickr_spearman": 0.8249417080825108, "eval_stsb_spearman": 0.859872749990992, "step": 600 }, { "epoch": 0.69, "eval_avg_sts": 0.8389197343591988, "eval_sickr_spearman": 0.8207355284673723, "eval_stsb_spearman": 0.8571039402510253, "step": 625 }, { "epoch": 0.72, "eval_avg_sts": 0.8418254593701419, "eval_sickr_spearman": 0.8221261729473099, "eval_stsb_spearman": 0.8615247457929738, "step": 650 }, { "epoch": 0.75, "eval_avg_sts": 0.844244457574689, "eval_sickr_spearman": 0.824336131955579, "eval_stsb_spearman": 0.8641527831937991, "step": 675 }, { "epoch": 0.78, "eval_avg_sts": 0.8422699522786281, "eval_sickr_spearman": 0.8214674744221877, "eval_stsb_spearman": 0.8630724301350685, "step": 700 }, { "epoch": 0.8, "eval_avg_sts": 0.8437980698256882, "eval_sickr_spearman": 0.824677537024601, "eval_stsb_spearman": 0.8629186026267753, "step": 725 }, { "epoch": 0.83, "eval_avg_sts": 0.8439136197370887, "eval_sickr_spearman": 0.8249638984513751, "eval_stsb_spearman": 0.8628633410228024, "step": 750 }, { "epoch": 0.86, "eval_avg_sts": 0.8426886128766484, "eval_sickr_spearman": 0.8233757020512226, "eval_stsb_spearman": 0.8620015237020744, "step": 775 }, { "epoch": 0.89, "eval_avg_sts": 0.841929144469251, "eval_sickr_spearman": 0.8214800585707644, "eval_stsb_spearman": 0.8623782303677376, "step": 800 }, { "epoch": 0.91, "eval_avg_sts": 0.8463814591231265, "eval_sickr_spearman": 0.827185240830685, "eval_stsb_spearman": 0.8655776774155678, "step": 825 }, { "epoch": 0.94, "eval_avg_sts": 0.8382240140191579, "eval_sickr_spearman": 0.8145595933822568, "eval_stsb_spearman": 0.8618884346560589, "step": 850 }, { "epoch": 0.97, "eval_avg_sts": 0.8402986385705378, "eval_sickr_spearman": 0.818052799327648, "eval_stsb_spearman": 0.8625444778134276, "step": 875 }, { "epoch": 1.0, "eval_avg_sts": 0.8417166888579826, "eval_sickr_spearman": 0.8214943238078914, "eval_stsb_spearman": 0.8619390539080737, "step": 900 }, { "epoch": 1.03, "eval_avg_sts": 0.840021113372968, "eval_sickr_spearman": 0.8206462386497989, "eval_stsb_spearman": 0.8593959880961373, "step": 925 }, { "epoch": 1.05, "eval_avg_sts": 0.8407725046557779, "eval_sickr_spearman": 0.8213717484370214, "eval_stsb_spearman": 0.8601732608745344, "step": 950 }, { "epoch": 1.08, "eval_avg_sts": 0.8431906318067501, "eval_sickr_spearman": 0.8246691796129508, "eval_stsb_spearman": 0.8617120840005495, "step": 975 }, { "epoch": 1.11, "learning_rate": 6.304508499630452e-06, "loss": 0.3038, "step": 1000 }, { "epoch": 1.11, "eval_avg_sts": 0.8416510189604846, "eval_sickr_spearman": 0.822419114634981, "eval_stsb_spearman": 0.8608829232859881, "step": 1000 }, { "epoch": 1.14, "eval_avg_sts": 0.8447615088290126, "eval_sickr_spearman": 0.8269052195093008, "eval_stsb_spearman": 0.8626177981487243, "step": 1025 }, { "epoch": 1.16, "eval_avg_sts": 0.8424856124518805, "eval_sickr_spearman": 0.8238848317264664, "eval_stsb_spearman": 0.8610863931772945, "step": 1050 }, { "epoch": 1.19, "eval_avg_sts": 0.8424277323953787, "eval_sickr_spearman": 0.8237316125128787, "eval_stsb_spearman": 0.8611238522778787, "step": 1075 }, { "epoch": 1.22, "eval_avg_sts": 0.8442776434640062, "eval_sickr_spearman": 0.8274288545771791, "eval_stsb_spearman": 0.8611264323508335, "step": 1100 }, { "epoch": 1.25, "eval_avg_sts": 0.8442605597470911, "eval_sickr_spearman": 0.8269961423843231, "eval_stsb_spearman": 0.8615249771098593, "step": 1125 }, { "epoch": 1.27, "eval_avg_sts": 0.8460938684955821, "eval_sickr_spearman": 0.8296871328734947, "eval_stsb_spearman": 0.8625006041176696, "step": 1150 }, { "epoch": 1.3, "eval_avg_sts": 0.8452328292042266, "eval_sickr_spearman": 0.8290738237392314, "eval_stsb_spearman": 0.8613918346692219, "step": 1175 }, { "epoch": 1.33, "eval_avg_sts": 0.8443542857305267, "eval_sickr_spearman": 0.8283039812453815, "eval_stsb_spearman": 0.860404590215672, "step": 1200 }, { "epoch": 1.36, "eval_avg_sts": 0.8455779584769261, "eval_sickr_spearman": 0.8298153759143346, "eval_stsb_spearman": 0.8613405410395174, "step": 1225 }, { "epoch": 1.39, "eval_avg_sts": 0.8465431787883896, "eval_sickr_spearman": 0.8306829136685097, "eval_stsb_spearman": 0.8624034439082695, "step": 1250 }, { "epoch": 1.41, "eval_avg_sts": 0.8452222856659524, "eval_sickr_spearman": 0.8282286684783264, "eval_stsb_spearman": 0.8622159028535784, "step": 1275 }, { "epoch": 1.44, "eval_avg_sts": 0.8460353103962084, "eval_sickr_spearman": 0.8289619112728808, "eval_stsb_spearman": 0.8631087095195359, "step": 1300 }, { "epoch": 1.47, "eval_avg_sts": 0.8428046052986686, "eval_sickr_spearman": 0.8233728201851361, "eval_stsb_spearman": 0.862236390412201, "step": 1325 }, { "epoch": 1.5, "eval_avg_sts": 0.8439709964632203, "eval_sickr_spearman": 0.8263711616924103, "eval_stsb_spearman": 0.8615708312340303, "step": 1350 }, { "epoch": 1.52, "eval_avg_sts": 0.8464117078835496, "eval_sickr_spearman": 0.8287957716930062, "eval_stsb_spearman": 0.8640276440740928, "step": 1375 }, { "epoch": 1.55, "eval_avg_sts": 0.8426142536649475, "eval_sickr_spearman": 0.8228226239181626, "eval_stsb_spearman": 0.8624058834117323, "step": 1400 }, { "epoch": 1.58, "eval_avg_sts": 0.84970489436635, "eval_sickr_spearman": 0.8333206856972879, "eval_stsb_spearman": 0.8660891030354121, "step": 1425 }, { "epoch": 1.61, "eval_avg_sts": 0.8459628076570953, "eval_sickr_spearman": 0.8295129240685788, "eval_stsb_spearman": 0.8624126912456118, "step": 1450 }, { "epoch": 1.64, "eval_avg_sts": 0.8464511583090627, "eval_sickr_spearman": 0.8300802674387656, "eval_stsb_spearman": 0.8628220491793598, "step": 1475 }, { "epoch": 1.66, "learning_rate": 4.456762749445676e-06, "loss": 0.2711, "step": 1500 }, { "epoch": 1.66, "eval_avg_sts": 0.8432266307908444, "eval_sickr_spearman": 0.8264625168473455, "eval_stsb_spearman": 0.8599907447343432, "step": 1500 }, { "epoch": 1.69, "eval_avg_sts": 0.8444286205972751, "eval_sickr_spearman": 0.8294252673084542, "eval_stsb_spearman": 0.859431973886096, "step": 1525 }, { "epoch": 1.72, "eval_avg_sts": 0.8448525205916575, "eval_sickr_spearman": 0.8308334911715182, "eval_stsb_spearman": 0.8588715500117969, "step": 1550 }, { "epoch": 1.75, "eval_avg_sts": 0.8411986614799187, "eval_sickr_spearman": 0.8257495912086997, "eval_stsb_spearman": 0.8566477317511376, "step": 1575 }, { "epoch": 1.77, "eval_avg_sts": 0.8429029812617075, "eval_sickr_spearman": 0.8264979157691056, "eval_stsb_spearman": 0.8593080467543093, "step": 1600 }, { "epoch": 1.8, "eval_avg_sts": 0.844172778094097, "eval_sickr_spearman": 0.8278518644875444, "eval_stsb_spearman": 0.8604936917006495, "step": 1625 }, { "epoch": 1.83, "eval_avg_sts": 0.8440312504721765, "eval_sickr_spearman": 0.828057053352888, "eval_stsb_spearman": 0.8600054475914649, "step": 1650 }, { "epoch": 1.86, "eval_avg_sts": 0.8466716345393903, "eval_sickr_spearman": 0.8323783154870722, "eval_stsb_spearman": 0.8609649535917084, "step": 1675 }, { "epoch": 1.88, "eval_avg_sts": 0.8470752337564638, "eval_sickr_spearman": 0.8329202984356999, "eval_stsb_spearman": 0.8612301690772276, "step": 1700 }, { "epoch": 1.91, "eval_avg_sts": 0.8491146738016275, "eval_sickr_spearman": 0.8357918378351774, "eval_stsb_spearman": 0.8624375097680775, "step": 1725 }, { "epoch": 1.94, "eval_avg_sts": 0.8490639696081586, "eval_sickr_spearman": 0.8353252637158076, "eval_stsb_spearman": 0.8628026755005095, "step": 1750 }, { "epoch": 1.97, "eval_avg_sts": 0.8490725041726443, "eval_sickr_spearman": 0.8349738681776864, "eval_stsb_spearman": 0.8631711401676022, "step": 1775 }, { "epoch": 2.0, "eval_avg_sts": 0.849465151594995, "eval_sickr_spearman": 0.8350664241101576, "eval_stsb_spearman": 0.8638638790798324, "step": 1800 }, { "epoch": 2.02, "eval_avg_sts": 0.8486443980616268, "eval_sickr_spearman": 0.8342315955360619, "eval_stsb_spearman": 0.8630572005871918, "step": 1825 }, { "epoch": 2.05, "eval_avg_sts": 0.8476111291438189, "eval_sickr_spearman": 0.8335225604166323, "eval_stsb_spearman": 0.8616996978710053, "step": 1850 }, { "epoch": 2.08, "eval_avg_sts": 0.8474970961473779, "eval_sickr_spearman": 0.8330892238194576, "eval_stsb_spearman": 0.8619049684752982, "step": 1875 }, { "epoch": 2.11, "eval_avg_sts": 0.8477943008360005, "eval_sickr_spearman": 0.8332226061881515, "eval_stsb_spearman": 0.8623659954838494, "step": 1900 }, { "epoch": 2.13, "eval_avg_sts": 0.8464807160435242, "eval_sickr_spearman": 0.8316015565146151, "eval_stsb_spearman": 0.8613598755724333, "step": 1925 }, { "epoch": 2.16, "eval_avg_sts": 0.8462238944734057, "eval_sickr_spearman": 0.831052512994076, "eval_stsb_spearman": 0.8613952759527355, "step": 1950 }, { "epoch": 2.19, "eval_avg_sts": 0.8464057290981915, "eval_sickr_spearman": 0.8310086125673615, "eval_stsb_spearman": 0.8618028456290214, "step": 1975 }, { "epoch": 2.22, "learning_rate": 2.609016999260902e-06, "loss": 0.258, "step": 2000 }, { "epoch": 2.22, "eval_avg_sts": 0.8468793796616104, "eval_sickr_spearman": 0.8316847944134073, "eval_stsb_spearman": 0.8620739649098136, "step": 2000 }, { "epoch": 2.25, "eval_avg_sts": 0.8473069362456496, "eval_sickr_spearman": 0.8321533858390374, "eval_stsb_spearman": 0.8624604866522616, "step": 2025 }, { "epoch": 2.27, "eval_avg_sts": 0.8458607867715203, "eval_sickr_spearman": 0.8302502975378566, "eval_stsb_spearman": 0.861471276005184, "step": 2050 }, { "epoch": 2.3, "eval_avg_sts": 0.8465971265934726, "eval_sickr_spearman": 0.8308937702038229, "eval_stsb_spearman": 0.8623004829831225, "step": 2075 }, { "epoch": 2.33, "eval_avg_sts": 0.8476369809742725, "eval_sickr_spearman": 0.8326747154140468, "eval_stsb_spearman": 0.8625992465344982, "step": 2100 }, { "epoch": 2.36, "eval_avg_sts": 0.8487784986875214, "eval_sickr_spearman": 0.833981881839685, "eval_stsb_spearman": 0.8635751155353578, "step": 2125 }, { "epoch": 2.38, "eval_avg_sts": 0.8482552739490947, "eval_sickr_spearman": 0.8330946513339202, "eval_stsb_spearman": 0.8634158965642693, "step": 2150 }, { "epoch": 2.41, "eval_avg_sts": 0.8459693374985795, "eval_sickr_spearman": 0.8297586992146375, "eval_stsb_spearman": 0.8621799757825214, "step": 2175 }, { "epoch": 2.44, "eval_avg_sts": 0.8476635726729035, "eval_sickr_spearman": 0.8323805729488398, "eval_stsb_spearman": 0.8629465723969671, "step": 2200 }, { "epoch": 2.47, "eval_avg_sts": 0.8479733460637723, "eval_sickr_spearman": 0.8331660735817588, "eval_stsb_spearman": 0.8627806185457858, "step": 2225 }, { "epoch": 2.49, "eval_avg_sts": 0.8473017297750429, "eval_sickr_spearman": 0.8320290333174142, "eval_stsb_spearman": 0.8625744262326718, "step": 2250 }, { "epoch": 2.52, "eval_avg_sts": 0.8479177356313778, "eval_sickr_spearman": 0.8327113151133426, "eval_stsb_spearman": 0.863124156149413, "step": 2275 }, { "epoch": 2.55, "eval_avg_sts": 0.8475060767928835, "eval_sickr_spearman": 0.8321914264713766, "eval_stsb_spearman": 0.8628207271143905, "step": 2300 }, { "epoch": 2.58, "eval_avg_sts": 0.8471482251359982, "eval_sickr_spearman": 0.831474706375717, "eval_stsb_spearman": 0.8628217438962794, "step": 2325 }, { "epoch": 2.61, "eval_avg_sts": 0.8471555097744191, "eval_sickr_spearman": 0.8313104880399002, "eval_stsb_spearman": 0.8630005315089381, "step": 2350 }, { "epoch": 2.63, "eval_avg_sts": 0.8463330579657068, "eval_sickr_spearman": 0.8301000562525582, "eval_stsb_spearman": 0.8625660596788554, "step": 2375 }, { "epoch": 2.66, "eval_avg_sts": 0.8462206147101088, "eval_sickr_spearman": 0.8299467890078692, "eval_stsb_spearman": 0.8624944404123482, "step": 2400 }, { "epoch": 2.69, "eval_avg_sts": 0.8466291774217871, "eval_sickr_spearman": 0.8307020300468819, "eval_stsb_spearman": 0.8625563247966924, "step": 2425 }, { "epoch": 2.72, "eval_avg_sts": 0.846255947089394, "eval_sickr_spearman": 0.8300505801238202, "eval_stsb_spearman": 0.8624613140549677, "step": 2450 }, { "epoch": 2.74, "eval_avg_sts": 0.84652808904023, "eval_sickr_spearman": 0.830373449281944, "eval_stsb_spearman": 0.8626827287985159, "step": 2475 }, { "epoch": 2.77, "learning_rate": 7.612712490761272e-07, "loss": 0.2459, "step": 2500 }, { "epoch": 2.77, "eval_avg_sts": 0.8462118162645162, "eval_sickr_spearman": 0.830052889710946, "eval_stsb_spearman": 0.8623707428180863, "step": 2500 }, { "epoch": 2.8, "eval_avg_sts": 0.8459259791683191, "eval_sickr_spearman": 0.8294702724505018, "eval_stsb_spearman": 0.8623816858861365, "step": 2525 }, { "epoch": 2.83, "eval_avg_sts": 0.8464449438786035, "eval_sickr_spearman": 0.8304476093025643, "eval_stsb_spearman": 0.8624422784546426, "step": 2550 }, { "epoch": 2.85, "eval_avg_sts": 0.84648379412736, "eval_sickr_spearman": 0.8305015962605808, "eval_stsb_spearman": 0.8624659919941392, "step": 2575 }, { "epoch": 2.88, "eval_avg_sts": 0.8465871172906757, "eval_sickr_spearman": 0.8306914151734642, "eval_stsb_spearman": 0.8624828194078872, "step": 2600 }, { "epoch": 2.91, "eval_avg_sts": 0.8464858615057194, "eval_sickr_spearman": 0.8305917026068788, "eval_stsb_spearman": 0.8623800204045601, "step": 2625 }, { "epoch": 2.94, "eval_avg_sts": 0.8466908586012467, "eval_sickr_spearman": 0.8309179778789479, "eval_stsb_spearman": 0.8624637393235455, "step": 2650 }, { "epoch": 2.97, "eval_avg_sts": 0.8467372932579469, "eval_sickr_spearman": 0.830980274217513, "eval_stsb_spearman": 0.8624943122983809, "step": 2675 }, { "epoch": 2.99, "eval_avg_sts": 0.8467338856246951, "eval_sickr_spearman": 0.8309889198157718, "eval_stsb_spearman": 0.8624788514336185, "step": 2700 }, { "epoch": 3.0, "step": 2706, "train_runtime": 7555.7932, "train_samples_per_second": 0.358 } ], "max_steps": 2706, "num_train_epochs": 3, "total_flos": 292973872557019392, "trial_name": null, "trial_params": null }