{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.996074326092646, "eval_steps": 100, "global_step": 1431, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002093692750588851, "grad_norm": 53.581159797745435, "learning_rate": 6.9444444444444435e-09, "logits/chosen": -0.48425233364105225, "logits/rejected": -0.32109448313713074, "logps/chosen": -276.5158996582031, "logps/rejected": -302.22406005859375, "loss": 0.6931, "rewards/accuracies": 0.0, "rewards/chosen": 0.0, "rewards/margins": 0.0, "rewards/rejected": 0.0, "step": 1 }, { "epoch": 0.02093692750588851, "grad_norm": 47.92244929429545, "learning_rate": 6.944444444444444e-08, "logits/chosen": -0.20008452236652374, "logits/rejected": -0.1900922954082489, "logps/chosen": -337.452392578125, "logps/rejected": -293.0785217285156, "loss": 0.7231, "rewards/accuracies": 0.3541666567325592, "rewards/chosen": -0.022724969312548637, "rewards/margins": -0.036751341074705124, "rewards/rejected": 0.014026367105543613, "step": 10 }, { "epoch": 0.04187385501177702, "grad_norm": 41.37562973132045, "learning_rate": 1.3888888888888888e-07, "logits/chosen": -0.042457859963178635, "logits/rejected": -0.12332990020513535, "logps/chosen": -298.8910217285156, "logps/rejected": -271.74114990234375, "loss": 0.7114, "rewards/accuracies": 0.4375, "rewards/chosen": 0.016111990436911583, "rewards/margins": -0.0034494102001190186, "rewards/rejected": 0.0195614043623209, "step": 20 }, { "epoch": 0.06281078251766553, "grad_norm": 50.166233912169, "learning_rate": 2.0833333333333333e-07, "logits/chosen": -0.0645759329199791, "logits/rejected": -0.09565907716751099, "logps/chosen": -323.93743896484375, "logps/rejected": -261.7337341308594, "loss": 0.7165, "rewards/accuracies": 0.4625000059604645, "rewards/chosen": -0.056218355894088745, "rewards/margins": 0.005095779895782471, "rewards/rejected": -0.061314135789871216, "step": 30 }, { "epoch": 0.08374771002355404, "grad_norm": 45.45611748658909, "learning_rate": 2.7777777777777776e-07, "logits/chosen": -0.13370418548583984, "logits/rejected": -0.16684015095233917, "logps/chosen": -272.07928466796875, "logps/rejected": -251.01589965820312, "loss": 0.7166, "rewards/accuracies": 0.6000000238418579, "rewards/chosen": 0.006498994771391153, "rewards/margins": 0.06555742770433426, "rewards/rejected": -0.05905843526124954, "step": 40 }, { "epoch": 0.10468463752944256, "grad_norm": 55.30410487113166, "learning_rate": 3.472222222222222e-07, "logits/chosen": -0.0792478546500206, "logits/rejected": -0.0551227442920208, "logps/chosen": -292.2696838378906, "logps/rejected": -266.82965087890625, "loss": 0.7243, "rewards/accuracies": 0.5, "rewards/chosen": -0.08804600685834885, "rewards/margins": -0.04349173232913017, "rewards/rejected": -0.044554274529218674, "step": 50 }, { "epoch": 0.12562156503533106, "grad_norm": 56.63523816899612, "learning_rate": 4.1666666666666667e-07, "logits/chosen": -0.1644289791584015, "logits/rejected": -0.19546563923358917, "logps/chosen": -269.5990295410156, "logps/rejected": -258.08721923828125, "loss": 0.7419, "rewards/accuracies": 0.518750011920929, "rewards/chosen": 0.04003779590129852, "rewards/margins": 0.05106702446937561, "rewards/rejected": -0.011029230430722237, "step": 60 }, { "epoch": 0.14655849254121958, "grad_norm": 50.48428456914726, "learning_rate": 4.861111111111111e-07, "logits/chosen": -0.1528700441122055, "logits/rejected": -0.12956030666828156, "logps/chosen": -334.1960144042969, "logps/rejected": -295.05865478515625, "loss": 0.7096, "rewards/accuracies": 0.5375000238418579, "rewards/chosen": -0.012429716996848583, "rewards/margins": 0.03767075017094612, "rewards/rejected": -0.05010046809911728, "step": 70 }, { "epoch": 0.16749542004710807, "grad_norm": 49.10207941889299, "learning_rate": 5.555555555555555e-07, "logits/chosen": 0.019698064774274826, "logits/rejected": -0.05375131219625473, "logps/chosen": -324.42889404296875, "logps/rejected": -256.3900451660156, "loss": 0.7125, "rewards/accuracies": 0.574999988079071, "rewards/chosen": 0.0010342865716665983, "rewards/margins": 0.04288307949900627, "rewards/rejected": -0.0418488010764122, "step": 80 }, { "epoch": 0.1884323475529966, "grad_norm": 48.35701594054669, "learning_rate": 6.249999999999999e-07, "logits/chosen": -0.18192127346992493, "logits/rejected": -0.15880808234214783, "logps/chosen": -282.22161865234375, "logps/rejected": -251.54296875, "loss": 0.6976, "rewards/accuracies": 0.4937500059604645, "rewards/chosen": -0.012317812070250511, "rewards/margins": -0.011760599911212921, "rewards/rejected": -0.0005572110530920327, "step": 90 }, { "epoch": 0.2093692750588851, "grad_norm": 44.92592146146067, "learning_rate": 6.944444444444444e-07, "logits/chosen": -0.11696960031986237, "logits/rejected": -0.13915769755840302, "logps/chosen": -316.96527099609375, "logps/rejected": -277.3512268066406, "loss": 0.6787, "rewards/accuracies": 0.5562499761581421, "rewards/chosen": 0.03938128799200058, "rewards/margins": 0.08465500175952911, "rewards/rejected": -0.045273713767528534, "step": 100 }, { "epoch": 0.2093692750588851, "eval_logits/chosen": -0.3141140341758728, "eval_logits/rejected": -0.3377441465854645, "eval_logps/chosen": -310.252685546875, "eval_logps/rejected": -274.4240417480469, "eval_loss": 0.6966869235038757, "eval_rewards/accuracies": 0.5515872836112976, "eval_rewards/chosen": 0.01587979681789875, "eval_rewards/margins": 0.08612197637557983, "eval_rewards/rejected": -0.07024218887090683, "eval_runtime": 19.212, "eval_samples_per_second": 104.102, "eval_steps_per_second": 3.279, "step": 100 }, { "epoch": 0.23030620256477363, "grad_norm": 42.34774239140926, "learning_rate": 7.638888888888888e-07, "logits/chosen": -0.15527260303497314, "logits/rejected": -0.1998877376317978, "logps/chosen": -317.2166748046875, "logps/rejected": -267.8033447265625, "loss": 0.6869, "rewards/accuracies": 0.5562499761581421, "rewards/chosen": -0.0031774670351296663, "rewards/margins": 0.06427686661481857, "rewards/rejected": -0.06745433807373047, "step": 110 }, { "epoch": 0.2512431300706621, "grad_norm": 42.69543501672853, "learning_rate": 8.333333333333333e-07, "logits/chosen": -0.08257915079593658, "logits/rejected": -0.12443940341472626, "logps/chosen": -275.12579345703125, "logps/rejected": -245.96347045898438, "loss": 0.6706, "rewards/accuracies": 0.5562499761581421, "rewards/chosen": 0.050213612616062164, "rewards/margins": 0.10280221700668335, "rewards/rejected": -0.052588604390621185, "step": 120 }, { "epoch": 0.2721800575765506, "grad_norm": 50.775507526530916, "learning_rate": 9.027777777777778e-07, "logits/chosen": -0.14645054936408997, "logits/rejected": -0.2005746066570282, "logps/chosen": -313.00238037109375, "logps/rejected": -257.37945556640625, "loss": 0.6662, "rewards/accuracies": 0.6187499761581421, "rewards/chosen": 0.12051638215780258, "rewards/margins": 0.18545812368392944, "rewards/rejected": -0.06494174152612686, "step": 130 }, { "epoch": 0.29311698508243916, "grad_norm": 45.04510687958917, "learning_rate": 9.722222222222222e-07, "logits/chosen": -0.18603107333183289, "logits/rejected": -0.14804694056510925, "logps/chosen": -336.45330810546875, "logps/rejected": -270.71844482421875, "loss": 0.6837, "rewards/accuracies": 0.574999988079071, "rewards/chosen": 0.1061311587691307, "rewards/margins": 0.20069436728954315, "rewards/rejected": -0.09456320852041245, "step": 140 }, { "epoch": 0.31405391258832765, "grad_norm": 47.07473020466515, "learning_rate": 9.999463737538052e-07, "logits/chosen": -0.09479381889104843, "logits/rejected": -0.18823939561843872, "logps/chosen": -300.7477111816406, "logps/rejected": -261.5872497558594, "loss": 0.6701, "rewards/accuracies": 0.543749988079071, "rewards/chosen": 0.014584893360733986, "rewards/margins": 0.1319422572851181, "rewards/rejected": -0.11735737323760986, "step": 150 }, { "epoch": 0.33499084009421615, "grad_norm": 40.24946321953983, "learning_rate": 9.996186994612174e-07, "logits/chosen": -0.07166972011327744, "logits/rejected": -0.05619664117693901, "logps/chosen": -277.3063049316406, "logps/rejected": -264.21929931640625, "loss": 0.6571, "rewards/accuracies": 0.6499999761581421, "rewards/chosen": -0.002465812023729086, "rewards/margins": 0.21548476815223694, "rewards/rejected": -0.21795055270195007, "step": 160 }, { "epoch": 0.3559277676001047, "grad_norm": 43.25422484420196, "learning_rate": 9.989933382359422e-07, "logits/chosen": -0.22567839920520782, "logits/rejected": -0.2581842541694641, "logps/chosen": -270.6056213378906, "logps/rejected": -234.0198211669922, "loss": 0.6614, "rewards/accuracies": 0.6499999761581421, "rewards/chosen": -0.0034525603987276554, "rewards/margins": 0.24006681144237518, "rewards/rejected": -0.2435193508863449, "step": 170 }, { "epoch": 0.3768646951059932, "grad_norm": 39.47362541006732, "learning_rate": 9.980706626858607e-07, "logits/chosen": -0.15520626306533813, "logits/rejected": -0.13547591865062714, "logps/chosen": -275.5711364746094, "logps/rejected": -280.95904541015625, "loss": 0.6323, "rewards/accuracies": 0.699999988079071, "rewards/chosen": 0.01858050376176834, "rewards/margins": 0.3474423885345459, "rewards/rejected": -0.32886189222335815, "step": 180 }, { "epoch": 0.39780162261188173, "grad_norm": 45.3164057858113, "learning_rate": 9.968512225671258e-07, "logits/chosen": -0.07492430508136749, "logits/rejected": -0.07894851267337799, "logps/chosen": -287.3063659667969, "logps/rejected": -286.6043395996094, "loss": 0.649, "rewards/accuracies": 0.612500011920929, "rewards/chosen": -0.07111965119838715, "rewards/margins": 0.22652164101600647, "rewards/rejected": -0.2976413071155548, "step": 190 }, { "epoch": 0.4187385501177702, "grad_norm": 51.9773301288437, "learning_rate": 9.953357444566038e-07, "logits/chosen": -0.09818016737699509, "logits/rejected": -0.11751595884561539, "logps/chosen": -284.3682861328125, "logps/rejected": -264.2423095703125, "loss": 0.645, "rewards/accuracies": 0.5687500238418579, "rewards/chosen": -0.06741360574960709, "rewards/margins": 0.13478204607963562, "rewards/rejected": -0.2021956443786621, "step": 200 }, { "epoch": 0.4187385501177702, "eval_logits/chosen": -0.3229367136955261, "eval_logits/rejected": -0.34633249044418335, "eval_logps/chosen": -310.3840026855469, "eval_logps/rejected": -274.8875732421875, "eval_loss": 0.6491106748580933, "eval_rewards/accuracies": 0.60317462682724, "eval_rewards/chosen": -0.04975215345621109, "eval_rewards/margins": 0.25227656960487366, "eval_rewards/rejected": -0.30202868580818176, "eval_runtime": 19.4848, "eval_samples_per_second": 102.644, "eval_steps_per_second": 3.233, "step": 200 }, { "epoch": 0.4396754776236587, "grad_norm": 42.51852593559685, "learning_rate": 9.935251313189563e-07, "logits/chosen": 0.02242279052734375, "logits/rejected": -0.06930123269557953, "logps/chosen": -321.75689697265625, "logps/rejected": -269.69781494140625, "loss": 0.6528, "rewards/accuracies": 0.612500011920929, "rewards/chosen": -0.06879940629005432, "rewards/margins": 0.2159956693649292, "rewards/rejected": -0.2847950756549835, "step": 210 }, { "epoch": 0.46061240512954726, "grad_norm": 39.56904653144407, "learning_rate": 9.914204619686312e-07, "logits/chosen": -0.21375274658203125, "logits/rejected": -0.06523901224136353, "logps/chosen": -263.26251220703125, "logps/rejected": -254.17361450195312, "loss": 0.6473, "rewards/accuracies": 0.574999988079071, "rewards/chosen": -0.09464406222105026, "rewards/margins": 0.11034605652093887, "rewards/rejected": -0.20499010384082794, "step": 220 }, { "epoch": 0.48154933263543576, "grad_norm": 49.49502162405857, "learning_rate": 9.89022990427073e-07, "logits/chosen": -0.1386515200138092, "logits/rejected": -0.027841920033097267, "logps/chosen": -275.6785583496094, "logps/rejected": -282.2340393066406, "loss": 0.651, "rewards/accuracies": 0.6875, "rewards/chosen": -0.0026134043000638485, "rewards/margins": 0.34593018889427185, "rewards/rejected": -0.34854358434677124, "step": 230 }, { "epoch": 0.5024862601413242, "grad_norm": 42.40141104653558, "learning_rate": 9.86334145175542e-07, "logits/chosen": -0.16665732860565186, "logits/rejected": -0.13909348845481873, "logps/chosen": -282.2431640625, "logps/rejected": -265.6712341308594, "loss": 0.6269, "rewards/accuracies": 0.5562499761581421, "rewards/chosen": -0.03417225927114487, "rewards/margins": 0.2094908207654953, "rewards/rejected": -0.24366307258605957, "step": 240 }, { "epoch": 0.5234231876472127, "grad_norm": 44.711963555505086, "learning_rate": 9.83355528303984e-07, "logits/chosen": -0.21623122692108154, "logits/rejected": -0.25620579719543457, "logps/chosen": -321.9479064941406, "logps/rejected": -276.6851501464844, "loss": 0.6483, "rewards/accuracies": 0.59375, "rewards/chosen": -0.033338677138090134, "rewards/margins": 0.21741199493408203, "rewards/rejected": -0.25075066089630127, "step": 250 }, { "epoch": 0.5443601151531012, "grad_norm": 44.08715279117413, "learning_rate": 9.800889145564616e-07, "logits/chosen": -0.023601394146680832, "logits/rejected": -0.08905109018087387, "logps/chosen": -307.87286376953125, "logps/rejected": -257.384765625, "loss": 0.6489, "rewards/accuracies": 0.6000000238418579, "rewards/chosen": -0.03719106689095497, "rewards/margins": 0.2362823486328125, "rewards/rejected": -0.2734734117984772, "step": 260 }, { "epoch": 0.5652970426589898, "grad_norm": 39.7549215734126, "learning_rate": 9.765362502737097e-07, "logits/chosen": -0.15661786496639252, "logits/rejected": -0.1753096580505371, "logps/chosen": -313.56787109375, "logps/rejected": -277.8585510253906, "loss": 0.6233, "rewards/accuracies": 0.637499988079071, "rewards/chosen": 0.07719334214925766, "rewards/margins": 0.3890419602394104, "rewards/rejected": -0.31184864044189453, "step": 270 }, { "epoch": 0.5862339701648783, "grad_norm": 46.953763281596736, "learning_rate": 9.726996522334514e-07, "logits/chosen": -0.22773197293281555, "logits/rejected": -0.25082847476005554, "logps/chosen": -299.99127197265625, "logps/rejected": -249.6244659423828, "loss": 0.6409, "rewards/accuracies": 0.6312500238418579, "rewards/chosen": -0.044135063886642456, "rewards/margins": 0.2800499200820923, "rewards/rejected": -0.32418501377105713, "step": 280 }, { "epoch": 0.6071708976707668, "grad_norm": 38.382090654521065, "learning_rate": 9.68581406389163e-07, "logits/chosen": -0.14438043534755707, "logits/rejected": -0.17269106209278107, "logps/chosen": -282.90325927734375, "logps/rejected": -274.38079833984375, "loss": 0.6217, "rewards/accuracies": 0.643750011920929, "rewards/chosen": -0.009734408929944038, "rewards/margins": 0.3537730574607849, "rewards/rejected": -0.363507479429245, "step": 290 }, { "epoch": 0.6281078251766553, "grad_norm": 41.7647459812509, "learning_rate": 9.641839665080363e-07, "logits/chosen": -0.1018938273191452, "logits/rejected": -0.08353041112422943, "logps/chosen": -316.49810791015625, "logps/rejected": -277.4931640625, "loss": 0.6161, "rewards/accuracies": 0.6937500238418579, "rewards/chosen": 0.03871753811836243, "rewards/margins": 0.39340126514434814, "rewards/rejected": -0.3546837270259857, "step": 300 }, { "epoch": 0.6281078251766553, "eval_logits/chosen": -0.33166003227233887, "eval_logits/rejected": -0.3552355170249939, "eval_logps/chosen": -310.4118957519531, "eval_logps/rejected": -275.1272277832031, "eval_loss": 0.6316225528717041, "eval_rewards/accuracies": 0.682539701461792, "eval_rewards/chosen": -0.06370855122804642, "eval_rewards/margins": 0.3581322431564331, "eval_rewards/rejected": -0.4218408465385437, "eval_runtime": 19.0833, "eval_samples_per_second": 104.804, "eval_steps_per_second": 3.301, "step": 300 }, { "epoch": 0.6490447526825438, "grad_norm": 40.9716290999305, "learning_rate": 9.595099527089568e-07, "logits/chosen": -0.11042879521846771, "logits/rejected": -0.18008281290531158, "logps/chosen": -323.7516174316406, "logps/rejected": -247.0631561279297, "loss": 0.6007, "rewards/accuracies": 0.7124999761581421, "rewards/chosen": 0.10534234344959259, "rewards/margins": 0.5895902514457703, "rewards/rejected": -0.48424798250198364, "step": 310 }, { "epoch": 0.6699816801884323, "grad_norm": 45.14020951986602, "learning_rate": 9.545621499013618e-07, "logits/chosen": -0.024479269981384277, "logits/rejected": -0.038955364376306534, "logps/chosen": -294.4266662597656, "logps/rejected": -252.0673828125, "loss": 0.5995, "rewards/accuracies": 0.668749988079071, "rewards/chosen": 0.06134527176618576, "rewards/margins": 0.4816582202911377, "rewards/rejected": -0.4203129708766937, "step": 320 }, { "epoch": 0.6909186076943209, "grad_norm": 38.030813091938484, "learning_rate": 9.493435061259129e-07, "logits/chosen": -0.012772688642144203, "logits/rejected": -0.030413877218961716, "logps/chosen": -291.36761474609375, "logps/rejected": -265.4248046875, "loss": 0.6232, "rewards/accuracies": 0.6187499761581421, "rewards/chosen": 0.001638062298297882, "rewards/margins": 0.40076717734336853, "rewards/rejected": -0.39912909269332886, "step": 330 }, { "epoch": 0.7118555352002094, "grad_norm": 45.93570520280886, "learning_rate": 9.438571307979704e-07, "logits/chosen": -0.04617694020271301, "logits/rejected": -0.07658630609512329, "logps/chosen": -296.7699890136719, "logps/rejected": -270.9905090332031, "loss": 0.6096, "rewards/accuracies": 0.6812499761581421, "rewards/chosen": -0.05764853209257126, "rewards/margins": 0.28755250573158264, "rewards/rejected": -0.34520095586776733, "step": 340 }, { "epoch": 0.7327924627060979, "grad_norm": 44.09128545700975, "learning_rate": 9.381062928549151e-07, "logits/chosen": -0.12188152968883514, "logits/rejected": -0.13376249372959137, "logps/chosen": -282.15179443359375, "logps/rejected": -247.45834350585938, "loss": 0.5964, "rewards/accuracies": 0.6187499761581421, "rewards/chosen": -0.09005177021026611, "rewards/margins": 0.41418519616127014, "rewards/rejected": -0.5042369961738586, "step": 350 }, { "epoch": 0.7537293902119864, "grad_norm": 40.36784058818516, "learning_rate": 9.320944188084241e-07, "logits/chosen": -0.07130910456180573, "logits/rejected": -0.18685731291770935, "logps/chosen": -340.55487060546875, "logps/rejected": -278.08551025390625, "loss": 0.6256, "rewards/accuracies": 0.65625, "rewards/chosen": 0.1223798543214798, "rewards/margins": 0.4791669249534607, "rewards/rejected": -0.3567870557308197, "step": 360 }, { "epoch": 0.7746663177178749, "grad_norm": 37.74697617657793, "learning_rate": 9.258250907028572e-07, "logits/chosen": -0.2023000717163086, "logits/rejected": -0.25707709789276123, "logps/chosen": -306.526611328125, "logps/rejected": -248.40023803710938, "loss": 0.603, "rewards/accuracies": 0.6625000238418579, "rewards/chosen": 0.05354640632867813, "rewards/margins": 0.42885661125183105, "rewards/rejected": -0.3753102421760559, "step": 370 }, { "epoch": 0.7956032452237635, "grad_norm": 36.818935480552355, "learning_rate": 9.193020439809746e-07, "logits/chosen": -0.25006169080734253, "logits/rejected": -0.27239733934402466, "logps/chosen": -306.9652099609375, "logps/rejected": -274.15850830078125, "loss": 0.6108, "rewards/accuracies": 0.6937500238418579, "rewards/chosen": -0.005802587606012821, "rewards/margins": 0.5873938798904419, "rewards/rejected": -0.5931965112686157, "step": 380 }, { "epoch": 0.816540172729652, "grad_norm": 40.218709775991016, "learning_rate": 9.125291652582547e-07, "logits/chosen": -0.19798080623149872, "logits/rejected": -0.16009968519210815, "logps/chosen": -308.05975341796875, "logps/rejected": -289.6929626464844, "loss": 0.6163, "rewards/accuracies": 0.6937500238418579, "rewards/chosen": 0.09920313209295273, "rewards/margins": 0.47261109948158264, "rewards/rejected": -0.3734079897403717, "step": 390 }, { "epoch": 0.8374771002355405, "grad_norm": 39.13573330990029, "learning_rate": 9.055104900071375e-07, "logits/chosen": -0.3008892834186554, "logits/rejected": -0.1968032568693161, "logps/chosen": -253.58798217773438, "logps/rejected": -239.539794921875, "loss": 0.5964, "rewards/accuracies": 0.78125, "rewards/chosen": 0.14220505952835083, "rewards/margins": 0.6365345120429993, "rewards/rejected": -0.49432945251464844, "step": 400 }, { "epoch": 0.8374771002355405, "eval_logits/chosen": -0.3291381299495697, "eval_logits/rejected": -0.35453417897224426, "eval_logps/chosen": -310.317626953125, "eval_logps/rejected": -275.15972900390625, "eval_loss": 0.6100037693977356, "eval_rewards/accuracies": 0.658730149269104, "eval_rewards/chosen": -0.016582150012254715, "eval_rewards/margins": 0.42150571942329407, "eval_rewards/rejected": -0.43808794021606445, "eval_runtime": 19.1374, "eval_samples_per_second": 104.507, "eval_steps_per_second": 3.292, "step": 400 }, { "epoch": 0.8584140277414289, "grad_norm": 41.59836395581152, "learning_rate": 8.982502001525777e-07, "logits/chosen": -0.05211949348449707, "logits/rejected": -0.16379515826702118, "logps/chosen": -334.3597717285156, "logps/rejected": -280.1282043457031, "loss": 0.6085, "rewards/accuracies": 0.706250011920929, "rewards/chosen": 0.10034932941198349, "rewards/margins": 0.5413358211517334, "rewards/rejected": -0.4409864842891693, "step": 410 }, { "epoch": 0.8793509552473174, "grad_norm": 43.48433949710367, "learning_rate": 8.90752621580335e-07, "logits/chosen": -0.10794836282730103, "logits/rejected": -0.10175999253988266, "logps/chosen": -289.7253723144531, "logps/rejected": -290.4524841308594, "loss": 0.5967, "rewards/accuracies": 0.737500011920929, "rewards/chosen": 0.03317990154027939, "rewards/margins": 0.5273382663726807, "rewards/rejected": -0.4941583275794983, "step": 420 }, { "epoch": 0.9002878827532059, "grad_norm": 38.200809011500716, "learning_rate": 8.83022221559489e-07, "logits/chosen": -0.08915697038173676, "logits/rejected": -0.18852075934410095, "logps/chosen": -325.81707763671875, "logps/rejected": -257.1981506347656, "loss": 0.5916, "rewards/accuracies": 0.637499988079071, "rewards/chosen": 0.053056418895721436, "rewards/margins": 0.5633317232131958, "rewards/rejected": -0.5102753043174744, "step": 430 }, { "epoch": 0.9212248102590945, "grad_norm": 37.18511688193762, "learning_rate": 8.750636060807145e-07, "logits/chosen": -0.0535130575299263, "logits/rejected": -0.1133667603135109, "logps/chosen": -299.4546813964844, "logps/rejected": -248.877685546875, "loss": 0.6032, "rewards/accuracies": 0.6312500238418579, "rewards/chosen": 0.14839240908622742, "rewards/margins": 0.4819253385066986, "rewards/rejected": -0.3335329294204712, "step": 440 }, { "epoch": 0.942161737764983, "grad_norm": 35.5219084800687, "learning_rate": 8.668815171119019e-07, "logits/chosen": -0.16904090344905853, "logits/rejected": -0.12047908455133438, "logps/chosen": -297.3148498535156, "logps/rejected": -285.4595031738281, "loss": 0.6148, "rewards/accuracies": 0.6937500238418579, "rewards/chosen": 0.051097553223371506, "rewards/margins": 0.505901038646698, "rewards/rejected": -0.4548035264015198, "step": 450 }, { "epoch": 0.9630986652708715, "grad_norm": 40.701223424626065, "learning_rate": 8.584808297727591e-07, "logits/chosen": -0.07098624855279922, "logits/rejected": -0.11652670055627823, "logps/chosen": -291.76434326171875, "logps/rejected": -246.9138641357422, "loss": 0.6087, "rewards/accuracies": 0.643750011920929, "rewards/chosen": 0.10639622062444687, "rewards/margins": 0.5133938193321228, "rewards/rejected": -0.40699753165245056, "step": 460 }, { "epoch": 0.98403559277676, "grad_norm": 41.789096950373676, "learning_rate": 8.498665494300771e-07, "logits/chosen": -0.19742052257061005, "logits/rejected": -0.16556285321712494, "logps/chosen": -302.3099060058594, "logps/rejected": -277.933837890625, "loss": 0.5919, "rewards/accuracies": 0.625, "rewards/chosen": 0.026506727561354637, "rewards/margins": 0.43121033906936646, "rewards/rejected": -0.40470361709594727, "step": 470 }, { "epoch": 1.0049725202826485, "grad_norm": 34.0036850645019, "learning_rate": 8.410438087153911e-07, "logits/chosen": -0.05161554738879204, "logits/rejected": -0.1036214604973793, "logps/chosen": -300.4537658691406, "logps/rejected": -268.56048583984375, "loss": 0.5867, "rewards/accuracies": 0.6625000238418579, "rewards/chosen": -0.00218582758679986, "rewards/margins": 0.4712887704372406, "rewards/rejected": -0.4734745919704437, "step": 480 }, { "epoch": 1.025909447788537, "grad_norm": 36.00706898235858, "learning_rate": 8.320178644668141e-07, "logits/chosen": -0.11621465533971786, "logits/rejected": -0.18176773190498352, "logps/chosen": -299.8227233886719, "logps/rejected": -256.3122253417969, "loss": 0.54, "rewards/accuracies": 0.7562500238418579, "rewards/chosen": 0.12694445252418518, "rewards/margins": 0.600742757320404, "rewards/rejected": -0.47379836440086365, "step": 490 }, { "epoch": 1.0468463752944255, "grad_norm": 36.99527595331141, "learning_rate": 8.22794094596864e-07, "logits/chosen": -0.1485815942287445, "logits/rejected": -0.20506855845451355, "logps/chosen": -305.8435363769531, "logps/rejected": -270.3700256347656, "loss": 0.5394, "rewards/accuracies": 0.7124999761581421, "rewards/chosen": 0.029846886172890663, "rewards/margins": 0.6080519556999207, "rewards/rejected": -0.5782050490379333, "step": 500 }, { "epoch": 1.0468463752944255, "eval_logits/chosen": -0.33202826976776123, "eval_logits/rejected": -0.35762789845466614, "eval_logps/chosen": -310.303955078125, "eval_logps/rejected": -275.2332458496094, "eval_loss": 0.6065964102745056, "eval_rewards/accuracies": 0.7103174328804016, "eval_rewards/chosen": -0.009755274280905724, "eval_rewards/margins": 0.465115487575531, "eval_rewards/rejected": -0.4748707413673401, "eval_runtime": 18.9724, "eval_samples_per_second": 105.416, "eval_steps_per_second": 3.321, "step": 500 }, { "epoch": 1.067783302800314, "grad_norm": 33.8725028749791, "learning_rate": 8.133779948881513e-07, "logits/chosen": -0.18220725655555725, "logits/rejected": -0.1532759964466095, "logps/chosen": -269.54156494140625, "logps/rejected": -259.2676086425781, "loss": 0.533, "rewards/accuracies": 0.78125, "rewards/chosen": 0.12358293682336807, "rewards/margins": 0.7069646120071411, "rewards/rejected": -0.5833816528320312, "step": 510 }, { "epoch": 1.0887202303062025, "grad_norm": 32.98315936865049, "learning_rate": 8.037751757188367e-07, "logits/chosen": -0.2609891891479492, "logits/rejected": -0.1464134156703949, "logps/chosen": -262.7670593261719, "logps/rejected": -260.43121337890625, "loss": 0.5216, "rewards/accuracies": 0.7437499761581421, "rewards/chosen": 0.10809774696826935, "rewards/margins": 0.6094505786895752, "rewards/rejected": -0.501352846622467, "step": 520 }, { "epoch": 1.109657157812091, "grad_norm": 36.61105396566652, "learning_rate": 7.939913587198095e-07, "logits/chosen": -0.2482234686613083, "logits/rejected": -0.3337472081184387, "logps/chosen": -288.12847900390625, "logps/rejected": -249.4586181640625, "loss": 0.5439, "rewards/accuracies": 0.71875, "rewards/chosen": 0.05145542696118355, "rewards/margins": 0.7037261128425598, "rewards/rejected": -0.6522706747055054, "step": 530 }, { "epoch": 1.1305940853179797, "grad_norm": 38.97199731536176, "learning_rate": 7.840323733655778e-07, "logits/chosen": -0.19931235909461975, "logits/rejected": -0.09966816008090973, "logps/chosen": -259.0215759277344, "logps/rejected": -237.9501495361328, "loss": 0.5534, "rewards/accuracies": 0.731249988079071, "rewards/chosen": 0.12085232883691788, "rewards/margins": 0.6305907964706421, "rewards/rejected": -0.5097384452819824, "step": 540 }, { "epoch": 1.151531012823868, "grad_norm": 35.71159175636079, "learning_rate": 7.739041535009041e-07, "logits/chosen": -0.14787928760051727, "logits/rejected": -0.24329273402690887, "logps/chosen": -305.64697265625, "logps/rejected": -244.08755493164062, "loss": 0.5301, "rewards/accuracies": 0.706250011920929, "rewards/chosen": 0.08590878546237946, "rewards/margins": 0.6826232075691223, "rewards/rejected": -0.596714437007904, "step": 550 }, { "epoch": 1.1724679403297567, "grad_norm": 40.90404154922072, "learning_rate": 7.636127338052511e-07, "logits/chosen": -0.10747908055782318, "logits/rejected": -0.11999531090259552, "logps/chosen": -294.2823486328125, "logps/rejected": -265.80010986328125, "loss": 0.5442, "rewards/accuracies": 0.7562500238418579, "rewards/chosen": 0.1678900569677353, "rewards/margins": 0.6707212924957275, "rewards/rejected": -0.502831220626831, "step": 560 }, { "epoch": 1.193404867835645, "grad_norm": 36.957100723172736, "learning_rate": 7.531642461971514e-07, "logits/chosen": -0.24748548865318298, "logits/rejected": -0.13145090639591217, "logps/chosen": -270.5980529785156, "logps/rejected": -276.2918395996094, "loss": 0.5296, "rewards/accuracies": 0.71875, "rewards/chosen": 0.1355637013912201, "rewards/margins": 0.7545391917228699, "rewards/rejected": -0.6189755797386169, "step": 570 }, { "epoch": 1.2143417953415336, "grad_norm": 36.431278984426584, "learning_rate": 7.425649161806352e-07, "logits/chosen": -0.22467997670173645, "logits/rejected": -0.20354416966438293, "logps/chosen": -284.69439697265625, "logps/rejected": -250.2189483642578, "loss": 0.5209, "rewards/accuracies": 0.7562500238418579, "rewards/chosen": 0.03756130859255791, "rewards/margins": 0.7149747610092163, "rewards/rejected": -0.6774134635925293, "step": 580 }, { "epoch": 1.235278722847422, "grad_norm": 34.3971566508403, "learning_rate": 7.318210591359008e-07, "logits/chosen": -0.02497723139822483, "logits/rejected": -0.0003952041151933372, "logps/chosen": -316.3713684082031, "logps/rejected": -274.1322937011719, "loss": 0.5209, "rewards/accuracies": 0.768750011920929, "rewards/chosen": 0.07891981303691864, "rewards/margins": 0.7175663113594055, "rewards/rejected": -0.6386464834213257, "step": 590 }, { "epoch": 1.2562156503533106, "grad_norm": 37.248359587110805, "learning_rate": 7.209390765564318e-07, "logits/chosen": -0.15565916895866394, "logits/rejected": -0.10866830497980118, "logps/chosen": -306.9658203125, "logps/rejected": -306.49078369140625, "loss": 0.5099, "rewards/accuracies": 0.706250011920929, "rewards/chosen": 0.1327342391014099, "rewards/margins": 0.7248380780220032, "rewards/rejected": -0.5921037197113037, "step": 600 }, { "epoch": 1.2562156503533106, "eval_logits/chosen": -0.33804643154144287, "eval_logits/rejected": -0.3634737432003021, "eval_logps/chosen": -310.3228759765625, "eval_logps/rejected": -275.3493347167969, "eval_loss": 0.6006649136543274, "eval_rewards/accuracies": 0.6785714030265808, "eval_rewards/chosen": -0.019210144877433777, "eval_rewards/margins": 0.5136736631393433, "eval_rewards/rejected": -0.5328837633132935, "eval_runtime": 19.1325, "eval_samples_per_second": 104.534, "eval_steps_per_second": 3.293, "step": 600 }, { "epoch": 1.2771525778591992, "grad_norm": 39.48209474577774, "learning_rate": 7.099254522348064e-07, "logits/chosen": -0.09819002449512482, "logits/rejected": -0.1692955642938614, "logps/chosen": -290.13140869140625, "logps/rejected": -237.3570098876953, "loss": 0.5202, "rewards/accuracies": 0.7749999761581421, "rewards/chosen": 0.1899166852235794, "rewards/margins": 0.8487440347671509, "rewards/rejected": -0.6588274240493774, "step": 610 }, { "epoch": 1.2980895053650876, "grad_norm": 35.38064058006504, "learning_rate": 6.987867483994716e-07, "logits/chosen": 0.08088377118110657, "logits/rejected": -0.028685202822089195, "logps/chosen": -286.01324462890625, "logps/rejected": -242.1278076171875, "loss": 0.5113, "rewards/accuracies": 0.731249988079071, "rewards/chosen": 0.08664991706609726, "rewards/margins": 0.6891879439353943, "rewards/rejected": -0.6025381088256836, "step": 620 }, { "epoch": 1.3190264328709762, "grad_norm": 36.280579625575726, "learning_rate": 6.875296018047809e-07, "logits/chosen": -0.15825395286083221, "logits/rejected": -0.13115188479423523, "logps/chosen": -291.768798828125, "logps/rejected": -271.0327453613281, "loss": 0.5133, "rewards/accuracies": 0.706250011920929, "rewards/chosen": 0.25919127464294434, "rewards/margins": 0.8277707099914551, "rewards/rejected": -0.5685793161392212, "step": 630 }, { "epoch": 1.3399633603768648, "grad_norm": 32.57724385812019, "learning_rate": 6.761607197766296e-07, "logits/chosen": -0.21067364513874054, "logits/rejected": -0.15081565082073212, "logps/chosen": -272.00518798828125, "logps/rejected": -279.40478515625, "loss": 0.5105, "rewards/accuracies": 0.762499988079071, "rewards/chosen": 0.14864543080329895, "rewards/margins": 0.7687338590621948, "rewards/rejected": -0.6200884580612183, "step": 640 }, { "epoch": 1.3609002878827532, "grad_norm": 37.48616481446126, "learning_rate": 6.646868762160398e-07, "logits/chosen": -0.19943957030773163, "logits/rejected": -0.161566823720932, "logps/chosen": -268.23638916015625, "logps/rejected": -252.7967987060547, "loss": 0.5372, "rewards/accuracies": 0.699999988079071, "rewards/chosen": 0.008694097399711609, "rewards/margins": 0.623866617679596, "rewards/rejected": -0.6151725053787231, "step": 650 }, { "epoch": 1.3818372153886418, "grad_norm": 39.563737783736045, "learning_rate": 6.531149075630796e-07, "logits/chosen": -0.11065585911273956, "logits/rejected": -0.17729897797107697, "logps/chosen": -263.4093933105469, "logps/rejected": -251.0884246826172, "loss": 0.5323, "rewards/accuracies": 0.6875, "rewards/chosen": -0.026829296723008156, "rewards/margins": 0.4506412148475647, "rewards/rejected": -0.4774704873561859, "step": 660 }, { "epoch": 1.4027741428945302, "grad_norm": 33.46296192971815, "learning_rate": 6.414517087235185e-07, "logits/chosen": -0.20335140824317932, "logits/rejected": -0.2963979244232178, "logps/chosen": -293.1023864746094, "logps/rejected": -253.64291381835938, "loss": 0.5049, "rewards/accuracies": 0.71875, "rewards/chosen": 0.00017919539823196828, "rewards/margins": 0.5864929556846619, "rewards/rejected": -0.5863137245178223, "step": 670 }, { "epoch": 1.4237110704004188, "grad_norm": 40.03881951253335, "learning_rate": 6.297042289606479e-07, "logits/chosen": -0.13722732663154602, "logits/rejected": -0.1250244826078415, "logps/chosen": -295.9792785644531, "logps/rejected": -296.83038330078125, "loss": 0.5133, "rewards/accuracies": 0.6812499761581421, "rewards/chosen": -0.014182251878082752, "rewards/margins": 0.5892963409423828, "rewards/rejected": -0.6034785509109497, "step": 680 }, { "epoch": 1.4446479979063072, "grad_norm": 29.250271504061402, "learning_rate": 6.178794677547137e-07, "logits/chosen": -0.18004044890403748, "logits/rejected": -0.1459943801164627, "logps/chosen": -298.6792297363281, "logps/rejected": -257.5166931152344, "loss": 0.5157, "rewards/accuracies": 0.7124999761581421, "rewards/chosen": 0.07589882612228394, "rewards/margins": 0.7056849598884583, "rewards/rejected": -0.6297860741615295, "step": 690 }, { "epoch": 1.4655849254121958, "grad_norm": 32.49512416553128, "learning_rate": 6.059844706324286e-07, "logits/chosen": -0.07275749742984772, "logits/rejected": 0.005568481981754303, "logps/chosen": -314.0689697265625, "logps/rejected": -328.4625244140625, "loss": 0.5056, "rewards/accuracies": 0.762499988079071, "rewards/chosen": 0.13801348209381104, "rewards/margins": 0.876538872718811, "rewards/rejected": -0.738525390625, "step": 700 }, { "epoch": 1.4655849254121958, "eval_logits/chosen": -0.3406723737716675, "eval_logits/rejected": -0.36724287271499634, "eval_logps/chosen": -310.4104309082031, "eval_logps/rejected": -275.4717102050781, "eval_loss": 0.5875913500785828, "eval_rewards/accuracies": 0.6904761791229248, "eval_rewards/chosen": -0.06298798322677612, "eval_rewards/margins": 0.5310800671577454, "eval_rewards/rejected": -0.5940679311752319, "eval_runtime": 19.0211, "eval_samples_per_second": 105.146, "eval_steps_per_second": 3.312, "step": 700 }, { "epoch": 1.4865218529180844, "grad_norm": 35.75327607918745, "learning_rate": 5.940263249690477e-07, "logits/chosen": -0.24695155024528503, "logits/rejected": -0.22096967697143555, "logps/chosen": -295.2511901855469, "logps/rejected": -276.71051025390625, "loss": 0.5132, "rewards/accuracies": 0.731249988079071, "rewards/chosen": 0.058757662773132324, "rewards/margins": 0.7594215273857117, "rewards/rejected": -0.7006638646125793, "step": 710 }, { "epoch": 1.5074587804239727, "grad_norm": 41.16638143070179, "learning_rate": 5.820121557655108e-07, "logits/chosen": -0.1299329400062561, "logits/rejected": -0.10874001681804657, "logps/chosen": -303.56732177734375, "logps/rejected": -280.8491516113281, "loss": 0.5135, "rewards/accuracies": 0.7437499761581421, "rewards/chosen": 0.11438952386379242, "rewards/margins": 0.7343131899833679, "rewards/rejected": -0.6199236512184143, "step": 720 }, { "epoch": 1.5283957079298613, "grad_norm": 41.49005357475057, "learning_rate": 5.699491214031657e-07, "logits/chosen": -0.14048215746879578, "logits/rejected": -0.18900522589683533, "logps/chosen": -280.69598388671875, "logps/rejected": -255.81298828125, "loss": 0.5166, "rewards/accuracies": 0.8125, "rewards/chosen": 0.11929772049188614, "rewards/margins": 0.7799339294433594, "rewards/rejected": -0.6606361269950867, "step": 730 }, { "epoch": 1.54933263543575, "grad_norm": 34.97801212344648, "learning_rate": 5.578444093786008e-07, "logits/chosen": 0.06411169469356537, "logits/rejected": 0.15786513686180115, "logps/chosen": -315.06182861328125, "logps/rejected": -282.93115234375, "loss": 0.5128, "rewards/accuracies": 0.7437499761581421, "rewards/chosen": 0.24365051090717316, "rewards/margins": 0.8540836572647095, "rewards/rejected": -0.6104331612586975, "step": 740 }, { "epoch": 1.5702695629416383, "grad_norm": 32.53803724377542, "learning_rate": 5.457052320211339e-07, "logits/chosen": -0.22511212527751923, "logits/rejected": -0.22842809557914734, "logps/chosen": -298.0352783203125, "logps/rejected": -268.8421936035156, "loss": 0.4961, "rewards/accuracies": 0.6937500238418579, "rewards/chosen": 0.09702634066343307, "rewards/margins": 0.632623016834259, "rewards/rejected": -0.5355967283248901, "step": 750 }, { "epoch": 1.5912064904475267, "grad_norm": 36.857273577646474, "learning_rate": 5.335388221955012e-07, "logits/chosen": -0.044903479516506195, "logits/rejected": 0.0046501667238771915, "logps/chosen": -358.9960632324219, "logps/rejected": -336.44354248046875, "loss": 0.4997, "rewards/accuracies": 0.6812499761581421, "rewards/chosen": 0.28686124086380005, "rewards/margins": 0.7968252301216125, "rewards/rejected": -0.5099639296531677, "step": 760 }, { "epoch": 1.6121434179534153, "grad_norm": 31.737574949447513, "learning_rate": 5.213524289923126e-07, "logits/chosen": -0.03366886079311371, "logits/rejected": -0.18763691186904907, "logps/chosen": -327.0910339355469, "logps/rejected": -272.4969787597656, "loss": 0.5114, "rewards/accuracies": 0.7562500238418579, "rewards/chosen": 0.2613201141357422, "rewards/margins": 0.8974519968032837, "rewards/rejected": -0.6361318826675415, "step": 770 }, { "epoch": 1.633080345459304, "grad_norm": 34.36622996446216, "learning_rate": 5.091533134088387e-07, "logits/chosen": -0.12894697487354279, "logits/rejected": -0.142494797706604, "logps/chosen": -320.5164794921875, "logps/rejected": -280.9849548339844, "loss": 0.5146, "rewards/accuracies": 0.7749999761581421, "rewards/chosen": 0.27436262369155884, "rewards/margins": 0.8554395437240601, "rewards/rejected": -0.581076979637146, "step": 780 }, { "epoch": 1.6540172729651923, "grad_norm": 38.709599843434866, "learning_rate": 4.969487440227038e-07, "logits/chosen": -0.21234026551246643, "logits/rejected": -0.22163410484790802, "logps/chosen": -300.9823303222656, "logps/rejected": -276.39508056640625, "loss": 0.4852, "rewards/accuracies": 0.78125, "rewards/chosen": 0.24367956817150116, "rewards/margins": 0.9389246106147766, "rewards/rejected": -0.6952449679374695, "step": 790 }, { "epoch": 1.674954200471081, "grad_norm": 31.812270366410278, "learning_rate": 4.847459926610619e-07, "logits/chosen": -0.018023919314146042, "logits/rejected": -0.12209578603506088, "logps/chosen": -350.00439453125, "logps/rejected": -305.96954345703125, "loss": 0.4936, "rewards/accuracies": 0.768750011920929, "rewards/chosen": 0.1853758990764618, "rewards/margins": 0.8932290077209473, "rewards/rejected": -0.7078530788421631, "step": 800 }, { "epoch": 1.674954200471081, "eval_logits/chosen": -0.3383854031562805, "eval_logits/rejected": -0.36581355333328247, "eval_logps/chosen": -310.3436584472656, "eval_logps/rejected": -275.40155029296875, "eval_loss": 0.5994271636009216, "eval_rewards/accuracies": 0.6746031641960144, "eval_rewards/chosen": -0.029591551050543785, "eval_rewards/margins": 0.5294089317321777, "eval_rewards/rejected": -0.559000551700592, "eval_runtime": 19.1971, "eval_samples_per_second": 104.182, "eval_steps_per_second": 3.282, "step": 800 }, { "epoch": 1.6958911279769695, "grad_norm": 35.049859279627235, "learning_rate": 4.7255233006783624e-07, "logits/chosen": -0.18587855994701385, "logits/rejected": -0.16283151507377625, "logps/chosen": -307.56439208984375, "logps/rejected": -278.2900390625, "loss": 0.5055, "rewards/accuracies": 0.768750011920929, "rewards/chosen": 0.10620725154876709, "rewards/margins": 0.892121434211731, "rewards/rejected": -0.7859140634536743, "step": 810 }, { "epoch": 1.7168280554828579, "grad_norm": 34.134111938828184, "learning_rate": 4.6037502157160567e-07, "logits/chosen": -0.2755785584449768, "logits/rejected": -0.31054019927978516, "logps/chosen": -320.56695556640625, "logps/rejected": -273.4154968261719, "loss": 0.5048, "rewards/accuracies": 0.7437499761581421, "rewards/chosen": 0.20151178538799286, "rewards/margins": 0.9227310419082642, "rewards/rejected": -0.7212191820144653, "step": 820 }, { "epoch": 1.7377649829887463, "grad_norm": 38.68230830225304, "learning_rate": 4.482213227567161e-07, "logits/chosen": -0.2091369926929474, "logits/rejected": -0.14194951951503754, "logps/chosen": -277.35693359375, "logps/rejected": -281.7249450683594, "loss": 0.484, "rewards/accuracies": 0.7562500238418579, "rewards/chosen": 0.10125979036092758, "rewards/margins": 0.8731620907783508, "rewards/rejected": -0.7719023823738098, "step": 830 }, { "epoch": 1.7587019104946349, "grad_norm": 33.945256383172804, "learning_rate": 4.3609847514019763e-07, "logits/chosen": -0.30677181482315063, "logits/rejected": -0.1776028573513031, "logps/chosen": -261.38873291015625, "logps/rejected": -267.8268127441406, "loss": 0.5094, "rewards/accuracies": 0.7437499761581421, "rewards/chosen": 0.18778590857982635, "rewards/margins": 0.8258863687515259, "rewards/rejected": -0.6381004452705383, "step": 840 }, { "epoch": 1.7796388380005235, "grad_norm": 34.20224125304341, "learning_rate": 4.240137018570661e-07, "logits/chosen": -0.11399509757757187, "logits/rejected": -0.1185418963432312, "logps/chosen": -275.3580017089844, "logps/rejected": -282.1163024902344, "loss": 0.5074, "rewards/accuracies": 0.737500011920929, "rewards/chosen": -0.03538894280791283, "rewards/margins": 0.7777508497238159, "rewards/rejected": -0.813139796257019, "step": 850 }, { "epoch": 1.8005757655064119, "grad_norm": 31.946083788257877, "learning_rate": 4.1197420335657366e-07, "logits/chosen": -0.09024197608232498, "logits/rejected": -0.20059815049171448, "logps/chosen": -298.12762451171875, "logps/rejected": -242.2689666748047, "loss": 0.5089, "rewards/accuracies": 0.75, "rewards/chosen": 0.15691380202770233, "rewards/margins": 0.8090406656265259, "rewards/rejected": -0.6521269083023071, "step": 860 }, { "epoch": 1.8215126930123005, "grad_norm": 28.583891688236477, "learning_rate": 3.9998715311197783e-07, "logits/chosen": -0.1159423366189003, "logits/rejected": -0.16631600260734558, "logps/chosen": -337.1079406738281, "logps/rejected": -285.5828857421875, "loss": 0.4894, "rewards/accuracies": 0.7124999761581421, "rewards/chosen": 0.11767788976430893, "rewards/margins": 0.6672422289848328, "rewards/rejected": -0.5495643615722656, "step": 870 }, { "epoch": 1.842449620518189, "grad_norm": 33.76166639382152, "learning_rate": 3.880596933463843e-07, "logits/chosen": -0.07985590398311615, "logits/rejected": -0.03050703927874565, "logps/chosen": -274.9603576660156, "logps/rejected": -266.6165771484375, "loss": 0.5075, "rewards/accuracies": 0.731249988079071, "rewards/chosen": 0.09320048242807388, "rewards/margins": 0.7023938298225403, "rewards/rejected": -0.6091933250427246, "step": 880 }, { "epoch": 1.8633865480240774, "grad_norm": 40.29693979290027, "learning_rate": 3.761989307772085e-07, "logits/chosen": -0.15825888514518738, "logits/rejected": -0.1759234219789505, "logps/chosen": -306.653076171875, "logps/rejected": -279.01177978515625, "loss": 0.5055, "rewards/accuracies": 0.8187500238418579, "rewards/chosen": 0.16093602776527405, "rewards/margins": 0.937556266784668, "rewards/rejected": -0.7766203284263611, "step": 890 }, { "epoch": 1.8843234755299658, "grad_norm": 36.002728955160904, "learning_rate": 3.6441193238179146e-07, "logits/chosen": -0.05288013815879822, "logits/rejected": -0.13031360507011414, "logps/chosen": -334.34417724609375, "logps/rejected": -269.53558349609375, "loss": 0.4904, "rewards/accuracies": 0.731249988079071, "rewards/chosen": 0.14437799155712128, "rewards/margins": 0.8378474116325378, "rewards/rejected": -0.6934694051742554, "step": 900 }, { "epoch": 1.8843234755299658, "eval_logits/chosen": -0.3443281650543213, "eval_logits/rejected": -0.3704880475997925, "eval_logps/chosen": -310.4006042480469, "eval_logps/rejected": -275.5133972167969, "eval_loss": 0.5989052653312683, "eval_rewards/accuracies": 0.6944444179534912, "eval_rewards/chosen": -0.05807310715317726, "eval_rewards/margins": 0.55684494972229, "eval_rewards/rejected": -0.614918053150177, "eval_runtime": 18.9036, "eval_samples_per_second": 105.8, "eval_steps_per_second": 3.333, "step": 900 }, { "epoch": 1.9052604030358546, "grad_norm": 31.165480893885753, "learning_rate": 3.5270572118669715e-07, "logits/chosen": -0.11026148498058319, "logits/rejected": -0.16978046298027039, "logps/chosen": -278.1309509277344, "logps/rejected": -235.88150024414062, "loss": 0.5272, "rewards/accuracies": 0.762499988079071, "rewards/chosen": 0.02903774380683899, "rewards/margins": 0.8374470472335815, "rewards/rejected": -0.8084093332290649, "step": 910 }, { "epoch": 1.926197330541743, "grad_norm": 40.996379136014625, "learning_rate": 3.4108727208319314e-07, "logits/chosen": -0.17259056866168976, "logits/rejected": -0.20306821167469025, "logps/chosen": -312.1188049316406, "logps/rejected": -266.6794128417969, "loss": 0.5039, "rewards/accuracies": 0.737500011920929, "rewards/chosen": 0.16847112774848938, "rewards/margins": 0.8200035095214844, "rewards/rejected": -0.6515323519706726, "step": 920 }, { "epoch": 1.9471342580476314, "grad_norm": 31.825399091982387, "learning_rate": 3.295635076714144e-07, "logits/chosen": -0.1496247947216034, "logits/rejected": -0.17214402556419373, "logps/chosen": -301.103515625, "logps/rejected": -270.370361328125, "loss": 0.4903, "rewards/accuracies": 0.78125, "rewards/chosen": 0.16043229401111603, "rewards/margins": 0.7891928553581238, "rewards/rejected": -0.628760576248169, "step": 930 }, { "epoch": 1.96807118555352, "grad_norm": 39.834235726892466, "learning_rate": 3.181412941356816e-07, "logits/chosen": -0.13259033858776093, "logits/rejected": -0.11601094901561737, "logps/chosen": -266.5997314453125, "logps/rejected": -231.60848999023438, "loss": 0.485, "rewards/accuracies": 0.78125, "rewards/chosen": 0.19742903113365173, "rewards/margins": 0.8145695924758911, "rewards/rejected": -0.6171405911445618, "step": 940 }, { "epoch": 1.9890081130594086, "grad_norm": 35.65864774290716, "learning_rate": 3.068274371534356e-07, "logits/chosen": -0.11888673156499863, "logits/rejected": -0.2420310229063034, "logps/chosen": -301.62213134765625, "logps/rejected": -250.2771453857422, "loss": 0.4887, "rewards/accuracies": 0.768750011920929, "rewards/chosen": 0.002846676157787442, "rewards/margins": 0.7688849568367004, "rewards/rejected": -0.7660382986068726, "step": 950 }, { "epoch": 2.009945040565297, "grad_norm": 28.814451971980255, "learning_rate": 2.956286778402226e-07, "logits/chosen": -0.10088515281677246, "logits/rejected": -0.12641310691833496, "logps/chosen": -301.3664855957031, "logps/rejected": -283.16461181640625, "loss": 0.4567, "rewards/accuracies": 0.762499988079071, "rewards/chosen": 0.20988380908966064, "rewards/margins": 0.9322754740715027, "rewards/rejected": -0.7223917245864868, "step": 960 }, { "epoch": 2.0308819680711854, "grad_norm": 28.79413061525845, "learning_rate": 2.84551688733146e-07, "logits/chosen": -0.07364392280578613, "logits/rejected": -0.1452295333147049, "logps/chosen": -299.0059509277344, "logps/rejected": -238.53231811523438, "loss": 0.4557, "rewards/accuracies": 0.84375, "rewards/chosen": 0.166302889585495, "rewards/margins": 0.9308949708938599, "rewards/rejected": -0.7645919919013977, "step": 970 }, { "epoch": 2.051818895577074, "grad_norm": 31.23059423273923, "learning_rate": 2.7360306981518147e-07, "logits/chosen": -0.09392131119966507, "logits/rejected": -0.047506559640169144, "logps/chosen": -262.2680969238281, "logps/rejected": -253.03271484375, "loss": 0.4445, "rewards/accuracies": 0.8125, "rewards/chosen": 0.040274180471897125, "rewards/margins": 0.7928990125656128, "rewards/rejected": -0.7526248097419739, "step": 980 }, { "epoch": 2.0727558230829626, "grad_norm": 27.855961833782285, "learning_rate": 2.6278934458271996e-07, "logits/chosen": -0.1288485825061798, "logits/rejected": -0.1765173375606537, "logps/chosen": -314.7231750488281, "logps/rejected": -302.44964599609375, "loss": 0.4327, "rewards/accuracies": 0.800000011920929, "rewards/chosen": 0.18189235031604767, "rewards/margins": 1.0036437511444092, "rewards/rejected": -0.8217514157295227, "step": 990 }, { "epoch": 2.093692750588851, "grad_norm": 35.285113595842645, "learning_rate": 2.5211695615868456e-07, "logits/chosen": -0.1857554316520691, "logits/rejected": -0.3039974272251129, "logps/chosen": -281.1855163574219, "logps/rejected": -240.62710571289062, "loss": 0.4622, "rewards/accuracies": 0.793749988079071, "rewards/chosen": 0.15526309609413147, "rewards/margins": 0.9393559694290161, "rewards/rejected": -0.7840928435325623, "step": 1000 }, { "epoch": 2.093692750588851, "eval_logits/chosen": -0.3450426459312439, "eval_logits/rejected": -0.37242141366004944, "eval_logps/chosen": -310.4169006347656, "eval_logps/rejected": -275.49713134765625, "eval_loss": 0.59389328956604, "eval_rewards/accuracies": 0.6944444179534912, "eval_rewards/chosen": -0.06623569875955582, "eval_rewards/margins": 0.5405489802360535, "eval_rewards/rejected": -0.6067846417427063, "eval_runtime": 19.108, "eval_samples_per_second": 104.668, "eval_steps_per_second": 3.297, "step": 1000 }, { "epoch": 2.11462967809474, "grad_norm": 32.59720699053956, "learning_rate": 2.4159226345353647e-07, "logits/chosen": -0.30413442850112915, "logits/rejected": -0.24426865577697754, "logps/chosen": -270.49920654296875, "logps/rejected": -255.44723510742188, "loss": 0.4508, "rewards/accuracies": 0.7562500238418579, "rewards/chosen": 0.03533598408102989, "rewards/margins": 0.7992294430732727, "rewards/rejected": -0.7638934254646301, "step": 1010 }, { "epoch": 2.135566605600628, "grad_norm": 30.8340208692361, "learning_rate": 2.312215373764551e-07, "logits/chosen": -0.07855603843927383, "logits/rejected": -0.094606414437294, "logps/chosen": -289.9374084472656, "logps/rejected": -277.69586181640625, "loss": 0.4353, "rewards/accuracies": 0.8125, "rewards/chosen": 0.19073505699634552, "rewards/margins": 0.8868581652641296, "rewards/rejected": -0.6961231231689453, "step": 1020 }, { "epoch": 2.1565035331065165, "grad_norm": 29.34387598294554, "learning_rate": 2.2101095709895512e-07, "logits/chosen": 0.009572875685989857, "logits/rejected": -0.09117701649665833, "logps/chosen": -282.7410583496094, "logps/rejected": -239.8011932373047, "loss": 0.438, "rewards/accuracies": 0.793749988079071, "rewards/chosen": 0.12627363204956055, "rewards/margins": 0.8894168138504028, "rewards/rejected": -0.7631431221961975, "step": 1030 }, { "epoch": 2.177440460612405, "grad_norm": 29.466746389871066, "learning_rate": 2.1096660637315932e-07, "logits/chosen": -0.0853545218706131, "logits/rejected": -0.1613493412733078, "logps/chosen": -309.2115783691406, "logps/rejected": -279.7373352050781, "loss": 0.4374, "rewards/accuracies": 0.856249988079071, "rewards/chosen": 0.2535983920097351, "rewards/margins": 1.087397575378418, "rewards/rejected": -0.8337991833686829, "step": 1040 }, { "epoch": 2.1983773881182938, "grad_norm": 31.3324256474218, "learning_rate": 2.0109446990692963e-07, "logits/chosen": -0.17987683415412903, "logits/rejected": -0.24151673913002014, "logps/chosen": -323.58477783203125, "logps/rejected": -268.08111572265625, "loss": 0.4365, "rewards/accuracies": 0.75, "rewards/chosen": 0.09657944738864899, "rewards/margins": 0.8588522672653198, "rewards/rejected": -0.7622728943824768, "step": 1050 }, { "epoch": 2.219314315624182, "grad_norm": 33.25666630785023, "learning_rate": 1.9140042979800737e-07, "logits/chosen": -0.13123273849487305, "logits/rejected": -0.12296972423791885, "logps/chosen": -260.5819396972656, "logps/rejected": -232.4111328125, "loss": 0.4355, "rewards/accuracies": 0.7437499761581421, "rewards/chosen": 0.05866159126162529, "rewards/margins": 0.7927514314651489, "rewards/rejected": -0.7340899109840393, "step": 1060 }, { "epoch": 2.2402512431300705, "grad_norm": 27.925843344985296, "learning_rate": 1.8189026202929391e-07, "logits/chosen": -0.1511206328868866, "logits/rejected": -0.17038318514823914, "logps/chosen": -290.31951904296875, "logps/rejected": -260.115966796875, "loss": 0.4534, "rewards/accuracies": 0.793749988079071, "rewards/chosen": 0.11966502666473389, "rewards/margins": 0.9545691609382629, "rewards/rejected": -0.8349041938781738, "step": 1070 }, { "epoch": 2.2611881706359593, "grad_norm": 26.475722050618995, "learning_rate": 1.725696330273575e-07, "logits/chosen": -0.08606094121932983, "logits/rejected": -0.1871510148048401, "logps/chosen": -288.9709777832031, "logps/rejected": -249.9591064453125, "loss": 0.4441, "rewards/accuracies": 0.793749988079071, "rewards/chosen": 0.19028839468955994, "rewards/margins": 1.0648086071014404, "rewards/rejected": -0.8745201826095581, "step": 1080 }, { "epoch": 2.2821250981418477, "grad_norm": 28.63389247775027, "learning_rate": 1.634440962862148e-07, "logits/chosen": -0.05144480615854263, "logits/rejected": -0.04060221463441849, "logps/chosen": -295.44122314453125, "logps/rejected": -262.346435546875, "loss": 0.4318, "rewards/accuracies": 0.8062499761581421, "rewards/chosen": 0.20048430562019348, "rewards/margins": 0.9130541086196899, "rewards/rejected": -0.7125697135925293, "step": 1090 }, { "epoch": 2.303062025647736, "grad_norm": 28.577071054830697, "learning_rate": 1.545190890584042e-07, "logits/chosen": -0.23821565508842468, "logits/rejected": -0.23792441189289093, "logps/chosen": -287.6651306152344, "logps/rejected": -261.96875, "loss": 0.4458, "rewards/accuracies": 0.8125, "rewards/chosen": 0.24947874248027802, "rewards/margins": 0.945774257183075, "rewards/rejected": -0.696295440196991, "step": 1100 }, { "epoch": 2.303062025647736, "eval_logits/chosen": -0.3449550271034241, "eval_logits/rejected": -0.3728056252002716, "eval_logps/chosen": -310.3917541503906, "eval_logps/rejected": -275.5622253417969, "eval_loss": 0.5923458933830261, "eval_rewards/accuracies": 0.6944444179534912, "eval_rewards/chosen": -0.05364745110273361, "eval_rewards/margins": 0.5857000946998596, "eval_rewards/rejected": -0.639347493648529, "eval_runtime": 19.0051, "eval_samples_per_second": 105.235, "eval_steps_per_second": 3.315, "step": 1100 }, { "epoch": 2.323998953153625, "grad_norm": 30.512738174296523, "learning_rate": 1.4579992911531496e-07, "logits/chosen": -0.2525126338005066, "logits/rejected": -0.3065794110298157, "logps/chosen": -325.3319091796875, "logps/rejected": -288.85089111328125, "loss": 0.4406, "rewards/accuracies": 0.8187500238418579, "rewards/chosen": 0.28674450516700745, "rewards/margins": 1.1190677881240845, "rewards/rejected": -0.8323231935501099, "step": 1110 }, { "epoch": 2.3449358806595133, "grad_norm": 28.019655950524385, "learning_rate": 1.372918115787112e-07, "logits/chosen": -0.19494856894016266, "logits/rejected": -0.16709737479686737, "logps/chosen": -269.15802001953125, "logps/rejected": -281.6461486816406, "loss": 0.4203, "rewards/accuracies": 0.862500011920929, "rewards/chosen": 0.2475571632385254, "rewards/margins": 1.078798770904541, "rewards/rejected": -0.8312416076660156, "step": 1120 }, { "epoch": 2.3658728081654017, "grad_norm": 30.412163422048742, "learning_rate": 1.289998058253297e-07, "logits/chosen": -0.30280619859695435, "logits/rejected": -0.23964910209178925, "logps/chosen": -300.67291259765625, "logps/rejected": -286.5229187011719, "loss": 0.4429, "rewards/accuracies": 0.8374999761581421, "rewards/chosen": 0.10387909412384033, "rewards/margins": 0.9766238331794739, "rewards/rejected": -0.8727447390556335, "step": 1130 }, { "epoch": 2.38680973567129, "grad_norm": 26.079069616215104, "learning_rate": 1.209288524664029e-07, "logits/chosen": -0.09895231574773788, "logits/rejected": -0.04007222130894661, "logps/chosen": -295.33795166015625, "logps/rejected": -295.7159118652344, "loss": 0.4524, "rewards/accuracies": 0.8125, "rewards/chosen": 0.3174125850200653, "rewards/margins": 1.068551778793335, "rewards/rejected": -0.7511391639709473, "step": 1140 }, { "epoch": 2.407746663177179, "grad_norm": 35.04317303338736, "learning_rate": 1.1308376040390344e-07, "logits/chosen": -0.2176963984966278, "logits/rejected": -0.2429191619157791, "logps/chosen": -268.51568603515625, "logps/rejected": -243.83602905273438, "loss": 0.4648, "rewards/accuracies": 0.768750011920929, "rewards/chosen": 0.1225685253739357, "rewards/margins": 0.8287593722343445, "rewards/rejected": -0.7061909437179565, "step": 1150 }, { "epoch": 2.4286835906830673, "grad_norm": 27.071258876733747, "learning_rate": 1.0546920396526382e-07, "logits/chosen": -0.05287874490022659, "logits/rejected": -0.08571253716945648, "logps/chosen": -345.3739013671875, "logps/rejected": -296.2100524902344, "loss": 0.4248, "rewards/accuracies": 0.824999988079071, "rewards/chosen": 0.31707775592803955, "rewards/margins": 1.1236298084259033, "rewards/rejected": -0.8065520524978638, "step": 1160 }, { "epoch": 2.4496205181889557, "grad_norm": 30.813022693471254, "learning_rate": 9.808972011828054e-08, "logits/chosen": -0.07085756957530975, "logits/rejected": -0.1990344077348709, "logps/chosen": -342.7474060058594, "logps/rejected": -266.599609375, "loss": 0.4366, "rewards/accuracies": 0.831250011920929, "rewards/chosen": 0.2785649299621582, "rewards/margins": 1.1454359292984009, "rewards/rejected": -0.8668708801269531, "step": 1170 }, { "epoch": 2.470557445694844, "grad_norm": 28.23769321193845, "learning_rate": 9.094970576786032e-08, "logits/chosen": 0.02408856526017189, "logits/rejected": -0.0395381897687912, "logps/chosen": -267.3003234863281, "logps/rejected": -249.65158081054688, "loss": 0.4323, "rewards/accuracies": 0.824999988079071, "rewards/chosen": 0.17695440351963043, "rewards/margins": 1.0320888757705688, "rewards/rejected": -0.8551343679428101, "step": 1180 }, { "epoch": 2.491494373200733, "grad_norm": 30.361270294186127, "learning_rate": 8.405341513622055e-08, "logits/chosen": -0.16236011683940887, "logits/rejected": -0.20971974730491638, "logps/chosen": -324.1960754394531, "logps/rejected": -260.82647705078125, "loss": 0.4368, "rewards/accuracies": 0.831250011920929, "rewards/chosen": 0.3019522428512573, "rewards/margins": 0.9704391360282898, "rewards/rejected": -0.6684868931770325, "step": 1190 }, { "epoch": 2.5124313007066212, "grad_norm": 29.87892753836197, "learning_rate": 7.740495722810269e-08, "logits/chosen": -0.1393619179725647, "logits/rejected": -0.17410680651664734, "logps/chosen": -275.013427734375, "logps/rejected": -218.1080322265625, "loss": 0.4462, "rewards/accuracies": 0.768750011920929, "rewards/chosen": 0.1310921609401703, "rewards/margins": 0.8609299659729004, "rewards/rejected": -0.7298377156257629, "step": 1200 }, { "epoch": 2.5124313007066212, "eval_logits/chosen": -0.34315019845962524, "eval_logits/rejected": -0.37096092104911804, "eval_logps/chosen": -310.3815612792969, "eval_logps/rejected": -275.54351806640625, "eval_loss": 0.589375913143158, "eval_rewards/accuracies": 0.7023809552192688, "eval_rewards/chosen": -0.04855651780962944, "eval_rewards/margins": 0.5814378261566162, "eval_rewards/rejected": -0.6299943923950195, "eval_runtime": 19.1944, "eval_samples_per_second": 104.197, "eval_steps_per_second": 3.282, "step": 1200 }, { "epoch": 2.5333682282125096, "grad_norm": 30.713812818544117, "learning_rate": 7.100829338251146e-08, "logits/chosen": -0.10057993978261948, "logits/rejected": -0.16287049651145935, "logps/chosen": -328.2908935546875, "logps/rejected": -289.701904296875, "loss": 0.4416, "rewards/accuracies": 0.8187500238418579, "rewards/chosen": 0.3149394094944, "rewards/margins": 1.1269749402999878, "rewards/rejected": -0.8120356798171997, "step": 1210 }, { "epoch": 2.5543051557183984, "grad_norm": 32.721460368023834, "learning_rate": 6.486723491243778e-08, "logits/chosen": -0.14739738404750824, "logits/rejected": -0.1756991297006607, "logps/chosen": -287.8624572753906, "logps/rejected": -264.6856994628906, "loss": 0.4523, "rewards/accuracies": 0.862500011920929, "rewards/chosen": 0.20502778887748718, "rewards/margins": 0.9769600033760071, "rewards/rejected": -0.7719322443008423, "step": 1220 }, { "epoch": 2.575242083224287, "grad_norm": 32.50553549993069, "learning_rate": 5.898544083397e-08, "logits/chosen": -0.12704332172870636, "logits/rejected": -0.1398163139820099, "logps/chosen": -319.8119201660156, "logps/rejected": -287.4822082519531, "loss": 0.4467, "rewards/accuracies": 0.8374999761581421, "rewards/chosen": 0.2838557958602905, "rewards/margins": 1.0057270526885986, "rewards/rejected": -0.7218713164329529, "step": 1230 }, { "epoch": 2.596179010730175, "grad_norm": 30.599102169827287, "learning_rate": 5.3366415686149137e-08, "logits/chosen": -0.1681247055530548, "logits/rejected": -0.15492555499076843, "logps/chosen": -248.78054809570312, "logps/rejected": -238.68106079101562, "loss": 0.4368, "rewards/accuracies": 0.7875000238418579, "rewards/chosen": 0.10712571442127228, "rewards/margins": 0.8596469759941101, "rewards/rejected": -0.7525211572647095, "step": 1240 }, { "epoch": 2.617115938236064, "grad_norm": 31.156979603329955, "learning_rate": 4.8013507442865585e-08, "logits/chosen": -0.19022394716739655, "logits/rejected": -0.10595899820327759, "logps/chosen": -271.9454345703125, "logps/rejected": -274.1131286621094, "loss": 0.4319, "rewards/accuracies": 0.7875000238418579, "rewards/chosen": 0.17164357006549835, "rewards/margins": 0.7940610647201538, "rewards/rejected": -0.6224175095558167, "step": 1250 }, { "epoch": 2.6380528657419524, "grad_norm": 28.881054799580607, "learning_rate": 4.292990551804171e-08, "logits/chosen": -0.08757440745830536, "logits/rejected": -0.08349265158176422, "logps/chosen": -287.8446350097656, "logps/rejected": -251.55636596679688, "loss": 0.4229, "rewards/accuracies": 0.793749988079071, "rewards/chosen": 0.27148956060409546, "rewards/margins": 1.0949037075042725, "rewards/rejected": -0.8234142065048218, "step": 1260 }, { "epoch": 2.658989793247841, "grad_norm": 27.816379754479705, "learning_rate": 3.811863886528882e-08, "logits/chosen": -0.05129946395754814, "logits/rejected": -0.07520854473114014, "logps/chosen": -320.88092041015625, "logps/rejected": -259.69488525390625, "loss": 0.4403, "rewards/accuracies": 0.824999988079071, "rewards/chosen": 0.1268620789051056, "rewards/margins": 0.9729422330856323, "rewards/rejected": -0.8460801839828491, "step": 1270 }, { "epoch": 2.6799267207537296, "grad_norm": 31.45496593116063, "learning_rate": 3.358257417317095e-08, "logits/chosen": -0.08449853211641312, "logits/rejected": -0.1029936671257019, "logps/chosen": -288.6929016113281, "logps/rejected": -251.7803192138672, "loss": 0.4427, "rewards/accuracies": 0.737500011920929, "rewards/chosen": 0.18886741995811462, "rewards/margins": 0.9686278104782104, "rewards/rejected": -0.779760479927063, "step": 1280 }, { "epoch": 2.700863648259618, "grad_norm": 29.618711306226224, "learning_rate": 2.9324414157151367e-08, "logits/chosen": -0.1431390345096588, "logits/rejected": -0.10319207608699799, "logps/chosen": -265.52508544921875, "logps/rejected": -260.0169677734375, "loss": 0.4661, "rewards/accuracies": 0.7875000238418579, "rewards/chosen": 0.10996869951486588, "rewards/margins": 0.7998045682907104, "rewards/rejected": -0.6898358464241028, "step": 1290 }, { "epoch": 2.7218005757655064, "grad_norm": 30.57983222127276, "learning_rate": 2.5346695949237717e-08, "logits/chosen": -0.1215812936425209, "logits/rejected": -0.1575727015733719, "logps/chosen": -285.28839111328125, "logps/rejected": -258.9991455078125, "loss": 0.4312, "rewards/accuracies": 0.8062499761581421, "rewards/chosen": 0.16850288212299347, "rewards/margins": 0.923494815826416, "rewards/rejected": -0.7549919486045837, "step": 1300 }, { "epoch": 2.7218005757655064, "eval_logits/chosen": -0.3442156910896301, "eval_logits/rejected": -0.37236616015434265, "eval_logps/chosen": -310.4347229003906, "eval_logps/rejected": -275.5621337890625, "eval_loss": 0.5860841870307922, "eval_rewards/accuracies": 0.6666666865348816, "eval_rewards/chosen": -0.07512283325195312, "eval_rewards/margins": 0.5641648769378662, "eval_rewards/rejected": -0.6392877101898193, "eval_runtime": 18.9961, "eval_samples_per_second": 105.285, "eval_steps_per_second": 3.316, "step": 1300 }, { "epoch": 2.7427375032713948, "grad_norm": 33.466317771235126, "learning_rate": 2.165178958628744e-08, "logits/chosen": -0.2976987659931183, "logits/rejected": -0.2995850145816803, "logps/chosen": -273.274658203125, "logps/rejected": -265.376953125, "loss": 0.4557, "rewards/accuracies": 0.8187500238418579, "rewards/chosen": 0.248153418302536, "rewards/margins": 0.9688236117362976, "rewards/rejected": -0.720670223236084, "step": 1310 }, { "epoch": 2.7636744307772836, "grad_norm": 34.66631251738303, "learning_rate": 1.824189659787284e-08, "logits/chosen": -0.10840437561273575, "logits/rejected": -0.2128714621067047, "logps/chosen": -305.4066162109375, "logps/rejected": -265.4433288574219, "loss": 0.4569, "rewards/accuracies": 0.7875000238418579, "rewards/chosen": 0.2427886724472046, "rewards/margins": 0.9924157857894897, "rewards/rejected": -0.7496271133422852, "step": 1320 }, { "epoch": 2.784611358283172, "grad_norm": 32.12579125137935, "learning_rate": 1.511904869454772e-08, "logits/chosen": -0.2719363570213318, "logits/rejected": -0.282664954662323, "logps/chosen": -258.68927001953125, "logps/rejected": -247.0824737548828, "loss": 0.4442, "rewards/accuracies": 0.800000011920929, "rewards/chosen": 0.14507904648780823, "rewards/margins": 0.9792217016220093, "rewards/rejected": -0.8341425657272339, "step": 1330 }, { "epoch": 2.8055482857890603, "grad_norm": 30.777443115008786, "learning_rate": 1.2285106557296476e-08, "logits/chosen": -0.005404007621109486, "logits/rejected": -0.11788828670978546, "logps/chosen": -291.2290954589844, "logps/rejected": -259.48468017578125, "loss": 0.4343, "rewards/accuracies": 0.856249988079071, "rewards/chosen": 0.14346763491630554, "rewards/margins": 0.9186245203018188, "rewards/rejected": -0.7751568555831909, "step": 1340 }, { "epoch": 2.8264852132949487, "grad_norm": 30.795896785948266, "learning_rate": 9.741758728888217e-09, "logits/chosen": -0.21444204449653625, "logits/rejected": -0.22242781519889832, "logps/chosen": -273.7785949707031, "logps/rejected": -255.1972198486328, "loss": 0.4474, "rewards/accuracies": 0.800000011920929, "rewards/chosen": 0.1873357743024826, "rewards/margins": 0.925756573677063, "rewards/rejected": -0.7384207844734192, "step": 1350 }, { "epoch": 2.8474221408008376, "grad_norm": 32.2751606467674, "learning_rate": 7.490520607794981e-09, "logits/chosen": -0.23268666863441467, "logits/rejected": -0.24138864874839783, "logps/chosen": -321.114990234375, "logps/rejected": -286.67596435546875, "loss": 0.4185, "rewards/accuracies": 0.824999988079071, "rewards/chosen": 0.2826289236545563, "rewards/margins": 1.1657564640045166, "rewards/rejected": -0.8831275701522827, "step": 1360 }, { "epoch": 2.868359068306726, "grad_norm": 35.16124310393445, "learning_rate": 5.532733545274781e-09, "logits/chosen": -0.15783634781837463, "logits/rejected": -0.04948469251394272, "logps/chosen": -257.70880126953125, "logps/rejected": -257.0361633300781, "loss": 0.4388, "rewards/accuracies": 0.78125, "rewards/chosen": 0.09304230660200119, "rewards/margins": 0.8344671130180359, "rewards/rejected": -0.7414248585700989, "step": 1370 }, { "epoch": 2.8892959958126143, "grad_norm": 28.606615842220055, "learning_rate": 3.869564046156459e-09, "logits/chosen": -0.187531977891922, "logits/rejected": -0.3003791868686676, "logps/chosen": -326.945068359375, "logps/rejected": -275.7688903808594, "loss": 0.4474, "rewards/accuracies": 0.7875000238418579, "rewards/chosen": 0.3150181770324707, "rewards/margins": 0.9270998239517212, "rewards/rejected": -0.6120817065238953, "step": 1380 }, { "epoch": 2.910232923318503, "grad_norm": 29.689707753715854, "learning_rate": 2.5020030738031052e-09, "logits/chosen": -0.06661088764667511, "logits/rejected": -0.03964465484023094, "logps/chosen": -326.2409973144531, "logps/rejected": -333.43048095703125, "loss": 0.4429, "rewards/accuracies": 0.8374999761581421, "rewards/chosen": 0.26736724376678467, "rewards/margins": 1.0932358503341675, "rewards/rejected": -0.8258686065673828, "step": 1390 }, { "epoch": 2.9311698508243915, "grad_norm": 28.977571013449776, "learning_rate": 1.4308654596684177e-09, "logits/chosen": -0.11069446802139282, "logits/rejected": -0.20247487723827362, "logps/chosen": -306.44610595703125, "logps/rejected": -266.9939270019531, "loss": 0.4454, "rewards/accuracies": 0.8187500238418579, "rewards/chosen": 0.33073872327804565, "rewards/margins": 1.0625050067901611, "rewards/rejected": -0.7317661046981812, "step": 1400 }, { "epoch": 2.9311698508243915, "eval_logits/chosen": -0.34011754393577576, "eval_logits/rejected": -0.36805158853530884, "eval_logps/chosen": -310.2955627441406, "eval_logps/rejected": -275.4775085449219, "eval_loss": 0.5941523313522339, "eval_rewards/accuracies": 0.6944444179534912, "eval_rewards/chosen": -0.005565390922129154, "eval_rewards/margins": 0.591437041759491, "eval_rewards/rejected": -0.5970024466514587, "eval_runtime": 19.2489, "eval_samples_per_second": 103.902, "eval_steps_per_second": 3.273, "step": 1400 }, { "epoch": 2.95210677833028, "grad_norm": 29.74874723420356, "learning_rate": 6.567894177967325e-10, "logits/chosen": -0.046352408826351166, "logits/rejected": -0.054122112691402435, "logps/chosen": -287.88287353515625, "logps/rejected": -262.4837646484375, "loss": 0.4161, "rewards/accuracies": 0.7875000238418579, "rewards/chosen": 0.250956654548645, "rewards/margins": 1.026626706123352, "rewards/rejected": -0.775670051574707, "step": 1410 }, { "epoch": 2.9730437058361687, "grad_norm": 29.04099364011046, "learning_rate": 1.802361645573125e-10, "logits/chosen": -0.15342023968696594, "logits/rejected": -0.1559501588344574, "logps/chosen": -272.7152404785156, "logps/rejected": -269.2229919433594, "loss": 0.4192, "rewards/accuracies": 0.824999988079071, "rewards/chosen": 0.05591464787721634, "rewards/margins": 1.0562889575958252, "rewards/rejected": -1.000374436378479, "step": 1420 }, { "epoch": 2.993980633342057, "grad_norm": 30.18988447303673, "learning_rate": 1.4896438384481846e-12, "logits/chosen": -0.20836491882801056, "logits/rejected": -0.19784407317638397, "logps/chosen": -317.96209716796875, "logps/rejected": -302.5794982910156, "loss": 0.4315, "rewards/accuracies": 0.78125, "rewards/chosen": 0.22425825893878937, "rewards/margins": 0.8794215321540833, "rewards/rejected": -0.6551632285118103, "step": 1430 }, { "epoch": 2.996074326092646, "step": 1431, "total_flos": 0.0, "train_loss": 0.5334697115221363, "train_runtime": 7355.3343, "train_samples_per_second": 24.935, "train_steps_per_second": 0.195 } ], "logging_steps": 10, "max_steps": 1431, "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": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }