multicse-bert-base-uncased / trainer_state.json
leoner24's picture
Upload 9 files
50ca12a verified
{
"best_metric": 0.8362939444102149,
"best_model_checkpoint": "checkpoints/multicse-bert-base-uncased",
"epoch": 6.0,
"global_step": 2706,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"eval_avg_sts": 0.808172199263909,
"eval_sickr_spearman": 0.783590147828092,
"eval_stsb_spearman": 0.8327542506997261,
"step": 25
},
{
"epoch": 0.11,
"eval_avg_sts": 0.820794223239678,
"eval_sickr_spearman": 0.8053590918084821,
"eval_stsb_spearman": 0.8362293546708739,
"step": 50
},
{
"epoch": 0.17,
"eval_avg_sts": 0.8218985782625993,
"eval_sickr_spearman": 0.8010904717614742,
"eval_stsb_spearman": 0.8427066847637243,
"step": 75
},
{
"epoch": 0.22,
"eval_avg_sts": 0.8212197665999863,
"eval_sickr_spearman": 0.7985843529817378,
"eval_stsb_spearman": 0.8438551802182349,
"step": 100
},
{
"epoch": 0.28,
"eval_avg_sts": 0.8263710498747726,
"eval_sickr_spearman": 0.8055955008897605,
"eval_stsb_spearman": 0.8471465988597847,
"step": 125
},
{
"epoch": 0.33,
"eval_avg_sts": 0.8263231728376124,
"eval_sickr_spearman": 0.8046682604764976,
"eval_stsb_spearman": 0.8479780851987271,
"step": 150
},
{
"epoch": 0.39,
"eval_avg_sts": 0.8240636839647479,
"eval_sickr_spearman": 0.80153019649514,
"eval_stsb_spearman": 0.8465971714343559,
"step": 175
},
{
"epoch": 0.44,
"eval_avg_sts": 0.8305466429958255,
"eval_sickr_spearman": 0.8140019522945605,
"eval_stsb_spearman": 0.8470913336970906,
"step": 200
},
{
"epoch": 0.5,
"eval_avg_sts": 0.8212438683719858,
"eval_sickr_spearman": 0.796099127731127,
"eval_stsb_spearman": 0.8463886090128445,
"step": 225
},
{
"epoch": 0.55,
"eval_avg_sts": 0.8290131151517519,
"eval_sickr_spearman": 0.8127541523102997,
"eval_stsb_spearman": 0.8452720779932043,
"step": 250
},
{
"epoch": 0.61,
"eval_avg_sts": 0.8291875600829677,
"eval_sickr_spearman": 0.8103600420591169,
"eval_stsb_spearman": 0.8480150781068185,
"step": 275
},
{
"epoch": 0.67,
"eval_avg_sts": 0.8327962239942688,
"eval_sickr_spearman": 0.816952310731498,
"eval_stsb_spearman": 0.8486401372570397,
"step": 300
},
{
"epoch": 0.72,
"eval_avg_sts": 0.8330122790068915,
"eval_sickr_spearman": 0.8143033474560845,
"eval_stsb_spearman": 0.8517212105576986,
"step": 325
},
{
"epoch": 0.78,
"eval_avg_sts": 0.8334940457333329,
"eval_sickr_spearman": 0.8149612294524823,
"eval_stsb_spearman": 0.8520268620141834,
"step": 350
},
{
"epoch": 0.83,
"eval_avg_sts": 0.8359867680300406,
"eval_sickr_spearman": 0.8166730579077367,
"eval_stsb_spearman": 0.8553004781523443,
"step": 375
},
{
"epoch": 0.89,
"eval_avg_sts": 0.8362939444102149,
"eval_sickr_spearman": 0.8178701370488788,
"eval_stsb_spearman": 0.8547177517715511,
"step": 400
},
{
"epoch": 0.94,
"eval_avg_sts": 0.8269789550924258,
"eval_sickr_spearman": 0.8014972471595535,
"eval_stsb_spearman": 0.852460663025298,
"step": 425
},
{
"epoch": 1.0,
"eval_avg_sts": 0.8271598937884023,
"eval_sickr_spearman": 0.8061173588068856,
"eval_stsb_spearman": 0.8482024287699189,
"step": 450
},
{
"epoch": 1.05,
"eval_avg_sts": 0.8282927205714137,
"eval_sickr_spearman": 0.8104696010014973,
"eval_stsb_spearman": 0.84611584014133,
"step": 475
},
{
"epoch": 1.11,
"learning_rate": 4.076127124907613e-05,
"loss": 0.4303,
"step": 500
},
{
"epoch": 1.11,
"eval_avg_sts": 0.8274629650840639,
"eval_sickr_spearman": 0.8056994401932726,
"eval_stsb_spearman": 0.8492264899748552,
"step": 500
},
{
"epoch": 1.16,
"eval_avg_sts": 0.8274341455051789,
"eval_sickr_spearman": 0.8072793272128764,
"eval_stsb_spearman": 0.8475889637974814,
"step": 525
},
{
"epoch": 1.22,
"eval_avg_sts": 0.8269940468993253,
"eval_sickr_spearman": 0.803170506640353,
"eval_stsb_spearman": 0.8508175871582977,
"step": 550
},
{
"epoch": 1.27,
"eval_avg_sts": 0.8288643821143353,
"eval_sickr_spearman": 0.8083313524276753,
"eval_stsb_spearman": 0.8493974118009953,
"step": 575
},
{
"epoch": 1.33,
"eval_avg_sts": 0.8342864948337284,
"eval_sickr_spearman": 0.8138802895146177,
"eval_stsb_spearman": 0.8546927001528392,
"step": 600
},
{
"epoch": 1.39,
"eval_avg_sts": 0.8270151161624402,
"eval_sickr_spearman": 0.8041265176833771,
"eval_stsb_spearman": 0.8499037146415034,
"step": 625
},
{
"epoch": 1.44,
"eval_avg_sts": 0.8279455772988316,
"eval_sickr_spearman": 0.8036888102559718,
"eval_stsb_spearman": 0.8522023443416914,
"step": 650
},
{
"epoch": 1.5,
"eval_avg_sts": 0.829012477308678,
"eval_sickr_spearman": 0.808486444854219,
"eval_stsb_spearman": 0.849538509763137,
"step": 675
},
{
"epoch": 1.55,
"eval_avg_sts": 0.8288300235840231,
"eval_sickr_spearman": 0.8088525379093803,
"eval_stsb_spearman": 0.848807509258666,
"step": 700
},
{
"epoch": 1.61,
"eval_avg_sts": 0.8305859335486241,
"eval_sickr_spearman": 0.8107295453224803,
"eval_stsb_spearman": 0.8504423217747678,
"step": 725
},
{
"epoch": 1.66,
"eval_avg_sts": 0.8280931139956361,
"eval_sickr_spearman": 0.8061409420776917,
"eval_stsb_spearman": 0.8500452859135805,
"step": 750
},
{
"epoch": 1.72,
"eval_avg_sts": 0.8302899379899211,
"eval_sickr_spearman": 0.8096262228913453,
"eval_stsb_spearman": 0.850953653088497,
"step": 775
},
{
"epoch": 1.77,
"eval_avg_sts": 0.8312188464560427,
"eval_sickr_spearman": 0.8104490436900817,
"eval_stsb_spearman": 0.8519886492220037,
"step": 800
},
{
"epoch": 1.83,
"eval_avg_sts": 0.8302662907658385,
"eval_sickr_spearman": 0.8117301772587404,
"eval_stsb_spearman": 0.8488024042729365,
"step": 825
},
{
"epoch": 1.88,
"eval_avg_sts": 0.83177529644248,
"eval_sickr_spearman": 0.8116331544338355,
"eval_stsb_spearman": 0.8519174384511247,
"step": 850
},
{
"epoch": 1.94,
"eval_avg_sts": 0.8342887017337668,
"eval_sickr_spearman": 0.8159248294095337,
"eval_stsb_spearman": 0.8526525740579998,
"step": 875
},
{
"epoch": 2.0,
"eval_avg_sts": 0.8335303856286564,
"eval_sickr_spearman": 0.8152034983281362,
"eval_stsb_spearman": 0.8518572729291767,
"step": 900
},
{
"epoch": 2.05,
"eval_avg_sts": 0.8316736063387226,
"eval_sickr_spearman": 0.8125293667555692,
"eval_stsb_spearman": 0.8508178459218759,
"step": 925
},
{
"epoch": 2.11,
"eval_avg_sts": 0.8280586113483762,
"eval_sickr_spearman": 0.809915706339713,
"eval_stsb_spearman": 0.8462015163570394,
"step": 950
},
{
"epoch": 2.16,
"eval_avg_sts": 0.8285809844295435,
"eval_sickr_spearman": 0.8105551443931586,
"eval_stsb_spearman": 0.8466068244659284,
"step": 975
},
{
"epoch": 2.22,
"learning_rate": 3.152254249815226e-05,
"loss": 0.2628,
"step": 1000
},
{
"epoch": 2.22,
"eval_avg_sts": 0.8304703081697632,
"eval_sickr_spearman": 0.8108091328575633,
"eval_stsb_spearman": 0.8501314834819631,
"step": 1000
},
{
"epoch": 2.27,
"eval_avg_sts": 0.8246676161757887,
"eval_sickr_spearman": 0.8022548417225369,
"eval_stsb_spearman": 0.8470803906290405,
"step": 1025
},
{
"epoch": 2.33,
"eval_avg_sts": 0.8247542776319872,
"eval_sickr_spearman": 0.8023693478683652,
"eval_stsb_spearman": 0.8471392073956092,
"step": 1050
},
{
"epoch": 2.38,
"eval_avg_sts": 0.8284712817725378,
"eval_sickr_spearman": 0.8063077540929862,
"eval_stsb_spearman": 0.8506348094520895,
"step": 1075
},
{
"epoch": 2.44,
"eval_avg_sts": 0.8267581222566869,
"eval_sickr_spearman": 0.8023707888014083,
"eval_stsb_spearman": 0.8511454557119653,
"step": 1100
},
{
"epoch": 2.49,
"eval_avg_sts": 0.8245678399799343,
"eval_sickr_spearman": 0.8010677050193924,
"eval_stsb_spearman": 0.8480679749404763,
"step": 1125
},
{
"epoch": 2.55,
"eval_avg_sts": 0.8264893834503197,
"eval_sickr_spearman": 0.8047740249618645,
"eval_stsb_spearman": 0.848204741938775,
"step": 1150
},
{
"epoch": 2.61,
"eval_avg_sts": 0.8239740308575658,
"eval_sickr_spearman": 0.802257483433116,
"eval_stsb_spearman": 0.8456905782820158,
"step": 1175
},
{
"epoch": 2.66,
"eval_avg_sts": 0.8252898688219781,
"eval_sickr_spearman": 0.8059969928666816,
"eval_stsb_spearman": 0.8445827447772745,
"step": 1200
},
{
"epoch": 2.72,
"eval_avg_sts": 0.8218363555031618,
"eval_sickr_spearman": 0.7991245587796122,
"eval_stsb_spearman": 0.8445481522267114,
"step": 1225
},
{
"epoch": 2.77,
"eval_avg_sts": 0.8265232671423588,
"eval_sickr_spearman": 0.8062044391937928,
"eval_stsb_spearman": 0.8468420950909247,
"step": 1250
},
{
"epoch": 2.83,
"eval_avg_sts": 0.8286104291951198,
"eval_sickr_spearman": 0.8096378464178936,
"eval_stsb_spearman": 0.8475830119723461,
"step": 1275
},
{
"epoch": 2.88,
"eval_avg_sts": 0.8314342022111989,
"eval_sickr_spearman": 0.8138266387743112,
"eval_stsb_spearman": 0.8490417656480866,
"step": 1300
},
{
"epoch": 2.94,
"eval_avg_sts": 0.8285621943597675,
"eval_sickr_spearman": 0.807191478328346,
"eval_stsb_spearman": 0.849932910391189,
"step": 1325
},
{
"epoch": 2.99,
"eval_avg_sts": 0.8284116030199242,
"eval_sickr_spearman": 0.8073644383246247,
"eval_stsb_spearman": 0.8494587677152238,
"step": 1350
},
{
"epoch": 3.05,
"eval_avg_sts": 0.8247221665272242,
"eval_sickr_spearman": 0.8022067145588959,
"eval_stsb_spearman": 0.8472376184955523,
"step": 1375
},
{
"epoch": 3.1,
"eval_avg_sts": 0.826858184586315,
"eval_sickr_spearman": 0.8056980472913309,
"eval_stsb_spearman": 0.848018321881299,
"step": 1400
},
{
"epoch": 3.16,
"eval_avg_sts": 0.8262245909726973,
"eval_sickr_spearman": 0.8059310941955087,
"eval_stsb_spearman": 0.846518087749886,
"step": 1425
},
{
"epoch": 3.22,
"eval_avg_sts": 0.8271328383994965,
"eval_sickr_spearman": 0.8059575113012996,
"eval_stsb_spearman": 0.8483081654976934,
"step": 1450
},
{
"epoch": 3.27,
"eval_avg_sts": 0.8262273295933256,
"eval_sickr_spearman": 0.8045855028887199,
"eval_stsb_spearman": 0.8478691562979312,
"step": 1475
},
{
"epoch": 3.33,
"learning_rate": 2.2283813747228384e-05,
"loss": 0.2284,
"step": 1500
},
{
"epoch": 3.33,
"eval_avg_sts": 0.8290942209780299,
"eval_sickr_spearman": 0.8098024490025217,
"eval_stsb_spearman": 0.848385992953538,
"step": 1500
},
{
"epoch": 3.38,
"eval_avg_sts": 0.8271287520959363,
"eval_sickr_spearman": 0.8068388820126888,
"eval_stsb_spearman": 0.8474186221791836,
"step": 1525
},
{
"epoch": 3.44,
"eval_avg_sts": 0.8284906943060749,
"eval_sickr_spearman": 0.8083666552872324,
"eval_stsb_spearman": 0.8486147333249174,
"step": 1550
},
{
"epoch": 3.49,
"eval_avg_sts": 0.8247556311383242,
"eval_sickr_spearman": 0.8033069629995387,
"eval_stsb_spearman": 0.8462042992771095,
"step": 1575
},
{
"epoch": 3.55,
"eval_avg_sts": 0.8256788195546352,
"eval_sickr_spearman": 0.8046946295511871,
"eval_stsb_spearman": 0.8466630095580832,
"step": 1600
},
{
"epoch": 3.6,
"eval_avg_sts": 0.8246935620550073,
"eval_sickr_spearman": 0.8025401944961806,
"eval_stsb_spearman": 0.8468469296138341,
"step": 1625
},
{
"epoch": 3.66,
"eval_avg_sts": 0.8263329601931413,
"eval_sickr_spearman": 0.8045876162571832,
"eval_stsb_spearman": 0.8480783041290992,
"step": 1650
},
{
"epoch": 3.71,
"eval_avg_sts": 0.8264865724885355,
"eval_sickr_spearman": 0.8057473272014063,
"eval_stsb_spearman": 0.8472258177756647,
"step": 1675
},
{
"epoch": 3.77,
"eval_avg_sts": 0.8254423729673166,
"eval_sickr_spearman": 0.8031947143154778,
"eval_stsb_spearman": 0.8476900316191552,
"step": 1700
},
{
"epoch": 3.82,
"eval_avg_sts": 0.8264107919338515,
"eval_sickr_spearman": 0.8053674972512337,
"eval_stsb_spearman": 0.8474540866164694,
"step": 1725
},
{
"epoch": 3.88,
"eval_avg_sts": 0.8264776461929313,
"eval_sickr_spearman": 0.8059907968545961,
"eval_stsb_spearman": 0.8469644955312665,
"step": 1750
},
{
"epoch": 3.94,
"eval_avg_sts": 0.8240221134684459,
"eval_sickr_spearman": 0.8008853789583333,
"eval_stsb_spearman": 0.8471588479785584,
"step": 1775
},
{
"epoch": 3.99,
"eval_avg_sts": 0.8260093129727113,
"eval_sickr_spearman": 0.8032525437616094,
"eval_stsb_spearman": 0.8487660821838133,
"step": 1800
},
{
"epoch": 4.05,
"eval_avg_sts": 0.8251871747358858,
"eval_sickr_spearman": 0.8022517677320448,
"eval_stsb_spearman": 0.8481225817397268,
"step": 1825
},
{
"epoch": 4.1,
"eval_avg_sts": 0.8236068675958164,
"eval_sickr_spearman": 0.8001952680928707,
"eval_stsb_spearman": 0.8470184670987619,
"step": 1850
},
{
"epoch": 4.16,
"eval_avg_sts": 0.8238228114044301,
"eval_sickr_spearman": 0.8002784579605614,
"eval_stsb_spearman": 0.8473671648482989,
"step": 1875
},
{
"epoch": 4.21,
"eval_avg_sts": 0.8236955591912043,
"eval_sickr_spearman": 0.7999801848206307,
"eval_stsb_spearman": 0.847410933561778,
"step": 1900
},
{
"epoch": 4.27,
"eval_avg_sts": 0.8217179921122288,
"eval_sickr_spearman": 0.7976729628319497,
"eval_stsb_spearman": 0.8457630213925079,
"step": 1925
},
{
"epoch": 4.32,
"eval_avg_sts": 0.8218133292332199,
"eval_sickr_spearman": 0.7972407309501078,
"eval_stsb_spearman": 0.8463859275163321,
"step": 1950
},
{
"epoch": 4.38,
"eval_avg_sts": 0.82307986157595,
"eval_sickr_spearman": 0.7997425269307149,
"eval_stsb_spearman": 0.846417196221185,
"step": 1975
},
{
"epoch": 4.43,
"learning_rate": 1.3045084996304511e-05,
"loss": 0.2149,
"step": 2000
},
{
"epoch": 4.43,
"eval_avg_sts": 0.8251845211566629,
"eval_sickr_spearman": 0.803791356657542,
"eval_stsb_spearman": 0.8465776856557838,
"step": 2000
},
{
"epoch": 4.49,
"eval_avg_sts": 0.8244897261222982,
"eval_sickr_spearman": 0.8012433547573516,
"eval_stsb_spearman": 0.8477360974872448,
"step": 2025
},
{
"epoch": 4.55,
"eval_avg_sts": 0.8248464356555265,
"eval_sickr_spearman": 0.80196872045127,
"eval_stsb_spearman": 0.847724150859783,
"step": 2050
},
{
"epoch": 4.6,
"eval_avg_sts": 0.8236282342217962,
"eval_sickr_spearman": 0.801061412945104,
"eval_stsb_spearman": 0.8461950554984884,
"step": 2075
},
{
"epoch": 4.66,
"eval_avg_sts": 0.8241232806486489,
"eval_sickr_spearman": 0.8016284200975811,
"eval_stsb_spearman": 0.8466181411997169,
"step": 2100
},
{
"epoch": 4.71,
"eval_avg_sts": 0.8240448338930326,
"eval_sickr_spearman": 0.8024957657273504,
"eval_stsb_spearman": 0.845593902058715,
"step": 2125
},
{
"epoch": 4.77,
"eval_avg_sts": 0.8252602189328375,
"eval_sickr_spearman": 0.8031946662843764,
"eval_stsb_spearman": 0.8473257715812985,
"step": 2150
},
{
"epoch": 4.82,
"eval_avg_sts": 0.8237954063381605,
"eval_sickr_spearman": 0.8006036285172974,
"eval_stsb_spearman": 0.8469871841590237,
"step": 2175
},
{
"epoch": 4.88,
"eval_avg_sts": 0.8238382480785117,
"eval_sickr_spearman": 0.8008013245308166,
"eval_stsb_spearman": 0.8468751716262067,
"step": 2200
},
{
"epoch": 4.93,
"eval_avg_sts": 0.8226554353280054,
"eval_sickr_spearman": 0.79934425303759,
"eval_stsb_spearman": 0.8459666176184208,
"step": 2225
},
{
"epoch": 4.99,
"eval_avg_sts": 0.8221324924350076,
"eval_sickr_spearman": 0.7977314166823997,
"eval_stsb_spearman": 0.8465335681876156,
"step": 2250
},
{
"epoch": 5.04,
"eval_avg_sts": 0.8230411082185226,
"eval_sickr_spearman": 0.7989547688360285,
"eval_stsb_spearman": 0.8471274476010168,
"step": 2275
},
{
"epoch": 5.1,
"eval_avg_sts": 0.8228022688627314,
"eval_sickr_spearman": 0.7994119768906178,
"eval_stsb_spearman": 0.846192560834845,
"step": 2300
},
{
"epoch": 5.16,
"eval_avg_sts": 0.8228479899857558,
"eval_sickr_spearman": 0.7989381981060323,
"eval_stsb_spearman": 0.8467577818654793,
"step": 2325
},
{
"epoch": 5.21,
"eval_avg_sts": 0.8221050116430979,
"eval_sickr_spearman": 0.7985421816746751,
"eval_stsb_spearman": 0.8456678416115206,
"step": 2350
},
{
"epoch": 5.27,
"eval_avg_sts": 0.822383318476755,
"eval_sickr_spearman": 0.7986474658490273,
"eval_stsb_spearman": 0.8461191711044828,
"step": 2375
},
{
"epoch": 5.32,
"eval_avg_sts": 0.823048712126393,
"eval_sickr_spearman": 0.7993529466669504,
"eval_stsb_spearman": 0.8467444775858354,
"step": 2400
},
{
"epoch": 5.38,
"eval_avg_sts": 0.8228378854074433,
"eval_sickr_spearman": 0.799309382457946,
"eval_stsb_spearman": 0.8463663883569406,
"step": 2425
},
{
"epoch": 5.43,
"eval_avg_sts": 0.8229990938054758,
"eval_sickr_spearman": 0.7993526104492402,
"eval_stsb_spearman": 0.8466455771617113,
"step": 2450
},
{
"epoch": 5.49,
"eval_avg_sts": 0.8223080164546823,
"eval_sickr_spearman": 0.7985109614587403,
"eval_stsb_spearman": 0.8461050714506243,
"step": 2475
},
{
"epoch": 5.54,
"learning_rate": 3.806356245380636e-06,
"loss": 0.2074,
"step": 2500
},
{
"epoch": 5.54,
"eval_avg_sts": 0.8224706658462584,
"eval_sickr_spearman": 0.7986079842836452,
"eval_stsb_spearman": 0.8463333474088716,
"step": 2500
},
{
"epoch": 5.6,
"eval_avg_sts": 0.8228255546038069,
"eval_sickr_spearman": 0.7993520821071245,
"eval_stsb_spearman": 0.8462990271004893,
"step": 2525
},
{
"epoch": 5.65,
"eval_avg_sts": 0.8222772197799051,
"eval_sickr_spearman": 0.7986904536848144,
"eval_stsb_spearman": 0.8458639858749959,
"step": 2550
},
{
"epoch": 5.71,
"eval_avg_sts": 0.822395438556291,
"eval_sickr_spearman": 0.7987432398652949,
"eval_stsb_spearman": 0.8460476372472872,
"step": 2575
},
{
"epoch": 5.76,
"eval_avg_sts": 0.8229151972681052,
"eval_sickr_spearman": 0.7992985754601224,
"eval_stsb_spearman": 0.8465318190760882,
"step": 2600
},
{
"epoch": 5.82,
"eval_avg_sts": 0.8227679691163096,
"eval_sickr_spearman": 0.7989778237647187,
"eval_stsb_spearman": 0.8465581144679004,
"step": 2625
},
{
"epoch": 5.88,
"eval_avg_sts": 0.8231044151175362,
"eval_sickr_spearman": 0.7993373845900845,
"eval_stsb_spearman": 0.8468714456449877,
"step": 2650
},
{
"epoch": 5.93,
"eval_avg_sts": 0.8230968701740264,
"eval_sickr_spearman": 0.7993484797745166,
"eval_stsb_spearman": 0.8468452605735363,
"step": 2675
},
{
"epoch": 5.99,
"eval_avg_sts": 0.8230334553806065,
"eval_sickr_spearman": 0.7992910345771966,
"eval_stsb_spearman": 0.8467758761840164,
"step": 2700
},
{
"epoch": 6.0,
"step": 2706,
"train_runtime": 3739.6542,
"train_samples_per_second": 0.724
}
],
"max_steps": 2706,
"num_train_epochs": 6,
"total_flos": 212939896792195584,
"trial_name": null,
"trial_params": null
}