{ "best_metric": 0.8485214656023966, "best_model_checkpoint": "result/esimcse-bert-base-uncased-0.1-bpe-0.32-160-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": 0.6100880461913585, "eval_sickr_spearman": 0.5832078028364882, "eval_stsb_spearman": 0.6369682895462287, "step": 125 }, { "epoch": 0.02, "eval_avg_sts": 0.6397205453652646, "eval_sickr_spearman": 0.616963004242962, "eval_stsb_spearman": 0.6624780864875672, "step": 250 }, { "epoch": 0.02, "eval_avg_sts": 0.6789809731427074, "eval_sickr_spearman": 0.6587511191783517, "eval_stsb_spearman": 0.6992108271070633, "step": 375 }, { "epoch": 0.03, "learning_rate": 2.9040061436068092e-05, "loss": 0.0108, "step": 500 }, { "epoch": 0.03, "eval_avg_sts": 0.7335141964825347, "eval_sickr_spearman": 0.7049946471142421, "eval_stsb_spearman": 0.7620337458508273, "step": 500 }, { "epoch": 0.04, "eval_avg_sts": 0.7519583861186683, "eval_sickr_spearman": 0.7213448663236887, "eval_stsb_spearman": 0.782571905913648, "step": 625 }, { "epoch": 0.05, "eval_avg_sts": 0.7678435373865832, "eval_sickr_spearman": 0.7283978012899625, "eval_stsb_spearman": 0.8072892734832039, "step": 750 }, { "epoch": 0.06, "eval_avg_sts": 0.7606834842782872, "eval_sickr_spearman": 0.719232746669049, "eval_stsb_spearman": 0.8021342218875254, "step": 875 }, { "epoch": 0.06, "learning_rate": 2.8080122872136184e-05, "loss": 0.0007, "step": 1000 }, { "epoch": 0.06, "eval_avg_sts": 0.7725764209069759, "eval_sickr_spearman": 0.7352987658512863, "eval_stsb_spearman": 0.8098540759626653, "step": 1000 }, { "epoch": 0.07, "eval_avg_sts": 0.749297683848744, "eval_sickr_spearman": 0.7265425039347125, "eval_stsb_spearman": 0.7720528637627754, "step": 1125 }, { "epoch": 0.08, "eval_avg_sts": 0.7274946000391853, "eval_sickr_spearman": 0.7107656319831328, "eval_stsb_spearman": 0.7442235680952377, "step": 1250 }, { "epoch": 0.09, "eval_avg_sts": 0.7476475148023185, "eval_sickr_spearman": 0.7236732700281041, "eval_stsb_spearman": 0.7716217595765328, "step": 1375 }, { "epoch": 0.1, "learning_rate": 2.7120184308204276e-05, "loss": 0.0006, "step": 1500 }, { "epoch": 0.1, "eval_avg_sts": 0.7566770100403266, "eval_sickr_spearman": 0.7318386053036846, "eval_stsb_spearman": 0.7815154147769687, "step": 1500 }, { "epoch": 0.1, "eval_avg_sts": 0.7600955301789452, "eval_sickr_spearman": 0.7316815916330834, "eval_stsb_spearman": 0.7885094687248068, "step": 1625 }, { "epoch": 0.11, "eval_avg_sts": 0.7270610894602345, "eval_sickr_spearman": 0.6906233092840458, "eval_stsb_spearman": 0.7634988696364233, "step": 1750 }, { "epoch": 0.12, "eval_avg_sts": 0.7308078942978946, "eval_sickr_spearman": 0.6979846039215525, "eval_stsb_spearman": 0.7636311846742367, "step": 1875 }, { "epoch": 0.13, "learning_rate": 2.6160245744272367e-05, "loss": 0.0004, "step": 2000 }, { "epoch": 0.13, "eval_avg_sts": 0.7009937398682455, "eval_sickr_spearman": 0.676284680633929, "eval_stsb_spearman": 0.7257027991025622, "step": 2000 }, { "epoch": 0.14, "eval_avg_sts": 0.7145112612407412, "eval_sickr_spearman": 0.6811648326644469, "eval_stsb_spearman": 0.7478576898170354, "step": 2125 }, { "epoch": 0.14, "eval_avg_sts": 0.7269807482138698, "eval_sickr_spearman": 0.6930580538470452, "eval_stsb_spearman": 0.7609034425806944, "step": 2250 }, { "epoch": 0.15, "eval_avg_sts": 0.7876865693494822, "eval_sickr_spearman": 0.7498401337805735, "eval_stsb_spearman": 0.825533004918391, "step": 2375 }, { "epoch": 0.16, "learning_rate": 2.5200307180340456e-05, "loss": 0.0006, "step": 2500 }, { "epoch": 0.16, "eval_avg_sts": 0.7800273423845525, "eval_sickr_spearman": 0.7402713297209711, "eval_stsb_spearman": 0.8197833550481338, "step": 2500 }, { "epoch": 0.17, "eval_avg_sts": 0.7774661815337005, "eval_sickr_spearman": 0.7407253196917641, "eval_stsb_spearman": 0.8142070433756369, "step": 2625 }, { "epoch": 0.18, "eval_avg_sts": 0.795139063492616, "eval_sickr_spearman": 0.7583184877442262, "eval_stsb_spearman": 0.8319596392410058, "step": 2750 }, { "epoch": 0.18, "eval_avg_sts": 0.8007774495654907, "eval_sickr_spearman": 0.7530334335285849, "eval_stsb_spearman": 0.8485214656023966, "step": 2875 }, { "epoch": 0.19, "learning_rate": 2.424036861640855e-05, "loss": 0.0005, "step": 3000 }, { "epoch": 0.19, "eval_avg_sts": 0.7910581147340385, "eval_sickr_spearman": 0.7508507561859327, "eval_stsb_spearman": 0.8312654732821445, "step": 3000 }, { "epoch": 0.2, "eval_avg_sts": 0.7798469609404326, "eval_sickr_spearman": 0.7498414786514137, "eval_stsb_spearman": 0.8098524432294515, "step": 3125 }, { "epoch": 0.21, "eval_avg_sts": 0.7100086424191657, "eval_sickr_spearman": 0.6737912900960736, "eval_stsb_spearman": 0.7462259947422578, "step": 3250 }, { "epoch": 0.22, "eval_avg_sts": 0.7098691907547254, "eval_sickr_spearman": 0.6749191564200434, "eval_stsb_spearman": 0.7448192250894073, "step": 3375 }, { "epoch": 0.22, "learning_rate": 2.3280430052476642e-05, "loss": 0.0005, "step": 3500 }, { "epoch": 0.22, "eval_avg_sts": 0.7558791570716834, "eval_sickr_spearman": 0.7183665057546127, "eval_stsb_spearman": 0.793391808388754, "step": 3500 }, { "epoch": 0.23, "eval_avg_sts": 0.7724894260205434, "eval_sickr_spearman": 0.7317967221832306, "eval_stsb_spearman": 0.8131821298578562, "step": 3625 }, { "epoch": 0.24, "eval_avg_sts": 0.7735778094480449, "eval_sickr_spearman": 0.7319867332205197, "eval_stsb_spearman": 0.8151688856755701, "step": 3750 }, { "epoch": 0.25, "eval_avg_sts": 0.7753994732757892, "eval_sickr_spearman": 0.7344932362490677, "eval_stsb_spearman": 0.8163057103025108, "step": 3875 }, { "epoch": 0.26, "learning_rate": 2.2320491488544734e-05, "loss": 0.0005, "step": 4000 }, { "epoch": 0.26, "eval_avg_sts": 0.7645563589773194, "eval_sickr_spearman": 0.7288089955493742, "eval_stsb_spearman": 0.8003037224052648, "step": 4000 }, { "epoch": 0.26, "eval_avg_sts": 0.77217921247597, "eval_sickr_spearman": 0.7348872353741646, "eval_stsb_spearman": 0.8094711895777754, "step": 4125 }, { "epoch": 0.27, "eval_avg_sts": 0.7459204678567914, "eval_sickr_spearman": 0.7152080285551439, "eval_stsb_spearman": 0.7766329071584389, "step": 4250 }, { "epoch": 0.28, "eval_avg_sts": 0.7630540681359231, "eval_sickr_spearman": 0.7283370419466434, "eval_stsb_spearman": 0.7977710943252029, "step": 4375 }, { "epoch": 0.29, "learning_rate": 2.1360552924612826e-05, "loss": 0.0005, "step": 4500 }, { "epoch": 0.29, "eval_avg_sts": 0.7261107657045172, "eval_sickr_spearman": 0.6958098517106376, "eval_stsb_spearman": 0.7564116796983967, "step": 4500 }, { "epoch": 0.3, "eval_avg_sts": 0.7402966337518628, "eval_sickr_spearman": 0.7071302059463835, "eval_stsb_spearman": 0.7734630615573422, "step": 4625 }, { "epoch": 0.3, "eval_avg_sts": 0.7563164963384006, "eval_sickr_spearman": 0.7236546819918475, "eval_stsb_spearman": 0.7889783106849536, "step": 4750 }, { "epoch": 0.31, "eval_avg_sts": 0.7653071609134422, "eval_sickr_spearman": 0.7303088147228807, "eval_stsb_spearman": 0.8003055071040037, "step": 4875 }, { "epoch": 0.32, "learning_rate": 2.0400614360680917e-05, "loss": 0.0003, "step": 5000 }, { "epoch": 0.32, "eval_avg_sts": 0.7611963687067248, "eval_sickr_spearman": 0.7255880779180358, "eval_stsb_spearman": 0.7968046594954138, "step": 5000 }, { "epoch": 0.33, "eval_avg_sts": 0.7744538434517783, "eval_sickr_spearman": 0.7411195109412667, "eval_stsb_spearman": 0.8077881759622897, "step": 5125 }, { "epoch": 0.34, "eval_avg_sts": 0.7765902002597658, "eval_sickr_spearman": 0.7444951367503373, "eval_stsb_spearman": 0.8086852637691941, "step": 5250 }, { "epoch": 0.34, "eval_avg_sts": 0.7699546022654327, "eval_sickr_spearman": 0.7376793313318634, "eval_stsb_spearman": 0.8022298731990021, "step": 5375 }, { "epoch": 0.35, "learning_rate": 1.944067579674901e-05, "loss": 0.0005, "step": 5500 }, { "epoch": 0.35, "eval_avg_sts": 0.7734752595558289, "eval_sickr_spearman": 0.7410133141759871, "eval_stsb_spearman": 0.8059372049356706, "step": 5500 }, { "epoch": 0.36, "eval_avg_sts": 0.7626449726319405, "eval_sickr_spearman": 0.7365559319003274, "eval_stsb_spearman": 0.7887340133635536, "step": 5625 }, { "epoch": 0.37, "eval_avg_sts": 0.7687278256378415, "eval_sickr_spearman": 0.7398524504853293, "eval_stsb_spearman": 0.7976032007903536, "step": 5750 }, { "epoch": 0.38, "eval_avg_sts": 0.7693941323907878, "eval_sickr_spearman": 0.7396455325003339, "eval_stsb_spearman": 0.7991427322812418, "step": 5875 }, { "epoch": 0.38, "learning_rate": 1.84807372328171e-05, "loss": 0.0005, "step": 6000 }, { "epoch": 0.38, "eval_avg_sts": 0.7574432337471098, "eval_sickr_spearman": 0.7347453034694149, "eval_stsb_spearman": 0.7801411640248046, "step": 6000 }, { "epoch": 0.39, "eval_avg_sts": 0.7708101615966496, "eval_sickr_spearman": 0.7320090676826885, "eval_stsb_spearman": 0.8096112555106109, "step": 6125 }, { "epoch": 0.4, "eval_avg_sts": 0.7635841238166383, "eval_sickr_spearman": 0.7288792650507782, "eval_stsb_spearman": 0.7982889825824986, "step": 6250 }, { "epoch": 0.41, "eval_avg_sts": 0.7627376362894998, "eval_sickr_spearman": 0.7300567955336349, "eval_stsb_spearman": 0.7954184770453646, "step": 6375 }, { "epoch": 0.42, "learning_rate": 1.7520798668885192e-05, "loss": 0.0005, "step": 6500 }, { "epoch": 0.42, "eval_avg_sts": 0.7591781252494068, "eval_sickr_spearman": 0.7227859434601362, "eval_stsb_spearman": 0.7955703070386773, "step": 6500 }, { "epoch": 0.42, "eval_avg_sts": 0.7527229076746123, "eval_sickr_spearman": 0.7119316830327459, "eval_stsb_spearman": 0.7935141323164787, "step": 6625 }, { "epoch": 0.43, "eval_avg_sts": 0.7584939992660324, "eval_sickr_spearman": 0.7191479717750108, "eval_stsb_spearman": 0.7978400267570542, "step": 6750 }, { "epoch": 0.44, "eval_avg_sts": 0.7630465793985837, "eval_sickr_spearman": 0.7249168913065396, "eval_stsb_spearman": 0.8011762674906276, "step": 6875 }, { "epoch": 0.45, "learning_rate": 1.6560860104953284e-05, "loss": 0.0004, "step": 7000 }, { "epoch": 0.45, "eval_avg_sts": 0.7655527346776364, "eval_sickr_spearman": 0.7304577591684402, "eval_stsb_spearman": 0.8006477101868326, "step": 7000 }, { "epoch": 0.46, "eval_avg_sts": 0.7395454013504682, "eval_sickr_spearman": 0.7105281181865213, "eval_stsb_spearman": 0.7685626845144151, "step": 7125 }, { "epoch": 0.46, "eval_avg_sts": 0.7229578267812158, "eval_sickr_spearman": 0.6942447582702768, "eval_stsb_spearman": 0.7516708952921549, "step": 7250 }, { "epoch": 0.47, "eval_avg_sts": 0.7452003408688526, "eval_sickr_spearman": 0.7146070634139502, "eval_stsb_spearman": 0.775793618323755, "step": 7375 }, { "epoch": 0.48, "learning_rate": 1.5600921541021372e-05, "loss": 0.0005, "step": 7500 }, { "epoch": 0.48, "eval_avg_sts": 0.7600508627663232, "eval_sickr_spearman": 0.7285831533104121, "eval_stsb_spearman": 0.7915185722222341, "step": 7500 }, { "epoch": 0.49, "eval_avg_sts": 0.7674997774484139, "eval_sickr_spearman": 0.7341920332119493, "eval_stsb_spearman": 0.8008075216848786, "step": 7625 }, { "epoch": 0.5, "eval_avg_sts": 0.7668269678433662, "eval_sickr_spearman": 0.7276831399805795, "eval_stsb_spearman": 0.8059707957061529, "step": 7750 }, { "epoch": 0.5, "eval_avg_sts": 0.7759267074313813, "eval_sickr_spearman": 0.7360665910388758, "eval_stsb_spearman": 0.8157868238238867, "step": 7875 }, { "epoch": 0.51, "learning_rate": 1.4640982977089467e-05, "loss": 0.0004, "step": 8000 }, { "epoch": 0.51, "eval_avg_sts": 0.7694891376849935, "eval_sickr_spearman": 0.7355848390914517, "eval_stsb_spearman": 0.8033934362785352, "step": 8000 }, { "epoch": 0.52, "eval_avg_sts": 0.7612899584011228, "eval_sickr_spearman": 0.7261187735578255, "eval_stsb_spearman": 0.79646114324442, "step": 8125 }, { "epoch": 0.53, "eval_avg_sts": 0.7590520798954239, "eval_sickr_spearman": 0.7263883721301976, "eval_stsb_spearman": 0.7917157876606503, "step": 8250 }, { "epoch": 0.54, "eval_avg_sts": 0.7681689830272878, "eval_sickr_spearman": 0.7343635698999812, "eval_stsb_spearman": 0.8019743961545942, "step": 8375 }, { "epoch": 0.54, "learning_rate": 1.368104441315756e-05, "loss": 0.0003, "step": 8500 }, { "epoch": 0.54, "eval_avg_sts": 0.7645627255636145, "eval_sickr_spearman": 0.7345889622342338, "eval_stsb_spearman": 0.7945364888929952, "step": 8500 }, { "epoch": 0.55, "eval_avg_sts": 0.7519813686443279, "eval_sickr_spearman": 0.7268361660889052, "eval_stsb_spearman": 0.7771265711997505, "step": 8625 }, { "epoch": 0.56, "eval_avg_sts": 0.7570879059121025, "eval_sickr_spearman": 0.7295248030541064, "eval_stsb_spearman": 0.7846510087700986, "step": 8750 }, { "epoch": 0.57, "eval_avg_sts": 0.7651801271677768, "eval_sickr_spearman": 0.7324815976586366, "eval_stsb_spearman": 0.797878656676917, "step": 8875 }, { "epoch": 0.58, "learning_rate": 1.2721105849225649e-05, "loss": 0.0004, "step": 9000 }, { "epoch": 0.58, "eval_avg_sts": 0.7712013823080692, "eval_sickr_spearman": 0.7386502800474348, "eval_stsb_spearman": 0.8037524845687036, "step": 9000 }, { "epoch": 0.58, "eval_avg_sts": 0.7620043628899366, "eval_sickr_spearman": 0.7352328191490116, "eval_stsb_spearman": 0.7887759066308615, "step": 9125 }, { "epoch": 0.59, "eval_avg_sts": 0.7406795525094927, "eval_sickr_spearman": 0.7231166856246392, "eval_stsb_spearman": 0.7582424193943462, "step": 9250 }, { "epoch": 0.6, "eval_avg_sts": 0.7653971603316696, "eval_sickr_spearman": 0.7354289301361836, "eval_stsb_spearman": 0.7953653905271556, "step": 9375 }, { "epoch": 0.61, "learning_rate": 1.176116728529374e-05, "loss": 0.0005, "step": 9500 }, { "epoch": 0.61, "eval_avg_sts": 0.7646069433356613, "eval_sickr_spearman": 0.7343778655434133, "eval_stsb_spearman": 0.7948360211279091, "step": 9500 }, { "epoch": 0.62, "eval_avg_sts": 0.7593680988773044, "eval_sickr_spearman": 0.732813492569574, "eval_stsb_spearman": 0.7859227051850348, "step": 9625 }, { "epoch": 0.62, "eval_avg_sts": 0.7587276133400723, "eval_sickr_spearman": 0.7302601592171238, "eval_stsb_spearman": 0.7871950674630208, "step": 9750 }, { "epoch": 0.63, "eval_avg_sts": 0.7470220132260748, "eval_sickr_spearman": 0.716697953321754, "eval_stsb_spearman": 0.7773460731303955, "step": 9875 }, { "epoch": 0.64, "learning_rate": 1.0801228721361832e-05, "loss": 0.0003, "step": 10000 }, { "epoch": 0.64, "eval_avg_sts": 0.7602204587910995, "eval_sickr_spearman": 0.7292309487755081, "eval_stsb_spearman": 0.7912099688066908, "step": 10000 }, { "epoch": 0.65, "eval_avg_sts": 0.7763161485207313, "eval_sickr_spearman": 0.7364229337804452, "eval_stsb_spearman": 0.8162093632610175, "step": 10125 }, { "epoch": 0.66, "eval_avg_sts": 0.7776963975561555, "eval_sickr_spearman": 0.7362918569046206, "eval_stsb_spearman": 0.8191009382076904, "step": 10250 }, { "epoch": 0.66, "eval_avg_sts": 0.7769543328958908, "eval_sickr_spearman": 0.7370006998996443, "eval_stsb_spearman": 0.8169079658921373, "step": 10375 }, { "epoch": 0.67, "learning_rate": 9.841290157429926e-06, "loss": 0.0005, "step": 10500 }, { "epoch": 0.67, "eval_avg_sts": 0.7786140293258825, "eval_sickr_spearman": 0.7414595711394486, "eval_stsb_spearman": 0.8157684875123163, "step": 10500 }, { "epoch": 0.68, "eval_avg_sts": 0.77959121226111, "eval_sickr_spearman": 0.7405204670441307, "eval_stsb_spearman": 0.8186619574780892, "step": 10625 }, { "epoch": 0.69, "eval_avg_sts": 0.7779319076421938, "eval_sickr_spearman": 0.7420048682340755, "eval_stsb_spearman": 0.813858947050312, "step": 10750 }, { "epoch": 0.7, "eval_avg_sts": 0.7775449329956121, "eval_sickr_spearman": 0.7400306458716649, "eval_stsb_spearman": 0.8150592201195593, "step": 10875 }, { "epoch": 0.7, "learning_rate": 8.881351593498018e-06, "loss": 0.0004, "step": 11000 }, { "epoch": 0.7, "eval_avg_sts": 0.778286005470163, "eval_sickr_spearman": 0.7363517997192154, "eval_stsb_spearman": 0.8202202112211106, "step": 11000 }, { "epoch": 0.71, "eval_avg_sts": 0.777618581685105, "eval_sickr_spearman": 0.7384216520045894, "eval_stsb_spearman": 0.8168155113656206, "step": 11125 }, { "epoch": 0.72, "eval_avg_sts": 0.7762628934419535, "eval_sickr_spearman": 0.7332475976643716, "eval_stsb_spearman": 0.8192781892195354, "step": 11250 }, { "epoch": 0.73, "eval_avg_sts": 0.7770120788854875, "eval_sickr_spearman": 0.733883289291905, "eval_stsb_spearman": 0.8201408684790699, "step": 11375 }, { "epoch": 0.74, "learning_rate": 7.921413029566108e-06, "loss": 0.0004, "step": 11500 }, { "epoch": 0.74, "eval_avg_sts": 0.7750375125081059, "eval_sickr_spearman": 0.7312441243611851, "eval_stsb_spearman": 0.8188309006550266, "step": 11500 }, { "epoch": 0.74, "eval_avg_sts": 0.7713758693823137, "eval_sickr_spearman": 0.7301794189356065, "eval_stsb_spearman": 0.812572319829021, "step": 11625 }, { "epoch": 0.75, "eval_avg_sts": 0.7729201610115823, "eval_sickr_spearman": 0.7338767570621094, "eval_stsb_spearman": 0.8119635649610553, "step": 11750 }, { "epoch": 0.76, "eval_avg_sts": 0.7721840581068564, "eval_sickr_spearman": 0.7340904474324076, "eval_stsb_spearman": 0.8102776687813052, "step": 11875 }, { "epoch": 0.77, "learning_rate": 6.961474465634199e-06, "loss": 0.0006, "step": 12000 }, { "epoch": 0.77, "eval_avg_sts": 0.762864859686734, "eval_sickr_spearman": 0.7334133049643331, "eval_stsb_spearman": 0.7923164144091348, "step": 12000 }, { "epoch": 0.78, "eval_avg_sts": 0.7653804206448536, "eval_sickr_spearman": 0.7362588595379327, "eval_stsb_spearman": 0.7945019817517746, "step": 12125 }, { "epoch": 0.78, "eval_avg_sts": 0.770245273378219, "eval_sickr_spearman": 0.7383542643692718, "eval_stsb_spearman": 0.8021362823871663, "step": 12250 }, { "epoch": 0.79, "eval_avg_sts": 0.769823742960263, "eval_sickr_spearman": 0.7377583424937291, "eval_stsb_spearman": 0.8018891434267971, "step": 12375 }, { "epoch": 0.8, "learning_rate": 6.001535901702292e-06, "loss": 0.0006, "step": 12500 }, { "epoch": 0.8, "eval_avg_sts": 0.7643310786346977, "eval_sickr_spearman": 0.7368435421357389, "eval_stsb_spearman": 0.7918186151336565, "step": 12500 }, { "epoch": 0.81, "eval_avg_sts": 0.7478178784310427, "eval_sickr_spearman": 0.7295915662851054, "eval_stsb_spearman": 0.76604419057698, "step": 12625 }, { "epoch": 0.82, "eval_avg_sts": 0.7521749358657968, "eval_sickr_spearman": 0.7287060648989924, "eval_stsb_spearman": 0.7756438068326013, "step": 12750 }, { "epoch": 0.82, "eval_avg_sts": 0.7552169285539614, "eval_sickr_spearman": 0.7275865559866728, "eval_stsb_spearman": 0.7828473011212499, "step": 12875 }, { "epoch": 0.83, "learning_rate": 5.0415973377703825e-06, "loss": 0.0006, "step": 13000 }, { "epoch": 0.83, "eval_avg_sts": 0.7586663192427485, "eval_sickr_spearman": 0.7291622643004515, "eval_stsb_spearman": 0.7881703741850457, "step": 13000 }, { "epoch": 0.84, "eval_avg_sts": 0.7590819682264265, "eval_sickr_spearman": 0.7291833019228814, "eval_stsb_spearman": 0.7889806345299715, "step": 13125 }, { "epoch": 0.85, "eval_avg_sts": 0.7599496756491293, "eval_sickr_spearman": 0.7258233342528796, "eval_stsb_spearman": 0.794076017045379, "step": 13250 }, { "epoch": 0.86, "eval_avg_sts": 0.7620834946535875, "eval_sickr_spearman": 0.7272929418635816, "eval_stsb_spearman": 0.7968740474435934, "step": 13375 }, { "epoch": 0.86, "learning_rate": 4.081658773838474e-06, "loss": 0.0005, "step": 13500 }, { "epoch": 0.86, "eval_avg_sts": 0.7638553003387081, "eval_sickr_spearman": 0.7278715725426066, "eval_stsb_spearman": 0.7998390281348094, "step": 13500 }, { "epoch": 0.87, "eval_avg_sts": 0.764322584988894, "eval_sickr_spearman": 0.7266260300201134, "eval_stsb_spearman": 0.8020191399576747, "step": 13625 }, { "epoch": 0.88, "eval_avg_sts": 0.7648945618293426, "eval_sickr_spearman": 0.7271069174077117, "eval_stsb_spearman": 0.8026822062509734, "step": 13750 }, { "epoch": 0.89, "eval_avg_sts": 0.7669716790989545, "eval_sickr_spearman": 0.7275461137992619, "eval_stsb_spearman": 0.8063972443986471, "step": 13875 }, { "epoch": 0.9, "learning_rate": 3.121720209906566e-06, "loss": 0.0004, "step": 14000 }, { "epoch": 0.9, "eval_avg_sts": 0.7674021960316728, "eval_sickr_spearman": 0.727724597372206, "eval_stsb_spearman": 0.8070797946911397, "step": 14000 }, { "epoch": 0.9, "eval_avg_sts": 0.7683497505006873, "eval_sickr_spearman": 0.7281690291538128, "eval_stsb_spearman": 0.8085304718475618, "step": 14125 }, { "epoch": 0.91, "eval_avg_sts": 0.7680069912021876, "eval_sickr_spearman": 0.7273477933814239, "eval_stsb_spearman": 0.8086661890229514, "step": 14250 }, { "epoch": 0.92, "eval_avg_sts": 0.76821821049172, "eval_sickr_spearman": 0.7266917845979821, "eval_stsb_spearman": 0.8097446363854579, "step": 14375 }, { "epoch": 0.93, "learning_rate": 2.1617816459746575e-06, "loss": 0.0003, "step": 14500 }, { "epoch": 0.93, "eval_avg_sts": 0.7677497628237885, "eval_sickr_spearman": 0.7264186797552051, "eval_stsb_spearman": 0.8090808458923718, "step": 14500 }, { "epoch": 0.94, "eval_avg_sts": 0.7680442088137338, "eval_sickr_spearman": 0.7256543608380205, "eval_stsb_spearman": 0.8104340567894471, "step": 14625 }, { "epoch": 0.94, "eval_avg_sts": 0.7698268910330168, "eval_sickr_spearman": 0.7279500553623565, "eval_stsb_spearman": 0.8117037267036772, "step": 14750 }, { "epoch": 0.95, "eval_avg_sts": 0.7708269865099182, "eval_sickr_spearman": 0.7296867639281557, "eval_stsb_spearman": 0.8119672090916807, "step": 14875 }, { "epoch": 0.96, "learning_rate": 1.2018430820427492e-06, "loss": 0.0007, "step": 15000 }, { "epoch": 0.96, "eval_avg_sts": 0.7723124686000136, "eval_sickr_spearman": 0.7316718893505929, "eval_stsb_spearman": 0.8129530478494341, "step": 15000 }, { "epoch": 0.97, "eval_avg_sts": 0.7726351825661049, "eval_sickr_spearman": 0.7322496074386905, "eval_stsb_spearman": 0.8130207576935193, "step": 15125 }, { "epoch": 0.98, "eval_avg_sts": 0.7724775113219677, "eval_sickr_spearman": 0.7322382240676497, "eval_stsb_spearman": 0.8127167985762856, "step": 15250 }, { "epoch": 0.98, "eval_avg_sts": 0.7726148952184836, "eval_sickr_spearman": 0.732653981281698, "eval_stsb_spearman": 0.8125758091552692, "step": 15375 }, { "epoch": 0.99, "learning_rate": 2.4190451811084087e-07, "loss": 0.0004, "step": 15500 }, { "epoch": 0.99, "eval_avg_sts": 0.7726350099777579, "eval_sickr_spearman": 0.7326541734061037, "eval_stsb_spearman": 0.812615846549412, "step": 15500 }, { "epoch": 1.0, "eval_avg_sts": 0.7724457544885928, "eval_sickr_spearman": 0.7325294846667704, "eval_stsb_spearman": 0.8123620243104152, "step": 15625 }, { "epoch": 1.0, "step": 15626, "train_runtime": 4555.3265, "train_samples_per_second": 3.43 } ], "max_steps": 15626, "num_train_epochs": 1, "total_flos": 107685402744674304, "trial_name": null, "trial_params": null }