mariadg's picture
Training in progress, epoch 3, checkpoint
00a8cd9 verified
Raw History Blame Contribute Delete
28.7 kB
{
"best_global_step": 7179,
"best_metric": 0.957727228351069,
"best_model_checkpoint": "./results_roberta_framing/checkpoint-7179",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 7179,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020894274968658588,
"grad_norm": 8.932930946350098,
"learning_rate": 1.986349073687143e-05,
"loss": 0.37680843353271487,
"step": 50
},
{
"epoch": 0.041788549937317176,
"grad_norm": 5.1799187660217285,
"learning_rate": 1.9724195570413708e-05,
"loss": 0.18981225967407225,
"step": 100
},
{
"epoch": 0.06268282490597576,
"grad_norm": 3.0934054851531982,
"learning_rate": 1.9584900403955985e-05,
"loss": 0.23419036865234374,
"step": 150
},
{
"epoch": 0.08357709987463435,
"grad_norm": 19.54111099243164,
"learning_rate": 1.944560523749826e-05,
"loss": 0.28510141372680664,
"step": 200
},
{
"epoch": 0.10447137484329294,
"grad_norm": 10.577996253967285,
"learning_rate": 1.9306310071040537e-05,
"loss": 0.2223600387573242,
"step": 250
},
{
"epoch": 0.12536564981195153,
"grad_norm": 2.6502151489257812,
"learning_rate": 1.916701490458281e-05,
"loss": 0.22706157684326173,
"step": 300
},
{
"epoch": 0.14625992478061012,
"grad_norm": 7.829952239990234,
"learning_rate": 1.902771973812509e-05,
"loss": 0.19802961349487305,
"step": 350
},
{
"epoch": 0.1671541997492687,
"grad_norm": 13.447933197021484,
"learning_rate": 1.8888424571667367e-05,
"loss": 0.1808658218383789,
"step": 400
},
{
"epoch": 0.1880484747179273,
"grad_norm": 7.538403511047363,
"learning_rate": 1.874912940520964e-05,
"loss": 0.24561376571655275,
"step": 450
},
{
"epoch": 0.20894274968658588,
"grad_norm": 0.8122928738594055,
"learning_rate": 1.8609834238751915e-05,
"loss": 0.19062108993530275,
"step": 500
},
{
"epoch": 0.22983702465524447,
"grad_norm": 9.346799850463867,
"learning_rate": 1.8470539072294193e-05,
"loss": 0.2701171684265137,
"step": 550
},
{
"epoch": 0.25073129962390306,
"grad_norm": 0.3724958598613739,
"learning_rate": 1.8331243905836467e-05,
"loss": 0.18619226455688476,
"step": 600
},
{
"epoch": 0.27162557459256165,
"grad_norm": 13.843843460083008,
"learning_rate": 1.8191948739378745e-05,
"loss": 0.2209018898010254,
"step": 650
},
{
"epoch": 0.29251984956122024,
"grad_norm": 3.4284515380859375,
"learning_rate": 1.8052653572921023e-05,
"loss": 0.18923908233642578,
"step": 700
},
{
"epoch": 0.3134141245298788,
"grad_norm": 0.16244427859783173,
"learning_rate": 1.7913358406463297e-05,
"loss": 0.16639476776123047,
"step": 750
},
{
"epoch": 0.3343083994985374,
"grad_norm": 7.5455403327941895,
"learning_rate": 1.777406324000557e-05,
"loss": 0.2010784149169922,
"step": 800
},
{
"epoch": 0.355202674467196,
"grad_norm": 10.769554138183594,
"learning_rate": 1.763476807354785e-05,
"loss": 0.15231707572937012,
"step": 850
},
{
"epoch": 0.3760969494358546,
"grad_norm": 3.8304085731506348,
"learning_rate": 1.7495472907090127e-05,
"loss": 0.20387311935424804,
"step": 900
},
{
"epoch": 0.3969912244045132,
"grad_norm": 9.061674118041992,
"learning_rate": 1.73561777406324e-05,
"loss": 0.16109375,
"step": 950
},
{
"epoch": 0.41788549937317176,
"grad_norm": 6.742269515991211,
"learning_rate": 1.721688257417468e-05,
"loss": 0.19855915069580077,
"step": 1000
},
{
"epoch": 0.43877977434183035,
"grad_norm": 7.964315891265869,
"learning_rate": 1.7077587407716953e-05,
"loss": 0.15794966697692872,
"step": 1050
},
{
"epoch": 0.45967404931048894,
"grad_norm": 0.09879713505506516,
"learning_rate": 1.693829224125923e-05,
"loss": 0.15434850692749025,
"step": 1100
},
{
"epoch": 0.48056832427914753,
"grad_norm": 0.15211047232151031,
"learning_rate": 1.6798997074801505e-05,
"loss": 0.17640254974365235,
"step": 1150
},
{
"epoch": 0.5014625992478061,
"grad_norm": 1.7318052053451538,
"learning_rate": 1.6659701908343782e-05,
"loss": 0.15716038703918456,
"step": 1200
},
{
"epoch": 0.5223568742164647,
"grad_norm": 0.8446729183197021,
"learning_rate": 1.6520406741886057e-05,
"loss": 0.1472008419036865,
"step": 1250
},
{
"epoch": 0.5432511491851233,
"grad_norm": 1.3359307050704956,
"learning_rate": 1.6381111575428334e-05,
"loss": 0.16255657196044923,
"step": 1300
},
{
"epoch": 0.5641454241537819,
"grad_norm": 1.6793346405029297,
"learning_rate": 1.624181640897061e-05,
"loss": 0.21821033477783203,
"step": 1350
},
{
"epoch": 0.5850396991224405,
"grad_norm": 18.243087768554688,
"learning_rate": 1.6102521242512886e-05,
"loss": 0.1500292205810547,
"step": 1400
},
{
"epoch": 0.6059339740910991,
"grad_norm": 1.5063047409057617,
"learning_rate": 1.5963226076055164e-05,
"loss": 0.17084882736206056,
"step": 1450
},
{
"epoch": 0.6268282490597576,
"grad_norm": 13.98779010772705,
"learning_rate": 1.5823930909597438e-05,
"loss": 0.147371826171875,
"step": 1500
},
{
"epoch": 0.6477225240284162,
"grad_norm": 6.434369087219238,
"learning_rate": 1.5684635743139712e-05,
"loss": 0.18003299713134766,
"step": 1550
},
{
"epoch": 0.6686167989970748,
"grad_norm": 22.631860733032227,
"learning_rate": 1.554534057668199e-05,
"loss": 0.16371349334716798,
"step": 1600
},
{
"epoch": 0.6895110739657334,
"grad_norm": 45.23455810546875,
"learning_rate": 1.5406045410224268e-05,
"loss": 0.14458242416381836,
"step": 1650
},
{
"epoch": 0.710405348934392,
"grad_norm": 1.9490578174591064,
"learning_rate": 1.5266750243766542e-05,
"loss": 0.1913561248779297,
"step": 1700
},
{
"epoch": 0.7312996239030506,
"grad_norm": 8.041529655456543,
"learning_rate": 1.512745507730882e-05,
"loss": 0.1529798412322998,
"step": 1750
},
{
"epoch": 0.7521938988717092,
"grad_norm": 13.91869831085205,
"learning_rate": 1.4988159910851094e-05,
"loss": 0.1795888900756836,
"step": 1800
},
{
"epoch": 0.7730881738403678,
"grad_norm": 0.15411277115345,
"learning_rate": 1.484886474439337e-05,
"loss": 0.13486359596252442,
"step": 1850
},
{
"epoch": 0.7939824488090264,
"grad_norm": 11.361255645751953,
"learning_rate": 1.4709569577935648e-05,
"loss": 0.14342088699340821,
"step": 1900
},
{
"epoch": 0.8148767237776849,
"grad_norm": 4.867748260498047,
"learning_rate": 1.4570274411477922e-05,
"loss": 0.17925350189208986,
"step": 1950
},
{
"epoch": 0.8357709987463435,
"grad_norm": 0.22107701003551483,
"learning_rate": 1.4430979245020198e-05,
"loss": 0.16497827529907227,
"step": 2000
},
{
"epoch": 0.8566652737150021,
"grad_norm": 0.3704015910625458,
"learning_rate": 1.4291684078562476e-05,
"loss": 0.18857778549194337,
"step": 2050
},
{
"epoch": 0.8775595486836607,
"grad_norm": 1.8854899406433105,
"learning_rate": 1.4152388912104752e-05,
"loss": 0.15048781394958496,
"step": 2100
},
{
"epoch": 0.8984538236523193,
"grad_norm": 2.3575544357299805,
"learning_rate": 1.4013093745647026e-05,
"loss": 0.15282381057739258,
"step": 2150
},
{
"epoch": 0.9193480986209779,
"grad_norm": 10.843013763427734,
"learning_rate": 1.3873798579189303e-05,
"loss": 0.17856983184814454,
"step": 2200
},
{
"epoch": 0.9402423735896365,
"grad_norm": 28.175739288330078,
"learning_rate": 1.373450341273158e-05,
"loss": 0.17273096084594727,
"step": 2250
},
{
"epoch": 0.9611366485582951,
"grad_norm": 3.3600142002105713,
"learning_rate": 1.3595208246273854e-05,
"loss": 0.16762380599975585,
"step": 2300
},
{
"epoch": 0.9820309235269536,
"grad_norm": 7.274984836578369,
"learning_rate": 1.3455913079816131e-05,
"loss": 0.14438682556152344,
"step": 2350
},
{
"epoch": 1.0,
"eval_accuracy": 0.9517291819036673,
"eval_f1": 0.9541757587780202,
"eval_loss": 0.17130780220031738,
"eval_precision": 0.9768480909829407,
"eval_recall": 0.9325319891430787,
"eval_roc_auc": 0.988670717759322,
"eval_runtime": 23.4469,
"eval_samples_per_second": 408.199,
"eval_steps_per_second": 25.547,
"step": 2393
},
{
"epoch": 1.0029251984956122,
"grad_norm": 13.274906158447266,
"learning_rate": 1.3316617913358407e-05,
"loss": 0.12662715911865235,
"step": 2400
},
{
"epoch": 1.0238194734642707,
"grad_norm": 9.537711143493652,
"learning_rate": 1.3177322746900683e-05,
"loss": 0.1331467056274414,
"step": 2450
},
{
"epoch": 1.0447137484329294,
"grad_norm": 0.07932496070861816,
"learning_rate": 1.303802758044296e-05,
"loss": 0.07700533390045167,
"step": 2500
},
{
"epoch": 1.065608023401588,
"grad_norm": 22.845592498779297,
"learning_rate": 1.2898732413985235e-05,
"loss": 0.1407607078552246,
"step": 2550
},
{
"epoch": 1.0865022983702466,
"grad_norm": 1.8887174129486084,
"learning_rate": 1.2759437247527511e-05,
"loss": 0.14862350463867188,
"step": 2600
},
{
"epoch": 1.107396573338905,
"grad_norm": 21.409822463989258,
"learning_rate": 1.2620142081069789e-05,
"loss": 0.1066131591796875,
"step": 2650
},
{
"epoch": 1.1282908483075638,
"grad_norm": 9.874686241149902,
"learning_rate": 1.2480846914612063e-05,
"loss": 0.1277271842956543,
"step": 2700
},
{
"epoch": 1.1491851232762222,
"grad_norm": 32.69708251953125,
"learning_rate": 1.234155174815434e-05,
"loss": 0.10314902305603027,
"step": 2750
},
{
"epoch": 1.170079398244881,
"grad_norm": 40.25661849975586,
"learning_rate": 1.2202256581696617e-05,
"loss": 0.1239256763458252,
"step": 2800
},
{
"epoch": 1.1909736732135394,
"grad_norm": 0.40529486536979675,
"learning_rate": 1.2062961415238891e-05,
"loss": 0.13213342666625977,
"step": 2850
},
{
"epoch": 1.2118679481821981,
"grad_norm": 9.9985933303833,
"learning_rate": 1.1923666248781167e-05,
"loss": 0.1504405117034912,
"step": 2900
},
{
"epoch": 1.2327622231508566,
"grad_norm": 5.924779415130615,
"learning_rate": 1.1784371082323445e-05,
"loss": 0.11065505981445313,
"step": 2950
},
{
"epoch": 1.2536564981195153,
"grad_norm": 7.170877933502197,
"learning_rate": 1.164507591586572e-05,
"loss": 0.14150952339172362,
"step": 3000
},
{
"epoch": 1.2745507730881738,
"grad_norm": 7.508606433868408,
"learning_rate": 1.1505780749407995e-05,
"loss": 0.12164650917053223,
"step": 3050
},
{
"epoch": 1.2954450480568325,
"grad_norm": 2.847343683242798,
"learning_rate": 1.1366485582950273e-05,
"loss": 0.1189763069152832,
"step": 3100
},
{
"epoch": 1.316339323025491,
"grad_norm": 0.18800053000450134,
"learning_rate": 1.1227190416492549e-05,
"loss": 0.12123541831970215,
"step": 3150
},
{
"epoch": 1.3372335979941496,
"grad_norm": 9.2164306640625,
"learning_rate": 1.1087895250034826e-05,
"loss": 0.1492047691345215,
"step": 3200
},
{
"epoch": 1.3581278729628081,
"grad_norm": 3.368389844894409,
"learning_rate": 1.09486000835771e-05,
"loss": 0.12039382934570313,
"step": 3250
},
{
"epoch": 1.3790221479314668,
"grad_norm": 15.344005584716797,
"learning_rate": 1.0809304917119377e-05,
"loss": 0.17583621978759767,
"step": 3300
},
{
"epoch": 1.3999164229001253,
"grad_norm": 0.2738807797431946,
"learning_rate": 1.0670009750661654e-05,
"loss": 0.11576725006103515,
"step": 3350
},
{
"epoch": 1.420810697868784,
"grad_norm": 0.5546051263809204,
"learning_rate": 1.053071458420393e-05,
"loss": 0.09594018936157227,
"step": 3400
},
{
"epoch": 1.4417049728374425,
"grad_norm": 6.343163013458252,
"learning_rate": 1.0391419417746204e-05,
"loss": 0.15849972724914552,
"step": 3450
},
{
"epoch": 1.4625992478061012,
"grad_norm": 0.42352578043937683,
"learning_rate": 1.0252124251288482e-05,
"loss": 0.13367960929870606,
"step": 3500
},
{
"epoch": 1.4834935227747597,
"grad_norm": 0.37602102756500244,
"learning_rate": 1.0112829084830758e-05,
"loss": 0.16289531707763671,
"step": 3550
},
{
"epoch": 1.5043877977434184,
"grad_norm": 17.831235885620117,
"learning_rate": 9.973533918373032e-06,
"loss": 0.13586066246032716,
"step": 3600
},
{
"epoch": 1.525282072712077,
"grad_norm": 3.6913325786590576,
"learning_rate": 9.83423875191531e-06,
"loss": 0.1345800304412842,
"step": 3650
},
{
"epoch": 1.5461763476807355,
"grad_norm": 0.21697098016738892,
"learning_rate": 9.694943585457586e-06,
"loss": 0.13902374267578124,
"step": 3700
},
{
"epoch": 1.567070622649394,
"grad_norm": 8.487095832824707,
"learning_rate": 9.55564841899986e-06,
"loss": 0.0743906021118164,
"step": 3750
},
{
"epoch": 1.5879648976180527,
"grad_norm": 16.863210678100586,
"learning_rate": 9.416353252542138e-06,
"loss": 0.14349569320678712,
"step": 3800
},
{
"epoch": 1.6088591725867114,
"grad_norm": 16.5794677734375,
"learning_rate": 9.277058086084414e-06,
"loss": 0.1369628143310547,
"step": 3850
},
{
"epoch": 1.6297534475553699,
"grad_norm": 15.142793655395508,
"learning_rate": 9.13776291962669e-06,
"loss": 0.14577944755554198,
"step": 3900
},
{
"epoch": 1.6506477225240284,
"grad_norm": 0.13267600536346436,
"learning_rate": 8.998467753168966e-06,
"loss": 0.1497889518737793,
"step": 3950
},
{
"epoch": 1.671541997492687,
"grad_norm": 6.159015655517578,
"learning_rate": 8.859172586711242e-06,
"loss": 0.11653865814208984,
"step": 4000
},
{
"epoch": 1.6924362724613455,
"grad_norm": 8.872601509094238,
"learning_rate": 8.719877420253518e-06,
"loss": 0.10274889945983887,
"step": 4050
},
{
"epoch": 1.713330547430004,
"grad_norm": 9.018329620361328,
"learning_rate": 8.580582253795794e-06,
"loss": 0.11837130546569824,
"step": 4100
},
{
"epoch": 1.7342248223986627,
"grad_norm": 14.152815818786621,
"learning_rate": 8.44128708733807e-06,
"loss": 0.16490467071533202,
"step": 4150
},
{
"epoch": 1.7551190973673214,
"grad_norm": 14.32945442199707,
"learning_rate": 8.301991920880346e-06,
"loss": 0.1048060703277588,
"step": 4200
},
{
"epoch": 1.77601337233598,
"grad_norm": 6.154604434967041,
"learning_rate": 8.162696754422622e-06,
"loss": 0.16529315948486328,
"step": 4250
},
{
"epoch": 1.7969076473046384,
"grad_norm": 0.08094485104084015,
"learning_rate": 8.0234015879649e-06,
"loss": 0.1271997547149658,
"step": 4300
},
{
"epoch": 1.817801922273297,
"grad_norm": 0.6882657408714294,
"learning_rate": 7.884106421507174e-06,
"loss": 0.13333623886108398,
"step": 4350
},
{
"epoch": 1.8386961972419558,
"grad_norm": 0.6915619373321533,
"learning_rate": 7.74481125504945e-06,
"loss": 0.13177142143249512,
"step": 4400
},
{
"epoch": 1.8595904722106142,
"grad_norm": 0.04286617785692215,
"learning_rate": 7.605516088591726e-06,
"loss": 0.13941577911376954,
"step": 4450
},
{
"epoch": 1.8804847471792727,
"grad_norm": 0.24726086854934692,
"learning_rate": 7.466220922134002e-06,
"loss": 0.09164502143859864,
"step": 4500
},
{
"epoch": 1.9013790221479314,
"grad_norm": 19.788192749023438,
"learning_rate": 7.326925755676278e-06,
"loss": 0.16358205795288086,
"step": 4550
},
{
"epoch": 1.9222732971165901,
"grad_norm": 0.27708864212036133,
"learning_rate": 7.187630589218555e-06,
"loss": 0.08937115669250488,
"step": 4600
},
{
"epoch": 1.9431675720852486,
"grad_norm": 0.12228301912546158,
"learning_rate": 7.04833542276083e-06,
"loss": 0.10156312942504883,
"step": 4650
},
{
"epoch": 1.964061847053907,
"grad_norm": 0.11465885490179062,
"learning_rate": 6.909040256303107e-06,
"loss": 0.1402867317199707,
"step": 4700
},
{
"epoch": 1.9849561220225658,
"grad_norm": 0.2828459143638611,
"learning_rate": 6.769745089845383e-06,
"loss": 0.1601162338256836,
"step": 4750
},
{
"epoch": 2.0,
"eval_accuracy": 0.948699195486365,
"eval_f1": 0.9528564570331253,
"eval_loss": 0.16155333817005157,
"eval_precision": 0.9438843446832794,
"eval_recall": 0.9620007754943777,
"eval_roc_auc": 0.9904143280362305,
"eval_runtime": 23.4021,
"eval_samples_per_second": 408.98,
"eval_steps_per_second": 25.596,
"step": 4786
},
{
"epoch": 2.0058503969912245,
"grad_norm": 15.84992790222168,
"learning_rate": 6.630449923387658e-06,
"loss": 0.12227592468261719,
"step": 4800
},
{
"epoch": 2.026744671959883,
"grad_norm": 0.45001888275146484,
"learning_rate": 6.491154756929935e-06,
"loss": 0.06678987979888916,
"step": 4850
},
{
"epoch": 2.0476389469285414,
"grad_norm": 0.8402959704399109,
"learning_rate": 6.351859590472211e-06,
"loss": 0.11400195121765137,
"step": 4900
},
{
"epoch": 2.0685332218972,
"grad_norm": 0.4083273410797119,
"learning_rate": 6.212564424014487e-06,
"loss": 0.08374635696411133,
"step": 4950
},
{
"epoch": 2.089427496865859,
"grad_norm": 0.15326806902885437,
"learning_rate": 6.073269257556763e-06,
"loss": 0.10893898010253907,
"step": 5000
},
{
"epoch": 2.1103217718345175,
"grad_norm": 11.168054580688477,
"learning_rate": 5.93397409109904e-06,
"loss": 0.1383556079864502,
"step": 5050
},
{
"epoch": 2.131216046803176,
"grad_norm": 0.11581141501665115,
"learning_rate": 5.794678924641315e-06,
"loss": 0.08604293823242187,
"step": 5100
},
{
"epoch": 2.1521103217718345,
"grad_norm": 3.59356427192688,
"learning_rate": 5.655383758183592e-06,
"loss": 0.09102669715881348,
"step": 5150
},
{
"epoch": 2.173004596740493,
"grad_norm": 0.0897458866238594,
"learning_rate": 5.516088591725868e-06,
"loss": 0.05512897491455078,
"step": 5200
},
{
"epoch": 2.193898871709152,
"grad_norm": 5.144851207733154,
"learning_rate": 5.3767934252681445e-06,
"loss": 0.10218334197998047,
"step": 5250
},
{
"epoch": 2.21479314667781,
"grad_norm": 0.227946937084198,
"learning_rate": 5.23749825881042e-06,
"loss": 0.09305851936340331,
"step": 5300
},
{
"epoch": 2.235687421646469,
"grad_norm": 0.26025137305259705,
"learning_rate": 5.0982030923526956e-06,
"loss": 0.07569239139556885,
"step": 5350
},
{
"epoch": 2.2565816966151275,
"grad_norm": 0.10767011344432831,
"learning_rate": 4.9589079258949715e-06,
"loss": 0.04926969051361084,
"step": 5400
},
{
"epoch": 2.2774759715837862,
"grad_norm": 0.4100989103317261,
"learning_rate": 4.8196127594372475e-06,
"loss": 0.09085386276245117,
"step": 5450
},
{
"epoch": 2.2983702465524445,
"grad_norm": 0.06200162693858147,
"learning_rate": 4.680317592979524e-06,
"loss": 0.08421978950500489,
"step": 5500
},
{
"epoch": 2.319264521521103,
"grad_norm": 2.6880674362182617,
"learning_rate": 4.5410224265218e-06,
"loss": 0.09992499351501465,
"step": 5550
},
{
"epoch": 2.340158796489762,
"grad_norm": 0.19707849621772766,
"learning_rate": 4.401727260064076e-06,
"loss": 0.04249430656433106,
"step": 5600
},
{
"epoch": 2.3610530714584206,
"grad_norm": 0.0682622566819191,
"learning_rate": 4.262432093606352e-06,
"loss": 0.08731508255004883,
"step": 5650
},
{
"epoch": 2.381947346427079,
"grad_norm": 7.576389789581299,
"learning_rate": 4.123136927148628e-06,
"loss": 0.05915518283843994,
"step": 5700
},
{
"epoch": 2.4028416213957375,
"grad_norm": 5.807775497436523,
"learning_rate": 3.983841760690904e-06,
"loss": 0.08766698837280273,
"step": 5750
},
{
"epoch": 2.4237358963643962,
"grad_norm": 25.983449935913086,
"learning_rate": 3.84454659423318e-06,
"loss": 0.07257685661315919,
"step": 5800
},
{
"epoch": 2.444630171333055,
"grad_norm": 0.14547644555568695,
"learning_rate": 3.7052514277754565e-06,
"loss": 0.14911593437194826,
"step": 5850
},
{
"epoch": 2.465524446301713,
"grad_norm": 0.35611000657081604,
"learning_rate": 3.5659562613177325e-06,
"loss": 0.13339613914489745,
"step": 5900
},
{
"epoch": 2.486418721270372,
"grad_norm": 0.08110082149505615,
"learning_rate": 3.426661094860009e-06,
"loss": 0.08725551605224609,
"step": 5950
},
{
"epoch": 2.5073129962390306,
"grad_norm": 0.5092394351959229,
"learning_rate": 3.2873659284022845e-06,
"loss": 0.0801594066619873,
"step": 6000
},
{
"epoch": 2.5282072712076893,
"grad_norm": 1.5373930931091309,
"learning_rate": 3.1480707619445604e-06,
"loss": 0.1282341194152832,
"step": 6050
},
{
"epoch": 2.5491015461763475,
"grad_norm": 0.4443158805370331,
"learning_rate": 3.008775595486837e-06,
"loss": 0.0929796314239502,
"step": 6100
},
{
"epoch": 2.5699958211450062,
"grad_norm": 10.2298002243042,
"learning_rate": 2.869480429029113e-06,
"loss": 0.10379323959350586,
"step": 6150
},
{
"epoch": 2.590890096113665,
"grad_norm": 0.0766865611076355,
"learning_rate": 2.730185262571389e-06,
"loss": 0.0929744815826416,
"step": 6200
},
{
"epoch": 2.611784371082323,
"grad_norm": 0.01663370430469513,
"learning_rate": 2.590890096113665e-06,
"loss": 0.0744728136062622,
"step": 6250
},
{
"epoch": 2.632678646050982,
"grad_norm": 0.07390784472227097,
"learning_rate": 2.451594929655941e-06,
"loss": 0.043207130432128905,
"step": 6300
},
{
"epoch": 2.6535729210196406,
"grad_norm": 18.12549591064453,
"learning_rate": 2.312299763198217e-06,
"loss": 0.09382804870605468,
"step": 6350
},
{
"epoch": 2.6744671959882993,
"grad_norm": 14.898078918457031,
"learning_rate": 2.1730045967404935e-06,
"loss": 0.11781403541564942,
"step": 6400
},
{
"epoch": 2.695361470956958,
"grad_norm": 15.47895336151123,
"learning_rate": 2.033709430282769e-06,
"loss": 0.11296468734741211,
"step": 6450
},
{
"epoch": 2.7162557459256162,
"grad_norm": 0.3714354932308197,
"learning_rate": 1.8944142638250454e-06,
"loss": 0.09556021690368652,
"step": 6500
},
{
"epoch": 2.737150020894275,
"grad_norm": 7.036530494689941,
"learning_rate": 1.7551190973673216e-06,
"loss": 0.09722694396972656,
"step": 6550
},
{
"epoch": 2.7580442958629336,
"grad_norm": 1.7828617095947266,
"learning_rate": 1.6158239309095974e-06,
"loss": 0.08951042175292968,
"step": 6600
},
{
"epoch": 2.778938570831592,
"grad_norm": 0.2427712231874466,
"learning_rate": 1.4765287644518736e-06,
"loss": 0.08594783782958984,
"step": 6650
},
{
"epoch": 2.7998328458002506,
"grad_norm": 0.13741722702980042,
"learning_rate": 1.3372335979941497e-06,
"loss": 0.09343706130981445,
"step": 6700
},
{
"epoch": 2.8207271207689093,
"grad_norm": 26.75634765625,
"learning_rate": 1.1979384315364257e-06,
"loss": 0.05327910423278809,
"step": 6750
},
{
"epoch": 2.841621395737568,
"grad_norm": 7.751676082611084,
"learning_rate": 1.058643265078702e-06,
"loss": 0.0780732774734497,
"step": 6800
},
{
"epoch": 2.8625156707062267,
"grad_norm": 0.48609209060668945,
"learning_rate": 9.19348098620978e-07,
"loss": 0.10226208686828614,
"step": 6850
},
{
"epoch": 2.883409945674885,
"grad_norm": 35.70721435546875,
"learning_rate": 7.80052932163254e-07,
"loss": 0.09009994506835937,
"step": 6900
},
{
"epoch": 2.9043042206435437,
"grad_norm": 0.20764575898647308,
"learning_rate": 6.407577657055301e-07,
"loss": 0.08318242073059082,
"step": 6950
},
{
"epoch": 2.9251984956122024,
"grad_norm": 0.6534445285797119,
"learning_rate": 5.014625992478062e-07,
"loss": 0.09149464607238769,
"step": 7000
},
{
"epoch": 2.9460927705808606,
"grad_norm": 15.274673461914062,
"learning_rate": 3.621674327900822e-07,
"loss": 0.06574362754821778,
"step": 7050
},
{
"epoch": 2.9669870455495193,
"grad_norm": 0.4896354675292969,
"learning_rate": 2.2287226633235828e-07,
"loss": 0.08324499130249023,
"step": 7100
},
{
"epoch": 2.987881320518178,
"grad_norm": 0.035827573388814926,
"learning_rate": 8.357709987463436e-08,
"loss": 0.09447690010070801,
"step": 7150
},
{
"epoch": 3.0,
"eval_accuracy": 0.9547591683209696,
"eval_f1": 0.957727228351069,
"eval_loss": 0.21484783291816711,
"eval_precision": 0.9646017699115044,
"eval_recall": 0.9509499806126406,
"eval_roc_auc": 0.9897728933171557,
"eval_runtime": 23.436,
"eval_samples_per_second": 408.389,
"eval_steps_per_second": 25.559,
"step": 7179
}
],
"logging_steps": 50,
"max_steps": 7179,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.025956770716096e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}