| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7990867579908676, | |
| "eval_steps": 50, | |
| "global_step": 1050, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0076103500761035, | |
| "grad_norm": 0.058339186012744904, | |
| "learning_rate": 4.999451708687114e-06, | |
| "logits/chosen": 14.268467903137207, | |
| "logits/rejected": 14.600369453430176, | |
| "logps/chosen": -0.2669850289821625, | |
| "logps/rejected": -0.3412467837333679, | |
| "loss": 0.9049, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.4004775583744049, | |
| "rewards/margins": 0.11139259487390518, | |
| "rewards/rejected": -0.5118702054023743, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015220700152207, | |
| "grad_norm": 0.049545690417289734, | |
| "learning_rate": 4.997807075247147e-06, | |
| "logits/chosen": 14.14539623260498, | |
| "logits/rejected": 15.191584587097168, | |
| "logps/chosen": -0.25579872727394104, | |
| "logps/rejected": -0.3931494653224945, | |
| "loss": 0.8989, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.38369807600975037, | |
| "rewards/margins": 0.2060261219739914, | |
| "rewards/rejected": -0.5897241830825806, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0228310502283105, | |
| "grad_norm": 0.061699289828538895, | |
| "learning_rate": 4.9950668210706795e-06, | |
| "logits/chosen": 14.284139633178711, | |
| "logits/rejected": 15.006326675415039, | |
| "logps/chosen": -0.275672048330307, | |
| "logps/rejected": -0.3603581488132477, | |
| "loss": 0.9004, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.4135080873966217, | |
| "rewards/margins": 0.12702910602092743, | |
| "rewards/rejected": -0.5405372381210327, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030441400304414, | |
| "grad_norm": 0.05706426501274109, | |
| "learning_rate": 4.9912321481237616e-06, | |
| "logits/chosen": 14.275796890258789, | |
| "logits/rejected": 14.935521125793457, | |
| "logps/chosen": -0.2802076041698456, | |
| "logps/rejected": -0.38278770446777344, | |
| "loss": 0.9138, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -0.42031145095825195, | |
| "rewards/margins": 0.15387018024921417, | |
| "rewards/rejected": -0.5741815567016602, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0380517503805175, | |
| "grad_norm": 0.05318514257669449, | |
| "learning_rate": 4.986304738420684e-06, | |
| "logits/chosen": 14.433627128601074, | |
| "logits/rejected": 15.458297729492188, | |
| "logps/chosen": -0.2581387162208557, | |
| "logps/rejected": -0.38208404183387756, | |
| "loss": 0.914, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -0.38720807433128357, | |
| "rewards/margins": 0.18591801822185516, | |
| "rewards/rejected": -0.5731261372566223, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0380517503805175, | |
| "eval_logits/chosen": 14.396967887878418, | |
| "eval_logits/rejected": 15.221076965332031, | |
| "eval_logps/chosen": -0.27519574761390686, | |
| "eval_logps/rejected": -0.3709692656993866, | |
| "eval_loss": 0.9084128141403198, | |
| "eval_rewards/accuracies": 0.5981308221817017, | |
| "eval_rewards/chosen": -0.4127936065196991, | |
| "eval_rewards/margins": 0.14366032183170319, | |
| "eval_rewards/rejected": -0.5564539432525635, | |
| "eval_runtime": 30.773, | |
| "eval_samples_per_second": 27.622, | |
| "eval_steps_per_second": 3.477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045662100456621, | |
| "grad_norm": 0.06310460716485977, | |
| "learning_rate": 4.980286753286196e-06, | |
| "logits/chosen": 14.548416137695312, | |
| "logits/rejected": 15.526041030883789, | |
| "logps/chosen": -0.29403647780418396, | |
| "logps/rejected": -0.40682005882263184, | |
| "loss": 0.9082, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.44105473160743713, | |
| "rewards/margins": 0.1691754311323166, | |
| "rewards/rejected": -0.6102300882339478, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0532724505327245, | |
| "grad_norm": 0.1258806735277176, | |
| "learning_rate": 4.973180832407471e-06, | |
| "logits/chosen": 14.390210151672363, | |
| "logits/rejected": 14.817584037780762, | |
| "logps/chosen": -0.25258123874664307, | |
| "logps/rejected": -0.36392712593078613, | |
| "loss": 0.896, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.3788718581199646, | |
| "rewards/margins": 0.1670188158750534, | |
| "rewards/rejected": -0.5458906888961792, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.060882800608828, | |
| "grad_norm": 0.09006265550851822, | |
| "learning_rate": 4.964990092676263e-06, | |
| "logits/chosen": 13.844560623168945, | |
| "logits/rejected": 14.811120986938477, | |
| "logps/chosen": -0.2630843222141266, | |
| "logps/rejected": -0.3794577717781067, | |
| "loss": 0.8977, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.3946264684200287, | |
| "rewards/margins": 0.17456015944480896, | |
| "rewards/rejected": -0.5691865682601929, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 0.07123688608407974, | |
| "learning_rate": 4.9557181268217225e-06, | |
| "logits/chosen": 13.927327156066895, | |
| "logits/rejected": 14.746416091918945, | |
| "logps/chosen": -0.25282323360443115, | |
| "logps/rejected": -0.3279832601547241, | |
| "loss": 0.9092, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -0.37923485040664673, | |
| "rewards/margins": 0.11274002492427826, | |
| "rewards/rejected": -0.4919748902320862, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.076103500761035, | |
| "grad_norm": 0.08333446085453033, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "logits/chosen": 14.406118392944336, | |
| "logits/rejected": 14.770090103149414, | |
| "logps/chosen": -0.28569403290748596, | |
| "logps/rejected": -0.3596845269203186, | |
| "loss": 0.8932, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -0.42854103446006775, | |
| "rewards/margins": 0.11098580062389374, | |
| "rewards/rejected": -0.5395268201828003, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.076103500761035, | |
| "eval_logits/chosen": 13.925265312194824, | |
| "eval_logits/rejected": 14.808513641357422, | |
| "eval_logps/chosen": -0.2667020559310913, | |
| "eval_logps/rejected": -0.3739235997200012, | |
| "eval_loss": 0.8984279036521912, | |
| "eval_rewards/accuracies": 0.5981308221817017, | |
| "eval_rewards/chosen": -0.40005311369895935, | |
| "eval_rewards/margins": 0.16083234548568726, | |
| "eval_rewards/rejected": -0.5608854293823242, | |
| "eval_runtime": 30.7791, | |
| "eval_samples_per_second": 27.616, | |
| "eval_steps_per_second": 3.476, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0837138508371385, | |
| "grad_norm": 0.08474570512771606, | |
| "learning_rate": 4.933947257182901e-06, | |
| "logits/chosen": 13.641456604003906, | |
| "logits/rejected": 14.799921035766602, | |
| "logps/chosen": -0.2721528708934784, | |
| "logps/rejected": -0.38378894329071045, | |
| "loss": 0.8995, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/chosen": -0.40822935104370117, | |
| "rewards/margins": 0.1674540936946869, | |
| "rewards/rejected": -0.5756834149360657, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.091324200913242, | |
| "grad_norm": 0.1004580408334732, | |
| "learning_rate": 4.921457902821578e-06, | |
| "logits/chosen": 13.835454940795898, | |
| "logits/rejected": 14.882522583007812, | |
| "logps/chosen": -0.28507837653160095, | |
| "logps/rejected": -0.39737468957901, | |
| "loss": 0.8795, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -0.42761754989624023, | |
| "rewards/margins": 0.16844449937343597, | |
| "rewards/rejected": -0.5960620641708374, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.0989345509893455, | |
| "grad_norm": 0.09537151455879211, | |
| "learning_rate": 4.907906416994146e-06, | |
| "logits/chosen": 13.607874870300293, | |
| "logits/rejected": 14.091131210327148, | |
| "logps/chosen": -0.2739318013191223, | |
| "logps/rejected": -0.36800479888916016, | |
| "loss": 0.8912, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/chosen": -0.4108976721763611, | |
| "rewards/margins": 0.14110951125621796, | |
| "rewards/rejected": -0.5520071983337402, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.106544901065449, | |
| "grad_norm": 0.10281535238027573, | |
| "learning_rate": 4.893298743830168e-06, | |
| "logits/chosen": 12.017224311828613, | |
| "logits/rejected": 13.04835319519043, | |
| "logps/chosen": -0.24072685837745667, | |
| "logps/rejected": -0.36906492710113525, | |
| "loss": 0.8908, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.3610902428627014, | |
| "rewards/margins": 0.19250717759132385, | |
| "rewards/rejected": -0.5535974502563477, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1141552511415525, | |
| "grad_norm": 0.707987368106842, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "logits/chosen": 12.522550582885742, | |
| "logits/rejected": 13.272679328918457, | |
| "logps/chosen": -0.2583540081977844, | |
| "logps/rejected": -0.3796755075454712, | |
| "loss": 0.8867, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -0.38753098249435425, | |
| "rewards/margins": 0.18198221921920776, | |
| "rewards/rejected": -0.569513201713562, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1141552511415525, | |
| "eval_logits/chosen": 11.989100456237793, | |
| "eval_logits/rejected": 12.92872142791748, | |
| "eval_logps/chosen": -0.27158522605895996, | |
| "eval_logps/rejected": -0.40521273016929626, | |
| "eval_loss": 0.8765817284584045, | |
| "eval_rewards/accuracies": 0.5981308221817017, | |
| "eval_rewards/chosen": -0.40737783908843994, | |
| "eval_rewards/margins": 0.20044119656085968, | |
| "eval_rewards/rejected": -0.6078190803527832, | |
| "eval_runtime": 30.7739, | |
| "eval_samples_per_second": 27.621, | |
| "eval_steps_per_second": 3.477, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.121765601217656, | |
| "grad_norm": 0.19342070817947388, | |
| "learning_rate": 4.860940925593703e-06, | |
| "logits/chosen": 11.095940589904785, | |
| "logits/rejected": 12.351040840148926, | |
| "logps/chosen": -0.24749942123889923, | |
| "logps/rejected": -0.43422192335128784, | |
| "loss": 0.8762, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.37124913930892944, | |
| "rewards/margins": 0.2800838053226471, | |
| "rewards/rejected": -0.6513329744338989, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1293759512937595, | |
| "grad_norm": 0.19374576210975647, | |
| "learning_rate": 4.84320497372973e-06, | |
| "logits/chosen": 10.510068893432617, | |
| "logits/rejected": 11.507593154907227, | |
| "logps/chosen": -0.26223134994506836, | |
| "logps/rejected": -0.43635931611061096, | |
| "loss": 0.8581, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.39334696531295776, | |
| "rewards/margins": 0.2611919641494751, | |
| "rewards/rejected": -0.6545389294624329, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 0.20330430567264557, | |
| "learning_rate": 4.824441214720629e-06, | |
| "logits/chosen": 9.89570140838623, | |
| "logits/rejected": 10.669364929199219, | |
| "logps/chosen": -0.3143860101699829, | |
| "logps/rejected": -0.46989941596984863, | |
| "loss": 0.8558, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/chosen": -0.47157901525497437, | |
| "rewards/margins": 0.23327013850212097, | |
| "rewards/rejected": -0.704849123954773, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1445966514459665, | |
| "grad_norm": 0.22942212224006653, | |
| "learning_rate": 4.804657878971252e-06, | |
| "logits/chosen": 8.887057304382324, | |
| "logits/rejected": 9.542157173156738, | |
| "logps/chosen": -0.2906036972999573, | |
| "logps/rejected": -0.4810206890106201, | |
| "loss": 0.8554, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -0.4359055459499359, | |
| "rewards/margins": 0.28562551736831665, | |
| "rewards/rejected": -0.7215310335159302, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.15220700152207, | |
| "grad_norm": 0.29071903228759766, | |
| "learning_rate": 4.783863644106502e-06, | |
| "logits/chosen": 6.791537284851074, | |
| "logits/rejected": 7.366445064544678, | |
| "logps/chosen": -0.31382033228874207, | |
| "logps/rejected": -0.5417486429214478, | |
| "loss": 0.838, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.4707304835319519, | |
| "rewards/margins": 0.34189245104789734, | |
| "rewards/rejected": -0.8126228451728821, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15220700152207, | |
| "eval_logits/chosen": 7.050150394439697, | |
| "eval_logits/rejected": 7.516275405883789, | |
| "eval_logps/chosen": -0.3289315402507782, | |
| "eval_logps/rejected": -0.5481724143028259, | |
| "eval_loss": 0.813983678817749, | |
| "eval_rewards/accuracies": 0.6168224215507507, | |
| "eval_rewards/chosen": -0.4933973252773285, | |
| "eval_rewards/margins": 0.3288613557815552, | |
| "eval_rewards/rejected": -0.8222586512565613, | |
| "eval_runtime": 30.7734, | |
| "eval_samples_per_second": 27.621, | |
| "eval_steps_per_second": 3.477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1598173515981735, | |
| "grad_norm": 0.23101097345352173, | |
| "learning_rate": 4.762067631165049e-06, | |
| "logits/chosen": 5.132790565490723, | |
| "logits/rejected": 5.848537445068359, | |
| "logps/chosen": -0.33372369408607483, | |
| "logps/rejected": -0.5993582010269165, | |
| "loss": 0.8212, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.5005855560302734, | |
| "rewards/margins": 0.3984517455101013, | |
| "rewards/rejected": -0.8990373611450195, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.167427701674277, | |
| "grad_norm": 0.5136363506317139, | |
| "learning_rate": 4.7392794005985324e-06, | |
| "logits/chosen": 3.807554244995117, | |
| "logits/rejected": 4.600871562957764, | |
| "logps/chosen": -0.32092416286468506, | |
| "logps/rejected": -0.651642918586731, | |
| "loss": 0.7851, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -0.4813862442970276, | |
| "rewards/margins": 0.4960783123970032, | |
| "rewards/rejected": -0.977464497089386, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1750380517503805, | |
| "grad_norm": 0.4106898009777069, | |
| "learning_rate": 4.715508948078037e-06, | |
| "logits/chosen": 2.760650396347046, | |
| "logits/rejected": 2.1608071327209473, | |
| "logps/chosen": -0.43665003776550293, | |
| "logps/rejected": -0.8352751731872559, | |
| "loss": 0.7685, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.6549750566482544, | |
| "rewards/margins": 0.5979377627372742, | |
| "rewards/rejected": -1.2529128789901733, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.182648401826484, | |
| "grad_norm": 0.4719419479370117, | |
| "learning_rate": 4.690766700109659e-06, | |
| "logits/chosen": 3.1216347217559814, | |
| "logits/rejected": 2.7202537059783936, | |
| "logps/chosen": -0.444007933139801, | |
| "logps/rejected": -0.7697597742080688, | |
| "loss": 0.7474, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.6660118699073792, | |
| "rewards/margins": 0.4886276125907898, | |
| "rewards/rejected": -1.154639482498169, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1902587519025875, | |
| "grad_norm": 0.548523485660553, | |
| "learning_rate": 4.665063509461098e-06, | |
| "logits/chosen": 1.3678622245788574, | |
| "logits/rejected": 0.46835970878601074, | |
| "logps/chosen": -0.48227253556251526, | |
| "logps/rejected": -0.997289776802063, | |
| "loss": 0.7017, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -0.7234088182449341, | |
| "rewards/margins": 0.7725256681442261, | |
| "rewards/rejected": -1.4959346055984497, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1902587519025875, | |
| "eval_logits/chosen": 2.1362831592559814, | |
| "eval_logits/rejected": 1.1932121515274048, | |
| "eval_logps/chosen": -0.500978946685791, | |
| "eval_logps/rejected": -1.0073517560958862, | |
| "eval_loss": 0.6914573907852173, | |
| "eval_rewards/accuracies": 0.6542056202888489, | |
| "eval_rewards/chosen": -0.7514683604240417, | |
| "eval_rewards/margins": 0.7595593929290771, | |
| "eval_rewards/rejected": -1.5110276937484741, | |
| "eval_runtime": 30.7706, | |
| "eval_samples_per_second": 27.624, | |
| "eval_steps_per_second": 3.477, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.197869101978691, | |
| "grad_norm": 0.700670063495636, | |
| "learning_rate": 4.638410650401267e-06, | |
| "logits/chosen": 2.537666082382202, | |
| "logits/rejected": 1.3070740699768066, | |
| "logps/chosen": -0.59038907289505, | |
| "logps/rejected": -1.0600087642669678, | |
| "loss": 0.6908, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.8855836987495422, | |
| "rewards/margins": 0.7044296264648438, | |
| "rewards/rejected": -1.5900132656097412, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 0.6454456448554993, | |
| "learning_rate": 4.610819813755038e-06, | |
| "logits/chosen": 2.312289237976074, | |
| "logits/rejected": 1.6705052852630615, | |
| "logps/chosen": -0.601074755191803, | |
| "logps/rejected": -1.12887442111969, | |
| "loss": 0.6868, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.9016121029853821, | |
| "rewards/margins": 0.7916995286941528, | |
| "rewards/rejected": -1.6933116912841797, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.213089802130898, | |
| "grad_norm": 0.8001136183738708, | |
| "learning_rate": 4.582303101775249e-06, | |
| "logits/chosen": 1.6213299036026, | |
| "logits/rejected": 0.9048928022384644, | |
| "logps/chosen": -0.6731385588645935, | |
| "logps/rejected": -1.3181935548782349, | |
| "loss": 0.632, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -1.0097079277038574, | |
| "rewards/margins": 0.9675822257995605, | |
| "rewards/rejected": -1.977290153503418, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2207001522070015, | |
| "grad_norm": 0.45858490467071533, | |
| "learning_rate": 4.55287302283426e-06, | |
| "logits/chosen": 1.0463030338287354, | |
| "logits/rejected": 0.05798797681927681, | |
| "logps/chosen": -0.677167534828186, | |
| "logps/rejected": -1.4764039516448975, | |
| "loss": 0.6447, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -1.0157512426376343, | |
| "rewards/margins": 1.1988548040390015, | |
| "rewards/rejected": -2.2146058082580566, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "grad_norm": 0.5778977870941162, | |
| "learning_rate": 4.522542485937369e-06, | |
| "logits/chosen": 2.3259291648864746, | |
| "logits/rejected": 1.6117414236068726, | |
| "logps/chosen": -0.7591919302940369, | |
| "logps/rejected": -1.5995824337005615, | |
| "loss": 0.5702, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -1.1387879848480225, | |
| "rewards/margins": 1.2605856657028198, | |
| "rewards/rejected": -2.3993735313415527, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.228310502283105, | |
| "eval_logits/chosen": 1.9625831842422485, | |
| "eval_logits/rejected": 1.028193473815918, | |
| "eval_logps/chosen": -0.7516441941261292, | |
| "eval_logps/rejected": -1.771378517150879, | |
| "eval_loss": 0.5786539912223816, | |
| "eval_rewards/accuracies": 0.6915887594223022, | |
| "eval_rewards/chosen": -1.1274662017822266, | |
| "eval_rewards/margins": 1.5296014547348022, | |
| "eval_rewards/rejected": -2.6570677757263184, | |
| "eval_runtime": 30.7716, | |
| "eval_samples_per_second": 27.623, | |
| "eval_steps_per_second": 3.477, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2359208523592085, | |
| "grad_norm": 0.5383133292198181, | |
| "learning_rate": 4.491324795060491e-06, | |
| "logits/chosen": 1.2824015617370605, | |
| "logits/rejected": 0.7073851823806763, | |
| "logps/chosen": -0.8315173387527466, | |
| "logps/rejected": -1.9733762741088867, | |
| "loss": 0.587, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -1.2472760677337646, | |
| "rewards/margins": 1.7127883434295654, | |
| "rewards/rejected": -2.96006441116333, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.243531202435312, | |
| "grad_norm": 3.721909284591675, | |
| "learning_rate": 4.4592336433146e-06, | |
| "logits/chosen": 1.993947982788086, | |
| "logits/rejected": 1.192871332168579, | |
| "logps/chosen": -0.9074883460998535, | |
| "logps/rejected": -1.9389015436172485, | |
| "loss": 0.5194, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -1.3612326383590698, | |
| "rewards/margins": 1.5471194982528687, | |
| "rewards/rejected": -2.9083518981933594, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.2511415525114155, | |
| "grad_norm": 0.9611485004425049, | |
| "learning_rate": 4.426283106939474e-06, | |
| "logits/chosen": 0.607239305973053, | |
| "logits/rejected": 0.040740929543972015, | |
| "logps/chosen": -0.9696615934371948, | |
| "logps/rejected": -2.3865818977355957, | |
| "loss": 0.4715, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -1.4544923305511475, | |
| "rewards/margins": 2.1253809928894043, | |
| "rewards/rejected": -3.5798733234405518, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.258751902587519, | |
| "grad_norm": 3.716665744781494, | |
| "learning_rate": 4.3924876391293915e-06, | |
| "logits/chosen": 1.486352801322937, | |
| "logits/rejected": 0.860406756401062, | |
| "logps/chosen": -0.9488881826400757, | |
| "logps/rejected": -2.771193027496338, | |
| "loss": 0.4584, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": -1.4233323335647583, | |
| "rewards/margins": 2.733457088470459, | |
| "rewards/rejected": -4.156789302825928, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2663622526636225, | |
| "grad_norm": 2.496544361114502, | |
| "learning_rate": 4.357862063693486e-06, | |
| "logits/chosen": 2.1065332889556885, | |
| "logits/rejected": 1.4116215705871582, | |
| "logps/chosen": -0.9290377497673035, | |
| "logps/rejected": -2.717181444168091, | |
| "loss": 0.4126, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.393556833267212, | |
| "rewards/margins": 2.682215452194214, | |
| "rewards/rejected": -4.075772285461426, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2663622526636225, | |
| "eval_logits/chosen": 2.3063719272613525, | |
| "eval_logits/rejected": 1.7392665147781372, | |
| "eval_logps/chosen": -0.9553582072257996, | |
| "eval_logps/rejected": -2.8578038215637207, | |
| "eval_loss": 0.43925610184669495, | |
| "eval_rewards/accuracies": 0.7196261882781982, | |
| "eval_rewards/chosen": -1.433037281036377, | |
| "eval_rewards/margins": 2.853668212890625, | |
| "eval_rewards/rejected": -4.286705493927002, | |
| "eval_runtime": 30.7732, | |
| "eval_samples_per_second": 27.621, | |
| "eval_steps_per_second": 3.477, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 1.0364434719085693, | |
| "learning_rate": 4.322421568553529e-06, | |
| "logits/chosen": 3.5145366191864014, | |
| "logits/rejected": 2.562318801879883, | |
| "logps/chosen": -0.9316509366035461, | |
| "logps/rejected": -2.7451562881469727, | |
| "loss": 0.4566, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -1.3974764347076416, | |
| "rewards/margins": 2.7202582359313965, | |
| "rewards/rejected": -4.117734432220459, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2815829528158295, | |
| "grad_norm": 0.7246320843696594, | |
| "learning_rate": 4.286181699082008e-06, | |
| "logits/chosen": 1.6608537435531616, | |
| "logits/rejected": 1.27449631690979, | |
| "logps/chosen": -1.0797128677368164, | |
| "logps/rejected": -3.467390537261963, | |
| "loss": 0.4299, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -1.6195694208145142, | |
| "rewards/margins": 3.5815162658691406, | |
| "rewards/rejected": -5.201085567474365, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.289193302891933, | |
| "grad_norm": 0.942298173904419, | |
| "learning_rate": 4.249158351283414e-06, | |
| "logits/chosen": 2.1106579303741455, | |
| "logits/rejected": 1.5492799282073975, | |
| "logps/chosen": -1.2671682834625244, | |
| "logps/rejected": -3.201054811477661, | |
| "loss": 0.4114, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.900752305984497, | |
| "rewards/margins": 2.900829792022705, | |
| "rewards/rejected": -4.801582336425781, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2968036529680365, | |
| "grad_norm": 0.4278697371482849, | |
| "learning_rate": 4.211367764821722e-06, | |
| "logits/chosen": 3.2620933055877686, | |
| "logits/rejected": 2.7777600288391113, | |
| "logps/chosen": -1.0661684274673462, | |
| "logps/rejected": -3.025578022003174, | |
| "loss": 0.4259, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -1.599252462387085, | |
| "rewards/margins": 2.9391140937805176, | |
| "rewards/rejected": -4.53836727142334, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.30441400304414, | |
| "grad_norm": 0.6019588708877563, | |
| "learning_rate": 4.172826515897146e-06, | |
| "logits/chosen": 3.057295560836792, | |
| "logits/rejected": 2.397916078567505, | |
| "logps/chosen": -1.0584070682525635, | |
| "logps/rejected": -3.479670286178589, | |
| "loss": 0.4167, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.5876106023788452, | |
| "rewards/margins": 3.631894588470459, | |
| "rewards/rejected": -5.219505310058594, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.30441400304414, | |
| "eval_logits/chosen": 3.2906479835510254, | |
| "eval_logits/rejected": 2.9191884994506836, | |
| "eval_logps/chosen": -1.1546303033828735, | |
| "eval_logps/rejected": -3.499722957611084, | |
| "eval_loss": 0.4080003499984741, | |
| "eval_rewards/accuracies": 0.7102803587913513, | |
| "eval_rewards/chosen": -1.731945514678955, | |
| "eval_rewards/margins": 3.517639398574829, | |
| "eval_rewards/rejected": -5.249584674835205, | |
| "eval_runtime": 30.7819, | |
| "eval_samples_per_second": 27.614, | |
| "eval_steps_per_second": 3.476, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3120243531202435, | |
| "grad_norm": 0.610105037689209, | |
| "learning_rate": 4.133551509975264e-06, | |
| "logits/chosen": 2.7366433143615723, | |
| "logits/rejected": 2.350151538848877, | |
| "logps/chosen": -1.3425816297531128, | |
| "logps/rejected": -4.451743125915527, | |
| "loss": 0.3834, | |
| "rewards/accuracies": 0.8125, | |
| "rewards/chosen": -2.0138726234436035, | |
| "rewards/margins": 4.663742542266846, | |
| "rewards/rejected": -6.677615165710449, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.319634703196347, | |
| "grad_norm": 0.9136129021644592, | |
| "learning_rate": 4.093559974371725e-06, | |
| "logits/chosen": 3.8271331787109375, | |
| "logits/rejected": 3.666091203689575, | |
| "logps/chosen": -1.3493579626083374, | |
| "logps/rejected": -3.8569908142089844, | |
| "loss": 0.397, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -2.0240368843078613, | |
| "rewards/margins": 3.7614493370056152, | |
| "rewards/rejected": -5.785486221313477, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3272450532724505, | |
| "grad_norm": 0.6076493859291077, | |
| "learning_rate": 4.052869450695776e-06, | |
| "logits/chosen": 3.027143955230713, | |
| "logits/rejected": 2.2761549949645996, | |
| "logps/chosen": -1.2890465259552002, | |
| "logps/rejected": -4.363173961639404, | |
| "loss": 0.3623, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -1.9335696697235107, | |
| "rewards/margins": 4.6111907958984375, | |
| "rewards/rejected": -6.544760704040527, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.334855403348554, | |
| "grad_norm": 1.0694931745529175, | |
| "learning_rate": 4.011497787155938e-06, | |
| "logits/chosen": 3.989302158355713, | |
| "logits/rejected": 3.3767571449279785, | |
| "logps/chosen": -1.3799726963043213, | |
| "logps/rejected": -4.611227512359619, | |
| "loss": 0.3786, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -2.0699591636657715, | |
| "rewards/margins": 4.846882343292236, | |
| "rewards/rejected": -6.916840553283691, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 2.3523929119110107, | |
| "learning_rate": 3.969463130731183e-06, | |
| "logits/chosen": 3.046278953552246, | |
| "logits/rejected": 2.7509286403656006, | |
| "logps/chosen": -1.577859878540039, | |
| "logps/rejected": -4.554004669189453, | |
| "loss": 0.3948, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -2.3667898178100586, | |
| "rewards/margins": 4.464217185974121, | |
| "rewards/rejected": -6.831006050109863, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "eval_logits/chosen": 3.555213451385498, | |
| "eval_logits/rejected": 3.359722375869751, | |
| "eval_logps/chosen": -1.6125141382217407, | |
| "eval_logps/rejected": -4.374329566955566, | |
| "eval_loss": 0.3748260736465454, | |
| "eval_rewards/accuracies": 0.7943925261497498, | |
| "eval_rewards/chosen": -2.418771266937256, | |
| "eval_rewards/margins": 4.142723560333252, | |
| "eval_rewards/rejected": -6.56149435043335, | |
| "eval_runtime": 30.7795, | |
| "eval_samples_per_second": 27.616, | |
| "eval_steps_per_second": 3.476, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.350076103500761, | |
| "grad_norm": 1.113964557647705, | |
| "learning_rate": 3.92678391921108e-06, | |
| "logits/chosen": 3.61175274848938, | |
| "logits/rejected": 3.547903537750244, | |
| "logps/chosen": -1.7464786767959595, | |
| "logps/rejected": -5.045803070068359, | |
| "loss": 0.3717, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -2.619718074798584, | |
| "rewards/margins": 4.948986053466797, | |
| "rewards/rejected": -7.568705081939697, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3576864535768645, | |
| "grad_norm": 1.5195355415344238, | |
| "learning_rate": 3.88347887310836e-06, | |
| "logits/chosen": 3.0807926654815674, | |
| "logits/rejected": 3.012016773223877, | |
| "logps/chosen": -2.164515733718872, | |
| "logps/rejected": -5.039651393890381, | |
| "loss": 0.3507, | |
| "rewards/accuracies": 0.8374999761581421, | |
| "rewards/chosen": -3.2467732429504395, | |
| "rewards/margins": 4.312704086303711, | |
| "rewards/rejected": -7.55947732925415, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.365296803652968, | |
| "grad_norm": 2.3880045413970947, | |
| "learning_rate": 3.839566987447492e-06, | |
| "logits/chosen": 2.4990105628967285, | |
| "logits/rejected": 2.5192058086395264, | |
| "logps/chosen": -2.5131685733795166, | |
| "logps/rejected": -5.811826705932617, | |
| "loss": 0.3326, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -3.7697532176971436, | |
| "rewards/margins": 4.947987079620361, | |
| "rewards/rejected": -8.717740058898926, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.3729071537290715, | |
| "grad_norm": 4.61068868637085, | |
| "learning_rate": 3.795067523432826e-06, | |
| "logits/chosen": 2.1001622676849365, | |
| "logits/rejected": 2.0562539100646973, | |
| "logps/chosen": -2.7572569847106934, | |
| "logps/rejected": -6.228929042816162, | |
| "loss": 0.3227, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.135885715484619, | |
| "rewards/margins": 5.207508563995361, | |
| "rewards/rejected": -9.343393325805664, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.380517503805175, | |
| "grad_norm": 8.403047561645508, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "logits/chosen": 3.1137287616729736, | |
| "logits/rejected": 2.6646764278411865, | |
| "logps/chosen": -2.8061861991882324, | |
| "logps/rejected": -6.236757755279541, | |
| "loss": 0.3422, | |
| "rewards/accuracies": 0.862500011920929, | |
| "rewards/chosen": -4.2092790603637695, | |
| "rewards/margins": 5.1458563804626465, | |
| "rewards/rejected": -9.355135917663574, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.380517503805175, | |
| "eval_logits/chosen": 3.3083701133728027, | |
| "eval_logits/rejected": 3.13222336769104, | |
| "eval_logps/chosen": -2.6677865982055664, | |
| "eval_logps/rejected": -5.843282222747803, | |
| "eval_loss": 0.30595287680625916, | |
| "eval_rewards/accuracies": 0.8878504633903503, | |
| "eval_rewards/chosen": -4.001679420471191, | |
| "eval_rewards/margins": 4.763244152069092, | |
| "eval_rewards/rejected": -8.764924049377441, | |
| "eval_runtime": 30.7793, | |
| "eval_samples_per_second": 27.616, | |
| "eval_steps_per_second": 3.476, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3881278538812785, | |
| "grad_norm": 2.3582851886749268, | |
| "learning_rate": 3.7043841852542884e-06, | |
| "logits/chosen": 2.7116522789001465, | |
| "logits/rejected": 2.5776076316833496, | |
| "logps/chosen": -2.7367191314697266, | |
| "logps/rejected": -6.1324052810668945, | |
| "loss": 0.2649, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -4.10507869720459, | |
| "rewards/margins": 5.093530178070068, | |
| "rewards/rejected": -9.1986083984375, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.395738203957382, | |
| "grad_norm": 2.8183226585388184, | |
| "learning_rate": 3.658240087799655e-06, | |
| "logits/chosen": 2.327544689178467, | |
| "logits/rejected": 2.3745343685150146, | |
| "logps/chosen": -2.6957223415374756, | |
| "logps/rejected": -6.291537284851074, | |
| "loss": 0.295, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -4.043583393096924, | |
| "rewards/margins": 5.393722057342529, | |
| "rewards/rejected": -9.437305450439453, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4033485540334855, | |
| "grad_norm": 1.8313360214233398, | |
| "learning_rate": 3.611587947962319e-06, | |
| "logits/chosen": 2.4468109607696533, | |
| "logits/rejected": 2.4551472663879395, | |
| "logps/chosen": -2.7839953899383545, | |
| "logps/rejected": -6.5379180908203125, | |
| "loss": 0.2618, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -4.175992965698242, | |
| "rewards/margins": 5.63088321685791, | |
| "rewards/rejected": -9.806875228881836, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 2.2132411003112793, | |
| "learning_rate": 3.564448228912682e-06, | |
| "logits/chosen": 3.125279664993286, | |
| "logits/rejected": 2.7795650959014893, | |
| "logps/chosen": -3.349208116531372, | |
| "logps/rejected": -6.923414707183838, | |
| "loss": 0.2592, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.023811340332031, | |
| "rewards/margins": 5.361310005187988, | |
| "rewards/rejected": -10.385122299194336, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.4185692541856925, | |
| "grad_norm": 6.05848503112793, | |
| "learning_rate": 3.516841607689501e-06, | |
| "logits/chosen": 2.841399669647217, | |
| "logits/rejected": 2.997351884841919, | |
| "logps/chosen": -3.256176710128784, | |
| "logps/rejected": -7.098822593688965, | |
| "loss": 0.2603, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.884264945983887, | |
| "rewards/margins": 5.763968467712402, | |
| "rewards/rejected": -10.648235321044922, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.4185692541856925, | |
| "eval_logits/chosen": 3.109469413757324, | |
| "eval_logits/rejected": 3.010756492614746, | |
| "eval_logps/chosen": -3.216036558151245, | |
| "eval_logps/rejected": -6.825747013092041, | |
| "eval_loss": 0.27887609601020813, | |
| "eval_rewards/accuracies": 0.8878504633903503, | |
| "eval_rewards/chosen": -4.824055194854736, | |
| "eval_rewards/margins": 5.414565563201904, | |
| "eval_rewards/rejected": -10.23862075805664, | |
| "eval_runtime": 30.773, | |
| "eval_samples_per_second": 27.622, | |
| "eval_steps_per_second": 3.477, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.426179604261796, | |
| "grad_norm": 1.8734403848648071, | |
| "learning_rate": 3.4687889661302577e-06, | |
| "logits/chosen": 1.8899682760238647, | |
| "logits/rejected": 1.7766664028167725, | |
| "logps/chosen": -3.1907763481140137, | |
| "logps/rejected": -7.273028373718262, | |
| "loss": 0.2669, | |
| "rewards/accuracies": 0.8999999761581421, | |
| "rewards/chosen": -4.7861647605896, | |
| "rewards/margins": 6.123377323150635, | |
| "rewards/rejected": -10.909541130065918, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4337899543378995, | |
| "grad_norm": 3.2115261554718018, | |
| "learning_rate": 3.4203113817116955e-06, | |
| "logits/chosen": 2.563091278076172, | |
| "logits/rejected": 2.530696392059326, | |
| "logps/chosen": -3.620448589324951, | |
| "logps/rejected": -7.546849250793457, | |
| "loss": 0.2683, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -5.430673599243164, | |
| "rewards/margins": 5.8896002769470215, | |
| "rewards/rejected": -11.320273399353027, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.441400304414003, | |
| "grad_norm": 3.684910297393799, | |
| "learning_rate": 3.3714301183045382e-06, | |
| "logits/chosen": 2.873882293701172, | |
| "logits/rejected": 3.193092107772827, | |
| "logps/chosen": -3.386859178543091, | |
| "logps/rejected": -7.514338493347168, | |
| "loss": 0.2715, | |
| "rewards/accuracies": 0.8500000238418579, | |
| "rewards/chosen": -5.080288887023926, | |
| "rewards/margins": 6.191219329833984, | |
| "rewards/rejected": -11.271509170532227, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.4490106544901065, | |
| "grad_norm": 2.661367416381836, | |
| "learning_rate": 3.3221666168464584e-06, | |
| "logits/chosen": 2.5157277584075928, | |
| "logits/rejected": 2.5739080905914307, | |
| "logps/chosen": -3.658534526824951, | |
| "logps/rejected": -7.9988884925842285, | |
| "loss": 0.2454, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -5.487801551818848, | |
| "rewards/margins": 6.510530948638916, | |
| "rewards/rejected": -11.998331069946289, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "grad_norm": 1.8180292844772339, | |
| "learning_rate": 3.272542485937369e-06, | |
| "logits/chosen": 2.6391870975494385, | |
| "logits/rejected": 2.72003173828125, | |
| "logps/chosen": -3.382587432861328, | |
| "logps/rejected": -8.08546257019043, | |
| "loss": 0.2706, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -5.073880672454834, | |
| "rewards/margins": 7.054312229156494, | |
| "rewards/rejected": -12.128194808959961, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.45662100456621, | |
| "eval_logits/chosen": 3.235776901245117, | |
| "eval_logits/rejected": 3.2310192584991455, | |
| "eval_logps/chosen": -3.201641082763672, | |
| "eval_logps/rejected": -7.113856315612793, | |
| "eval_loss": 0.26078400015830994, | |
| "eval_rewards/accuracies": 0.8878504633903503, | |
| "eval_rewards/chosen": -4.802461624145508, | |
| "eval_rewards/margins": 5.8683247566223145, | |
| "eval_rewards/rejected": -10.67078685760498, | |
| "eval_runtime": 30.7777, | |
| "eval_samples_per_second": 27.617, | |
| "eval_steps_per_second": 3.477, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4642313546423135, | |
| "grad_norm": 3.1237454414367676, | |
| "learning_rate": 3.222579492361179e-06, | |
| "logits/chosen": 3.097729444503784, | |
| "logits/rejected": 2.8835232257843018, | |
| "logps/chosen": -3.2986862659454346, | |
| "logps/rejected": -7.824951171875, | |
| "loss": 0.2455, | |
| "rewards/accuracies": 0.8999999761581421, | |
| "rewards/chosen": -4.948029518127441, | |
| "rewards/margins": 6.789399147033691, | |
| "rewards/rejected": -11.7374267578125, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.471841704718417, | |
| "grad_norm": 2.250023365020752, | |
| "learning_rate": 3.1722995515381644e-06, | |
| "logits/chosen": 3.303495407104492, | |
| "logits/rejected": 3.124060869216919, | |
| "logps/chosen": -2.9880855083465576, | |
| "logps/rejected": -6.581275939941406, | |
| "loss": 0.2754, | |
| "rewards/accuracies": 0.875, | |
| "rewards/chosen": -4.482128143310547, | |
| "rewards/margins": 5.389786243438721, | |
| "rewards/rejected": -9.87191390991211, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 4.364448547363281, | |
| "learning_rate": 3.121724717912138e-06, | |
| "logits/chosen": 2.8994319438934326, | |
| "logits/rejected": 2.593780755996704, | |
| "logps/chosen": -3.4450290203094482, | |
| "logps/rejected": -7.1797990798950195, | |
| "loss": 0.2316, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -5.167544364929199, | |
| "rewards/margins": 5.602154731750488, | |
| "rewards/rejected": -10.769698143005371, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.487062404870624, | |
| "grad_norm": 3.65561580657959, | |
| "learning_rate": 3.0708771752766397e-06, | |
| "logits/chosen": 3.1075518131256104, | |
| "logits/rejected": 2.8703231811523438, | |
| "logps/chosen": -3.26599383354187, | |
| "logps/rejected": -7.536534786224365, | |
| "loss": 0.2549, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -4.898990631103516, | |
| "rewards/margins": 6.4058122634887695, | |
| "rewards/rejected": -11.304803848266602, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.4946727549467275, | |
| "grad_norm": 3.1211891174316406, | |
| "learning_rate": 3.019779227044398e-06, | |
| "logits/chosen": 3.2364888191223145, | |
| "logits/rejected": 3.3938751220703125, | |
| "logps/chosen": -3.538849353790283, | |
| "logps/rejected": -7.827691555023193, | |
| "loss": 0.2571, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -5.308274269104004, | |
| "rewards/margins": 6.433261871337891, | |
| "rewards/rejected": -11.741537094116211, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.4946727549467275, | |
| "eval_logits/chosen": 3.091616153717041, | |
| "eval_logits/rejected": 3.0459396839141846, | |
| "eval_logps/chosen": -3.361125946044922, | |
| "eval_logps/rejected": -7.390212535858154, | |
| "eval_loss": 0.2536354660987854, | |
| "eval_rewards/accuracies": 0.8971962332725525, | |
| "eval_rewards/chosen": -5.041689395904541, | |
| "eval_rewards/margins": 6.043630599975586, | |
| "eval_rewards/rejected": -11.085319519042969, | |
| "eval_runtime": 30.7751, | |
| "eval_samples_per_second": 27.62, | |
| "eval_steps_per_second": 3.477, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.502283105022831, | |
| "grad_norm": 4.375415802001953, | |
| "learning_rate": 2.9684532864643123e-06, | |
| "logits/chosen": 1.8274192810058594, | |
| "logits/rejected": 1.9628839492797852, | |
| "logps/chosen": -3.083608627319336, | |
| "logps/rejected": -8.370513916015625, | |
| "loss": 0.2166, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -4.625412940979004, | |
| "rewards/margins": 7.930357456207275, | |
| "rewards/rejected": -12.555770874023438, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5098934550989346, | |
| "grad_norm": 3.6583638191223145, | |
| "learning_rate": 2.9169218667902562e-06, | |
| "logits/chosen": 2.5409281253814697, | |
| "logits/rejected": 2.46968150138855, | |
| "logps/chosen": -3.252990245819092, | |
| "logps/rejected": -7.6487884521484375, | |
| "loss": 0.2103, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.879485607147217, | |
| "rewards/margins": 6.593697547912598, | |
| "rewards/rejected": -11.473182678222656, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.517503805175038, | |
| "grad_norm": 2.009876251220703, | |
| "learning_rate": 2.8652075714060296e-06, | |
| "logits/chosen": 3.553900957107544, | |
| "logits/rejected": 3.4104526042938232, | |
| "logps/chosen": -2.9901890754699707, | |
| "logps/rejected": -7.472288608551025, | |
| "loss": 0.2405, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -4.485283374786377, | |
| "rewards/margins": 6.723149299621582, | |
| "rewards/rejected": -11.208433151245117, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5251141552511416, | |
| "grad_norm": 2.9065611362457275, | |
| "learning_rate": 2.813333083910761e-06, | |
| "logits/chosen": 2.323111057281494, | |
| "logits/rejected": 2.0086140632629395, | |
| "logps/chosen": -3.430807590484619, | |
| "logps/rejected": -8.105338096618652, | |
| "loss": 0.2182, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.146210670471191, | |
| "rewards/margins": 7.011796474456787, | |
| "rewards/rejected": -12.15800666809082, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.532724505327245, | |
| "grad_norm": 4.097139358520508, | |
| "learning_rate": 2.761321158169134e-06, | |
| "logits/chosen": 1.9292926788330078, | |
| "logits/rejected": 2.0105385780334473, | |
| "logps/chosen": -3.337139129638672, | |
| "logps/rejected": -7.7645721435546875, | |
| "loss": 0.245, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.005709171295166, | |
| "rewards/margins": 6.641148567199707, | |
| "rewards/rejected": -11.646858215332031, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.532724505327245, | |
| "eval_logits/chosen": 2.946713924407959, | |
| "eval_logits/rejected": 2.912729501724243, | |
| "eval_logps/chosen": -3.3646414279937744, | |
| "eval_logps/rejected": -7.633481979370117, | |
| "eval_loss": 0.2412233203649521, | |
| "eval_rewards/accuracies": 0.9065420627593994, | |
| "eval_rewards/chosen": -5.046962261199951, | |
| "eval_rewards/margins": 6.403261184692383, | |
| "eval_rewards/rejected": -11.450223922729492, | |
| "eval_runtime": 30.7742, | |
| "eval_samples_per_second": 27.621, | |
| "eval_steps_per_second": 3.477, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5403348554033486, | |
| "grad_norm": 4.534071922302246, | |
| "learning_rate": 2.70919460833079e-06, | |
| "logits/chosen": 2.4406304359436035, | |
| "logits/rejected": 2.713369607925415, | |
| "logps/chosen": -3.4392433166503906, | |
| "logps/rejected": -8.228872299194336, | |
| "loss": 0.2245, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.158864498138428, | |
| "rewards/margins": 7.184444427490234, | |
| "rewards/rejected": -12.34330940246582, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 1.5941667556762695, | |
| "learning_rate": 2.6569762988232838e-06, | |
| "logits/chosen": 3.3259758949279785, | |
| "logits/rejected": 3.3186354637145996, | |
| "logps/chosen": -3.7198212146759033, | |
| "logps/rejected": -7.6400909423828125, | |
| "loss": 0.2339, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.5797319412231445, | |
| "rewards/margins": 5.8804030418396, | |
| "rewards/rejected": -11.460134506225586, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 5.972750186920166, | |
| "learning_rate": 2.604689134322999e-06, | |
| "logits/chosen": 2.455244302749634, | |
| "logits/rejected": 2.5398240089416504, | |
| "logps/chosen": -3.892965316772461, | |
| "logps/rejected": -8.59666633605957, | |
| "loss": 0.2041, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.83944845199585, | |
| "rewards/margins": 7.055548667907715, | |
| "rewards/rejected": -12.894998550415039, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.563165905631659, | |
| "grad_norm": 3.1441280841827393, | |
| "learning_rate": 2.5523560497083927e-06, | |
| "logits/chosen": 2.3029608726501465, | |
| "logits/rejected": 2.3662524223327637, | |
| "logps/chosen": -3.682513475418091, | |
| "logps/rejected": -8.340951919555664, | |
| "loss": 0.2723, | |
| "rewards/accuracies": 0.887499988079071, | |
| "rewards/chosen": -5.523770332336426, | |
| "rewards/margins": 6.9876580238342285, | |
| "rewards/rejected": -12.511428833007812, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5707762557077626, | |
| "grad_norm": 2.30711030960083, | |
| "learning_rate": 2.5e-06, | |
| "logits/chosen": 1.8446356058120728, | |
| "logits/rejected": 1.9468234777450562, | |
| "logps/chosen": -3.808454990386963, | |
| "logps/rejected": -8.047523498535156, | |
| "loss": 0.1936, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.712681770324707, | |
| "rewards/margins": 6.3586015701293945, | |
| "rewards/rejected": -12.071284294128418, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5707762557077626, | |
| "eval_logits/chosen": 2.7250914573669434, | |
| "eval_logits/rejected": 2.7465131282806396, | |
| "eval_logps/chosen": -3.5594334602355957, | |
| "eval_logps/rejected": -7.899675369262695, | |
| "eval_loss": 0.2329329252243042, | |
| "eval_rewards/accuracies": 0.9345794320106506, | |
| "eval_rewards/chosen": -5.339150905609131, | |
| "eval_rewards/margins": 6.510361671447754, | |
| "eval_rewards/rejected": -11.84951114654541, | |
| "eval_runtime": 30.7783, | |
| "eval_samples_per_second": 27.617, | |
| "eval_steps_per_second": 3.476, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.578386605783866, | |
| "grad_norm": 3.0719997882843018, | |
| "learning_rate": 2.447643950291608e-06, | |
| "logits/chosen": 2.3534064292907715, | |
| "logits/rejected": 2.401563882827759, | |
| "logps/chosen": -3.610807418823242, | |
| "logps/rejected": -7.985041618347168, | |
| "loss": 0.1847, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.416211128234863, | |
| "rewards/margins": 6.561351776123047, | |
| "rewards/rejected": -11.97756290435791, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5859969558599696, | |
| "grad_norm": 3.6076536178588867, | |
| "learning_rate": 2.3953108656770018e-06, | |
| "logits/chosen": 1.969351053237915, | |
| "logits/rejected": 2.2207655906677246, | |
| "logps/chosen": -2.9666709899902344, | |
| "logps/rejected": -8.2462797164917, | |
| "loss": 0.2211, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.450006484985352, | |
| "rewards/margins": 7.919413089752197, | |
| "rewards/rejected": -12.369420051574707, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.593607305936073, | |
| "grad_norm": 3.9795055389404297, | |
| "learning_rate": 2.3430237011767166e-06, | |
| "logits/chosen": 2.6336114406585693, | |
| "logits/rejected": 2.438262462615967, | |
| "logps/chosen": -3.4108245372772217, | |
| "logps/rejected": -8.591341018676758, | |
| "loss": 0.2306, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -5.116236209869385, | |
| "rewards/margins": 7.770774841308594, | |
| "rewards/rejected": -12.887011528015137, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6012176560121766, | |
| "grad_norm": 3.288729667663574, | |
| "learning_rate": 2.290805391669212e-06, | |
| "logits/chosen": 1.6185804605484009, | |
| "logits/rejected": 1.6822645664215088, | |
| "logps/chosen": -3.2728798389434814, | |
| "logps/rejected": -7.791805267333984, | |
| "loss": 0.2329, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.909319877624512, | |
| "rewards/margins": 6.778387546539307, | |
| "rewards/rejected": -11.687707901000977, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.60882800608828, | |
| "grad_norm": 2.315206289291382, | |
| "learning_rate": 2.238678841830867e-06, | |
| "logits/chosen": 2.018578052520752, | |
| "logits/rejected": 1.8465204238891602, | |
| "logps/chosen": -3.2794997692108154, | |
| "logps/rejected": -8.164708137512207, | |
| "loss": 0.2082, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.919250011444092, | |
| "rewards/margins": 7.327812194824219, | |
| "rewards/rejected": -12.247061729431152, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.60882800608828, | |
| "eval_logits/chosen": 3.08111572265625, | |
| "eval_logits/rejected": 3.0503101348876953, | |
| "eval_logps/chosen": -3.4727284908294678, | |
| "eval_logps/rejected": -7.895880699157715, | |
| "eval_loss": 0.22325536608695984, | |
| "eval_rewards/accuracies": 0.9252336621284485, | |
| "eval_rewards/chosen": -5.209092617034912, | |
| "eval_rewards/margins": 6.634730339050293, | |
| "eval_rewards/rejected": -11.84382152557373, | |
| "eval_runtime": 30.7753, | |
| "eval_samples_per_second": 27.62, | |
| "eval_steps_per_second": 3.477, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 2.4823191165924072, | |
| "learning_rate": 2.186666916089239e-06, | |
| "logits/chosen": 2.6345906257629395, | |
| "logits/rejected": 2.5206990242004395, | |
| "logps/chosen": -3.123882532119751, | |
| "logps/rejected": -7.772116184234619, | |
| "loss": 0.1931, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -4.685823440551758, | |
| "rewards/margins": 6.972352027893066, | |
| "rewards/rejected": -11.658174514770508, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.624048706240487, | |
| "grad_norm": 1.3935630321502686, | |
| "learning_rate": 2.134792428593971e-06, | |
| "logits/chosen": 2.4640917778015137, | |
| "logits/rejected": 2.531430721282959, | |
| "logps/chosen": -3.5584664344787598, | |
| "logps/rejected": -8.64016342163086, | |
| "loss": 0.205, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -5.337700366973877, | |
| "rewards/margins": 7.622546195983887, | |
| "rewards/rejected": -12.960246086120605, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6316590563165906, | |
| "grad_norm": 2.7727415561676025, | |
| "learning_rate": 2.0830781332097446e-06, | |
| "logits/chosen": 3.5152816772460938, | |
| "logits/rejected": 3.3117728233337402, | |
| "logps/chosen": -3.820496082305908, | |
| "logps/rejected": -8.241179466247559, | |
| "loss": 0.2315, | |
| "rewards/accuracies": 0.9125000238418579, | |
| "rewards/chosen": -5.730743408203125, | |
| "rewards/margins": 6.631025791168213, | |
| "rewards/rejected": -12.361770629882812, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.639269406392694, | |
| "grad_norm": 3.5436055660247803, | |
| "learning_rate": 2.031546713535688e-06, | |
| "logits/chosen": 2.813575506210327, | |
| "logits/rejected": 2.650791645050049, | |
| "logps/chosen": -3.552276134490967, | |
| "logps/rejected": -8.587823867797852, | |
| "loss": 0.1964, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.328413963317871, | |
| "rewards/margins": 7.553321838378906, | |
| "rewards/rejected": -12.881736755371094, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6468797564687976, | |
| "grad_norm": 4.140048027038574, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "logits/chosen": 2.695815324783325, | |
| "logits/rejected": 2.509413242340088, | |
| "logps/chosen": -3.706005573272705, | |
| "logps/rejected": -8.673744201660156, | |
| "loss": 0.1882, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -5.55900764465332, | |
| "rewards/margins": 7.451608180999756, | |
| "rewards/rejected": -13.01061725616455, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6468797564687976, | |
| "eval_logits/chosen": 3.0777766704559326, | |
| "eval_logits/rejected": 3.120222806930542, | |
| "eval_logps/chosen": -3.801321268081665, | |
| "eval_logps/rejected": -8.376675605773926, | |
| "eval_loss": 0.21778903901576996, | |
| "eval_rewards/accuracies": 0.9345794320106506, | |
| "eval_rewards/chosen": -5.701981067657471, | |
| "eval_rewards/margins": 6.863031387329102, | |
| "eval_rewards/rejected": -12.565014839172363, | |
| "eval_runtime": 30.7706, | |
| "eval_samples_per_second": 27.624, | |
| "eval_steps_per_second": 3.477, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.654490106544901, | |
| "grad_norm": 3.0274274349212646, | |
| "learning_rate": 1.9291228247233607e-06, | |
| "logits/chosen": 2.446882486343384, | |
| "logits/rejected": 2.352177143096924, | |
| "logps/chosen": -3.8477814197540283, | |
| "logps/rejected": -9.340738296508789, | |
| "loss": 0.1916, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.771672248840332, | |
| "rewards/margins": 8.239435195922852, | |
| "rewards/rejected": -14.011106491088867, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6621004566210046, | |
| "grad_norm": 4.4860520362854, | |
| "learning_rate": 1.8782752820878636e-06, | |
| "logits/chosen": 2.77601957321167, | |
| "logits/rejected": 2.853281021118164, | |
| "logps/chosen": -4.01420259475708, | |
| "logps/rejected": -9.463164329528809, | |
| "loss": 0.2013, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -6.021303653717041, | |
| "rewards/margins": 8.173443794250488, | |
| "rewards/rejected": -14.194747924804688, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.669710806697108, | |
| "grad_norm": 6.593935012817383, | |
| "learning_rate": 1.827700448461836e-06, | |
| "logits/chosen": 2.5073022842407227, | |
| "logits/rejected": 2.9579524993896484, | |
| "logps/chosen": -3.9602768421173096, | |
| "logps/rejected": -9.482460021972656, | |
| "loss": 0.2163, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.940415382385254, | |
| "rewards/margins": 8.283275604248047, | |
| "rewards/rejected": -14.2236909866333, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6773211567732116, | |
| "grad_norm": 3.101680040359497, | |
| "learning_rate": 1.7774205076388207e-06, | |
| "logits/chosen": 2.27485990524292, | |
| "logits/rejected": 2.5005619525909424, | |
| "logps/chosen": -3.828552722930908, | |
| "logps/rejected": -8.851189613342285, | |
| "loss": 0.1935, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.742828845977783, | |
| "rewards/margins": 7.5339555740356445, | |
| "rewards/rejected": -13.27678394317627, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 3.6742115020751953, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "logits/chosen": 2.381319761276245, | |
| "logits/rejected": 2.543203353881836, | |
| "logps/chosen": -3.4646923542022705, | |
| "logps/rejected": -9.015104293823242, | |
| "loss": 0.1903, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -5.197038173675537, | |
| "rewards/margins": 8.325616836547852, | |
| "rewards/rejected": -13.522656440734863, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "eval_logits/chosen": 3.069916009902954, | |
| "eval_logits/rejected": 3.104632616043091, | |
| "eval_logps/chosen": -3.6102888584136963, | |
| "eval_logps/rejected": -8.349987983703613, | |
| "eval_loss": 0.2161051481962204, | |
| "eval_rewards/accuracies": 0.9345794320106506, | |
| "eval_rewards/chosen": -5.415433406829834, | |
| "eval_rewards/margins": 7.1095476150512695, | |
| "eval_rewards/rejected": -12.524979591369629, | |
| "eval_runtime": 30.7844, | |
| "eval_samples_per_second": 27.611, | |
| "eval_steps_per_second": 3.476, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6925418569254186, | |
| "grad_norm": 2.9264719486236572, | |
| "learning_rate": 1.677833383153542e-06, | |
| "logits/chosen": 2.0955498218536377, | |
| "logits/rejected": 2.1619057655334473, | |
| "logps/chosen": -3.460951328277588, | |
| "logps/rejected": -8.898179054260254, | |
| "loss": 0.1687, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.191426753997803, | |
| "rewards/margins": 8.155839920043945, | |
| "rewards/rejected": -13.347267150878906, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.700152207001522, | |
| "grad_norm": 2.0860531330108643, | |
| "learning_rate": 1.6285698816954626e-06, | |
| "logits/chosen": 3.346489429473877, | |
| "logits/rejected": 3.2421345710754395, | |
| "logps/chosen": -3.63940691947937, | |
| "logps/rejected": -8.418205261230469, | |
| "loss": 0.2161, | |
| "rewards/accuracies": 0.987500011920929, | |
| "rewards/chosen": -5.459110260009766, | |
| "rewards/margins": 7.168198585510254, | |
| "rewards/rejected": -12.627306938171387, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7077625570776256, | |
| "grad_norm": 2.778262138366699, | |
| "learning_rate": 1.5796886182883053e-06, | |
| "logits/chosen": 1.7459516525268555, | |
| "logits/rejected": 2.1579155921936035, | |
| "logps/chosen": -3.3034520149230957, | |
| "logps/rejected": -9.191883087158203, | |
| "loss": 0.2007, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -4.955178260803223, | |
| "rewards/margins": 8.832646369934082, | |
| "rewards/rejected": -13.787823677062988, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.715372907153729, | |
| "grad_norm": 3.695908546447754, | |
| "learning_rate": 1.5312110338697427e-06, | |
| "logits/chosen": 2.7586328983306885, | |
| "logits/rejected": 2.920232057571411, | |
| "logps/chosen": -3.6659629344940186, | |
| "logps/rejected": -8.657777786254883, | |
| "loss": 0.1907, | |
| "rewards/accuracies": 0.987500011920929, | |
| "rewards/chosen": -5.498944282531738, | |
| "rewards/margins": 7.487723350524902, | |
| "rewards/rejected": -12.986666679382324, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.7229832572298326, | |
| "grad_norm": 3.2104835510253906, | |
| "learning_rate": 1.4831583923105e-06, | |
| "logits/chosen": 2.8813366889953613, | |
| "logits/rejected": 3.21830677986145, | |
| "logps/chosen": -3.41332745552063, | |
| "logps/rejected": -8.479570388793945, | |
| "loss": 0.2074, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -5.119990825653076, | |
| "rewards/margins": 7.599363803863525, | |
| "rewards/rejected": -12.719354629516602, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7229832572298326, | |
| "eval_logits/chosen": 3.281101703643799, | |
| "eval_logits/rejected": 3.3282196521759033, | |
| "eval_logps/chosen": -3.6136667728424072, | |
| "eval_logps/rejected": -8.419679641723633, | |
| "eval_loss": 0.21113382279872894, | |
| "eval_rewards/accuracies": 0.9252336621284485, | |
| "eval_rewards/chosen": -5.4205002784729, | |
| "eval_rewards/margins": 7.209019660949707, | |
| "eval_rewards/rejected": -12.629520416259766, | |
| "eval_runtime": 30.777, | |
| "eval_samples_per_second": 27.618, | |
| "eval_steps_per_second": 3.477, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.730593607305936, | |
| "grad_norm": 6.422901153564453, | |
| "learning_rate": 1.4355517710873184e-06, | |
| "logits/chosen": 2.0251851081848145, | |
| "logits/rejected": 2.1296639442443848, | |
| "logps/chosen": -3.15910005569458, | |
| "logps/rejected": -8.686817169189453, | |
| "loss": 0.187, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -4.738650321960449, | |
| "rewards/margins": 8.29157543182373, | |
| "rewards/rejected": -13.03022575378418, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7382039573820396, | |
| "grad_norm": 1.537139654159546, | |
| "learning_rate": 1.388412052037682e-06, | |
| "logits/chosen": 3.1659352779388428, | |
| "logits/rejected": 3.161760091781616, | |
| "logps/chosen": -3.755237102508545, | |
| "logps/rejected": -8.484071731567383, | |
| "loss": 0.1823, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.6328558921813965, | |
| "rewards/margins": 7.093251705169678, | |
| "rewards/rejected": -12.726107597351074, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.745814307458143, | |
| "grad_norm": 3.024386405944824, | |
| "learning_rate": 1.3417599122003464e-06, | |
| "logits/chosen": 2.7146401405334473, | |
| "logits/rejected": 2.9919748306274414, | |
| "logps/chosen": -3.507610321044922, | |
| "logps/rejected": -9.035795211791992, | |
| "loss": 0.2122, | |
| "rewards/accuracies": 0.925000011920929, | |
| "rewards/chosen": -5.261415004730225, | |
| "rewards/margins": 8.292278289794922, | |
| "rewards/rejected": -13.553693771362305, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 3.5992636680603027, | |
| "learning_rate": 1.2956158147457116e-06, | |
| "logits/chosen": 2.9386534690856934, | |
| "logits/rejected": 2.974626064300537, | |
| "logps/chosen": -3.5809288024902344, | |
| "logps/rejected": -9.47168254852295, | |
| "loss": 0.2058, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -5.371392726898193, | |
| "rewards/margins": 8.836130142211914, | |
| "rewards/rejected": -14.20752239227295, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.76103500761035, | |
| "grad_norm": 3.0734636783599854, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "logits/chosen": 2.984003782272339, | |
| "logits/rejected": 3.055147647857666, | |
| "logps/chosen": -4.086684226989746, | |
| "logps/rejected": -9.243562698364258, | |
| "loss": 0.2135, | |
| "rewards/accuracies": 0.9750000238418579, | |
| "rewards/chosen": -6.130026817321777, | |
| "rewards/margins": 7.735315799713135, | |
| "rewards/rejected": -13.865341186523438, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.76103500761035, | |
| "eval_logits/chosen": 3.18290638923645, | |
| "eval_logits/rejected": 3.2487096786499023, | |
| "eval_logps/chosen": -3.576455593109131, | |
| "eval_logps/rejected": -8.458187103271484, | |
| "eval_loss": 0.20949731767177582, | |
| "eval_rewards/accuracies": 0.9439252614974976, | |
| "eval_rewards/chosen": -5.364683151245117, | |
| "eval_rewards/margins": 7.322596549987793, | |
| "eval_rewards/rejected": -12.687278747558594, | |
| "eval_runtime": 30.7759, | |
| "eval_samples_per_second": 27.619, | |
| "eval_steps_per_second": 3.477, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7686453576864536, | |
| "grad_norm": 4.717663288116455, | |
| "learning_rate": 1.204932476567175e-06, | |
| "logits/chosen": 2.96572208404541, | |
| "logits/rejected": 2.8679356575012207, | |
| "logps/chosen": -3.6380767822265625, | |
| "logps/rejected": -8.982633590698242, | |
| "loss": 0.1686, | |
| "rewards/accuracies": 0.9375, | |
| "rewards/chosen": -5.457114219665527, | |
| "rewards/margins": 8.01683521270752, | |
| "rewards/rejected": -13.473950386047363, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.776255707762557, | |
| "grad_norm": 2.1752161979675293, | |
| "learning_rate": 1.160433012552508e-06, | |
| "logits/chosen": 2.227342128753662, | |
| "logits/rejected": 2.576072931289673, | |
| "logps/chosen": -3.2803902626037598, | |
| "logps/rejected": -8.933613777160645, | |
| "loss": 0.1802, | |
| "rewards/accuracies": 0.987500011920929, | |
| "rewards/chosen": -4.920585632324219, | |
| "rewards/margins": 8.479835510253906, | |
| "rewards/rejected": -13.400421142578125, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.7838660578386606, | |
| "grad_norm": 3.252668857574463, | |
| "learning_rate": 1.11652112689164e-06, | |
| "logits/chosen": 2.558826446533203, | |
| "logits/rejected": 2.4980645179748535, | |
| "logps/chosen": -3.639244794845581, | |
| "logps/rejected": -9.068904876708984, | |
| "loss": 0.2142, | |
| "rewards/accuracies": 0.949999988079071, | |
| "rewards/chosen": -5.458867073059082, | |
| "rewards/margins": 8.144488334655762, | |
| "rewards/rejected": -13.603355407714844, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.791476407914764, | |
| "grad_norm": 4.632419109344482, | |
| "learning_rate": 1.073216080788921e-06, | |
| "logits/chosen": 1.8568460941314697, | |
| "logits/rejected": 2.2069149017333984, | |
| "logps/chosen": -3.4306697845458984, | |
| "logps/rejected": -8.670662879943848, | |
| "loss": 0.169, | |
| "rewards/accuracies": 0.987500011920929, | |
| "rewards/chosen": -5.146004676818848, | |
| "rewards/margins": 7.859990119934082, | |
| "rewards/rejected": -13.00599479675293, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7990867579908676, | |
| "grad_norm": 4.621112823486328, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "logits/chosen": 2.480006694793701, | |
| "logits/rejected": 2.7665817737579346, | |
| "logps/chosen": -3.486351728439331, | |
| "logps/rejected": -8.768314361572266, | |
| "loss": 0.1901, | |
| "rewards/accuracies": 0.9624999761581421, | |
| "rewards/chosen": -5.229527473449707, | |
| "rewards/margins": 7.922944068908691, | |
| "rewards/rejected": -13.152471542358398, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.7990867579908676, | |
| "eval_logits/chosen": 3.231480598449707, | |
| "eval_logits/rejected": 3.311223030090332, | |
| "eval_logps/chosen": -3.6841485500335693, | |
| "eval_logps/rejected": -8.640739440917969, | |
| "eval_loss": 0.20705747604370117, | |
| "eval_rewards/accuracies": 0.9252336621284485, | |
| "eval_rewards/chosen": -5.526222229003906, | |
| "eval_rewards/margins": 7.434886455535889, | |
| "eval_rewards/rejected": -12.961106300354004, | |
| "eval_runtime": 30.7718, | |
| "eval_samples_per_second": 27.623, | |
| "eval_steps_per_second": 3.477, | |
| "step": 1050 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.4442753349341676e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |