{ "best_metric": 0.8592533976547048, "best_model_checkpoint": "checkpoints/multicse-roberta-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": 0.5258570395156345, "eval_sickr_spearman": 0.5533369246344159, "eval_stsb_spearman": 0.4983771543968531, "step": 25 }, { "epoch": 0.06, "eval_avg_sts": 0.7850148023693055, "eval_sickr_spearman": 0.7550652932127213, "eval_stsb_spearman": 0.8149643115258898, "step": 50 }, { "epoch": 0.08, "eval_avg_sts": 0.8230417971117017, "eval_sickr_spearman": 0.8039761803358758, "eval_stsb_spearman": 0.8421074138875275, "step": 75 }, { "epoch": 0.11, "eval_avg_sts": 0.8229977066254568, "eval_sickr_spearman": 0.8013150171606973, "eval_stsb_spearman": 0.8446803960902164, "step": 100 }, { "epoch": 0.14, "eval_avg_sts": 0.8250867364664243, "eval_sickr_spearman": 0.8020941296571249, "eval_stsb_spearman": 0.8480793432757237, "step": 125 }, { "epoch": 0.17, "eval_avg_sts": 0.8343038041059325, "eval_sickr_spearman": 0.8130164981863546, "eval_stsb_spearman": 0.8555911100255104, "step": 150 }, { "epoch": 0.19, "eval_avg_sts": 0.8341218485661299, "eval_sickr_spearman": 0.8137427764712003, "eval_stsb_spearman": 0.8545009206610595, "step": 175 }, { "epoch": 0.22, "eval_avg_sts": 0.8292804411707589, "eval_sickr_spearman": 0.8028885640749114, "eval_stsb_spearman": 0.8556723182666065, "step": 200 }, { "epoch": 0.25, "eval_avg_sts": 0.8343114076624676, "eval_sickr_spearman": 0.8119119269465824, "eval_stsb_spearman": 0.8567108883783526, "step": 225 }, { "epoch": 0.28, "eval_avg_sts": 0.8374413121168582, "eval_sickr_spearman": 0.8194021370603487, "eval_stsb_spearman": 0.8554804871733678, "step": 250 }, { "epoch": 0.3, "eval_avg_sts": 0.790030690165741, "eval_sickr_spearman": 0.7826885079918957, "eval_stsb_spearman": 0.7973728723395863, "step": 275 }, { "epoch": 0.33, "eval_avg_sts": 0.8296463453278495, "eval_sickr_spearman": 0.813207854094484, "eval_stsb_spearman": 0.846084836561215, "step": 300 }, { "epoch": 0.36, "eval_avg_sts": 0.8310185376263133, "eval_sickr_spearman": 0.81294286650785, "eval_stsb_spearman": 0.8490942087447765, "step": 325 }, { "epoch": 0.39, "eval_avg_sts": 0.8143706216478173, "eval_sickr_spearman": 0.8089154106211628, "eval_stsb_spearman": 0.8198258326744716, "step": 350 }, { "epoch": 0.42, "eval_avg_sts": 0.8350372402041332, "eval_sickr_spearman": 0.8196295643256583, "eval_stsb_spearman": 0.8504449160826081, "step": 375 }, { "epoch": 0.44, "eval_avg_sts": 0.8164152692168181, "eval_sickr_spearman": 0.7969415932503514, "eval_stsb_spearman": 0.8358889451832846, "step": 400 }, { "epoch": 0.47, "eval_avg_sts": 0.8336510848982669, "eval_sickr_spearman": 0.8124280691626363, "eval_stsb_spearman": 0.8548741006338975, "step": 425 }, { "epoch": 0.5, "eval_avg_sts": 0.8287756211043293, "eval_sickr_spearman": 0.8041324735399555, "eval_stsb_spearman": 0.8534187686687033, "step": 450 }, { "epoch": 0.53, "eval_avg_sts": 0.7419793879287948, "eval_sickr_spearman": 0.7170895028606776, "eval_stsb_spearman": 0.766869272996912, "step": 475 }, { "epoch": 0.55, "learning_rate": 8.152254249815226e-06, "loss": 0.6723, "step": 500 }, { "epoch": 0.55, "eval_avg_sts": 0.8448102989750537, "eval_sickr_spearman": 0.8239814222714584, "eval_stsb_spearman": 0.865639175678649, "step": 500 }, { "epoch": 0.58, "eval_avg_sts": 0.8357715679368597, "eval_sickr_spearman": 0.8123892120015728, "eval_stsb_spearman": 0.8591539238721466, "step": 525 }, { "epoch": 0.61, "eval_avg_sts": 0.7209666511512107, "eval_sickr_spearman": 0.6828403015759127, "eval_stsb_spearman": 0.7590930007265089, "step": 550 }, { "epoch": 0.64, "eval_avg_sts": 0.8322843696635686, "eval_sickr_spearman": 0.8107304579134076, "eval_stsb_spearman": 0.8538382814137295, "step": 575 }, { "epoch": 0.67, "eval_avg_sts": 0.8417184990226367, "eval_sickr_spearman": 0.8216292912029326, "eval_stsb_spearman": 0.8618077068423408, "step": 600 }, { "epoch": 0.69, "eval_avg_sts": 0.8001972328140533, "eval_sickr_spearman": 0.7744180806663685, "eval_stsb_spearman": 0.8259763849617381, "step": 625 }, { "epoch": 0.72, "eval_avg_sts": 0.8280003805677492, "eval_sickr_spearman": 0.8052124048246901, "eval_stsb_spearman": 0.8507883563108082, "step": 650 }, { "epoch": 0.75, "eval_avg_sts": 0.8502864910727694, "eval_sickr_spearman": 0.8340239570845448, "eval_stsb_spearman": 0.8665490250609942, "step": 675 }, { "epoch": 0.78, "eval_avg_sts": 0.8491384622588354, "eval_sickr_spearman": 0.8335061337799405, "eval_stsb_spearman": 0.8647707907377303, "step": 700 }, { "epoch": 0.8, "eval_avg_sts": 0.833430245079678, "eval_sickr_spearman": 0.8096134946494643, "eval_stsb_spearman": 0.8572469955098916, "step": 725 }, { "epoch": 0.83, "eval_avg_sts": 0.8440579172879747, "eval_sickr_spearman": 0.825622452883193, "eval_stsb_spearman": 0.8624933816927564, "step": 750 }, { "epoch": 0.86, "eval_avg_sts": 0.7868824796982673, "eval_sickr_spearman": 0.7489995895054065, "eval_stsb_spearman": 0.8247653698911281, "step": 775 }, { "epoch": 0.89, "eval_avg_sts": 0.8339843444164832, "eval_sickr_spearman": 0.8106915046901414, "eval_stsb_spearman": 0.8572771841428249, "step": 800 }, { "epoch": 0.91, "eval_avg_sts": 0.8184786625842368, "eval_sickr_spearman": 0.7940952221480274, "eval_stsb_spearman": 0.8428621030204463, "step": 825 }, { "epoch": 0.94, "eval_avg_sts": 0.8413785182540383, "eval_sickr_spearman": 0.8238849758197707, "eval_stsb_spearman": 0.858872060688306, "step": 850 }, { "epoch": 0.97, "eval_avg_sts": 0.8450123523064677, "eval_sickr_spearman": 0.8247908904239951, "eval_stsb_spearman": 0.8652338141889402, "step": 875 }, { "epoch": 1.0, "eval_avg_sts": 0.836423550431332, "eval_sickr_spearman": 0.8192137110494071, "eval_stsb_spearman": 0.8536333898132569, "step": 900 }, { "epoch": 1.03, "eval_avg_sts": 0.8230741682060118, "eval_sickr_spearman": 0.8026094553444544, "eval_stsb_spearman": 0.8435388810675691, "step": 925 }, { "epoch": 1.05, "eval_avg_sts": 0.8500639069789373, "eval_sickr_spearman": 0.8328587225636562, "eval_stsb_spearman": 0.8672690913942185, "step": 950 }, { "epoch": 1.08, "eval_avg_sts": 0.8323002280574656, "eval_sickr_spearman": 0.8130526656057375, "eval_stsb_spearman": 0.8515477905091938, "step": 975 }, { "epoch": 1.11, "learning_rate": 6.304508499630452e-06, "loss": 0.2548, "step": 1000 }, { "epoch": 1.11, "eval_avg_sts": 0.8239924175524644, "eval_sickr_spearman": 0.8011878788351906, "eval_stsb_spearman": 0.8467969562697383, "step": 1000 }, { "epoch": 1.14, "eval_avg_sts": 0.8430266753860738, "eval_sickr_spearman": 0.8271581993205753, "eval_stsb_spearman": 0.8588951514515721, "step": 1025 }, { "epoch": 1.16, "eval_avg_sts": 0.8592533976547048, "eval_sickr_spearman": 0.8491095173931258, "eval_stsb_spearman": 0.8693972779162836, "step": 1050 }, { "epoch": 1.19, "eval_avg_sts": 0.8411301121031662, "eval_sickr_spearman": 0.8243206659409158, "eval_stsb_spearman": 0.8579395582654168, "step": 1075 }, { "epoch": 1.22, "eval_avg_sts": 0.847249395072464, "eval_sickr_spearman": 0.8336754434125099, "eval_stsb_spearman": 0.8608233467324182, "step": 1100 }, { "epoch": 1.25, "eval_avg_sts": 0.8526050717559741, "eval_sickr_spearman": 0.8367417969594204, "eval_stsb_spearman": 0.8684683465525278, "step": 1125 }, { "epoch": 1.27, "eval_avg_sts": 0.844364830879988, "eval_sickr_spearman": 0.8298262309432596, "eval_stsb_spearman": 0.8589034308167164, "step": 1150 }, { "epoch": 1.3, "eval_avg_sts": 0.848322685283306, "eval_sickr_spearman": 0.8344140656904253, "eval_stsb_spearman": 0.8622313048761867, "step": 1175 }, { "epoch": 1.33, "eval_avg_sts": 0.8556312662617278, "eval_sickr_spearman": 0.8397956143888556, "eval_stsb_spearman": 0.8714669181346, "step": 1200 }, { "epoch": 1.36, "eval_avg_sts": 0.8410090445747178, "eval_sickr_spearman": 0.8271102162502385, "eval_stsb_spearman": 0.854907872899197, "step": 1225 }, { "epoch": 1.39, "eval_avg_sts": 0.8433567077421059, "eval_sickr_spearman": 0.8297940981363974, "eval_stsb_spearman": 0.8569193173478145, "step": 1250 }, { "epoch": 1.41, "eval_avg_sts": 0.8482515472422293, "eval_sickr_spearman": 0.8282899081326601, "eval_stsb_spearman": 0.8682131863517984, "step": 1275 }, { "epoch": 1.44, "eval_avg_sts": 0.8255461568624773, "eval_sickr_spearman": 0.8016815905268729, "eval_stsb_spearman": 0.8494107231980819, "step": 1300 }, { "epoch": 1.47, "eval_avg_sts": 0.8414977629623656, "eval_sickr_spearman": 0.8257801870203159, "eval_stsb_spearman": 0.8572153389044153, "step": 1325 }, { "epoch": 1.5, "eval_avg_sts": 0.8378396186869672, "eval_sickr_spearman": 0.818870768985139, "eval_stsb_spearman": 0.8568084683887955, "step": 1350 }, { "epoch": 1.52, "eval_avg_sts": 0.8388588093044617, "eval_sickr_spearman": 0.8194774978585052, "eval_stsb_spearman": 0.8582401207504181, "step": 1375 }, { "epoch": 1.55, "eval_avg_sts": 0.8105082650410843, "eval_sickr_spearman": 0.7798514549232508, "eval_stsb_spearman": 0.8411650751589178, "step": 1400 }, { "epoch": 1.58, "eval_avg_sts": 0.8317602737815382, "eval_sickr_spearman": 0.808493025115116, "eval_stsb_spearman": 0.8550275224479604, "step": 1425 }, { "epoch": 1.61, "eval_avg_sts": 0.8302226748348518, "eval_sickr_spearman": 0.8096536486502666, "eval_stsb_spearman": 0.8507917010194369, "step": 1450 }, { "epoch": 1.64, "eval_avg_sts": 0.8389729127479303, "eval_sickr_spearman": 0.82068802570805, "eval_stsb_spearman": 0.8572577997878106, "step": 1475 }, { "epoch": 1.66, "learning_rate": 4.456762749445676e-06, "loss": 0.2263, "step": 1500 }, { "epoch": 1.66, "eval_avg_sts": 0.8369919843777802, "eval_sickr_spearman": 0.8199678954041884, "eval_stsb_spearman": 0.8540160733513722, "step": 1500 }, { "epoch": 1.69, "eval_avg_sts": 0.8419013805527449, "eval_sickr_spearman": 0.8240405485573288, "eval_stsb_spearman": 0.859762212548161, "step": 1525 }, { "epoch": 1.72, "eval_avg_sts": 0.8480363963137308, "eval_sickr_spearman": 0.8348668548836823, "eval_stsb_spearman": 0.8612059377437794, "step": 1550 }, { "epoch": 1.75, "eval_avg_sts": 0.8091657034677889, "eval_sickr_spearman": 0.7825481611134937, "eval_stsb_spearman": 0.8357832458220842, "step": 1575 }, { "epoch": 1.77, "eval_avg_sts": 0.8226090989602317, "eval_sickr_spearman": 0.8031343872520715, "eval_stsb_spearman": 0.8420838106683919, "step": 1600 }, { "epoch": 1.8, "eval_avg_sts": 0.8462010311383265, "eval_sickr_spearman": 0.8290648419232626, "eval_stsb_spearman": 0.8633372203533903, "step": 1625 }, { "epoch": 1.83, "eval_avg_sts": 0.8425324447977967, "eval_sickr_spearman": 0.8293013470667437, "eval_stsb_spearman": 0.8557635425288497, "step": 1650 }, { "epoch": 1.86, "eval_avg_sts": 0.8380198548580302, "eval_sickr_spearman": 0.8243921362198557, "eval_stsb_spearman": 0.8516475734962046, "step": 1675 }, { "epoch": 1.88, "eval_avg_sts": 0.8132086349641947, "eval_sickr_spearman": 0.7851564900770903, "eval_stsb_spearman": 0.8412607798512991, "step": 1700 }, { "epoch": 1.91, "eval_avg_sts": 0.8097006725652637, "eval_sickr_spearman": 0.7851859811733733, "eval_stsb_spearman": 0.834215363957154, "step": 1725 }, { "epoch": 1.94, "eval_avg_sts": 0.8376290282716883, "eval_sickr_spearman": 0.8213424974962457, "eval_stsb_spearman": 0.8539155590471308, "step": 1750 }, { "epoch": 1.97, "eval_avg_sts": 0.842835929581756, "eval_sickr_spearman": 0.8281722319341366, "eval_stsb_spearman": 0.8574996272293754, "step": 1775 }, { "epoch": 2.0, "eval_avg_sts": 0.8359820146737951, "eval_sickr_spearman": 0.8189481951206572, "eval_stsb_spearman": 0.8530158342269328, "step": 1800 }, { "epoch": 2.02, "eval_avg_sts": 0.8468289826472446, "eval_sickr_spearman": 0.833371886851421, "eval_stsb_spearman": 0.8602860784430681, "step": 1825 }, { "epoch": 2.05, "eval_avg_sts": 0.8338277707857178, "eval_sickr_spearman": 0.8164911160954891, "eval_stsb_spearman": 0.8511644254759464, "step": 1850 }, { "epoch": 2.08, "eval_avg_sts": 0.8341757574943203, "eval_sickr_spearman": 0.8175209029103222, "eval_stsb_spearman": 0.8508306120783183, "step": 1875 }, { "epoch": 2.11, "eval_avg_sts": 0.8453760865720144, "eval_sickr_spearman": 0.8318047761047997, "eval_stsb_spearman": 0.8589473970392288, "step": 1900 }, { "epoch": 2.13, "eval_avg_sts": 0.8316563095078086, "eval_sickr_spearman": 0.8132579505332841, "eval_stsb_spearman": 0.850054668482333, "step": 1925 }, { "epoch": 2.16, "eval_avg_sts": 0.8418222098580312, "eval_sickr_spearman": 0.825691617669264, "eval_stsb_spearman": 0.8579528020467985, "step": 1950 }, { "epoch": 2.19, "eval_avg_sts": 0.8282466528439865, "eval_sickr_spearman": 0.8085680016644609, "eval_stsb_spearman": 0.8479253040235121, "step": 1975 }, { "epoch": 2.22, "learning_rate": 2.609016999260902e-06, "loss": 0.2138, "step": 2000 }, { "epoch": 2.22, "eval_avg_sts": 0.8395154203911175, "eval_sickr_spearman": 0.8241901654383085, "eval_stsb_spearman": 0.8548406753439265, "step": 2000 }, { "epoch": 2.25, "eval_avg_sts": 0.8354243601616307, "eval_sickr_spearman": 0.8186561660239136, "eval_stsb_spearman": 0.8521925542993478, "step": 2025 }, { "epoch": 2.27, "eval_avg_sts": 0.8361344462215647, "eval_sickr_spearman": 0.8192864781680858, "eval_stsb_spearman": 0.8529824142750437, "step": 2050 }, { "epoch": 2.3, "eval_avg_sts": 0.8303651499407738, "eval_sickr_spearman": 0.8091401961758931, "eval_stsb_spearman": 0.8515901037056545, "step": 2075 }, { "epoch": 2.33, "eval_avg_sts": 0.8314677597128309, "eval_sickr_spearman": 0.8115453535804066, "eval_stsb_spearman": 0.8513901658452553, "step": 2100 }, { "epoch": 2.36, "eval_avg_sts": 0.8406198858453933, "eval_sickr_spearman": 0.8232477471969915, "eval_stsb_spearman": 0.8579920244937951, "step": 2125 }, { "epoch": 2.38, "eval_avg_sts": 0.8310127908616497, "eval_sickr_spearman": 0.808406521101426, "eval_stsb_spearman": 0.8536190606218734, "step": 2150 }, { "epoch": 2.41, "eval_avg_sts": 0.8360186536704766, "eval_sickr_spearman": 0.8149144951907831, "eval_stsb_spearman": 0.85712281215017, "step": 2175 }, { "epoch": 2.44, "eval_avg_sts": 0.8310352588949227, "eval_sickr_spearman": 0.8092654612884438, "eval_stsb_spearman": 0.8528050565014016, "step": 2200 }, { "epoch": 2.47, "eval_avg_sts": 0.820254245514857, "eval_sickr_spearman": 0.7949483986028726, "eval_stsb_spearman": 0.8455600924268415, "step": 2225 }, { "epoch": 2.49, "eval_avg_sts": 0.8271707424843158, "eval_sickr_spearman": 0.8042670566861851, "eval_stsb_spearman": 0.8500744282824465, "step": 2250 }, { "epoch": 2.52, "eval_avg_sts": 0.831725837948319, "eval_sickr_spearman": 0.8097772326742668, "eval_stsb_spearman": 0.8536744432223711, "step": 2275 }, { "epoch": 2.55, "eval_avg_sts": 0.8478084080683095, "eval_sickr_spearman": 0.833967952820268, "eval_stsb_spearman": 0.8616488633163509, "step": 2300 }, { "epoch": 2.58, "eval_avg_sts": 0.8417932529667509, "eval_sickr_spearman": 0.824586422025173, "eval_stsb_spearman": 0.8590000839083288, "step": 2325 }, { "epoch": 2.61, "eval_avg_sts": 0.8443266422798352, "eval_sickr_spearman": 0.8284084008599079, "eval_stsb_spearman": 0.8602448836997627, "step": 2350 }, { "epoch": 2.63, "eval_avg_sts": 0.8414441103010829, "eval_sickr_spearman": 0.8235661453684245, "eval_stsb_spearman": 0.8593220752337413, "step": 2375 }, { "epoch": 2.66, "eval_avg_sts": 0.8332215941917105, "eval_sickr_spearman": 0.8123268676319063, "eval_stsb_spearman": 0.8541163207515148, "step": 2400 }, { "epoch": 2.69, "eval_avg_sts": 0.8352256220211349, "eval_sickr_spearman": 0.8149729490412333, "eval_stsb_spearman": 0.8554782950010364, "step": 2425 }, { "epoch": 2.72, "eval_avg_sts": 0.8367509129954576, "eval_sickr_spearman": 0.8170744538224549, "eval_stsb_spearman": 0.8564273721684602, "step": 2450 }, { "epoch": 2.74, "eval_avg_sts": 0.8332216363076352, "eval_sickr_spearman": 0.8119204284515368, "eval_stsb_spearman": 0.8545228441637336, "step": 2475 }, { "epoch": 2.77, "learning_rate": 7.612712490761272e-07, "loss": 0.2031, "step": 2500 }, { "epoch": 2.77, "eval_avg_sts": 0.8372319946443687, "eval_sickr_spearman": 0.8181658645404332, "eval_stsb_spearman": 0.8562981247483044, "step": 2500 }, { "epoch": 2.8, "eval_avg_sts": 0.8296643440620797, "eval_sickr_spearman": 0.8083195367767216, "eval_stsb_spearman": 0.8510091513474377, "step": 2525 }, { "epoch": 2.83, "eval_avg_sts": 0.8263914133784362, "eval_sickr_spearman": 0.8030280944245891, "eval_stsb_spearman": 0.8497547323322834, "step": 2550 }, { "epoch": 2.85, "eval_avg_sts": 0.8200950718061857, "eval_sickr_spearman": 0.7943617467299074, "eval_stsb_spearman": 0.845828396882464, "step": 2575 }, { "epoch": 2.88, "eval_avg_sts": 0.8200823058439606, "eval_sickr_spearman": 0.7944934480100508, "eval_stsb_spearman": 0.8456711636778702, "step": 2600 }, { "epoch": 2.91, "eval_avg_sts": 0.8192258345292275, "eval_sickr_spearman": 0.7934071285888249, "eval_stsb_spearman": 0.8450445404696301, "step": 2625 }, { "epoch": 2.94, "eval_avg_sts": 0.824292679030638, "eval_sickr_spearman": 0.8000518952550778, "eval_stsb_spearman": 0.8485334628061982, "step": 2650 }, { "epoch": 2.97, "eval_avg_sts": 0.8236712234461467, "eval_sickr_spearman": 0.7990280162657215, "eval_stsb_spearman": 0.8483144306265721, "step": 2675 }, { "epoch": 2.99, "eval_avg_sts": 0.8240279287421932, "eval_sickr_spearman": 0.7991273445834955, "eval_stsb_spearman": 0.8489285129008908, "step": 2700 }, { "epoch": 3.0, "step": 2706, "train_runtime": 7654.807, "train_samples_per_second": 0.354 } ], "max_steps": 2706, "num_train_epochs": 3, "total_flos": 325226340493098624, "trial_name": null, "trial_params": null }