checkpoint-800/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0152380952380953,
  "eval_steps": 50,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 0.04658036306500435,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 15.106437683105469,
      "logits/rejected": 15.158523559570312,
      "logps/chosen": -0.30069679021835327,
      "logps/rejected": -0.30243945121765137,
      "loss": 0.9981,
      "rewards/accuracies": 0.3499999940395355,
      "rewards/chosen": -0.45104512572288513,
      "rewards/margins": 0.002613987773656845,
      "rewards/rejected": -0.45365914702415466,
      "step": 10
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 0.05173320695757866,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.680102348327637,
      "logits/rejected": 14.592491149902344,
      "logps/chosen": -0.3225177228450775,
      "logps/rejected": -0.27230435609817505,
      "loss": 0.9967,
      "rewards/accuracies": 0.26249998807907104,
      "rewards/chosen": -0.4837765693664551,
      "rewards/margins": -0.07532001286745071,
      "rewards/rejected": -0.40845656394958496,
      "step": 20
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.04962443560361862,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 15.399703979492188,
      "logits/rejected": 15.089459419250488,
      "logps/chosen": -0.2997470498085022,
      "logps/rejected": -0.28447264432907104,
      "loss": 0.9988,
      "rewards/accuracies": 0.3125,
      "rewards/chosen": -0.4496205747127533,
      "rewards/margins": -0.022911589592695236,
      "rewards/rejected": -0.42670899629592896,
      "step": 30
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 0.05171326920390129,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 15.099847793579102,
      "logits/rejected": 15.159170150756836,
      "logps/chosen": -0.29869550466537476,
      "logps/rejected": -0.2806033790111542,
      "loss": 0.9841,
      "rewards/accuracies": 0.375,
      "rewards/chosen": -0.44804325699806213,
      "rewards/margins": -0.02713816799223423,
      "rewards/rejected": -0.42090511322021484,
      "step": 40
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.048664532601833344,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 15.207334518432617,
      "logits/rejected": 15.135488510131836,
      "logps/chosen": -0.3121686577796936,
      "logps/rejected": -0.3194735050201416,
      "loss": 0.9953,
      "rewards/accuracies": 0.3499999940395355,
      "rewards/chosen": -0.468252956867218,
      "rewards/margins": 0.010957291349768639,
      "rewards/rejected": -0.47921022772789,
      "step": 50
    },
    {
      "epoch": 0.06349206349206349,
      "eval_logits/chosen": 15.441752433776855,
      "eval_logits/rejected": 15.288756370544434,
      "eval_logps/chosen": -0.33557233214378357,
      "eval_logps/rejected": -0.31198158860206604,
      "eval_loss": 0.9914231300354004,
      "eval_rewards/accuracies": 0.3125,
      "eval_rewards/chosen": -0.5033585429191589,
      "eval_rewards/margins": -0.03538615256547928,
      "eval_rewards/rejected": -0.46797239780426025,
      "eval_runtime": 19.0844,
      "eval_samples_per_second": 26.723,
      "eval_steps_per_second": 3.354,
      "step": 50
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.0722479596734047,
      "learning_rate": 4.980286753286196e-06,
      "logits/chosen": 15.281786918640137,
      "logits/rejected": 15.110156059265137,
      "logps/chosen": -0.30892473459243774,
      "logps/rejected": -0.26251715421676636,
      "loss": 1.0022,
      "rewards/accuracies": 0.25,
      "rewards/chosen": -0.4633871018886566,
      "rewards/margins": -0.0696113258600235,
      "rewards/rejected": -0.3937757611274719,
      "step": 60
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.07008200883865356,
      "learning_rate": 4.973180832407471e-06,
      "logits/chosen": 14.836176872253418,
      "logits/rejected": 14.98499584197998,
      "logps/chosen": -0.29483428597450256,
      "logps/rejected": -0.29870957136154175,
      "loss": 0.9849,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": -0.44225144386291504,
      "rewards/margins": 0.0058129094541072845,
      "rewards/rejected": -0.44806432723999023,
      "step": 70
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 0.06503555178642273,
      "learning_rate": 4.964990092676263e-06,
      "logits/chosen": 15.508198738098145,
      "logits/rejected": 15.592549324035645,
      "logps/chosen": -0.3066270351409912,
      "logps/rejected": -0.2757572531700134,
      "loss": 0.9886,
      "rewards/accuracies": 0.3125,
      "rewards/chosen": -0.45994052290916443,
      "rewards/margins": -0.046304650604724884,
      "rewards/rejected": -0.41363590955734253,
      "step": 80
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.10515156388282776,
      "learning_rate": 4.9557181268217225e-06,
      "logits/chosen": 15.301602363586426,
      "logits/rejected": 15.421157836914062,
      "logps/chosen": -0.31223705410957336,
      "logps/rejected": -0.29449179768562317,
      "loss": 0.981,
      "rewards/accuracies": 0.2750000059604645,
      "rewards/chosen": -0.46835556626319885,
      "rewards/margins": -0.02661792002618313,
      "rewards/rejected": -0.44173765182495117,
      "step": 90
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.05785346403717995,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": 16.00307846069336,
      "logits/rejected": 15.64977741241455,
      "logps/chosen": -0.32283931970596313,
      "logps/rejected": -0.28576889634132385,
      "loss": 0.9883,
      "rewards/accuracies": 0.2750000059604645,
      "rewards/chosen": -0.4842589795589447,
      "rewards/margins": -0.055605631321668625,
      "rewards/rejected": -0.42865338921546936,
      "step": 100
    },
    {
      "epoch": 0.12698412698412698,
      "eval_logits/chosen": 15.624425888061523,
      "eval_logits/rejected": 15.548928260803223,
      "eval_logps/chosen": -0.33450835943222046,
      "eval_logps/rejected": -0.31935107707977295,
      "eval_loss": 0.9836427569389343,
      "eval_rewards/accuracies": 0.359375,
      "eval_rewards/chosen": -0.5017625689506531,
      "eval_rewards/margins": -0.022735953330993652,
      "eval_rewards/rejected": -0.4790266156196594,
      "eval_runtime": 18.6768,
      "eval_samples_per_second": 27.307,
      "eval_steps_per_second": 3.427,
      "step": 100
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 0.08603859692811966,
      "learning_rate": 4.933947257182901e-06,
      "logits/chosen": 15.40850830078125,
      "logits/rejected": 15.258935928344727,
      "logps/chosen": -0.3209790587425232,
      "logps/rejected": -0.29926618933677673,
      "loss": 0.9852,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.4814685881137848,
      "rewards/margins": -0.03256931155920029,
      "rewards/rejected": -0.4488992691040039,
      "step": 110
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.13407552242279053,
      "learning_rate": 4.921457902821578e-06,
      "logits/chosen": 15.610095024108887,
      "logits/rejected": 15.964601516723633,
      "logps/chosen": -0.2977743446826935,
      "logps/rejected": -0.3102283179759979,
      "loss": 0.9839,
      "rewards/accuracies": 0.38749998807907104,
      "rewards/chosen": -0.4466615617275238,
      "rewards/margins": 0.018680967390537262,
      "rewards/rejected": -0.4653424620628357,
      "step": 120
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 0.1397980898618698,
      "learning_rate": 4.907906416994146e-06,
      "logits/chosen": 15.487627983093262,
      "logits/rejected": 15.767982482910156,
      "logps/chosen": -0.2769243121147156,
      "logps/rejected": -0.3168947100639343,
      "loss": 0.9737,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.415386438369751,
      "rewards/margins": 0.05995568633079529,
      "rewards/rejected": -0.47534212470054626,
      "step": 130
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.09849797189235687,
      "learning_rate": 4.893298743830168e-06,
      "logits/chosen": 15.779914855957031,
      "logits/rejected": 15.66816234588623,
      "logps/chosen": -0.2959491014480591,
      "logps/rejected": -0.3029848635196686,
      "loss": 0.9804,
      "rewards/accuracies": 0.375,
      "rewards/chosen": -0.4439236521720886,
      "rewards/margins": 0.010553586296737194,
      "rewards/rejected": -0.4544772207736969,
      "step": 140
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.08089074492454529,
      "learning_rate": 4.8776412907378845e-06,
      "logits/chosen": 15.029818534851074,
      "logits/rejected": 15.431653022766113,
      "logps/chosen": -0.2956623435020447,
      "logps/rejected": -0.3162347376346588,
      "loss": 0.9728,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.443493515253067,
      "rewards/margins": 0.030858617275953293,
      "rewards/rejected": -0.4743521809577942,
      "step": 150
    },
    {
      "epoch": 0.19047619047619047,
      "eval_logits/chosen": 15.575506210327148,
      "eval_logits/rejected": 15.54050064086914,
      "eval_logps/chosen": -0.3363308906555176,
      "eval_logps/rejected": -0.3436908721923828,
      "eval_loss": 0.9609583616256714,
      "eval_rewards/accuracies": 0.4375,
      "eval_rewards/chosen": -0.5044962763786316,
      "eval_rewards/margins": 0.01103996392339468,
      "eval_rewards/rejected": -0.5155363082885742,
      "eval_runtime": 18.6082,
      "eval_samples_per_second": 27.407,
      "eval_steps_per_second": 3.439,
      "step": 150
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 0.12168499082326889,
      "learning_rate": 4.860940925593703e-06,
      "logits/chosen": 15.47050952911377,
      "logits/rejected": 15.637664794921875,
      "logps/chosen": -0.32601848244667053,
      "logps/rejected": -0.35739919543266296,
      "loss": 0.9531,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.489027738571167,
      "rewards/margins": 0.04707105830311775,
      "rewards/rejected": -0.5360987782478333,
      "step": 160
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 0.12861700356006622,
      "learning_rate": 4.84320497372973e-06,
      "logits/chosen": 15.594339370727539,
      "logits/rejected": 15.680140495300293,
      "logps/chosen": -0.29271024465560913,
      "logps/rejected": -0.3383347690105438,
      "loss": 0.9386,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.4390653669834137,
      "rewards/margins": 0.06843684613704681,
      "rewards/rejected": -0.5075021982192993,
      "step": 170
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.10320646315813065,
      "learning_rate": 4.824441214720629e-06,
      "logits/chosen": 15.644658088684082,
      "logits/rejected": 15.526695251464844,
      "logps/chosen": -0.30950039625167847,
      "logps/rejected": -0.33660295605659485,
      "loss": 0.9313,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.46425050497055054,
      "rewards/margins": 0.04065385088324547,
      "rewards/rejected": -0.5049043893814087,
      "step": 180
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 0.29178574681282043,
      "learning_rate": 4.804657878971252e-06,
      "logits/chosen": 15.795066833496094,
      "logits/rejected": 15.640788078308105,
      "logps/chosen": -0.34224197268486023,
      "logps/rejected": -0.34523850679397583,
      "loss": 0.9406,
      "rewards/accuracies": 0.375,
      "rewards/chosen": -0.5133630037307739,
      "rewards/margins": 0.0044947536662220955,
      "rewards/rejected": -0.5178577303886414,
      "step": 190
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.15747429430484772,
      "learning_rate": 4.783863644106502e-06,
      "logits/chosen": 15.24070930480957,
      "logits/rejected": 15.132087707519531,
      "logps/chosen": -0.3026728630065918,
      "logps/rejected": -0.3765440583229065,
      "loss": 0.9031,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.4540092945098877,
      "rewards/margins": 0.11080671846866608,
      "rewards/rejected": -0.5648160576820374,
      "step": 200
    },
    {
      "epoch": 0.25396825396825395,
      "eval_logits/chosen": 15.073077201843262,
      "eval_logits/rejected": 15.098322868347168,
      "eval_logps/chosen": -0.3540771007537842,
      "eval_logps/rejected": -0.41381165385246277,
      "eval_loss": 0.9153187274932861,
      "eval_rewards/accuracies": 0.5,
      "eval_rewards/chosen": -0.5311156511306763,
      "eval_rewards/margins": 0.08960187435150146,
      "eval_rewards/rejected": -0.6207175254821777,
      "eval_runtime": 18.5936,
      "eval_samples_per_second": 27.429,
      "eval_steps_per_second": 3.442,
      "step": 200
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.9226244688034058,
      "learning_rate": 4.762067631165049e-06,
      "logits/chosen": 15.300783157348633,
      "logits/rejected": 15.6528902053833,
      "logps/chosen": -0.3110392093658447,
      "logps/rejected": -0.4790540635585785,
      "loss": 0.8977,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.4665588438510895,
      "rewards/margins": 0.25202232599258423,
      "rewards/rejected": -0.7185810804367065,
      "step": 210
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 0.187363401055336,
      "learning_rate": 4.7392794005985324e-06,
      "logits/chosen": 15.123028755187988,
      "logits/rejected": 14.940861701965332,
      "logps/chosen": -0.33024150133132935,
      "logps/rejected": -0.35755541920661926,
      "loss": 0.9074,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": -0.49536222219467163,
      "rewards/margins": 0.04097090661525726,
      "rewards/rejected": -0.5363331437110901,
      "step": 220
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 0.27345994114875793,
      "learning_rate": 4.715508948078037e-06,
      "logits/chosen": 14.54762077331543,
      "logits/rejected": 14.207303047180176,
      "logps/chosen": -0.2951691150665283,
      "logps/rejected": -0.41360992193222046,
      "loss": 0.896,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.4427536427974701,
      "rewards/margins": 0.1776612401008606,
      "rewards/rejected": -0.6204149723052979,
      "step": 230
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.20160575211048126,
      "learning_rate": 4.690766700109659e-06,
      "logits/chosen": 14.768750190734863,
      "logits/rejected": 14.940885543823242,
      "logps/chosen": -0.3044833838939667,
      "logps/rejected": -0.4275297224521637,
      "loss": 0.891,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.4567251205444336,
      "rewards/margins": 0.18456946313381195,
      "rewards/rejected": -0.6412945985794067,
      "step": 240
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.9059060215950012,
      "learning_rate": 4.665063509461098e-06,
      "logits/chosen": 14.839933395385742,
      "logits/rejected": 14.69981861114502,
      "logps/chosen": -0.3137063980102539,
      "logps/rejected": -0.49661844968795776,
      "loss": 0.8621,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.47055959701538086,
      "rewards/margins": 0.2743679881095886,
      "rewards/rejected": -0.7449275851249695,
      "step": 250
    },
    {
      "epoch": 0.31746031746031744,
      "eval_logits/chosen": 14.19374942779541,
      "eval_logits/rejected": 14.215425491333008,
      "eval_logps/chosen": -0.3999108076095581,
      "eval_logps/rejected": -0.7892026305198669,
      "eval_loss": 0.7948001623153687,
      "eval_rewards/accuracies": 0.53125,
      "eval_rewards/chosen": -0.5998662114143372,
      "eval_rewards/margins": 0.5839377641677856,
      "eval_rewards/rejected": -1.1838040351867676,
      "eval_runtime": 18.6098,
      "eval_samples_per_second": 27.405,
      "eval_steps_per_second": 3.439,
      "step": 250
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 0.8104033470153809,
      "learning_rate": 4.638410650401267e-06,
      "logits/chosen": 14.144885063171387,
      "logits/rejected": 14.350593566894531,
      "logps/chosen": -0.3469873368740082,
      "logps/rejected": -0.8288809657096863,
      "loss": 0.7939,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.5204810500144958,
      "rewards/margins": 0.7228401899337769,
      "rewards/rejected": -1.243321418762207,
      "step": 260
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.39150306582450867,
      "learning_rate": 4.610819813755038e-06,
      "logits/chosen": 14.15583324432373,
      "logits/rejected": 13.783352851867676,
      "logps/chosen": -0.34353378415107727,
      "logps/rejected": -1.1232259273529053,
      "loss": 0.7635,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.5153006911277771,
      "rewards/margins": 1.1695382595062256,
      "rewards/rejected": -1.684838891029358,
      "step": 270
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.1740872859954834,
      "learning_rate": 4.582303101775249e-06,
      "logits/chosen": 13.705289840698242,
      "logits/rejected": 13.493337631225586,
      "logps/chosen": -0.35998308658599854,
      "logps/rejected": -1.3943986892700195,
      "loss": 0.7678,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.539974570274353,
      "rewards/margins": 1.5516235828399658,
      "rewards/rejected": -2.0915980339050293,
      "step": 280
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 0.22531260550022125,
      "learning_rate": 4.55287302283426e-06,
      "logits/chosen": 13.186914443969727,
      "logits/rejected": 13.140413284301758,
      "logps/chosen": -0.3548193573951721,
      "logps/rejected": -1.2321991920471191,
      "loss": 0.7719,
      "rewards/accuracies": 0.5874999761581421,
      "rewards/chosen": -0.5322290062904358,
      "rewards/margins": 1.3160697221755981,
      "rewards/rejected": -1.8482987880706787,
      "step": 290
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.5229180455207825,
      "learning_rate": 4.522542485937369e-06,
      "logits/chosen": 13.780011177062988,
      "logits/rejected": 13.604715347290039,
      "logps/chosen": -0.4277075231075287,
      "logps/rejected": -1.415838599205017,
      "loss": 0.7644,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.6415613293647766,
      "rewards/margins": 1.482196569442749,
      "rewards/rejected": -2.123757839202881,
      "step": 300
    },
    {
      "epoch": 0.38095238095238093,
      "eval_logits/chosen": 13.13498592376709,
      "eval_logits/rejected": 13.13513469696045,
      "eval_logps/chosen": -0.476482629776001,
      "eval_logps/rejected": -1.4701811075210571,
      "eval_loss": 0.7514793872833252,
      "eval_rewards/accuracies": 0.546875,
      "eval_rewards/chosen": -0.7147239446640015,
      "eval_rewards/margins": 1.4905478954315186,
      "eval_rewards/rejected": -2.2052717208862305,
      "eval_runtime": 18.6093,
      "eval_samples_per_second": 27.406,
      "eval_steps_per_second": 3.439,
      "step": 300
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 0.7556002736091614,
      "learning_rate": 4.491324795060491e-06,
      "logits/chosen": 13.26073932647705,
      "logits/rejected": 13.28388786315918,
      "logps/chosen": -0.39378833770751953,
      "logps/rejected": -1.4242979288101196,
      "loss": 0.7092,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.5906823873519897,
      "rewards/margins": 1.5457642078399658,
      "rewards/rejected": -2.136446714401245,
      "step": 310
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 0.8167753219604492,
      "learning_rate": 4.4592336433146e-06,
      "logits/chosen": 12.952977180480957,
      "logits/rejected": 12.89118480682373,
      "logps/chosen": -0.4167153835296631,
      "logps/rejected": -1.1332799196243286,
      "loss": 0.7364,
      "rewards/accuracies": 0.512499988079071,
      "rewards/chosen": -0.6250730752944946,
      "rewards/margins": 1.074846625328064,
      "rewards/rejected": -1.6999199390411377,
      "step": 320
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 2.9806692600250244,
      "learning_rate": 4.426283106939474e-06,
      "logits/chosen": 12.890368461608887,
      "logits/rejected": 12.765925407409668,
      "logps/chosen": -0.5025959014892578,
      "logps/rejected": -1.2589428424835205,
      "loss": 0.748,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.7538937926292419,
      "rewards/margins": 1.1345205307006836,
      "rewards/rejected": -1.8884143829345703,
      "step": 330
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 1.568097710609436,
      "learning_rate": 4.3924876391293915e-06,
      "logits/chosen": 13.032608032226562,
      "logits/rejected": 12.877195358276367,
      "logps/chosen": -0.5034081935882568,
      "logps/rejected": -1.585137963294983,
      "loss": 0.7516,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.7551122903823853,
      "rewards/margins": 1.6225944757461548,
      "rewards/rejected": -2.37770676612854,
      "step": 340
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5996735095977783,
      "learning_rate": 4.357862063693486e-06,
      "logits/chosen": 12.859817504882812,
      "logits/rejected": 12.712678909301758,
      "logps/chosen": -0.5043476819992065,
      "logps/rejected": -1.525444507598877,
      "loss": 0.7497,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -0.7565216422080994,
      "rewards/margins": 1.5316450595855713,
      "rewards/rejected": -2.2881667613983154,
      "step": 350
    },
    {
      "epoch": 0.4444444444444444,
      "eval_logits/chosen": 12.228137969970703,
      "eval_logits/rejected": 12.226001739501953,
      "eval_logps/chosen": -0.5828607082366943,
      "eval_logps/rejected": -1.6681612730026245,
      "eval_loss": 0.7238383889198303,
      "eval_rewards/accuracies": 0.6875,
      "eval_rewards/chosen": -0.8742910623550415,
      "eval_rewards/margins": 1.6279507875442505,
      "eval_rewards/rejected": -2.502241611480713,
      "eval_runtime": 18.6038,
      "eval_samples_per_second": 27.414,
      "eval_steps_per_second": 3.44,
      "step": 350
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.605993926525116,
      "learning_rate": 4.322421568553529e-06,
      "logits/chosen": 11.993739128112793,
      "logits/rejected": 11.75650691986084,
      "logps/chosen": -0.5674928426742554,
      "logps/rejected": -1.7509374618530273,
      "loss": 0.7241,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -0.8512393236160278,
      "rewards/margins": 1.7751665115356445,
      "rewards/rejected": -2.626405954360962,
      "step": 360
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 0.931057870388031,
      "learning_rate": 4.286181699082008e-06,
      "logits/chosen": 11.784490585327148,
      "logits/rejected": 12.052295684814453,
      "logps/chosen": -0.5866945385932922,
      "logps/rejected": -1.8955312967300415,
      "loss": 0.7141,
      "rewards/accuracies": 0.75,
      "rewards/chosen": -0.8800417184829712,
      "rewards/margins": 1.9632551670074463,
      "rewards/rejected": -2.843297243118286,
      "step": 370
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 1.3936405181884766,
      "learning_rate": 4.249158351283414e-06,
      "logits/chosen": 11.842119216918945,
      "logits/rejected": 11.340182304382324,
      "logps/chosen": -0.7804869413375854,
      "logps/rejected": -1.8759396076202393,
      "loss": 0.6654,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -1.1707303524017334,
      "rewards/margins": 1.6431787014007568,
      "rewards/rejected": -2.8139090538024902,
      "step": 380
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 1.737855076789856,
      "learning_rate": 4.211367764821722e-06,
      "logits/chosen": 11.465726852416992,
      "logits/rejected": 11.05290699005127,
      "logps/chosen": -1.3201282024383545,
      "logps/rejected": -2.3962795734405518,
      "loss": 0.6301,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -1.9801921844482422,
      "rewards/margins": 1.6142269372940063,
      "rewards/rejected": -3.594419002532959,
      "step": 390
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 1.6870065927505493,
      "learning_rate": 4.172826515897146e-06,
      "logits/chosen": 10.830609321594238,
      "logits/rejected": 10.663077354431152,
      "logps/chosen": -2.5642189979553223,
      "logps/rejected": -3.535013198852539,
      "loss": 0.6274,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": -3.8463282585144043,
      "rewards/margins": 1.4561914205551147,
      "rewards/rejected": -5.302519798278809,
      "step": 400
    },
    {
      "epoch": 0.5079365079365079,
      "eval_logits/chosen": 9.964677810668945,
      "eval_logits/rejected": 9.858954429626465,
      "eval_logps/chosen": -2.578787088394165,
      "eval_logps/rejected": -3.803541898727417,
      "eval_loss": 0.590033233165741,
      "eval_rewards/accuracies": 0.796875,
      "eval_rewards/chosen": -3.868180513381958,
      "eval_rewards/margins": 1.837132453918457,
      "eval_rewards/rejected": -5.705312728881836,
      "eval_runtime": 18.5898,
      "eval_samples_per_second": 27.434,
      "eval_steps_per_second": 3.443,
      "step": 400
    },
    {
      "epoch": 0.5206349206349207,
      "grad_norm": 2.0417189598083496,
      "learning_rate": 4.133551509975264e-06,
      "logits/chosen": 9.34677505493164,
      "logits/rejected": 9.576300621032715,
      "logps/chosen": -2.1631455421447754,
      "logps/rejected": -3.024636745452881,
      "loss": 0.6309,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": -3.244718074798584,
      "rewards/margins": 1.2922370433807373,
      "rewards/rejected": -4.536954879760742,
      "step": 410
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.9144859313964844,
      "learning_rate": 4.093559974371725e-06,
      "logits/chosen": 9.20117473602295,
      "logits/rejected": 9.481060028076172,
      "logps/chosen": -2.7644081115722656,
      "logps/rejected": -3.905733585357666,
      "loss": 0.5839,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -4.14661169052124,
      "rewards/margins": 1.7119888067245483,
      "rewards/rejected": -5.858600616455078,
      "step": 420
    },
    {
      "epoch": 0.546031746031746,
      "grad_norm": 2.4795055389404297,
      "learning_rate": 4.052869450695776e-06,
      "logits/chosen": 9.674077987670898,
      "logits/rejected": 9.64409065246582,
      "logps/chosen": -2.562514066696167,
      "logps/rejected": -3.8458714485168457,
      "loss": 0.5266,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -3.843771457672119,
      "rewards/margins": 1.9250361919403076,
      "rewards/rejected": -5.768807411193848,
      "step": 430
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 1.897057056427002,
      "learning_rate": 4.011497787155938e-06,
      "logits/chosen": 8.887510299682617,
      "logits/rejected": 8.687074661254883,
      "logps/chosen": -3.2801125049591064,
      "logps/rejected": -4.673043251037598,
      "loss": 0.5665,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": -4.920168876647949,
      "rewards/margins": 2.089395523071289,
      "rewards/rejected": -7.009564399719238,
      "step": 440
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.1004762649536133,
      "learning_rate": 3.969463130731183e-06,
      "logits/chosen": 8.606618881225586,
      "logits/rejected": 8.299476623535156,
      "logps/chosen": -3.3771705627441406,
      "logps/rejected": -4.999676704406738,
      "loss": 0.5118,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -5.0657548904418945,
      "rewards/margins": 2.433760166168213,
      "rewards/rejected": -7.499515533447266,
      "step": 450
    },
    {
      "epoch": 0.5714285714285714,
      "eval_logits/chosen": 8.417736053466797,
      "eval_logits/rejected": 8.183667182922363,
      "eval_logps/chosen": -3.3982253074645996,
      "eval_logps/rejected": -5.010103225708008,
      "eval_loss": 0.5201926827430725,
      "eval_rewards/accuracies": 0.796875,
      "eval_rewards/chosen": -5.0973381996154785,
      "eval_rewards/margins": 2.4178173542022705,
      "eval_rewards/rejected": -7.515154838562012,
      "eval_runtime": 18.6069,
      "eval_samples_per_second": 27.409,
      "eval_steps_per_second": 3.44,
      "step": 450
    },
    {
      "epoch": 0.5841269841269842,
      "grad_norm": 2.016348123550415,
      "learning_rate": 3.92678391921108e-06,
      "logits/chosen": 9.348031997680664,
      "logits/rejected": 8.707467079162598,
      "logps/chosen": -3.687103271484375,
      "logps/rejected": -5.414787769317627,
      "loss": 0.4783,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -5.5306549072265625,
      "rewards/margins": 2.591526508331299,
      "rewards/rejected": -8.12218189239502,
      "step": 460
    },
    {
      "epoch": 0.5968253968253968,
      "grad_norm": 2.9189071655273438,
      "learning_rate": 3.88347887310836e-06,
      "logits/chosen": 8.294754028320312,
      "logits/rejected": 7.891358852386475,
      "logps/chosen": -3.737588405609131,
      "logps/rejected": -5.187026023864746,
      "loss": 0.534,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -5.606382846832275,
      "rewards/margins": 2.1741559505462646,
      "rewards/rejected": -7.780538082122803,
      "step": 470
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 2.306356906890869,
      "learning_rate": 3.839566987447492e-06,
      "logits/chosen": 8.484542846679688,
      "logits/rejected": 8.39714241027832,
      "logps/chosen": -3.494408369064331,
      "logps/rejected": -5.29335880279541,
      "loss": 0.4829,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.241612911224365,
      "rewards/margins": 2.6984262466430664,
      "rewards/rejected": -7.940038204193115,
      "step": 480
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.2581255435943604,
      "learning_rate": 3.795067523432826e-06,
      "logits/chosen": 8.763944625854492,
      "logits/rejected": 8.361797332763672,
      "logps/chosen": -3.9699864387512207,
      "logps/rejected": -6.275031566619873,
      "loss": 0.4437,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": -5.954979419708252,
      "rewards/margins": 3.4575679302215576,
      "rewards/rejected": -9.412548065185547,
      "step": 490
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 2.2695906162261963,
      "learning_rate": 3.7500000000000005e-06,
      "logits/chosen": 7.8348212242126465,
      "logits/rejected": 7.482022285461426,
      "logps/chosen": -3.7032783031463623,
      "logps/rejected": -5.9005255699157715,
      "loss": 0.4411,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -5.554916858673096,
      "rewards/margins": 3.2958710193634033,
      "rewards/rejected": -8.850788116455078,
      "step": 500
    },
    {
      "epoch": 0.6349206349206349,
      "eval_logits/chosen": 7.651264190673828,
      "eval_logits/rejected": 7.331784248352051,
      "eval_logps/chosen": -3.6274948120117188,
      "eval_logps/rejected": -5.359984874725342,
      "eval_loss": 0.4819534122943878,
      "eval_rewards/accuracies": 0.796875,
      "eval_rewards/chosen": -5.441242694854736,
      "eval_rewards/margins": 2.5987353324890137,
      "eval_rewards/rejected": -8.03997802734375,
      "eval_runtime": 18.6061,
      "eval_samples_per_second": 27.41,
      "eval_steps_per_second": 3.44,
      "step": 500
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 4.491377353668213,
      "learning_rate": 3.7043841852542884e-06,
      "logits/chosen": 8.346134185791016,
      "logits/rejected": 7.885122776031494,
      "logps/chosen": -3.1610424518585205,
      "logps/rejected": -4.682709217071533,
      "loss": 0.5284,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -4.7415642738342285,
      "rewards/margins": 2.2825000286102295,
      "rewards/rejected": -7.0240631103515625,
      "step": 510
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 2.4325833320617676,
      "learning_rate": 3.658240087799655e-06,
      "logits/chosen": 7.592903137207031,
      "logits/rejected": 7.519273281097412,
      "logps/chosen": -3.836571455001831,
      "logps/rejected": -5.284958839416504,
      "loss": 0.5357,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -5.754857063293457,
      "rewards/margins": 2.1725804805755615,
      "rewards/rejected": -7.927438259124756,
      "step": 520
    },
    {
      "epoch": 0.6730158730158731,
      "grad_norm": 3.2697038650512695,
      "learning_rate": 3.611587947962319e-06,
      "logits/chosen": 8.396175384521484,
      "logits/rejected": 8.135710716247559,
      "logps/chosen": -3.09209942817688,
      "logps/rejected": -4.844483375549316,
      "loss": 0.5079,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -4.638149261474609,
      "rewards/margins": 2.6285760402679443,
      "rewards/rejected": -7.266725063323975,
      "step": 530
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 3.9283788204193115,
      "learning_rate": 3.564448228912682e-06,
      "logits/chosen": 7.992170810699463,
      "logits/rejected": 7.327617645263672,
      "logps/chosen": -3.6388747692108154,
      "logps/rejected": -5.46083927154541,
      "loss": 0.4713,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -5.458312511444092,
      "rewards/margins": 2.7329471111297607,
      "rewards/rejected": -8.191259384155273,
      "step": 540
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 5.740615367889404,
      "learning_rate": 3.516841607689501e-06,
      "logits/chosen": 7.8473920822143555,
      "logits/rejected": 7.583371162414551,
      "logps/chosen": -3.4951674938201904,
      "logps/rejected": -5.054746150970459,
      "loss": 0.5543,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -5.242751121520996,
      "rewards/margins": 2.3393683433532715,
      "rewards/rejected": -7.582118988037109,
      "step": 550
    },
    {
      "epoch": 0.6984126984126984,
      "eval_logits/chosen": 7.201205253601074,
      "eval_logits/rejected": 6.811280727386475,
      "eval_logps/chosen": -3.9208078384399414,
      "eval_logps/rejected": -5.703615665435791,
      "eval_loss": 0.458388090133667,
      "eval_rewards/accuracies": 0.84375,
      "eval_rewards/chosen": -5.881211757659912,
      "eval_rewards/margins": 2.674211025238037,
      "eval_rewards/rejected": -8.555423736572266,
      "eval_runtime": 18.6149,
      "eval_samples_per_second": 27.397,
      "eval_steps_per_second": 3.438,
      "step": 550
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.257397413253784,
      "learning_rate": 3.4687889661302577e-06,
      "logits/chosen": 7.826712608337402,
      "logits/rejected": 7.213566780090332,
      "logps/chosen": -4.419582843780518,
      "logps/rejected": -6.427667140960693,
      "loss": 0.4126,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -6.629374027252197,
      "rewards/margins": 3.0121266841888428,
      "rewards/rejected": -9.641500473022461,
      "step": 560
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 3.2082905769348145,
      "learning_rate": 3.4203113817116955e-06,
      "logits/chosen": 6.789637565612793,
      "logits/rejected": 6.794576168060303,
      "logps/chosen": -3.8381495475769043,
      "logps/rejected": -5.592730522155762,
      "loss": 0.4379,
      "rewards/accuracies": 0.8999999761581421,
      "rewards/chosen": -5.757224082946777,
      "rewards/margins": 2.6318702697753906,
      "rewards/rejected": -8.389094352722168,
      "step": 570
    },
    {
      "epoch": 0.7365079365079366,
      "grad_norm": 1.4739922285079956,
      "learning_rate": 3.3714301183045382e-06,
      "logits/chosen": 6.731423854827881,
      "logits/rejected": 6.7872209548950195,
      "logps/chosen": -2.9625697135925293,
      "logps/rejected": -4.8117570877075195,
      "loss": 0.4483,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -4.443854808807373,
      "rewards/margins": 2.773780345916748,
      "rewards/rejected": -7.217635154724121,
      "step": 580
    },
    {
      "epoch": 0.7492063492063492,
      "grad_norm": 2.3974905014038086,
      "learning_rate": 3.3221666168464584e-06,
      "logits/chosen": 7.254199981689453,
      "logits/rejected": 6.7625627517700195,
      "logps/chosen": -3.562770366668701,
      "logps/rejected": -5.307286262512207,
      "loss": 0.4229,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -5.344155788421631,
      "rewards/margins": 2.616774082183838,
      "rewards/rejected": -7.960929870605469,
      "step": 590
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 2.3709428310394287,
      "learning_rate": 3.272542485937369e-06,
      "logits/chosen": 7.226127624511719,
      "logits/rejected": 6.73668909072876,
      "logps/chosen": -3.8387343883514404,
      "logps/rejected": -5.65582275390625,
      "loss": 0.4304,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -5.7581024169921875,
      "rewards/margins": 2.725632429122925,
      "rewards/rejected": -8.483735084533691,
      "step": 600
    },
    {
      "epoch": 0.7619047619047619,
      "eval_logits/chosen": 6.816856861114502,
      "eval_logits/rejected": 6.3922905921936035,
      "eval_logps/chosen": -3.8147382736206055,
      "eval_logps/rejected": -5.733050346374512,
      "eval_loss": 0.43386051058769226,
      "eval_rewards/accuracies": 0.875,
      "eval_rewards/chosen": -5.722107410430908,
      "eval_rewards/margins": 2.877467393875122,
      "eval_rewards/rejected": -8.59957504272461,
      "eval_runtime": 18.5848,
      "eval_samples_per_second": 27.442,
      "eval_steps_per_second": 3.444,
      "step": 600
    },
    {
      "epoch": 0.7746031746031746,
      "grad_norm": 8.223690032958984,
      "learning_rate": 3.222579492361179e-06,
      "logits/chosen": 6.017186164855957,
      "logits/rejected": 6.098165988922119,
      "logps/chosen": -4.070714950561523,
      "logps/rejected": -5.999022006988525,
      "loss": 0.4752,
      "rewards/accuracies": 0.862500011920929,
      "rewards/chosen": -6.106072902679443,
      "rewards/margins": 2.8924598693847656,
      "rewards/rejected": -8.998533248901367,
      "step": 610
    },
    {
      "epoch": 0.7873015873015873,
      "grad_norm": 2.494403839111328,
      "learning_rate": 3.1722995515381644e-06,
      "logits/chosen": 5.941250801086426,
      "logits/rejected": 5.958924770355225,
      "logps/chosen": -3.984475612640381,
      "logps/rejected": -5.801859378814697,
      "loss": 0.4245,
      "rewards/accuracies": 0.887499988079071,
      "rewards/chosen": -5.97671365737915,
      "rewards/margins": 2.726074695587158,
      "rewards/rejected": -8.702788352966309,
      "step": 620
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.906548023223877,
      "learning_rate": 3.121724717912138e-06,
      "logits/chosen": 6.673853874206543,
      "logits/rejected": 6.525673866271973,
      "logps/chosen": -3.4477615356445312,
      "logps/rejected": -5.480903148651123,
      "loss": 0.3671,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.171643257141113,
      "rewards/margins": 3.0497121810913086,
      "rewards/rejected": -8.221354484558105,
      "step": 630
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 3.656189441680908,
      "learning_rate": 3.0708771752766397e-06,
      "logits/chosen": 6.097588062286377,
      "logits/rejected": 6.049706935882568,
      "logps/chosen": -3.8336167335510254,
      "logps/rejected": -5.6922125816345215,
      "loss": 0.4461,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -5.750425338745117,
      "rewards/margins": 2.787893772125244,
      "rewards/rejected": -8.53831958770752,
      "step": 640
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 4.886603355407715,
      "learning_rate": 3.019779227044398e-06,
      "logits/chosen": 7.281914710998535,
      "logits/rejected": 7.21079158782959,
      "logps/chosen": -3.3890902996063232,
      "logps/rejected": -5.331442356109619,
      "loss": 0.4231,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": -5.083634853363037,
      "rewards/margins": 2.9135282039642334,
      "rewards/rejected": -7.99716329574585,
      "step": 650
    },
    {
      "epoch": 0.8253968253968254,
      "eval_logits/chosen": 7.003323554992676,
      "eval_logits/rejected": 6.476384162902832,
      "eval_logps/chosen": -3.6840155124664307,
      "eval_logps/rejected": -5.79384708404541,
      "eval_loss": 0.4155474007129669,
      "eval_rewards/accuracies": 0.875,
      "eval_rewards/chosen": -5.5260233879089355,
      "eval_rewards/margins": 3.164747476577759,
      "eval_rewards/rejected": -8.690771102905273,
      "eval_runtime": 18.6081,
      "eval_samples_per_second": 27.407,
      "eval_steps_per_second": 3.439,
      "step": 650
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 4.255698204040527,
      "learning_rate": 2.9684532864643123e-06,
      "logits/chosen": 7.213356018066406,
      "logits/rejected": 6.562827110290527,
      "logps/chosen": -4.553462505340576,
      "logps/rejected": -7.089639186859131,
      "loss": 0.4137,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -6.830193996429443,
      "rewards/margins": 3.804264783859253,
      "rewards/rejected": -10.6344575881958,
      "step": 660
    },
    {
      "epoch": 0.8507936507936508,
      "grad_norm": 2.784740924835205,
      "learning_rate": 2.9169218667902562e-06,
      "logits/chosen": 7.139246463775635,
      "logits/rejected": 7.061759948730469,
      "logps/chosen": -3.2805087566375732,
      "logps/rejected": -5.112305641174316,
      "loss": 0.4138,
      "rewards/accuracies": 0.875,
      "rewards/chosen": -4.920762538909912,
      "rewards/margins": 2.7476963996887207,
      "rewards/rejected": -7.668459415435791,
      "step": 670
    },
    {
      "epoch": 0.8634920634920635,
      "grad_norm": 2.966514825820923,
      "learning_rate": 2.8652075714060296e-06,
      "logits/chosen": 7.687324523925781,
      "logits/rejected": 6.8130292892456055,
      "logps/chosen": -3.9359238147735596,
      "logps/rejected": -6.452606201171875,
      "loss": 0.4267,
      "rewards/accuracies": 0.949999988079071,
      "rewards/chosen": -5.903885841369629,
      "rewards/margins": 3.7750232219696045,
      "rewards/rejected": -9.678911209106445,
      "step": 680
    },
    {
      "epoch": 0.8761904761904762,
      "grad_norm": 2.919829845428467,
      "learning_rate": 2.813333083910761e-06,
      "logits/chosen": 7.361714839935303,
      "logits/rejected": 6.8447113037109375,
      "logps/chosen": -4.811502456665039,
      "logps/rejected": -7.118119716644287,
      "loss": 0.3531,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -7.217253684997559,
      "rewards/margins": 3.4599266052246094,
      "rewards/rejected": -10.677180290222168,
      "step": 690
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 4.350555896759033,
      "learning_rate": 2.761321158169134e-06,
      "logits/chosen": 7.161977291107178,
      "logits/rejected": 6.46688985824585,
      "logps/chosen": -5.0110602378845215,
      "logps/rejected": -7.346589088439941,
      "loss": 0.4327,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -7.516589164733887,
      "rewards/margins": 3.503293514251709,
      "rewards/rejected": -11.01988410949707,
      "step": 700
    },
    {
      "epoch": 0.8888888888888888,
      "eval_logits/chosen": 6.070926666259766,
      "eval_logits/rejected": 5.528128147125244,
      "eval_logps/chosen": -4.264724254608154,
      "eval_logps/rejected": -6.332221031188965,
      "eval_loss": 0.40030673146247864,
      "eval_rewards/accuracies": 0.875,
      "eval_rewards/chosen": -6.3970866203308105,
      "eval_rewards/margins": 3.1012446880340576,
      "eval_rewards/rejected": -9.498331069946289,
      "eval_runtime": 18.5969,
      "eval_samples_per_second": 27.424,
      "eval_steps_per_second": 3.441,
      "step": 700
    },
    {
      "epoch": 0.9015873015873016,
      "grad_norm": 2.253688335418701,
      "learning_rate": 2.70919460833079e-06,
      "logits/chosen": 6.234388828277588,
      "logits/rejected": 5.7127604484558105,
      "logps/chosen": -4.306221008300781,
      "logps/rejected": -6.937534332275391,
      "loss": 0.3878,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -6.459331512451172,
      "rewards/margins": 3.946969509124756,
      "rewards/rejected": -10.406301498413086,
      "step": 710
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 5.499817371368408,
      "learning_rate": 2.6569762988232838e-06,
      "logits/chosen": 6.5680670738220215,
      "logits/rejected": 5.752740383148193,
      "logps/chosen": -4.220452308654785,
      "logps/rejected": -6.862195014953613,
      "loss": 0.3841,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -6.330678462982178,
      "rewards/margins": 3.9626128673553467,
      "rewards/rejected": -10.293292045593262,
      "step": 720
    },
    {
      "epoch": 0.926984126984127,
      "grad_norm": 4.771604061126709,
      "learning_rate": 2.604689134322999e-06,
      "logits/chosen": 6.312363624572754,
      "logits/rejected": 5.750403881072998,
      "logps/chosen": -4.694201946258545,
      "logps/rejected": -6.822142601013184,
      "loss": 0.4237,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": -7.041302680969238,
      "rewards/margins": 3.1919119358062744,
      "rewards/rejected": -10.233213424682617,
      "step": 730
    },
    {
      "epoch": 0.9396825396825397,
      "grad_norm": 2.910656452178955,
      "learning_rate": 2.5523560497083927e-06,
      "logits/chosen": 5.823894500732422,
      "logits/rejected": 5.497160911560059,
      "logps/chosen": -4.014594078063965,
      "logps/rejected": -6.6623029708862305,
      "loss": 0.3566,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -6.021890640258789,
      "rewards/margins": 3.9715638160705566,
      "rewards/rejected": -9.99345588684082,
      "step": 740
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.6968085765838623,
      "learning_rate": 2.5e-06,
      "logits/chosen": 5.813364028930664,
      "logits/rejected": 5.676685333251953,
      "logps/chosen": -3.678469181060791,
      "logps/rejected": -6.177823066711426,
      "loss": 0.3494,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -5.517704486846924,
      "rewards/margins": 3.749030351638794,
      "rewards/rejected": -9.26673412322998,
      "step": 750
    },
    {
      "epoch": 0.9523809523809523,
      "eval_logits/chosen": 6.183505535125732,
      "eval_logits/rejected": 5.580399036407471,
      "eval_logps/chosen": -3.959765911102295,
      "eval_logps/rejected": -6.2080864906311035,
      "eval_loss": 0.37998583912849426,
      "eval_rewards/accuracies": 0.890625,
      "eval_rewards/chosen": -5.939648628234863,
      "eval_rewards/margins": 3.372481107711792,
      "eval_rewards/rejected": -9.312129974365234,
      "eval_runtime": 18.6645,
      "eval_samples_per_second": 27.325,
      "eval_steps_per_second": 3.429,
      "step": 750
    },
    {
      "epoch": 0.9650793650793651,
      "grad_norm": 2.2613444328308105,
      "learning_rate": 2.447643950291608e-06,
      "logits/chosen": 6.018897533416748,
      "logits/rejected": 5.643963813781738,
      "logps/chosen": -3.9108989238739014,
      "logps/rejected": -6.244706630706787,
      "loss": 0.3948,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -5.866348743438721,
      "rewards/margins": 3.500711441040039,
      "rewards/rejected": -9.367059707641602,
      "step": 760
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 6.015537261962891,
      "learning_rate": 2.3953108656770018e-06,
      "logits/chosen": 5.021273136138916,
      "logits/rejected": 4.748461723327637,
      "logps/chosen": -3.692396640777588,
      "logps/rejected": -6.072467803955078,
      "loss": 0.3751,
      "rewards/accuracies": 0.9125000238418579,
      "rewards/chosen": -5.538595199584961,
      "rewards/margins": 3.570105791091919,
      "rewards/rejected": -9.108701705932617,
      "step": 770
    },
    {
      "epoch": 0.9904761904761905,
      "grad_norm": 4.150258541107178,
      "learning_rate": 2.3430237011767166e-06,
      "logits/chosen": 6.515981197357178,
      "logits/rejected": 5.819984436035156,
      "logps/chosen": -4.485560894012451,
      "logps/rejected": -6.801682949066162,
      "loss": 0.3818,
      "rewards/accuracies": 0.9375,
      "rewards/chosen": -6.728341579437256,
      "rewards/margins": 3.4741833209991455,
      "rewards/rejected": -10.20252513885498,
      "step": 780
    },
    {
      "epoch": 1.0025396825396826,
      "grad_norm": 2.078934907913208,
      "learning_rate": 2.290805391669212e-06,
      "logits/chosen": 7.137444972991943,
      "logits/rejected": 6.565527439117432,
      "logps/chosen": -4.413013935089111,
      "logps/rejected": -7.346111297607422,
      "loss": 0.3495,
      "rewards/accuracies": 0.9473684430122375,
      "rewards/chosen": -6.619520664215088,
      "rewards/margins": 4.399644374847412,
      "rewards/rejected": -11.019165992736816,
      "step": 790
    },
    {
      "epoch": 1.0152380952380953,
      "grad_norm": 3.736583709716797,
      "learning_rate": 2.238678841830867e-06,
      "logits/chosen": 6.755683898925781,
      "logits/rejected": 6.001730442047119,
      "logps/chosen": -4.394175052642822,
      "logps/rejected": -6.807177543640137,
      "loss": 0.386,
      "rewards/accuracies": 0.925000011920929,
      "rewards/chosen": -6.591261386871338,
      "rewards/margins": 3.61950421333313,
      "rewards/rejected": -10.210765838623047,
      "step": 800
    },
    {
      "epoch": 1.0152380952380953,
      "eval_logits/chosen": 6.0334320068359375,
      "eval_logits/rejected": 5.392582416534424,
      "eval_logps/chosen": -3.8732340335845947,
      "eval_logps/rejected": -6.17905855178833,
      "eval_loss": 0.3669988214969635,
      "eval_rewards/accuracies": 0.890625,
      "eval_rewards/chosen": -5.809851169586182,
      "eval_rewards/margins": 3.4587368965148926,
      "eval_rewards/rejected": -9.26858901977539,
      "eval_runtime": 18.6021,
      "eval_samples_per_second": 27.416,
      "eval_steps_per_second": 3.44,
      "step": 800
    }
  ],
  "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": 1.9424793463713956e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}