checkpoint-700/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6431606753187091,
  "eval_steps": 50,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00918800964741013,
      "grad_norm": 0.036612071096897125,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 15.01579761505127,
      "logits/rejected": 15.359031677246094,
      "logps/chosen": -0.2681262791156769,
      "logps/rejected": -0.31947994232177734,
      "loss": 0.9551,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.40218934416770935,
      "rewards/margins": 0.07703053951263428,
      "rewards/rejected": -0.479219913482666,
      "step": 10
    },
    {
      "epoch": 0.01837601929482026,
      "grad_norm": 0.05575725808739662,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.570712089538574,
      "logits/rejected": 15.321355819702148,
      "logps/chosen": -0.2867889404296875,
      "logps/rejected": -0.3514837622642517,
      "loss": 0.923,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.43018341064453125,
      "rewards/margins": 0.09704220294952393,
      "rewards/rejected": -0.5272256135940552,
      "step": 20
    },
    {
      "epoch": 0.02756402894223039,
      "grad_norm": 0.0492466576397419,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.748420715332031,
      "logits/rejected": 14.969354629516602,
      "logps/chosen": -0.28405922651290894,
      "logps/rejected": -0.32855403423309326,
      "loss": 0.9357,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.426088809967041,
      "rewards/margins": 0.06674225628376007,
      "rewards/rejected": -0.4928310811519623,
      "step": 30
    },
    {
      "epoch": 0.03675203858964052,
      "grad_norm": 0.05719422921538353,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.28278923034668,
      "logits/rejected": 14.76964282989502,
      "logps/chosen": -0.27940627932548523,
      "logps/rejected": -0.3408831059932709,
      "loss": 0.9215,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.41910940408706665,
      "rewards/margins": 0.09221524000167847,
      "rewards/rejected": -0.5113246440887451,
      "step": 40
    },
    {
      "epoch": 0.04594004823705065,
      "grad_norm": 0.06247895210981369,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.943578720092773,
      "logits/rejected": 14.936178207397461,
      "logps/chosen": -0.2819541394710541,
      "logps/rejected": -0.3245392441749573,
      "loss": 0.9464,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.4229312539100647,
      "rewards/margins": 0.06387762725353241,
      "rewards/rejected": -0.4868088662624359,
      "step": 50
    },
    {
      "epoch": 0.04594004823705065,
      "eval_logits/chosen": 14.7594575881958,
      "eval_logits/rejected": 15.193694114685059,
      "eval_logps/chosen": -0.2807807922363281,
      "eval_logps/rejected": -0.36209535598754883,
      "eval_loss": 0.9397181868553162,
      "eval_rewards/accuracies": 0.5681818127632141,
      "eval_rewards/chosen": -0.4211711883544922,
      "eval_rewards/margins": 0.12197184562683105,
      "eval_rewards/rejected": -0.5431429743766785,
      "eval_runtime": 24.9762,
      "eval_samples_per_second": 28.187,
      "eval_steps_per_second": 3.523,
      "step": 50
    },
    {
      "epoch": 0.05512805788446078,
      "grad_norm": 0.11519577354192734,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 14.996228218078613,
      "logits/rejected": 15.37781810760498,
      "logps/chosen": -0.2809831202030182,
      "logps/rejected": -0.35486167669296265,
      "loss": 0.9318,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.4214746952056885,
      "rewards/margins": 0.1108178049325943,
      "rewards/rejected": -0.5322924852371216,
      "step": 60
    },
    {
      "epoch": 0.06431606753187091,
      "grad_norm": 0.06691388040781021,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.612454414367676,
      "logits/rejected": 15.678136825561523,
      "logps/chosen": -0.2569667100906372,
      "logps/rejected": -0.40047627687454224,
      "loss": 0.9158,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -0.3854501247406006,
      "rewards/margins": 0.21526429057121277,
      "rewards/rejected": -0.600714385509491,
      "step": 70
    },
    {
      "epoch": 0.07350407717928104,
      "grad_norm": 0.05976058170199394,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 14.873895645141602,
      "logits/rejected": 15.50474739074707,
      "logps/chosen": -0.28742527961730957,
      "logps/rejected": -0.37555089592933655,
      "loss": 0.9372,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.43113788962364197,
      "rewards/margins": 0.13218846917152405,
      "rewards/rejected": -0.5633264183998108,
      "step": 80
    },
    {
      "epoch": 0.08269208682669117,
      "grad_norm": 0.0602131113409996,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 14.356691360473633,
      "logits/rejected": 14.895658493041992,
      "logps/chosen": -0.2613506317138672,
      "logps/rejected": -0.3317110538482666,
      "loss": 0.9324,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.3920259475708008,
      "rewards/margins": 0.10554064810276031,
      "rewards/rejected": -0.4975665509700775,
      "step": 90
    },
    {
      "epoch": 0.0918800964741013,
      "grad_norm": 0.07126503437757492,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 14.862826347351074,
      "logits/rejected": 15.257089614868164,
      "logps/chosen": -0.2707213759422302,
      "logps/rejected": -0.3511395752429962,
      "loss": 0.9353,
      "rewards/accuracies": 0.637499988079071,
      "rewards/chosen": -0.4060820937156677,
      "rewards/margins": 0.1206272691488266,
      "rewards/rejected": -0.5267094373703003,
      "step": 100
    },
    {
      "epoch": 0.0918800964741013,
      "eval_logits/chosen": 14.664334297180176,
      "eval_logits/rejected": 15.113536834716797,
      "eval_logps/chosen": -0.2750833034515381,
      "eval_logps/rejected": -0.36540210247039795,
      "eval_loss": 0.9324077367782593,
      "eval_rewards/accuracies": 0.5795454382896423,
      "eval_rewards/chosen": -0.41262495517730713,
      "eval_rewards/margins": 0.1354781985282898,
      "eval_rewards/rejected": -0.5481031537055969,
      "eval_runtime": 24.4286,
      "eval_samples_per_second": 28.819,
      "eval_steps_per_second": 3.602,
      "step": 100
    },
    {
      "epoch": 0.10106810612151143,
      "grad_norm": 0.07136944681406021,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 14.942098617553711,
      "logits/rejected": 15.138586044311523,
      "logps/chosen": -0.2860812246799469,
      "logps/rejected": -0.36259371042251587,
      "loss": 0.934,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.42912182211875916,
      "rewards/margins": 0.11476878076791763,
      "rewards/rejected": -0.5438905954360962,
      "step": 110
    },
    {
      "epoch": 0.11025611576892155,
      "grad_norm": 0.07038908451795578,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 14.488851547241211,
      "logits/rejected": 14.702054023742676,
      "logps/chosen": -0.2662215232849121,
      "logps/rejected": -0.3013685941696167,
      "loss": 0.9202,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.39933228492736816,
      "rewards/margins": 0.05272058770060539,
      "rewards/rejected": -0.45205289125442505,
      "step": 120
    },
    {
      "epoch": 0.11944412541633169,
      "grad_norm": 0.06875801086425781,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 14.075657844543457,
      "logits/rejected": 14.696513175964355,
      "logps/chosen": -0.250360369682312,
      "logps/rejected": -0.3504650592803955,
      "loss": 0.9266,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.375540554523468,
      "rewards/margins": 0.15015706419944763,
      "rewards/rejected": -0.5256975889205933,
      "step": 130
    },
    {
      "epoch": 0.12863213506374183,
      "grad_norm": 0.0984601378440857,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 13.738212585449219,
      "logits/rejected": 14.311574935913086,
      "logps/chosen": -0.26711025834083557,
      "logps/rejected": -0.3587702810764313,
      "loss": 0.9185,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.40066537261009216,
      "rewards/margins": 0.13749003410339355,
      "rewards/rejected": -0.5381554365158081,
      "step": 140
    },
    {
      "epoch": 0.13782014471115195,
      "grad_norm": 0.10201425850391388,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 13.7462797164917,
      "logits/rejected": 14.230626106262207,
      "logps/chosen": -0.25559619069099426,
      "logps/rejected": -0.3708702623844147,
      "loss": 0.9106,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.3833943009376526,
      "rewards/margins": 0.17291104793548584,
      "rewards/rejected": -0.5563054084777832,
      "step": 150
    },
    {
      "epoch": 0.13782014471115195,
      "eval_logits/chosen": 13.458538055419922,
      "eval_logits/rejected": 13.998083114624023,
      "eval_logps/chosen": -0.2759075462818146,
      "eval_logps/rejected": -0.3873325288295746,
      "eval_loss": 0.9164085388183594,
      "eval_rewards/accuracies": 0.5795454382896423,
      "eval_rewards/chosen": -0.41386130452156067,
      "eval_rewards/margins": 0.1671374887228012,
      "eval_rewards/rejected": -0.5809988379478455,
      "eval_runtime": 24.4393,
      "eval_samples_per_second": 28.806,
      "eval_steps_per_second": 3.601,
      "step": 150
    },
    {
      "epoch": 0.14700815435856207,
      "grad_norm": 0.11537656933069229,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 12.686149597167969,
      "logits/rejected": 13.478736877441406,
      "logps/chosen": -0.23941929638385773,
      "logps/rejected": -0.3713286519050598,
      "loss": 0.9094,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.3591288924217224,
      "rewards/margins": 0.1978640854358673,
      "rewards/rejected": -0.5569929480552673,
      "step": 160
    },
    {
      "epoch": 0.1561961640059722,
      "grad_norm": 0.1196313351392746,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 13.221656799316406,
      "logits/rejected": 13.317082405090332,
      "logps/chosen": -0.3033878207206726,
      "logps/rejected": -0.3784424960613251,
      "loss": 0.9057,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4550817608833313,
      "rewards/margins": 0.11258199065923691,
      "rewards/rejected": -0.5676637887954712,
      "step": 170
    },
    {
      "epoch": 0.16538417365338234,
      "grad_norm": 0.18745549023151398,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 11.797627449035645,
      "logits/rejected": 12.031414985656738,
      "logps/chosen": -0.2746419608592987,
      "logps/rejected": -0.3629845976829529,
      "loss": 0.8954,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.41196292638778687,
      "rewards/margins": 0.13251398503780365,
      "rewards/rejected": -0.5444768667221069,
      "step": 180
    },
    {
      "epoch": 0.17457218330079247,
      "grad_norm": 0.1806156188249588,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 10.275301933288574,
      "logits/rejected": 10.937273025512695,
      "logps/chosen": -0.2880379557609558,
      "logps/rejected": -0.4154580533504486,
      "loss": 0.8875,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.43205690383911133,
      "rewards/margins": 0.19113019108772278,
      "rewards/rejected": -0.6231871247291565,
      "step": 190
    },
    {
      "epoch": 0.1837601929482026,
      "grad_norm": 0.1839464157819748,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 10.020039558410645,
      "logits/rejected": 10.66059398651123,
      "logps/chosen": -0.3136019706726074,
      "logps/rejected": -0.4385503828525543,
      "loss": 0.8647,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": -0.47040295600891113,
      "rewards/margins": 0.18742261826992035,
      "rewards/rejected": -0.6578255891799927,
      "step": 200
    },
    {
      "epoch": 0.1837601929482026,
      "eval_logits/chosen": 9.442557334899902,
      "eval_logits/rejected": 10.053345680236816,
      "eval_logps/chosen": -0.3080674409866333,
      "eval_logps/rejected": -0.4899139702320099,
      "eval_loss": 0.8702690005302429,
      "eval_rewards/accuracies": 0.6931818127632141,
      "eval_rewards/chosen": -0.46210116147994995,
      "eval_rewards/margins": 0.27276986837387085,
      "eval_rewards/rejected": -0.7348710894584656,
      "eval_runtime": 24.4185,
      "eval_samples_per_second": 28.831,
      "eval_steps_per_second": 3.604,
      "step": 200
    },
    {
      "epoch": 0.19294820259561274,
      "grad_norm": 0.269613116979599,
      "learning_rate": 4.762067631165049e-06,
      "logits/chosen": 7.941342353820801,
      "logits/rejected": 8.542920112609863,
      "logps/chosen": -0.3083941638469696,
      "logps/rejected": -0.5024437308311462,
      "loss": 0.8471,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.4625912606716156,
      "rewards/margins": 0.29107433557510376,
      "rewards/rejected": -0.7536656856536865,
      "step": 210
    },
    {
      "epoch": 0.20213621224302286,
      "grad_norm": 0.2640094459056854,
      "learning_rate": 4.7392794005985324e-06,
      "logits/chosen": 7.587499141693115,
      "logits/rejected": 7.592519283294678,
      "logps/chosen": -0.3381899893283844,
      "logps/rejected": -0.48494213819503784,
      "loss": 0.8427,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.5072849988937378,
      "rewards/margins": 0.22012826800346375,
      "rewards/rejected": -0.7274132966995239,
      "step": 220
    },
    {
      "epoch": 0.21132422189043298,
      "grad_norm": 0.29708293080329895,
      "learning_rate": 4.715508948078037e-06,
      "logits/chosen": 6.250656604766846,
      "logits/rejected": 6.7652716636657715,
      "logps/chosen": -0.3644888997077942,
      "logps/rejected": -0.5470594167709351,
      "loss": 0.8201,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.5467333793640137,
      "rewards/margins": 0.2738557755947113,
      "rewards/rejected": -0.8205891847610474,
      "step": 230
    },
    {
      "epoch": 0.2205122315378431,
      "grad_norm": 0.35299497842788696,
      "learning_rate": 4.690766700109659e-06,
      "logits/chosen": 4.6331706047058105,
      "logits/rejected": 4.710076332092285,
      "logps/chosen": -0.3634452223777771,
      "logps/rejected": -0.7193974256515503,
      "loss": 0.7877,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -0.545167863368988,
      "rewards/margins": 0.5339283347129822,
      "rewards/rejected": -1.0790963172912598,
      "step": 240
    },
    {
      "epoch": 0.22970024118525326,
      "grad_norm": 0.4265730082988739,
      "learning_rate": 4.665063509461098e-06,
      "logits/chosen": 4.992984771728516,
      "logits/rejected": 4.606354713439941,
      "logps/chosen": -0.413116455078125,
      "logps/rejected": -0.7104976177215576,
      "loss": 0.7902,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.6196746826171875,
      "rewards/margins": 0.4460717737674713,
      "rewards/rejected": -1.0657463073730469,
      "step": 250
    },
    {
      "epoch": 0.22970024118525326,
      "eval_logits/chosen": 4.127804279327393,
      "eval_logits/rejected": 3.742251396179199,
      "eval_logps/chosen": -0.420327365398407,
      "eval_logps/rejected": -0.7902651429176331,
      "eval_loss": 0.7682384252548218,
      "eval_rewards/accuracies": 0.7159090638160706,
      "eval_rewards/chosen": -0.6304910182952881,
      "eval_rewards/margins": 0.5549066662788391,
      "eval_rewards/rejected": -1.185397744178772,
      "eval_runtime": 24.4318,
      "eval_samples_per_second": 28.815,
      "eval_steps_per_second": 3.602,
      "step": 250
    },
    {
      "epoch": 0.23888825083266338,
      "grad_norm": 0.7236106395721436,
      "learning_rate": 4.638410650401267e-06,
      "logits/chosen": 2.454423427581787,
      "logits/rejected": 1.816563367843628,
      "logps/chosen": -0.4492695927619934,
      "logps/rejected": -0.8738088607788086,
      "loss": 0.6911,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.6739044189453125,
      "rewards/margins": 0.6368088126182556,
      "rewards/rejected": -1.3107131719589233,
      "step": 260
    },
    {
      "epoch": 0.2480762604800735,
      "grad_norm": 0.5856125950813293,
      "learning_rate": 4.610819813755038e-06,
      "logits/chosen": 3.2105612754821777,
      "logits/rejected": 2.5531132221221924,
      "logps/chosen": -0.537078320980072,
      "logps/rejected": -1.2025481462478638,
      "loss": 0.6774,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.80561763048172,
      "rewards/margins": 0.9982045888900757,
      "rewards/rejected": -1.8038222789764404,
      "step": 270
    },
    {
      "epoch": 0.25726427012748365,
      "grad_norm": 0.7396731972694397,
      "learning_rate": 4.582303101775249e-06,
      "logits/chosen": 2.0327231884002686,
      "logits/rejected": 1.4601097106933594,
      "logps/chosen": -0.47658151388168335,
      "logps/rejected": -1.3808696269989014,
      "loss": 0.628,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.7148722410202026,
      "rewards/margins": 1.3564319610595703,
      "rewards/rejected": -2.0713045597076416,
      "step": 280
    },
    {
      "epoch": 0.2664522797748938,
      "grad_norm": 2.412203550338745,
      "learning_rate": 4.55287302283426e-06,
      "logits/chosen": 1.2262591123580933,
      "logits/rejected": 0.22599482536315918,
      "logps/chosen": -0.5671601891517639,
      "logps/rejected": -1.6760343313217163,
      "loss": 0.5988,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -0.8507402539253235,
      "rewards/margins": 1.6633113622665405,
      "rewards/rejected": -2.5140514373779297,
      "step": 290
    },
    {
      "epoch": 0.2756402894223039,
      "grad_norm": 1.0477895736694336,
      "learning_rate": 4.522542485937369e-06,
      "logits/chosen": 1.9952911138534546,
      "logits/rejected": 1.1298446655273438,
      "logps/chosen": -0.6152974367141724,
      "logps/rejected": -2.128481388092041,
      "loss": 0.5927,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.9229460954666138,
      "rewards/margins": 2.2697763442993164,
      "rewards/rejected": -3.192722797393799,
      "step": 300
    },
    {
      "epoch": 0.2756402894223039,
      "eval_logits/chosen": 1.6342910528182983,
      "eval_logits/rejected": 0.633538007736206,
      "eval_logps/chosen": -0.606099545955658,
      "eval_logps/rejected": -1.882785439491272,
      "eval_loss": 0.5978505611419678,
      "eval_rewards/accuracies": 0.7159090638160706,
      "eval_rewards/chosen": -0.909149169921875,
      "eval_rewards/margins": 1.9150291681289673,
      "eval_rewards/rejected": -2.824178457260132,
      "eval_runtime": 24.4299,
      "eval_samples_per_second": 28.817,
      "eval_steps_per_second": 3.602,
      "step": 300
    },
    {
      "epoch": 0.284828299069714,
      "grad_norm": 3.0767388343811035,
      "learning_rate": 4.491324795060491e-06,
      "logits/chosen": 1.0374902486801147,
      "logits/rejected": 0.6220051646232605,
      "logps/chosen": -0.6778531074523926,
      "logps/rejected": -1.8290255069732666,
      "loss": 0.5792,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -1.0167796611785889,
      "rewards/margins": 1.726758599281311,
      "rewards/rejected": -2.7435383796691895,
      "step": 310
    },
    {
      "epoch": 0.29401630871712414,
      "grad_norm": 0.6015120148658752,
      "learning_rate": 4.4592336433146e-06,
      "logits/chosen": 1.0050956010818481,
      "logits/rejected": -0.016118621453642845,
      "logps/chosen": -0.6865260004997253,
      "logps/rejected": -2.113417148590088,
      "loss": 0.5384,
      "rewards/accuracies": 0.762499988079071,
      "rewards/chosen": -1.0297890901565552,
      "rewards/margins": 2.140336513519287,
      "rewards/rejected": -3.1701254844665527,
      "step": 320
    },
    {
      "epoch": 0.30320431836453426,
      "grad_norm": 0.7415631413459778,
      "learning_rate": 4.426283106939474e-06,
      "logits/chosen": 0.5536144971847534,
      "logits/rejected": -0.1644023358821869,
      "logps/chosen": -0.8181726336479187,
      "logps/rejected": -2.581185817718506,
      "loss": 0.5671,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -1.2272589206695557,
      "rewards/margins": 2.644519805908203,
      "rewards/rejected": -3.871778964996338,
      "step": 330
    },
    {
      "epoch": 0.3123923280119444,
      "grad_norm": 0.8956871628761292,
      "learning_rate": 4.3924876391293915e-06,
      "logits/chosen": 1.6062015295028687,
      "logits/rejected": 0.9243733286857605,
      "logps/chosen": -0.8991573452949524,
      "logps/rejected": -2.935060977935791,
      "loss": 0.5124,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -1.348736047744751,
      "rewards/margins": 3.0538551807403564,
      "rewards/rejected": -4.402591228485107,
      "step": 340
    },
    {
      "epoch": 0.32158033765935456,
      "grad_norm": 1.1822264194488525,
      "learning_rate": 4.357862063693486e-06,
      "logits/chosen": 1.8171085119247437,
      "logits/rejected": 1.228049397468567,
      "logps/chosen": -0.8822734951972961,
      "logps/rejected": -2.4744174480438232,
      "loss": 0.516,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -1.3234103918075562,
      "rewards/margins": 2.388216018676758,
      "rewards/rejected": -3.7116265296936035,
      "step": 350
    },
    {
      "epoch": 0.32158033765935456,
      "eval_logits/chosen": 1.1368330717086792,
      "eval_logits/rejected": 0.2795785665512085,
      "eval_logps/chosen": -0.9485350251197815,
      "eval_logps/rejected": -2.6484899520874023,
      "eval_loss": 0.5133901238441467,
      "eval_rewards/accuracies": 0.7727272510528564,
      "eval_rewards/chosen": -1.4228025674819946,
      "eval_rewards/margins": 2.5499324798583984,
      "eval_rewards/rejected": -3.9727354049682617,
      "eval_runtime": 24.4277,
      "eval_samples_per_second": 28.82,
      "eval_steps_per_second": 3.602,
      "step": 350
    },
    {
      "epoch": 0.3307683473067647,
      "grad_norm": 2.5278775691986084,
      "learning_rate": 4.322421568553529e-06,
      "logits/chosen": 1.1921958923339844,
      "logits/rejected": 0.7565670013427734,
      "logps/chosen": -1.4180412292480469,
      "logps/rejected": -3.0890870094299316,
      "loss": 0.4811,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -2.1270618438720703,
      "rewards/margins": 2.5065689086914062,
      "rewards/rejected": -4.633630752563477,
      "step": 360
    },
    {
      "epoch": 0.3399563569541748,
      "grad_norm": 1.7325788736343384,
      "learning_rate": 4.286181699082008e-06,
      "logits/chosen": 0.997096836566925,
      "logits/rejected": 0.4399908483028412,
      "logps/chosen": -1.9010308980941772,
      "logps/rejected": -3.6025185585021973,
      "loss": 0.4326,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -2.851546287536621,
      "rewards/margins": 2.552231550216675,
      "rewards/rejected": -5.403778076171875,
      "step": 370
    },
    {
      "epoch": 0.34914436660158493,
      "grad_norm": 4.608370304107666,
      "learning_rate": 4.249158351283414e-06,
      "logits/chosen": 1.0715999603271484,
      "logits/rejected": 0.6113725900650024,
      "logps/chosen": -2.4032845497131348,
      "logps/rejected": -3.9940528869628906,
      "loss": 0.4027,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -3.6049270629882812,
      "rewards/margins": 2.3861520290374756,
      "rewards/rejected": -5.991078853607178,
      "step": 380
    },
    {
      "epoch": 0.35833237624899505,
      "grad_norm": 4.600816249847412,
      "learning_rate": 4.211367764821722e-06,
      "logits/chosen": 1.4443682432174683,
      "logits/rejected": 0.8617011904716492,
      "logps/chosen": -2.349093198776245,
      "logps/rejected": -3.9943203926086426,
      "loss": 0.4118,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": -3.5236401557922363,
      "rewards/margins": 2.467839479446411,
      "rewards/rejected": -5.991480350494385,
      "step": 390
    },
    {
      "epoch": 0.3675203858964052,
      "grad_norm": 2.1458094120025635,
      "learning_rate": 4.172826515897146e-06,
      "logits/chosen": 1.3029582500457764,
      "logits/rejected": 0.7705980539321899,
      "logps/chosen": -2.192617416381836,
      "logps/rejected": -3.8413078784942627,
      "loss": 0.3557,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": -3.288925886154175,
      "rewards/margins": 2.4730350971221924,
      "rewards/rejected": -5.761960506439209,
      "step": 400
    },
    {
      "epoch": 0.3675203858964052,
      "eval_logits/chosen": 0.8742353320121765,
      "eval_logits/rejected": 0.14320053160190582,
      "eval_logps/chosen": -2.0894505977630615,
      "eval_logps/rejected": -4.20783805847168,
      "eval_loss": 0.4082850515842438,
      "eval_rewards/accuracies": 0.8863636255264282,
      "eval_rewards/chosen": -3.1341757774353027,
      "eval_rewards/margins": 3.1775810718536377,
      "eval_rewards/rejected": -6.311756610870361,
      "eval_runtime": 24.4316,
      "eval_samples_per_second": 28.815,
      "eval_steps_per_second": 3.602,
      "step": 400
    },
    {
      "epoch": 0.3767083955438153,
      "grad_norm": 2.5496387481689453,
      "learning_rate": 4.133551509975264e-06,
      "logits/chosen": 1.9024279117584229,
      "logits/rejected": 1.4777928590774536,
      "logps/chosen": -2.7541470527648926,
      "logps/rejected": -4.542642116546631,
      "loss": 0.4184,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -4.13122034072876,
      "rewards/margins": 2.6827428340911865,
      "rewards/rejected": -6.813962459564209,
      "step": 410
    },
    {
      "epoch": 0.3858964051912255,
      "grad_norm": 2.6187174320220947,
      "learning_rate": 4.093559974371725e-06,
      "logits/chosen": 1.9345887899398804,
      "logits/rejected": 1.4047685861587524,
      "logps/chosen": -2.389430522918701,
      "logps/rejected": -4.439882755279541,
      "loss": 0.4096,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -3.5841457843780518,
      "rewards/margins": 3.0756776332855225,
      "rewards/rejected": -6.659823417663574,
      "step": 420
    },
    {
      "epoch": 0.3950844148386356,
      "grad_norm": 3.762899398803711,
      "learning_rate": 4.052869450695776e-06,
      "logits/chosen": 1.2521915435791016,
      "logits/rejected": 0.7238092422485352,
      "logps/chosen": -2.5571534633636475,
      "logps/rejected": -4.675185203552246,
      "loss": 0.4083,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -3.835730791091919,
      "rewards/margins": 3.1770474910736084,
      "rewards/rejected": -7.012777805328369,
      "step": 430
    },
    {
      "epoch": 0.4042724244860457,
      "grad_norm": 3.2343404293060303,
      "learning_rate": 4.011497787155938e-06,
      "logits/chosen": 1.9626567363739014,
      "logits/rejected": 1.3136894702911377,
      "logps/chosen": -2.892967939376831,
      "logps/rejected": -5.003688335418701,
      "loss": 0.3783,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -4.339452266693115,
      "rewards/margins": 3.1660804748535156,
      "rewards/rejected": -7.505532264709473,
      "step": 440
    },
    {
      "epoch": 0.41346043413345585,
      "grad_norm": 3.2979824542999268,
      "learning_rate": 3.969463130731183e-06,
      "logits/chosen": 1.159234881401062,
      "logits/rejected": 0.5396692752838135,
      "logps/chosen": -2.7545204162597656,
      "logps/rejected": -5.4179182052612305,
      "loss": 0.347,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -4.131781101226807,
      "rewards/margins": 3.9950966835021973,
      "rewards/rejected": -8.126876831054688,
      "step": 450
    },
    {
      "epoch": 0.41346043413345585,
      "eval_logits/chosen": 0.9304068088531494,
      "eval_logits/rejected": 0.30015668272972107,
      "eval_logps/chosen": -2.485308885574341,
      "eval_logps/rejected": -4.880238056182861,
      "eval_loss": 0.36501914262771606,
      "eval_rewards/accuracies": 0.9204545617103577,
      "eval_rewards/chosen": -3.7279627323150635,
      "eval_rewards/margins": 3.592393636703491,
      "eval_rewards/rejected": -7.320356845855713,
      "eval_runtime": 24.4234,
      "eval_samples_per_second": 28.825,
      "eval_steps_per_second": 3.603,
      "step": 450
    },
    {
      "epoch": 0.42264844378086597,
      "grad_norm": 3.155860185623169,
      "learning_rate": 3.92678391921108e-06,
      "logits/chosen": 1.633522391319275,
      "logits/rejected": 1.0575059652328491,
      "logps/chosen": -2.7214303016662598,
      "logps/rejected": -4.766176223754883,
      "loss": 0.3689,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -4.082144737243652,
      "rewards/margins": 3.0671191215515137,
      "rewards/rejected": -7.149264335632324,
      "step": 460
    },
    {
      "epoch": 0.4318364534282761,
      "grad_norm": 2.9949357509613037,
      "learning_rate": 3.88347887310836e-06,
      "logits/chosen": 1.3139212131500244,
      "logits/rejected": 0.5838541388511658,
      "logps/chosen": -2.5324313640594482,
      "logps/rejected": -4.993292808532715,
      "loss": 0.3587,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -3.7986464500427246,
      "rewards/margins": 3.6912925243377686,
      "rewards/rejected": -7.489938259124756,
      "step": 470
    },
    {
      "epoch": 0.4410244630756862,
      "grad_norm": 2.4548208713531494,
      "learning_rate": 3.839566987447492e-06,
      "logits/chosen": 1.2342166900634766,
      "logits/rejected": 0.8118699193000793,
      "logps/chosen": -2.876863479614258,
      "logps/rejected": -5.457588195800781,
      "loss": 0.2922,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/chosen": -4.315295219421387,
      "rewards/margins": 3.871086597442627,
      "rewards/rejected": -8.186381340026855,
      "step": 480
    },
    {
      "epoch": 0.45021247272309634,
      "grad_norm": 2.0953762531280518,
      "learning_rate": 3.795067523432826e-06,
      "logits/chosen": 1.8121936321258545,
      "logits/rejected": 1.454637050628662,
      "logps/chosen": -3.2022106647491455,
      "logps/rejected": -5.47930908203125,
      "loss": 0.3086,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -4.803316116333008,
      "rewards/margins": 3.4156479835510254,
      "rewards/rejected": -8.218963623046875,
      "step": 490
    },
    {
      "epoch": 0.4594004823705065,
      "grad_norm": 2.4918301105499268,
      "learning_rate": 3.7500000000000005e-06,
      "logits/chosen": 1.5386875867843628,
      "logits/rejected": 1.2544763088226318,
      "logps/chosen": -3.2174277305603027,
      "logps/rejected": -6.012864112854004,
      "loss": 0.3128,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -4.826140880584717,
      "rewards/margins": 4.193154335021973,
      "rewards/rejected": -9.019296646118164,
      "step": 500
    },
    {
      "epoch": 0.4594004823705065,
      "eval_logits/chosen": 0.8257808685302734,
      "eval_logits/rejected": 0.27475622296333313,
      "eval_logps/chosen": -2.755974054336548,
      "eval_logps/rejected": -5.469714641571045,
      "eval_loss": 0.32884541153907776,
      "eval_rewards/accuracies": 0.9204545617103577,
      "eval_rewards/chosen": -4.133961200714111,
      "eval_rewards/margins": 4.070610523223877,
      "eval_rewards/rejected": -8.204572677612305,
      "eval_runtime": 24.4191,
      "eval_samples_per_second": 28.83,
      "eval_steps_per_second": 3.604,
      "step": 500
    },
    {
      "epoch": 0.46858849201791664,
      "grad_norm": 4.017474174499512,
      "learning_rate": 3.7043841852542884e-06,
      "logits/chosen": 1.8042447566986084,
      "logits/rejected": 1.4390740394592285,
      "logps/chosen": -3.4311797618865967,
      "logps/rejected": -6.114380359649658,
      "loss": 0.335,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.1467695236206055,
      "rewards/margins": 4.0248003005981445,
      "rewards/rejected": -9.171568870544434,
      "step": 510
    },
    {
      "epoch": 0.47777650166532676,
      "grad_norm": 5.516397953033447,
      "learning_rate": 3.658240087799655e-06,
      "logits/chosen": 1.1141811609268188,
      "logits/rejected": 0.7766789197921753,
      "logps/chosen": -3.1831612586975098,
      "logps/rejected": -5.615653991699219,
      "loss": 0.3306,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -4.774742603302002,
      "rewards/margins": 3.6487393379211426,
      "rewards/rejected": -8.423480987548828,
      "step": 520
    },
    {
      "epoch": 0.4869645113127369,
      "grad_norm": 4.1005635261535645,
      "learning_rate": 3.611587947962319e-06,
      "logits/chosen": 1.5796890258789062,
      "logits/rejected": 1.1561863422393799,
      "logps/chosen": -3.286179304122925,
      "logps/rejected": -5.805339813232422,
      "loss": 0.3151,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -4.929268836975098,
      "rewards/margins": 3.778740644454956,
      "rewards/rejected": -8.708009719848633,
      "step": 530
    },
    {
      "epoch": 0.496152520960147,
      "grad_norm": 2.8616511821746826,
      "learning_rate": 3.564448228912682e-06,
      "logits/chosen": 0.6956934928894043,
      "logits/rejected": 0.1268310248851776,
      "logps/chosen": -2.8933937549591064,
      "logps/rejected": -5.794272422790527,
      "loss": 0.2995,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -4.340090274810791,
      "rewards/margins": 4.351318836212158,
      "rewards/rejected": -8.691408157348633,
      "step": 540
    },
    {
      "epoch": 0.5053405306075571,
      "grad_norm": 2.237276315689087,
      "learning_rate": 3.516841607689501e-06,
      "logits/chosen": 1.7460235357284546,
      "logits/rejected": 0.9990445375442505,
      "logps/chosen": -2.860546827316284,
      "logps/rejected": -5.517810821533203,
      "loss": 0.3203,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -4.290820121765137,
      "rewards/margins": 3.985896348953247,
      "rewards/rejected": -8.276716232299805,
      "step": 550
    },
    {
      "epoch": 0.5053405306075571,
      "eval_logits/chosen": 0.8703196048736572,
      "eval_logits/rejected": 0.3152187466621399,
      "eval_logps/chosen": -2.709866523742676,
      "eval_logps/rejected": -5.687611103057861,
      "eval_loss": 0.304200142621994,
      "eval_rewards/accuracies": 0.9204545617103577,
      "eval_rewards/chosen": -4.064799785614014,
      "eval_rewards/margins": 4.466617107391357,
      "eval_rewards/rejected": -8.531416893005371,
      "eval_runtime": 24.6083,
      "eval_samples_per_second": 28.608,
      "eval_steps_per_second": 3.576,
      "step": 550
    },
    {
      "epoch": 0.5145285402549673,
      "grad_norm": 3.7983174324035645,
      "learning_rate": 3.4687889661302577e-06,
      "logits/chosen": 1.084142804145813,
      "logits/rejected": 0.9131366610527039,
      "logps/chosen": -3.4958484172821045,
      "logps/rejected": -7.143038749694824,
      "loss": 0.2728,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/chosen": -5.243772506713867,
      "rewards/margins": 5.470786094665527,
      "rewards/rejected": -10.714558601379395,
      "step": 560
    },
    {
      "epoch": 0.5237165499023774,
      "grad_norm": 2.398188829421997,
      "learning_rate": 3.4203113817116955e-06,
      "logits/chosen": 1.2777886390686035,
      "logits/rejected": 0.6827106475830078,
      "logps/chosen": -3.4014134407043457,
      "logps/rejected": -6.260494232177734,
      "loss": 0.2833,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -5.102120399475098,
      "rewards/margins": 4.288620948791504,
      "rewards/rejected": -9.390741348266602,
      "step": 570
    },
    {
      "epoch": 0.5329045595497875,
      "grad_norm": 4.97003173828125,
      "learning_rate": 3.3714301183045382e-06,
      "logits/chosen": 1.6978384256362915,
      "logits/rejected": 1.1092720031738281,
      "logps/chosen": -3.179011106491089,
      "logps/rejected": -6.802459716796875,
      "loss": 0.2942,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -4.768516540527344,
      "rewards/margins": 5.435172080993652,
      "rewards/rejected": -10.203688621520996,
      "step": 580
    },
    {
      "epoch": 0.5420925691971976,
      "grad_norm": 4.482264995574951,
      "learning_rate": 3.3221666168464584e-06,
      "logits/chosen": 1.0245933532714844,
      "logits/rejected": 0.7797524929046631,
      "logps/chosen": -3.2393958568573,
      "logps/rejected": -5.916412353515625,
      "loss": 0.3347,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -4.859094142913818,
      "rewards/margins": 4.015524864196777,
      "rewards/rejected": -8.874618530273438,
      "step": 590
    },
    {
      "epoch": 0.5512805788446078,
      "grad_norm": 3.913116931915283,
      "learning_rate": 3.272542485937369e-06,
      "logits/chosen": 1.3320618867874146,
      "logits/rejected": 0.9762558937072754,
      "logps/chosen": -3.2751450538635254,
      "logps/rejected": -6.7808518409729,
      "loss": 0.2776,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -4.912716865539551,
      "rewards/margins": 5.258560657501221,
      "rewards/rejected": -10.17127799987793,
      "step": 600
    },
    {
      "epoch": 0.5512805788446078,
      "eval_logits/chosen": 0.9448758959770203,
      "eval_logits/rejected": 0.42817041277885437,
      "eval_logps/chosen": -2.835143804550171,
      "eval_logps/rejected": -6.087582588195801,
      "eval_loss": 0.28658536076545715,
      "eval_rewards/accuracies": 0.9204545617103577,
      "eval_rewards/chosen": -4.252715587615967,
      "eval_rewards/margins": 4.878659248352051,
      "eval_rewards/rejected": -9.13137435913086,
      "eval_runtime": 24.4325,
      "eval_samples_per_second": 28.814,
      "eval_steps_per_second": 3.602,
      "step": 600
    },
    {
      "epoch": 0.560468588492018,
      "grad_norm": 3.8335089683532715,
      "learning_rate": 3.222579492361179e-06,
      "logits/chosen": 1.295569658279419,
      "logits/rejected": 1.0852326154708862,
      "logps/chosen": -3.4870052337646484,
      "logps/rejected": -6.572986602783203,
      "loss": 0.3243,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -5.230508327484131,
      "rewards/margins": 4.628971576690674,
      "rewards/rejected": -9.859478950500488,
      "step": 610
    },
    {
      "epoch": 0.569656598139428,
      "grad_norm": 3.095102071762085,
      "learning_rate": 3.1722995515381644e-06,
      "logits/chosen": 1.8339803218841553,
      "logits/rejected": 1.467551589012146,
      "logps/chosen": -3.6670470237731934,
      "logps/rejected": -6.880410194396973,
      "loss": 0.2615,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -5.500569820404053,
      "rewards/margins": 4.820044040679932,
      "rewards/rejected": -10.3206148147583,
      "step": 620
    },
    {
      "epoch": 0.5788446077868382,
      "grad_norm": 4.381973743438721,
      "learning_rate": 3.121724717912138e-06,
      "logits/chosen": 2.390763521194458,
      "logits/rejected": 2.155505418777466,
      "logps/chosen": -3.3569788932800293,
      "logps/rejected": -6.319291114807129,
      "loss": 0.2649,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -5.035468101501465,
      "rewards/margins": 4.4434685707092285,
      "rewards/rejected": -9.478937149047852,
      "step": 630
    },
    {
      "epoch": 0.5880326174342483,
      "grad_norm": 3.9204964637756348,
      "learning_rate": 3.0708771752766397e-06,
      "logits/chosen": 1.4343383312225342,
      "logits/rejected": 1.1991338729858398,
      "logps/chosen": -3.654259443283081,
      "logps/rejected": -6.873109340667725,
      "loss": 0.2761,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -5.481389045715332,
      "rewards/margins": 4.828273773193359,
      "rewards/rejected": -10.309663772583008,
      "step": 640
    },
    {
      "epoch": 0.5972206270816585,
      "grad_norm": 3.179067373275757,
      "learning_rate": 3.019779227044398e-06,
      "logits/chosen": 2.0368576049804688,
      "logits/rejected": 1.8037185668945312,
      "logps/chosen": -3.791682720184326,
      "logps/rejected": -6.912911415100098,
      "loss": 0.2739,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.68752384185791,
      "rewards/margins": 4.68184232711792,
      "rewards/rejected": -10.369367599487305,
      "step": 650
    },
    {
      "epoch": 0.5972206270816585,
      "eval_logits/chosen": 1.0889618396759033,
      "eval_logits/rejected": 0.5887767672538757,
      "eval_logps/chosen": -3.0191192626953125,
      "eval_logps/rejected": -6.388964653015137,
      "eval_loss": 0.27443525195121765,
      "eval_rewards/accuracies": 0.9204545617103577,
      "eval_rewards/chosen": -4.528679370880127,
      "eval_rewards/margins": 5.054768085479736,
      "eval_rewards/rejected": -9.583446502685547,
      "eval_runtime": 24.4235,
      "eval_samples_per_second": 28.825,
      "eval_steps_per_second": 3.603,
      "step": 650
    },
    {
      "epoch": 0.6064086367290685,
      "grad_norm": 2.804940700531006,
      "learning_rate": 2.9684532864643123e-06,
      "logits/chosen": 1.8347485065460205,
      "logits/rejected": 1.3636573553085327,
      "logps/chosen": -3.398799419403076,
      "logps/rejected": -6.337627410888672,
      "loss": 0.2678,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": -5.098199367523193,
      "rewards/margins": 4.408241271972656,
      "rewards/rejected": -9.506441116333008,
      "step": 660
    },
    {
      "epoch": 0.6155966463764787,
      "grad_norm": 3.7368969917297363,
      "learning_rate": 2.9169218667902562e-06,
      "logits/chosen": 1.6734691858291626,
      "logits/rejected": 1.0945308208465576,
      "logps/chosen": -3.354790210723877,
      "logps/rejected": -6.3691864013671875,
      "loss": 0.294,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.0321855545043945,
      "rewards/margins": 4.521594524383545,
      "rewards/rejected": -9.553780555725098,
      "step": 670
    },
    {
      "epoch": 0.6247846560238888,
      "grad_norm": 4.483130931854248,
      "learning_rate": 2.8652075714060296e-06,
      "logits/chosen": 1.640228509902954,
      "logits/rejected": 1.1519067287445068,
      "logps/chosen": -3.4700570106506348,
      "logps/rejected": -6.6276445388793945,
      "loss": 0.23,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.205085277557373,
      "rewards/margins": 4.736380577087402,
      "rewards/rejected": -9.941465377807617,
      "step": 680
    },
    {
      "epoch": 0.633972665671299,
      "grad_norm": 8.508203506469727,
      "learning_rate": 2.813333083910761e-06,
      "logits/chosen": 1.0501906871795654,
      "logits/rejected": 0.5691097974777222,
      "logps/chosen": -3.4982333183288574,
      "logps/rejected": -7.144225120544434,
      "loss": 0.2808,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.247350215911865,
      "rewards/margins": 5.468987464904785,
      "rewards/rejected": -10.716337203979492,
      "step": 690
    },
    {
      "epoch": 0.6431606753187091,
      "grad_norm": 2.271857738494873,
      "learning_rate": 2.761321158169134e-06,
      "logits/chosen": 1.2119544744491577,
      "logits/rejected": 0.7247776389122009,
      "logps/chosen": -4.096956253051758,
      "logps/rejected": -7.4536261558532715,
      "loss": 0.2808,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -6.145434379577637,
      "rewards/margins": 5.035003662109375,
      "rewards/rejected": -11.180438995361328,
      "step": 700
    },
    {
      "epoch": 0.6431606753187091,
      "eval_logits/chosen": 1.085008978843689,
      "eval_logits/rejected": 0.5991834998130798,
      "eval_logps/chosen": -3.179896354675293,
      "eval_logps/rejected": -6.738409519195557,
      "eval_loss": 0.26070258021354675,
      "eval_rewards/accuracies": 0.9090909361839294,
      "eval_rewards/chosen": -4.7698445320129395,
      "eval_rewards/margins": 5.337769031524658,
      "eval_rewards/rejected": -10.107613563537598,
      "eval_runtime": 24.465,
      "eval_samples_per_second": 28.776,
      "eval_steps_per_second": 3.597,
      "step": 700
    }
  ],
  "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": 1.7003924517279498e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}