{ "best_metric": 0.8509895356755377, "best_model_checkpoint": "result/esimcse-roberta-base-0.1-bpe-0.3-160-bs64", "epoch": 1.0, "global_step": 15626, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "eval_avg_sts": 0.7581765037912359, "eval_sickr_spearman": 0.7151382873958556, "eval_stsb_spearman": 0.8012147201866162, "step": 125 }, { "epoch": 0.02, "eval_avg_sts": 0.7681462302822064, "eval_sickr_spearman": 0.7191643023494997, "eval_stsb_spearman": 0.817128158214913, "step": 250 }, { "epoch": 0.02, "eval_avg_sts": 0.7689880945057068, "eval_sickr_spearman": 0.7167425261838887, "eval_stsb_spearman": 0.821233662827525, "step": 375 }, { "epoch": 0.03, "learning_rate": 9.680020478689364e-06, "loss": 0.2173, "step": 500 }, { "epoch": 0.03, "eval_avg_sts": 0.77171181346581, "eval_sickr_spearman": 0.7162504475496553, "eval_stsb_spearman": 0.8271731793819647, "step": 500 }, { "epoch": 0.04, "eval_avg_sts": 0.7748967925777871, "eval_sickr_spearman": 0.7145534607047452, "eval_stsb_spearman": 0.835240124450829, "step": 625 }, { "epoch": 0.05, "eval_avg_sts": 0.7740832357556943, "eval_sickr_spearman": 0.7138060487352668, "eval_stsb_spearman": 0.8343604227761218, "step": 750 }, { "epoch": 0.06, "eval_avg_sts": 0.7762465978643387, "eval_sickr_spearman": 0.7208324225024454, "eval_stsb_spearman": 0.8316607732262321, "step": 875 }, { "epoch": 0.06, "learning_rate": 9.36004095737873e-06, "loss": 0.001, "step": 1000 }, { "epoch": 0.06, "eval_avg_sts": 0.7733397471522039, "eval_sickr_spearman": 0.7168732668420033, "eval_stsb_spearman": 0.8298062274624045, "step": 1000 }, { "epoch": 0.07, "eval_avg_sts": 0.7653409481290172, "eval_sickr_spearman": 0.7163877684686668, "eval_stsb_spearman": 0.8142941277893675, "step": 1125 }, { "epoch": 0.08, "eval_avg_sts": 0.7736208665177124, "eval_sickr_spearman": 0.7180561287771196, "eval_stsb_spearman": 0.8291856042583052, "step": 1250 }, { "epoch": 0.09, "eval_avg_sts": 0.7769947892835245, "eval_sickr_spearman": 0.719469443936936, "eval_stsb_spearman": 0.834520134630113, "step": 1375 }, { "epoch": 0.1, "learning_rate": 9.040061436068092e-06, "loss": 0.0009, "step": 1500 }, { "epoch": 0.1, "eval_avg_sts": 0.7724765591275501, "eval_sickr_spearman": 0.7175171717878825, "eval_stsb_spearman": 0.8274359464672176, "step": 1500 }, { "epoch": 0.1, "eval_avg_sts": 0.7805406775721991, "eval_sickr_spearman": 0.7221231622913917, "eval_stsb_spearman": 0.8389581928530065, "step": 1625 }, { "epoch": 0.11, "eval_avg_sts": 0.7788261300626871, "eval_sickr_spearman": 0.7156971292610881, "eval_stsb_spearman": 0.841955130864286, "step": 1750 }, { "epoch": 0.12, "eval_avg_sts": 0.7840241297108503, "eval_sickr_spearman": 0.7276132612790723, "eval_stsb_spearman": 0.8404349981426283, "step": 1875 }, { "epoch": 0.13, "learning_rate": 8.720081914757458e-06, "loss": 0.0007, "step": 2000 }, { "epoch": 0.13, "eval_avg_sts": 0.7859614716903541, "eval_sickr_spearman": 0.73084517803264, "eval_stsb_spearman": 0.8410777653480682, "step": 2000 }, { "epoch": 0.14, "eval_avg_sts": 0.7879631319134857, "eval_sickr_spearman": 0.7249367281514335, "eval_stsb_spearman": 0.8509895356755377, "step": 2125 }, { "epoch": 0.14, "eval_avg_sts": 0.785546295104504, "eval_sickr_spearman": 0.7227898820104544, "eval_stsb_spearman": 0.8483027081985536, "step": 2250 }, { "epoch": 0.15, "eval_avg_sts": 0.7834786244087628, "eval_sickr_spearman": 0.723430760996943, "eval_stsb_spearman": 0.8435264878205825, "step": 2375 }, { "epoch": 0.16, "learning_rate": 8.400102393446819e-06, "loss": 0.0009, "step": 2500 }, { "epoch": 0.16, "eval_avg_sts": 0.7820490328984251, "eval_sickr_spearman": 0.7255294799742813, "eval_stsb_spearman": 0.8385685858225688, "step": 2500 }, { "epoch": 0.17, "eval_avg_sts": 0.7808832119394027, "eval_sickr_spearman": 0.7211363152812443, "eval_stsb_spearman": 0.8406301085975609, "step": 2625 }, { "epoch": 0.18, "eval_avg_sts": 0.7801816610620529, "eval_sickr_spearman": 0.7208986573913285, "eval_stsb_spearman": 0.8394646647327774, "step": 2750 }, { "epoch": 0.18, "eval_avg_sts": 0.7804005291249532, "eval_sickr_spearman": 0.7246992623859235, "eval_stsb_spearman": 0.8361017958639829, "step": 2875 }, { "epoch": 0.19, "learning_rate": 8.080122872136184e-06, "loss": 0.0007, "step": 3000 }, { "epoch": 0.19, "eval_avg_sts": 0.7782109243211895, "eval_sickr_spearman": 0.722025947342081, "eval_stsb_spearman": 0.8343959013002981, "step": 3000 }, { "epoch": 0.2, "eval_avg_sts": 0.7856724922536673, "eval_sickr_spearman": 0.7338031734147062, "eval_stsb_spearman": 0.8375418110926284, "step": 3125 }, { "epoch": 0.21, "eval_avg_sts": 0.7856388427423309, "eval_sickr_spearman": 0.732672281131346, "eval_stsb_spearman": 0.8386054043533157, "step": 3250 }, { "epoch": 0.22, "eval_avg_sts": 0.7828902827361719, "eval_sickr_spearman": 0.7300378712796683, "eval_stsb_spearman": 0.8357426941926754, "step": 3375 }, { "epoch": 0.22, "learning_rate": 7.760143350825547e-06, "loss": 0.0007, "step": 3500 }, { "epoch": 0.22, "eval_avg_sts": 0.7802120728333768, "eval_sickr_spearman": 0.7278627828510433, "eval_stsb_spearman": 0.8325613628157101, "step": 3500 }, { "epoch": 0.23, "eval_avg_sts": 0.7814736917323457, "eval_sickr_spearman": 0.7240533881648852, "eval_stsb_spearman": 0.8388939952998063, "step": 3625 }, { "epoch": 0.24, "eval_avg_sts": 0.7752603635110975, "eval_sickr_spearman": 0.7130665618975255, "eval_stsb_spearman": 0.8374541651246696, "step": 3750 }, { "epoch": 0.25, "eval_avg_sts": 0.7738531430333261, "eval_sickr_spearman": 0.7116984440041625, "eval_stsb_spearman": 0.8360078420624897, "step": 3875 }, { "epoch": 0.26, "learning_rate": 7.440163829514912e-06, "loss": 0.0008, "step": 4000 }, { "epoch": 0.26, "eval_avg_sts": 0.7716461848796647, "eval_sickr_spearman": 0.7067132959859007, "eval_stsb_spearman": 0.8365790737734288, "step": 4000 }, { "epoch": 0.26, "eval_avg_sts": 0.7726640328663634, "eval_sickr_spearman": 0.7067841898916234, "eval_stsb_spearman": 0.8385438758411035, "step": 4125 }, { "epoch": 0.27, "eval_avg_sts": 0.7710462569066159, "eval_sickr_spearman": 0.7075652236321085, "eval_stsb_spearman": 0.8345272901811234, "step": 4250 }, { "epoch": 0.28, "eval_avg_sts": 0.7746792058093399, "eval_sickr_spearman": 0.7143302601763624, "eval_stsb_spearman": 0.8350281514423173, "step": 4375 }, { "epoch": 0.29, "learning_rate": 7.120184308204276e-06, "loss": 0.0007, "step": 4500 }, { "epoch": 0.29, "eval_avg_sts": 0.7565698440366436, "eval_sickr_spearman": 0.7096718197100826, "eval_stsb_spearman": 0.8034678683632046, "step": 4500 }, { "epoch": 0.3, "eval_avg_sts": 0.7675338058741563, "eval_sickr_spearman": 0.7151141757829338, "eval_stsb_spearman": 0.819953435965379, "step": 4625 }, { "epoch": 0.3, "eval_avg_sts": 0.7690480296047658, "eval_sickr_spearman": 0.7127470109796578, "eval_stsb_spearman": 0.8253490482298739, "step": 4750 }, { "epoch": 0.31, "eval_avg_sts": 0.7684443815823148, "eval_sickr_spearman": 0.713693800051206, "eval_stsb_spearman": 0.8231949631134236, "step": 4875 }, { "epoch": 0.32, "learning_rate": 6.800204786893639e-06, "loss": 0.0004, "step": 5000 }, { "epoch": 0.32, "eval_avg_sts": 0.7691689362019429, "eval_sickr_spearman": 0.7142018250111167, "eval_stsb_spearman": 0.824136047392769, "step": 5000 }, { "epoch": 0.33, "eval_avg_sts": 0.7695187713024993, "eval_sickr_spearman": 0.7115182313115667, "eval_stsb_spearman": 0.8275193112934319, "step": 5125 }, { "epoch": 0.34, "eval_avg_sts": 0.7653115806051607, "eval_sickr_spearman": 0.7045340768825521, "eval_stsb_spearman": 0.8260890843277693, "step": 5250 }, { "epoch": 0.34, "eval_avg_sts": 0.7668890157040491, "eval_sickr_spearman": 0.7114907094904426, "eval_stsb_spearman": 0.8222873219176555, "step": 5375 }, { "epoch": 0.35, "learning_rate": 6.480225265583003e-06, "loss": 0.0006, "step": 5500 }, { "epoch": 0.35, "eval_avg_sts": 0.7699847309597411, "eval_sickr_spearman": 0.7107595800643516, "eval_stsb_spearman": 0.8292098818551306, "step": 5500 }, { "epoch": 0.36, "eval_avg_sts": 0.7567106410293966, "eval_sickr_spearman": 0.7000862527960785, "eval_stsb_spearman": 0.8133350292627146, "step": 5625 }, { "epoch": 0.37, "eval_avg_sts": 0.7573616140937487, "eval_sickr_spearman": 0.699952438147472, "eval_stsb_spearman": 0.8147707900400254, "step": 5750 }, { "epoch": 0.38, "eval_avg_sts": 0.7537503092076071, "eval_sickr_spearman": 0.6944211284747575, "eval_stsb_spearman": 0.8130794899404568, "step": 5875 }, { "epoch": 0.38, "learning_rate": 6.1602457442723675e-06, "loss": 0.0006, "step": 6000 }, { "epoch": 0.38, "eval_avg_sts": 0.7520214801965759, "eval_sickr_spearman": 0.6948064820015954, "eval_stsb_spearman": 0.8092364783915562, "step": 6000 }, { "epoch": 0.39, "eval_avg_sts": 0.7575813676798819, "eval_sickr_spearman": 0.7104122191387511, "eval_stsb_spearman": 0.8047505162210129, "step": 6125 }, { "epoch": 0.4, "eval_avg_sts": 0.7601457988270166, "eval_sickr_spearman": 0.7141828046949473, "eval_stsb_spearman": 0.8061087929590859, "step": 6250 }, { "epoch": 0.41, "eval_avg_sts": 0.7635874777468191, "eval_sickr_spearman": 0.71502354109452, "eval_stsb_spearman": 0.8121514143991182, "step": 6375 }, { "epoch": 0.42, "learning_rate": 5.840266222961732e-06, "loss": 0.0006, "step": 6500 }, { "epoch": 0.42, "eval_avg_sts": 0.7661782010291336, "eval_sickr_spearman": 0.7131075804581537, "eval_stsb_spearman": 0.8192488216001136, "step": 6500 }, { "epoch": 0.42, "eval_avg_sts": 0.7668687543410466, "eval_sickr_spearman": 0.715227337057922, "eval_stsb_spearman": 0.8185101716241713, "step": 6625 }, { "epoch": 0.43, "eval_avg_sts": 0.7653179212909831, "eval_sickr_spearman": 0.706994422022618, "eval_stsb_spearman": 0.8236414205593481, "step": 6750 }, { "epoch": 0.44, "eval_avg_sts": 0.7660646063264975, "eval_sickr_spearman": 0.708211338008654, "eval_stsb_spearman": 0.823917874644341, "step": 6875 }, { "epoch": 0.45, "learning_rate": 5.520286701651095e-06, "loss": 0.0005, "step": 7000 }, { "epoch": 0.45, "eval_avg_sts": 0.7679532903699651, "eval_sickr_spearman": 0.7082187828293769, "eval_stsb_spearman": 0.8276877979105532, "step": 7000 }, { "epoch": 0.46, "eval_avg_sts": 0.7681556050474033, "eval_sickr_spearman": 0.7095044313215708, "eval_stsb_spearman": 0.8268067787732358, "step": 7125 }, { "epoch": 0.46, "eval_avg_sts": 0.7631361714276783, "eval_sickr_spearman": 0.7091408358836844, "eval_stsb_spearman": 0.8171315069716724, "step": 7250 }, { "epoch": 0.47, "eval_avg_sts": 0.7696379675303331, "eval_sickr_spearman": 0.7148051917073824, "eval_stsb_spearman": 0.8244707433532837, "step": 7375 }, { "epoch": 0.48, "learning_rate": 5.200307180340458e-06, "loss": 0.0007, "step": 7500 }, { "epoch": 0.48, "eval_avg_sts": 0.7739437746585223, "eval_sickr_spearman": 0.7161355091239138, "eval_stsb_spearman": 0.8317520401931309, "step": 7500 }, { "epoch": 0.49, "eval_avg_sts": 0.7628158501141427, "eval_sickr_spearman": 0.7044322509475033, "eval_stsb_spearman": 0.8211994492807821, "step": 7625 }, { "epoch": 0.5, "eval_avg_sts": 0.7566107770472272, "eval_sickr_spearman": 0.7021283431048213, "eval_stsb_spearman": 0.8110932109896332, "step": 7750 }, { "epoch": 0.5, "eval_avg_sts": 0.7576093285240451, "eval_sickr_spearman": 0.7070185336355399, "eval_stsb_spearman": 0.8082001234125501, "step": 7875 }, { "epoch": 0.51, "learning_rate": 4.8803276590298225e-06, "loss": 0.0004, "step": 8000 }, { "epoch": 0.51, "eval_avg_sts": 0.760233390447007, "eval_sickr_spearman": 0.7091670608650695, "eval_stsb_spearman": 0.8112997200289445, "step": 8000 }, { "epoch": 0.52, "eval_avg_sts": 0.7602377460168234, "eval_sickr_spearman": 0.7104034774782894, "eval_stsb_spearman": 0.8100720145553574, "step": 8125 }, { "epoch": 0.53, "eval_avg_sts": 0.7616580314424666, "eval_sickr_spearman": 0.7110805719152625, "eval_stsb_spearman": 0.8122354909696707, "step": 8250 }, { "epoch": 0.54, "eval_avg_sts": 0.7651474794871342, "eval_sickr_spearman": 0.7107735571148701, "eval_stsb_spearman": 0.8195214018593985, "step": 8375 }, { "epoch": 0.54, "learning_rate": 4.560348137719187e-06, "loss": 0.0004, "step": 8500 }, { "epoch": 0.54, "eval_avg_sts": 0.7653451370230322, "eval_sickr_spearman": 0.7108329235562477, "eval_stsb_spearman": 0.8198573504898168, "step": 8500 }, { "epoch": 0.55, "eval_avg_sts": 0.7693105360724941, "eval_sickr_spearman": 0.7174611194925042, "eval_stsb_spearman": 0.821159952652484, "step": 8625 }, { "epoch": 0.56, "eval_avg_sts": 0.7688644948269532, "eval_sickr_spearman": 0.7159121645022266, "eval_stsb_spearman": 0.8218168251516798, "step": 8750 }, { "epoch": 0.57, "eval_avg_sts": 0.7658999611274551, "eval_sickr_spearman": 0.7111667877423439, "eval_stsb_spearman": 0.8206331345125664, "step": 8875 }, { "epoch": 0.58, "learning_rate": 4.24036861640855e-06, "loss": 0.0005, "step": 9000 }, { "epoch": 0.58, "eval_avg_sts": 0.7680124691016457, "eval_sickr_spearman": 0.7111179881432828, "eval_stsb_spearman": 0.8249069500600086, "step": 9000 }, { "epoch": 0.58, "eval_avg_sts": 0.7700973304120509, "eval_sickr_spearman": 0.7201923120135797, "eval_stsb_spearman": 0.8200023488105221, "step": 9125 }, { "epoch": 0.59, "eval_avg_sts": 0.7709943925570436, "eval_sickr_spearman": 0.7219245056558439, "eval_stsb_spearman": 0.8200642794582433, "step": 9250 }, { "epoch": 0.6, "eval_avg_sts": 0.7704940850500881, "eval_sickr_spearman": 0.7215150405160838, "eval_stsb_spearman": 0.8194731295840925, "step": 9375 }, { "epoch": 0.61, "learning_rate": 3.920389095097914e-06, "loss": 0.0007, "step": 9500 }, { "epoch": 0.61, "eval_avg_sts": 0.772013094506881, "eval_sickr_spearman": 0.7239060767767745, "eval_stsb_spearman": 0.8201201122369877, "step": 9500 }, { "epoch": 0.62, "eval_avg_sts": 0.7722529224488867, "eval_sickr_spearman": 0.7238736077522024, "eval_stsb_spearman": 0.8206322371455709, "step": 9625 }, { "epoch": 0.62, "eval_avg_sts": 0.769809433747652, "eval_sickr_spearman": 0.7224149992637298, "eval_stsb_spearman": 0.8172038682315741, "step": 9750 }, { "epoch": 0.63, "eval_avg_sts": 0.7692010357381744, "eval_sickr_spearman": 0.7215842533332562, "eval_stsb_spearman": 0.8168178181430927, "step": 9875 }, { "epoch": 0.64, "learning_rate": 3.600409573787278e-06, "loss": 0.0005, "step": 10000 }, { "epoch": 0.64, "eval_avg_sts": 0.7667248884742295, "eval_sickr_spearman": 0.719994904186669, "eval_stsb_spearman": 0.8134548727617901, "step": 10000 }, { "epoch": 0.65, "eval_avg_sts": 0.7631501690436606, "eval_sickr_spearman": 0.716718222446561, "eval_stsb_spearman": 0.8095821156407603, "step": 10125 }, { "epoch": 0.66, "eval_avg_sts": 0.7629832948957905, "eval_sickr_spearman": 0.7177377786367878, "eval_stsb_spearman": 0.8082288111547933, "step": 10250 }, { "epoch": 0.66, "eval_avg_sts": 0.7669126925997836, "eval_sickr_spearman": 0.7264237230208561, "eval_stsb_spearman": 0.8074016621787109, "step": 10375 }, { "epoch": 0.67, "learning_rate": 3.280430052476642e-06, "loss": 0.0006, "step": 10500 }, { "epoch": 0.67, "eval_avg_sts": 0.7718219901997241, "eval_sickr_spearman": 0.7337559108108911, "eval_stsb_spearman": 0.8098880695885572, "step": 10500 }, { "epoch": 0.68, "eval_avg_sts": 0.7714922632909542, "eval_sickr_spearman": 0.7311764005081574, "eval_stsb_spearman": 0.8118081260737511, "step": 10625 }, { "epoch": 0.69, "eval_avg_sts": 0.7727876566370058, "eval_sickr_spearman": 0.7285461693623048, "eval_stsb_spearman": 0.8170291439117067, "step": 10750 }, { "epoch": 0.7, "eval_avg_sts": 0.772842738222782, "eval_sickr_spearman": 0.7248763530569258, "eval_stsb_spearman": 0.8208091233886382, "step": 10875 }, { "epoch": 0.7, "learning_rate": 2.960450531166006e-06, "loss": 0.0005, "step": 11000 }, { "epoch": 0.7, "eval_avg_sts": 0.7737373423612539, "eval_sickr_spearman": 0.7237420025342619, "eval_stsb_spearman": 0.8237326821882459, "step": 11000 }, { "epoch": 0.71, "eval_avg_sts": 0.7736646449640281, "eval_sickr_spearman": 0.7248283219554877, "eval_stsb_spearman": 0.8225009679725683, "step": 11125 }, { "epoch": 0.72, "eval_avg_sts": 0.7733368787551957, "eval_sickr_spearman": 0.7176964238584496, "eval_stsb_spearman": 0.8289773336519419, "step": 11250 }, { "epoch": 0.73, "eval_avg_sts": 0.772262796771174, "eval_sickr_spearman": 0.7156863222632646, "eval_stsb_spearman": 0.8288392712790835, "step": 11375 }, { "epoch": 0.74, "learning_rate": 2.640471009855369e-06, "loss": 0.0006, "step": 11500 }, { "epoch": 0.74, "eval_avg_sts": 0.7728128954421813, "eval_sickr_spearman": 0.717364721071918, "eval_stsb_spearman": 0.8282610698124449, "step": 11500 }, { "epoch": 0.74, "eval_avg_sts": 0.7681791597143148, "eval_sickr_spearman": 0.7144295404630349, "eval_stsb_spearman": 0.8219287789655949, "step": 11625 }, { "epoch": 0.75, "eval_avg_sts": 0.7668750327968881, "eval_sickr_spearman": 0.7139568663937824, "eval_stsb_spearman": 0.8197931991999937, "step": 11750 }, { "epoch": 0.76, "eval_avg_sts": 0.7640936046803386, "eval_sickr_spearman": 0.7124148278821119, "eval_stsb_spearman": 0.8157723814785652, "step": 11875 }, { "epoch": 0.77, "learning_rate": 2.3204914885447333e-06, "loss": 0.0007, "step": 12000 }, { "epoch": 0.77, "eval_avg_sts": 0.7638027953353596, "eval_sickr_spearman": 0.7146511079339689, "eval_stsb_spearman": 0.8129544827367502, "step": 12000 }, { "epoch": 0.78, "eval_avg_sts": 0.7619683130589899, "eval_sickr_spearman": 0.7137378445712247, "eval_stsb_spearman": 0.8101987815467552, "step": 12125 }, { "epoch": 0.78, "eval_avg_sts": 0.7636607985650499, "eval_sickr_spearman": 0.7154829585797756, "eval_stsb_spearman": 0.811838638550324, "step": 12250 }, { "epoch": 0.79, "eval_avg_sts": 0.7656556423146959, "eval_sickr_spearman": 0.7171441142230127, "eval_stsb_spearman": 0.8141671704063791, "step": 12375 }, { "epoch": 0.8, "learning_rate": 2.000511967234097e-06, "loss": 0.0007, "step": 12500 }, { "epoch": 0.8, "eval_avg_sts": 0.7654090921860195, "eval_sickr_spearman": 0.7177945513986876, "eval_stsb_spearman": 0.8130236329733512, "step": 12500 }, { "epoch": 0.81, "eval_avg_sts": 0.7631961636347036, "eval_sickr_spearman": 0.7180557925594095, "eval_stsb_spearman": 0.8083365347099974, "step": 12625 }, { "epoch": 0.82, "eval_avg_sts": 0.7639726864144019, "eval_sickr_spearman": 0.7181145345964683, "eval_stsb_spearman": 0.8098308382323353, "step": 12750 }, { "epoch": 0.82, "eval_avg_sts": 0.7630039855353228, "eval_sickr_spearman": 0.7154700382134888, "eval_stsb_spearman": 0.8105379328571569, "step": 12875 }, { "epoch": 0.83, "learning_rate": 1.6805324459234608e-06, "loss": 0.0007, "step": 13000 }, { "epoch": 0.83, "eval_avg_sts": 0.7623670598777739, "eval_sickr_spearman": 0.7141997116426535, "eval_stsb_spearman": 0.8105344081128942, "step": 13000 }, { "epoch": 0.84, "eval_avg_sts": 0.762649541131944, "eval_sickr_spearman": 0.714223871286677, "eval_stsb_spearman": 0.8110752109772111, "step": 13125 }, { "epoch": 0.85, "eval_avg_sts": 0.762339972693242, "eval_sickr_spearman": 0.7139050408353308, "eval_stsb_spearman": 0.8107749045511534, "step": 13250 }, { "epoch": 0.86, "eval_avg_sts": 0.7621756663732473, "eval_sickr_spearman": 0.7133488406806774, "eval_stsb_spearman": 0.8110024920658171, "step": 13375 }, { "epoch": 0.86, "learning_rate": 1.3605529246128248e-06, "loss": 0.0006, "step": 13500 }, { "epoch": 0.86, "eval_avg_sts": 0.7614721810339764, "eval_sickr_spearman": 0.7150819949449702, "eval_stsb_spearman": 0.8078623671229826, "step": 13500 }, { "epoch": 0.87, "eval_avg_sts": 0.7613416141094851, "eval_sickr_spearman": 0.7152224378855754, "eval_stsb_spearman": 0.8074607903333948, "step": 13625 }, { "epoch": 0.88, "eval_avg_sts": 0.7619056768073365, "eval_sickr_spearman": 0.7157069276057815, "eval_stsb_spearman": 0.8081044260088914, "step": 13750 }, { "epoch": 0.89, "eval_avg_sts": 0.7625807690636458, "eval_sickr_spearman": 0.7158452091468218, "eval_stsb_spearman": 0.8093163289804698, "step": 13875 }, { "epoch": 0.9, "learning_rate": 1.0405734033021888e-06, "loss": 0.0005, "step": 14000 }, { "epoch": 0.9, "eval_avg_sts": 0.7626740159905894, "eval_sickr_spearman": 0.7153790192762635, "eval_stsb_spearman": 0.8099690127049152, "step": 14000 }, { "epoch": 0.9, "eval_avg_sts": 0.7623073492171049, "eval_sickr_spearman": 0.7137424075258613, "eval_stsb_spearman": 0.8108722909083483, "step": 14125 }, { "epoch": 0.91, "eval_avg_sts": 0.7627676837162675, "eval_sickr_spearman": 0.7135836167045069, "eval_stsb_spearman": 0.811951750728028, "step": 14250 }, { "epoch": 0.92, "eval_avg_sts": 0.7622897188554142, "eval_sickr_spearman": 0.7125857225410286, "eval_stsb_spearman": 0.8119937151697998, "step": 14375 }, { "epoch": 0.93, "learning_rate": 7.205938819915525e-07, "loss": 0.0003, "step": 14500 }, { "epoch": 0.93, "eval_avg_sts": 0.762755661091796, "eval_sickr_spearman": 0.7135279486579401, "eval_stsb_spearman": 0.8119833735256521, "step": 14500 }, { "epoch": 0.94, "eval_avg_sts": 0.7635781922303508, "eval_sickr_spearman": 0.7126439362359717, "eval_stsb_spearman": 0.8145124482247301, "step": 14625 }, { "epoch": 0.94, "eval_avg_sts": 0.7627630570209332, "eval_sickr_spearman": 0.7108910892200891, "eval_stsb_spearman": 0.8146350248217772, "step": 14750 }, { "epoch": 0.95, "eval_avg_sts": 0.7620568929343465, "eval_sickr_spearman": 0.7104201923015899, "eval_stsb_spearman": 0.8136935935671031, "step": 14875 }, { "epoch": 0.96, "learning_rate": 4.0061436068091647e-07, "loss": 0.0007, "step": 15000 }, { "epoch": 0.96, "eval_avg_sts": 0.7614322691019428, "eval_sickr_spearman": 0.7104694241805639, "eval_stsb_spearman": 0.8123951140233218, "step": 15000 }, { "epoch": 0.97, "eval_avg_sts": 0.7614246018155921, "eval_sickr_spearman": 0.7104402212708896, "eval_stsb_spearman": 0.8124089823602947, "step": 15125 }, { "epoch": 0.98, "eval_avg_sts": 0.7615696008749822, "eval_sickr_spearman": 0.7107793208470427, "eval_stsb_spearman": 0.8123598809029217, "step": 15250 }, { "epoch": 0.98, "eval_avg_sts": 0.7613961550857908, "eval_sickr_spearman": 0.7105805201181903, "eval_stsb_spearman": 0.8122117900533915, "step": 15375 }, { "epoch": 0.99, "learning_rate": 8.06348393702803e-08, "loss": 0.0005, "step": 15500 }, { "epoch": 0.99, "eval_avg_sts": 0.7614175786889548, "eval_sickr_spearman": 0.7106010293985044, "eval_stsb_spearman": 0.812234127979405, "step": 15500 }, { "epoch": 1.0, "eval_avg_sts": 0.7613506554623436, "eval_sickr_spearman": 0.7104816721114307, "eval_stsb_spearman": 0.8122196388132565, "step": 15625 }, { "epoch": 1.0, "step": 15626, "train_runtime": 4633.8657, "train_samples_per_second": 3.372 } ], "max_steps": 15626, "num_train_epochs": 1, "total_flos": 119690591356191744, "trial_name": null, "trial_params": null }