{
  "best_global_step": 100,
  "best_metric": 0.04428481683135033,
  "best_model_checkpoint": "runs/dpo_run_14b_v1/checkpoint-100",
  "epoch": 0.11678832116788321,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023357664233576644,
      "grad_norm": 1.242694616317749,
      "learning_rate": 1.9379844961240311e-07,
      "logits/chosen": 5.179401397705078,
      "logits/rejected": 5.192930698394775,
      "logps/chosen": -368.911865234375,
      "logps/rejected": -398.83880615234375,
      "loss": 0.6931473016738892,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004671532846715329,
      "grad_norm": 1.392399787902832,
      "learning_rate": 5.813953488372093e-07,
      "logits/chosen": 5.403897762298584,
      "logits/rejected": 5.4565606117248535,
      "logps/chosen": -338.43792724609375,
      "logps/rejected": -367.03057861328125,
      "loss": 0.6949559450149536,
      "rewards/accuracies": 0.625,
      "rewards/chosen": 0.004504585638642311,
      "rewards/margins": -0.003222561441361904,
      "rewards/rejected": 0.007727146148681641,
      "step": 4
    },
    {
      "epoch": 0.0070072992700729924,
      "grad_norm": 1.066603183746338,
      "learning_rate": 9.689922480620155e-07,
      "logits/chosen": 5.291868209838867,
      "logits/rejected": 5.328356742858887,
      "logps/chosen": -362.3431701660156,
      "logps/rejected": -387.5829772949219,
      "loss": 0.689236581325531,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": -0.0034066196531057358,
      "rewards/margins": 0.008255671709775925,
      "rewards/rejected": -0.01166229322552681,
      "step": 6
    },
    {
      "epoch": 0.009343065693430658,
      "grad_norm": 1.0005714893341064,
      "learning_rate": 1.3565891472868218e-06,
      "logits/chosen": 5.323437690734863,
      "logits/rejected": 5.410858631134033,
      "logps/chosen": -379.9283447265625,
      "logps/rejected": -389.0852355957031,
      "loss": 0.6943775415420532,
      "rewards/accuracies": 0.375,
      "rewards/chosen": 0.014657974243164062,
      "rewards/margins": -0.0012350091710686684,
      "rewards/rejected": 0.015892982482910156,
      "step": 8
    },
    {
      "epoch": 0.01167883211678832,
      "grad_norm": 1.2461222410202026,
      "learning_rate": 1.744186046511628e-06,
      "logits/chosen": 5.435908317565918,
      "logits/rejected": 5.494542121887207,
      "logps/chosen": -363.2003479003906,
      "logps/rejected": -389.67376708984375,
      "loss": 0.693260908126831,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.028497030958533287,
      "rewards/margins": 0.00012636138126254082,
      "rewards/rejected": -0.028623390942811966,
      "step": 10
    },
    {
      "epoch": 0.014014598540145985,
      "grad_norm": 1.4030137062072754,
      "learning_rate": 2.131782945736434e-06,
      "logits/chosen": 5.3550801277160645,
      "logits/rejected": 5.375768661499023,
      "logps/chosen": -370.96429443359375,
      "logps/rejected": -402.4786071777344,
      "loss": 0.6882913112640381,
      "rewards/accuracies": 0.5,
      "rewards/chosen": 0.01622028276324272,
      "rewards/margins": 0.010086631402373314,
      "rewards/rejected": 0.006133650429546833,
      "step": 12
    },
    {
      "epoch": 0.01635036496350365,
      "grad_norm": 1.1157702207565308,
      "learning_rate": 2.5193798449612402e-06,
      "logits/chosen": 5.515308380126953,
      "logits/rejected": 5.561104774475098,
      "logps/chosen": -336.7254333496094,
      "logps/rejected": -357.52203369140625,
      "loss": 0.6896716356277466,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.017319394275546074,
      "rewards/margins": 0.007328510750085115,
      "rewards/rejected": -0.024647902697324753,
      "step": 14
    },
    {
      "epoch": 0.018686131386861315,
      "grad_norm": 0.9470655918121338,
      "learning_rate": 2.9069767441860468e-06,
      "logits/chosen": 5.553088665008545,
      "logits/rejected": 5.582851886749268,
      "logps/chosen": -415.6842041015625,
      "logps/rejected": -441.1054992675781,
      "loss": 0.6904245018959045,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": 0.03270244598388672,
      "rewards/margins": 0.005826758686453104,
      "rewards/rejected": 0.026875685900449753,
      "step": 16
    },
    {
      "epoch": 0.021021897810218976,
      "grad_norm": 1.4397331476211548,
      "learning_rate": 3.2945736434108533e-06,
      "logits/chosen": 5.440742015838623,
      "logits/rejected": 5.489529132843018,
      "logps/chosen": -392.46221923828125,
      "logps/rejected": -420.1712341308594,
      "loss": 0.683630108833313,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": 0.011020278558135033,
      "rewards/margins": 0.01951923407614231,
      "rewards/rejected": -0.008498954586684704,
      "step": 18
    },
    {
      "epoch": 0.02335766423357664,
      "grad_norm": 1.5941083431243896,
      "learning_rate": 3.6821705426356594e-06,
      "logits/chosen": 5.318347930908203,
      "logits/rejected": 5.397945404052734,
      "logps/chosen": -345.2221374511719,
      "logps/rejected": -365.9537048339844,
      "loss": 0.6902388334274292,
      "rewards/accuracies": 0.5625,
      "rewards/chosen": 0.006536484230309725,
      "rewards/margins": 0.006013393402099609,
      "rewards/rejected": 0.0005230908282101154,
      "step": 20
    },
    {
      "epoch": 0.025693430656934305,
      "grad_norm": 1.1363905668258667,
      "learning_rate": 4.0697674418604655e-06,
      "logits/chosen": 5.632981300354004,
      "logits/rejected": 5.7265520095825195,
      "logps/chosen": -347.9439697265625,
      "logps/rejected": -370.65777587890625,
      "loss": 0.691262423992157,
      "rewards/accuracies": 0.5,
      "rewards/chosen": 0.011908342130482197,
      "rewards/margins": 0.004538153763860464,
      "rewards/rejected": 0.007370188366621733,
      "step": 22
    },
    {
      "epoch": 0.02802919708029197,
      "grad_norm": 1.0684627294540405,
      "learning_rate": 4.457364341085272e-06,
      "logits/chosen": 5.35699987411499,
      "logits/rejected": 5.405580520629883,
      "logps/chosen": -347.1539001464844,
      "logps/rejected": -377.6044921875,
      "loss": 0.6769475936889648,
      "rewards/accuracies": 0.875,
      "rewards/chosen": 0.01244144607335329,
      "rewards/margins": 0.03289356082677841,
      "rewards/rejected": -0.020452119410037994,
      "step": 24
    },
    {
      "epoch": 0.029197080291970802,
      "eval_logits/chosen": 5.295141220092773,
      "eval_logits/rejected": 5.345211029052734,
      "eval_logps/chosen": -370.1607666015625,
      "eval_logps/rejected": -395.7251892089844,
      "eval_loss": 0.6836819648742676,
      "eval_rewards/accuracies": 0.665354311466217,
      "eval_rewards/chosen": 0.024636391550302505,
      "eval_rewards/margins": 0.019555427134037018,
      "eval_rewards/rejected": 0.005080964416265488,
      "eval_runtime": 454.4375,
      "eval_samples_per_second": 1.677,
      "eval_steps_per_second": 1.677,
      "step": 25
    },
    {
      "epoch": 0.030364963503649634,
      "grad_norm": 1.592353105545044,
      "learning_rate": 4.844961240310078e-06,
      "logits/chosen": 5.157042026519775,
      "logits/rejected": 5.244912147521973,
      "logps/chosen": -387.54876708984375,
      "logps/rejected": -412.0630187988281,
      "loss": 0.6849788427352905,
      "rewards/accuracies": 0.625,
      "rewards/chosen": 0.026385309174656868,
      "rewards/margins": 0.016966437920928,
      "rewards/rejected": 0.009418869391083717,
      "step": 26
    },
    {
      "epoch": 0.0327007299270073,
      "grad_norm": 1.3181558847427368,
      "learning_rate": 5.232558139534884e-06,
      "logits/chosen": 5.545513153076172,
      "logits/rejected": 5.54400110244751,
      "logps/chosen": -360.41650390625,
      "logps/rejected": -391.2162170410156,
      "loss": 0.675189733505249,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": 0.045946408063173294,
      "rewards/margins": 0.03675585240125656,
      "rewards/rejected": 0.009190557524561882,
      "step": 28
    },
    {
      "epoch": 0.035036496350364967,
      "grad_norm": 1.443650722503662,
      "learning_rate": 5.620155038759691e-06,
      "logits/chosen": 5.136168003082275,
      "logits/rejected": 5.239327907562256,
      "logps/chosen": -378.6293640136719,
      "logps/rejected": -405.3665466308594,
      "loss": 0.6752142310142517,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": 0.04194517061114311,
      "rewards/margins": 0.03668833151459694,
      "rewards/rejected": 0.005256845150142908,
      "step": 30
    },
    {
      "epoch": 0.03737226277372263,
      "grad_norm": 1.379568338394165,
      "learning_rate": 6.007751937984497e-06,
      "logits/chosen": 5.411487579345703,
      "logits/rejected": 5.427243232727051,
      "logps/chosen": -358.5367736816406,
      "logps/rejected": -382.4181213378906,
      "loss": 0.6700581312179565,
      "rewards/accuracies": 0.875,
      "rewards/chosen": 0.06658173352479935,
      "rewards/margins": 0.047193337231874466,
      "rewards/rejected": 0.019388392567634583,
      "step": 32
    },
    {
      "epoch": 0.039708029197080295,
      "grad_norm": 1.3260451555252075,
      "learning_rate": 6.395348837209303e-06,
      "logits/chosen": 5.207217216491699,
      "logits/rejected": 5.254848480224609,
      "logps/chosen": -326.9423828125,
      "logps/rejected": -346.52081298828125,
      "loss": 0.6610866785049438,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 0.07038869708776474,
      "rewards/margins": 0.06587495654821396,
      "rewards/rejected": 0.0045137410052120686,
      "step": 34
    },
    {
      "epoch": 0.04204379562043795,
      "grad_norm": 1.5776340961456299,
      "learning_rate": 6.782945736434108e-06,
      "logits/chosen": 5.550538063049316,
      "logits/rejected": 5.6374335289001465,
      "logps/chosen": -359.9613952636719,
      "logps/rejected": -384.31683349609375,
      "loss": 0.6281551718711853,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.11738375574350357,
      "rewards/margins": 0.1363767683506012,
      "rewards/rejected": -0.018992995843291283,
      "step": 36
    },
    {
      "epoch": 0.04437956204379562,
      "grad_norm": 1.8589071035385132,
      "learning_rate": 7.170542635658915e-06,
      "logits/chosen": 5.39143180847168,
      "logits/rejected": 5.412029266357422,
      "logps/chosen": -325.8544616699219,
      "logps/rejected": -351.9772644042969,
      "loss": 0.6270830631256104,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 0.1617884635925293,
      "rewards/margins": 0.1388537436723709,
      "rewards/rejected": 0.022934721782803535,
      "step": 38
    },
    {
      "epoch": 0.04671532846715328,
      "grad_norm": 1.3231571912765503,
      "learning_rate": 7.558139534883721e-06,
      "logits/chosen": 5.189720153808594,
      "logits/rejected": 5.203127384185791,
      "logps/chosen": -343.3839111328125,
      "logps/rejected": -374.7848205566406,
      "loss": 0.641180157661438,
      "rewards/accuracies": 0.875,
      "rewards/chosen": 0.15248623490333557,
      "rewards/margins": 0.11158552765846252,
      "rewards/rejected": 0.04090070724487305,
      "step": 40
    },
    {
      "epoch": 0.049051094890510946,
      "grad_norm": 2.5331315994262695,
      "learning_rate": 7.945736434108528e-06,
      "logits/chosen": 5.420182228088379,
      "logits/rejected": 5.45302677154541,
      "logps/chosen": -341.813720703125,
      "logps/rejected": -372.44952392578125,
      "loss": 0.6093671321868896,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 0.2898235321044922,
      "rewards/margins": 0.18158456683158875,
      "rewards/rejected": 0.10823898762464523,
      "step": 42
    },
    {
      "epoch": 0.05138686131386861,
      "grad_norm": 1.5247384309768677,
      "learning_rate": 8.333333333333334e-06,
      "logits/chosen": 5.383636951446533,
      "logits/rejected": 5.397551536560059,
      "logps/chosen": -354.49627685546875,
      "logps/rejected": -376.88818359375,
      "loss": 0.5815833210945129,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": 0.32459571957588196,
      "rewards/margins": 0.2510552406311035,
      "rewards/rejected": 0.07354050129652023,
      "step": 44
    },
    {
      "epoch": 0.053722627737226275,
      "grad_norm": 2.0814144611358643,
      "learning_rate": 8.72093023255814e-06,
      "logits/chosen": 5.269731044769287,
      "logits/rejected": 5.287116050720215,
      "logps/chosen": -331.1025390625,
      "logps/rejected": -362.90118408203125,
      "loss": 0.5269681215286255,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 0.6465227603912354,
      "rewards/margins": 0.37582656741142273,
      "rewards/rejected": 0.27069616317749023,
      "step": 46
    },
    {
      "epoch": 0.05605839416058394,
      "grad_norm": 1.769063115119934,
      "learning_rate": 9.108527131782946e-06,
      "logits/chosen": 5.472540855407715,
      "logits/rejected": 5.465417861938477,
      "logps/chosen": -369.40283203125,
      "logps/rejected": -400.18438720703125,
      "loss": 0.5066201686859131,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.6377636194229126,
      "rewards/margins": 0.42650213837623596,
      "rewards/rejected": 0.21126146614551544,
      "step": 48
    },
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 2.84169602394104,
      "learning_rate": 9.496124031007753e-06,
      "logits/chosen": 5.050387382507324,
      "logits/rejected": 5.112288951873779,
      "logps/chosen": -363.4556579589844,
      "logps/rejected": -397.8169860839844,
      "loss": 0.529259979724884,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.7923164367675781,
      "rewards/margins": 0.3787059783935547,
      "rewards/rejected": 0.4136104881763458,
      "step": 50
    },
    {
      "epoch": 0.058394160583941604,
      "eval_logits/chosen": 5.22359037399292,
      "eval_logits/rejected": 5.286833763122559,
      "eval_logps/chosen": -361.462890625,
      "eval_logps/rejected": -392.5708312988281,
      "eval_loss": 0.4610801041126251,
      "eval_rewards/accuracies": 0.9619422554969788,
      "eval_rewards/chosen": 0.8944254517555237,
      "eval_rewards/margins": 0.5739086270332336,
      "eval_rewards/rejected": 0.3205168545246124,
      "eval_runtime": 454.5598,
      "eval_samples_per_second": 1.676,
      "eval_steps_per_second": 1.676,
      "step": 50
    },
    {
      "epoch": 0.06072992700729927,
      "grad_norm": 1.6907895803451538,
      "learning_rate": 9.883720930232558e-06,
      "logits/chosen": 5.486469268798828,
      "logits/rejected": 5.541717529296875,
      "logps/chosen": -343.4534606933594,
      "logps/rejected": -379.39508056640625,
      "loss": 0.44602835178375244,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 0.9869746565818787,
      "rewards/margins": 0.6056646108627319,
      "rewards/rejected": 0.3813100755214691,
      "step": 52
    },
    {
      "epoch": 0.06306569343065693,
      "grad_norm": 1.9458682537078857,
      "learning_rate": 1.0271317829457365e-05,
      "logits/chosen": 5.169528961181641,
      "logits/rejected": 5.2688751220703125,
      "logps/chosen": -379.5437316894531,
      "logps/rejected": -401.5587463378906,
      "loss": 0.43609702587127686,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.7794930934906006,
      "rewards/margins": 0.6265671253204346,
      "rewards/rejected": 0.15292587876319885,
      "step": 54
    },
    {
      "epoch": 0.0654014598540146,
      "grad_norm": 2.1266520023345947,
      "learning_rate": 1.065891472868217e-05,
      "logits/chosen": 5.097426414489746,
      "logits/rejected": 5.15327262878418,
      "logps/chosen": -378.0788269042969,
      "logps/rejected": -413.27392578125,
      "loss": 0.3928414583206177,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 1.274291753768921,
      "rewards/margins": 0.7864217758178711,
      "rewards/rejected": 0.4878700375556946,
      "step": 56
    },
    {
      "epoch": 0.06773722627737226,
      "grad_norm": 1.5381489992141724,
      "learning_rate": 1.1046511627906977e-05,
      "logits/chosen": 5.138954162597656,
      "logits/rejected": 5.20254373550415,
      "logps/chosen": -372.93438720703125,
      "logps/rejected": -401.8287658691406,
      "loss": 0.35855019092559814,
      "rewards/accuracies": 0.875,
      "rewards/chosen": 1.2897911071777344,
      "rewards/margins": 0.9354276061058044,
      "rewards/rejected": 0.35436347126960754,
      "step": 58
    },
    {
      "epoch": 0.07007299270072993,
      "grad_norm": 2.358330726623535,
      "learning_rate": 1.1434108527131783e-05,
      "logits/chosen": 5.071888446807861,
      "logits/rejected": 5.187964916229248,
      "logps/chosen": -360.984619140625,
      "logps/rejected": -392.3192138671875,
      "loss": 0.42801612615585327,
      "rewards/accuracies": 0.875,
      "rewards/chosen": 1.3823509216308594,
      "rewards/margins": 0.729066014289856,
      "rewards/rejected": 0.6532848477363586,
      "step": 60
    },
    {
      "epoch": 0.07240875912408759,
      "grad_norm": 2.177586317062378,
      "learning_rate": 1.182170542635659e-05,
      "logits/chosen": 5.264093399047852,
      "logits/rejected": 5.310842990875244,
      "logps/chosen": -364.808349609375,
      "logps/rejected": -401.0321044921875,
      "loss": 0.31365492939949036,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.6637591123580933,
      "rewards/margins": 1.0887457132339478,
      "rewards/rejected": 0.5750135183334351,
      "step": 62
    },
    {
      "epoch": 0.07474452554744526,
      "grad_norm": 1.697789192199707,
      "learning_rate": 1.2209302325581395e-05,
      "logits/chosen": 5.191982269287109,
      "logits/rejected": 5.261416912078857,
      "logps/chosen": -359.8249816894531,
      "logps/rejected": -397.2122497558594,
      "loss": 0.3037749230861664,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.6470392942428589,
      "rewards/margins": 1.114844799041748,
      "rewards/rejected": 0.5321945548057556,
      "step": 64
    },
    {
      "epoch": 0.07708029197080292,
      "grad_norm": 1.3219914436340332,
      "learning_rate": 1.2596899224806202e-05,
      "logits/chosen": 5.293405532836914,
      "logits/rejected": 5.3094048500061035,
      "logps/chosen": -352.3752136230469,
      "logps/rejected": -392.6779479980469,
      "loss": 0.25026455521583557,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.5671364068984985,
      "rewards/margins": 1.4098074436187744,
      "rewards/rejected": 0.15732917189598083,
      "step": 66
    },
    {
      "epoch": 0.07941605839416059,
      "grad_norm": 1.8173967599868774,
      "learning_rate": 1.2984496124031009e-05,
      "logits/chosen": 5.025746822357178,
      "logits/rejected": 5.114965438842773,
      "logps/chosen": -319.99700927734375,
      "logps/rejected": -364.115234375,
      "loss": 0.3108353912830353,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 1.4788665771484375,
      "rewards/margins": 1.2637410163879395,
      "rewards/rejected": 0.2151254564523697,
      "step": 68
    },
    {
      "epoch": 0.08175182481751825,
      "grad_norm": 1.0658400058746338,
      "learning_rate": 1.3372093023255814e-05,
      "logits/chosen": 4.945235729217529,
      "logits/rejected": 4.959147930145264,
      "logps/chosen": -383.84033203125,
      "logps/rejected": -431.7752685546875,
      "loss": 0.22991834580898285,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3950352668762207,
      "rewards/margins": 1.4965243339538574,
      "rewards/rejected": -0.1014888733625412,
      "step": 70
    },
    {
      "epoch": 0.0840875912408759,
      "grad_norm": 1.0350896120071411,
      "learning_rate": 1.375968992248062e-05,
      "logits/chosen": 5.00426721572876,
      "logits/rejected": 5.120238780975342,
      "logps/chosen": -350.9471435546875,
      "logps/rejected": -382.6837158203125,
      "loss": 0.22603684663772583,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.2978975772857666,
      "rewards/margins": 1.644275426864624,
      "rewards/rejected": -0.34637776017189026,
      "step": 72
    },
    {
      "epoch": 0.08642335766423358,
      "grad_norm": 1.1595423221588135,
      "learning_rate": 1.4147286821705426e-05,
      "logits/chosen": 4.890130043029785,
      "logits/rejected": 4.9504714012146,
      "logps/chosen": -352.34967041015625,
      "logps/rejected": -399.23028564453125,
      "loss": 0.18921935558319092,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.1984589099884033,
      "rewards/margins": 1.7495291233062744,
      "rewards/rejected": -0.5510700941085815,
      "step": 74
    },
    {
      "epoch": 0.08759124087591241,
      "eval_logits/chosen": 4.930174827575684,
      "eval_logits/rejected": 5.032296657562256,
      "eval_logps/chosen": -359.19647216796875,
      "eval_logps/rejected": -405.1120300292969,
      "eval_loss": 0.16020436584949493,
      "eval_rewards/accuracies": 0.9960629940032959,
      "eval_rewards/chosen": 1.1210675239562988,
      "eval_rewards/margins": 2.0546727180480957,
      "eval_rewards/rejected": -0.9336051344871521,
      "eval_runtime": 454.3435,
      "eval_samples_per_second": 1.677,
      "eval_steps_per_second": 1.677,
      "step": 75
    },
    {
      "epoch": 0.08875912408759123,
      "grad_norm": 1.1433167457580566,
      "learning_rate": 1.4534883720930233e-05,
      "logits/chosen": 5.037275314331055,
      "logits/rejected": 5.1315507888793945,
      "logps/chosen": -313.110595703125,
      "logps/rejected": -356.1000061035156,
      "loss": 0.15998858213424683,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.2128857374191284,
      "rewards/margins": 2.0945115089416504,
      "rewards/rejected": -0.8816256523132324,
      "step": 76
    },
    {
      "epoch": 0.0910948905109489,
      "grad_norm": 0.9839214086532593,
      "learning_rate": 1.4922480620155039e-05,
      "logits/chosen": 4.817085266113281,
      "logits/rejected": 4.874035835266113,
      "logps/chosen": -366.2629089355469,
      "logps/rejected": -405.7989196777344,
      "loss": 0.1894684135913849,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.0605502128601074,
      "rewards/margins": 1.90762460231781,
      "rewards/rejected": -0.8470743894577026,
      "step": 78
    },
    {
      "epoch": 0.09343065693430656,
      "grad_norm": 0.9212782979011536,
      "learning_rate": 1.5310077519379846e-05,
      "logits/chosen": 5.046716690063477,
      "logits/rejected": 5.157979965209961,
      "logps/chosen": -348.0658264160156,
      "logps/rejected": -395.23870849609375,
      "loss": 0.15948188304901123,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.676516056060791,
      "rewards/margins": 2.167430877685547,
      "rewards/rejected": -1.4909145832061768,
      "step": 80
    },
    {
      "epoch": 0.09576642335766423,
      "grad_norm": 0.9820688366889954,
      "learning_rate": 1.569767441860465e-05,
      "logits/chosen": 4.690741539001465,
      "logits/rejected": 4.771791458129883,
      "logps/chosen": -378.8666076660156,
      "logps/rejected": -436.9100036621094,
      "loss": 0.12085139006376266,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.8719685077667236,
      "rewards/margins": 2.646538257598877,
      "rewards/rejected": -1.7745698690414429,
      "step": 82
    },
    {
      "epoch": 0.09810218978102189,
      "grad_norm": 0.66785728931427,
      "learning_rate": 1.608527131782946e-05,
      "logits/chosen": 4.880465984344482,
      "logits/rejected": 4.961792945861816,
      "logps/chosen": -346.51214599609375,
      "logps/rejected": -400.1110534667969,
      "loss": 0.08720710873603821,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.1337480545043945,
      "rewards/margins": 2.903944253921509,
      "rewards/rejected": -1.7701961994171143,
      "step": 84
    },
    {
      "epoch": 0.10043795620437956,
      "grad_norm": 0.5760660767555237,
      "learning_rate": 1.647286821705426e-05,
      "logits/chosen": 4.464397430419922,
      "logits/rejected": 4.680055618286133,
      "logps/chosen": -341.7489318847656,
      "logps/rejected": -398.322021484375,
      "loss": 0.07942983508110046,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.2459325790405273,
      "rewards/margins": 3.0152552127838135,
      "rewards/rejected": -1.7693227529525757,
      "step": 86
    },
    {
      "epoch": 0.10277372262773722,
      "grad_norm": 1.6020294427871704,
      "learning_rate": 1.686046511627907e-05,
      "logits/chosen": 4.563863277435303,
      "logits/rejected": 4.680974960327148,
      "logps/chosen": -344.9147644042969,
      "logps/rejected": -395.4453125,
      "loss": 0.1258174479007721,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": 1.0706769227981567,
      "rewards/margins": 3.118717670440674,
      "rewards/rejected": -2.0480403900146484,
      "step": 88
    },
    {
      "epoch": 0.10510948905109489,
      "grad_norm": 0.46413859724998474,
      "learning_rate": 1.7248062015503875e-05,
      "logits/chosen": 4.4989237785339355,
      "logits/rejected": 4.673248291015625,
      "logps/chosen": -326.9678649902344,
      "logps/rejected": -388.4164123535156,
      "loss": 0.06663060188293457,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.4128761291503906,
      "rewards/margins": 3.760685920715332,
      "rewards/rejected": -2.3478102684020996,
      "step": 90
    },
    {
      "epoch": 0.10744525547445255,
      "grad_norm": 0.6699568629264832,
      "learning_rate": 1.7635658914728684e-05,
      "logits/chosen": 4.7294535636901855,
      "logits/rejected": 4.813880920410156,
      "logps/chosen": -362.7267150878906,
      "logps/rejected": -439.2985534667969,
      "loss": 0.04481709748506546,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.477597713470459,
      "rewards/margins": 4.37883186340332,
      "rewards/rejected": -2.9012341499328613,
      "step": 92
    },
    {
      "epoch": 0.10978102189781022,
      "grad_norm": 0.4152977168560028,
      "learning_rate": 1.802325581395349e-05,
      "logits/chosen": 4.785149574279785,
      "logits/rejected": 4.891542434692383,
      "logps/chosen": -381.59246826171875,
      "logps/rejected": -444.2817687988281,
      "loss": 0.05632612109184265,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.71366286277771,
      "rewards/margins": 3.4584720134735107,
      "rewards/rejected": -2.744809150695801,
      "step": 94
    },
    {
      "epoch": 0.11211678832116788,
      "grad_norm": 0.3152717649936676,
      "learning_rate": 1.8410852713178295e-05,
      "logits/chosen": 4.603940486907959,
      "logits/rejected": 4.804995536804199,
      "logps/chosen": -356.7286376953125,
      "logps/rejected": -414.69635009765625,
      "loss": 0.040920041501522064,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7566397190093994,
      "rewards/margins": 4.020595550537109,
      "rewards/rejected": -2.263956069946289,
      "step": 96
    },
    {
      "epoch": 0.11445255474452555,
      "grad_norm": 0.37698569893836975,
      "learning_rate": 1.8798449612403103e-05,
      "logits/chosen": 4.558542728424072,
      "logits/rejected": 4.690641403198242,
      "logps/chosen": -339.794189453125,
      "logps/rejected": -413.8865966796875,
      "loss": 0.025794224813580513,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.3867536783218384,
      "rewards/margins": 4.6542744636535645,
      "rewards/rejected": -3.2675204277038574,
      "step": 98
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 0.15023073554039001,
      "learning_rate": 1.918604651162791e-05,
      "logits/chosen": 4.387497425079346,
      "logits/rejected": 4.494588375091553,
      "logps/chosen": -346.2568054199219,
      "logps/rejected": -418.9315185546875,
      "loss": 0.015155203640460968,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.7938623428344727,
      "rewards/margins": 4.942529201507568,
      "rewards/rejected": -3.1486666202545166,
      "step": 100
    },
    {
      "epoch": 0.11678832116788321,
      "eval_logits/chosen": 4.285891056060791,
      "eval_logits/rejected": 4.425926208496094,
      "eval_logps/chosen": -353.15850830078125,
      "eval_logps/rejected": -424.4124755859375,
      "eval_loss": 0.04428481683135033,
      "eval_rewards/accuracies": 0.9921259880065918,
      "eval_rewards/chosen": 1.7248634099960327,
      "eval_rewards/margins": 4.588510513305664,
      "eval_rewards/rejected": -2.863647222518921,
      "eval_runtime": 454.7251,
      "eval_samples_per_second": 1.676,
      "eval_steps_per_second": 1.676,
      "step": 100
    }
  ],
  "logging_steps": 2,
  "max_steps": 2571,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}