{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 100,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013333333333333334,
      "grad_norm": 75.5,
      "kl": 0.0,
      "learning_rate": 1e-06,
      "logits/chosen": 1803143936.0,
      "logps/chosen": -1764.083251953125,
      "loss": 0.632,
      "rewards/chosen": -0.6753141283988953,
      "step": 1
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 77.0,
      "kl": 2.966403007507324,
      "learning_rate": 9.88e-07,
      "logits/chosen": 1835470165.3333333,
      "logps/chosen": -1562.392795138889,
      "loss": 0.5078,
      "rewards/chosen": 0.2530868848164876,
      "step": 10
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 70.0,
      "kl": 17.817913055419922,
      "learning_rate": 9.746666666666666e-07,
      "logits/chosen": 1839740518.4,
      "logps/chosen": -1660.749609375,
      "loss": 0.4871,
      "rewards/chosen": 1.8496942520141602,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 63.0,
      "kl": 30.11983871459961,
      "learning_rate": 9.613333333333334e-07,
      "logits/chosen": 1844791091.2,
      "logps/chosen": -1590.46630859375,
      "loss": 0.5174,
      "rewards/chosen": 2.9328380584716798,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 44.0,
      "kl": 39.447776794433594,
      "learning_rate": 9.479999999999999e-07,
      "logits/chosen": 1830737728.2397003,
      "logits/rejected": 1802774180.2264152,
      "logps/chosen": -1604.0685861423221,
      "logps/rejected": -1642.3963738207547,
      "loss": 0.497,
      "rewards/chosen": 4.055163894253277,
      "rewards/margins": 0.6231006295864137,
      "rewards/rejected": 3.4320632646668634,
      "step": 40
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 61.0,
      "kl": 27.023143768310547,
      "learning_rate": 9.346666666666666e-07,
      "logits/rejected": 1793442406.4,
      "logps/rejected": -1498.494921875,
      "loss": 0.4883,
      "rewards/rejected": 2.6893266677856444,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 70.5,
      "kl": 16.976736068725586,
      "learning_rate": 9.213333333333333e-07,
      "logits/rejected": 1816138956.8,
      "logps/rejected": -1576.112890625,
      "loss": 0.4765,
      "rewards/rejected": 1.6485807418823242,
      "step": 60
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 78.0,
      "kl": 3.4582889080047607,
      "learning_rate": 9.08e-07,
      "logits/rejected": 1791525068.8,
      "logps/rejected": -1609.57080078125,
      "loss": 0.4898,
      "rewards/rejected": 0.33603610992431643,
      "step": 70
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 96.0,
      "kl": 4.4611639976501465,
      "learning_rate": 8.946666666666667e-07,
      "logits/chosen": 1793128038.4,
      "logits/rejected": 1786466099.2,
      "logps/chosen": -1679.2375,
      "logps/rejected": -1366.859375,
      "loss": 0.4474,
      "rewards/chosen": 0.8079164505004883,
      "rewards/margins": 1.4511647701263428,
      "rewards/rejected": -0.6432483196258545,
      "step": 80
    },
    {
      "epoch": 1.2,
      "grad_norm": 73.0,
      "kl": 20.16000747680664,
      "learning_rate": 8.813333333333332e-07,
      "logits/chosen": 1788976128.0,
      "logps/chosen": -1553.37900390625,
      "loss": 0.4946,
      "rewards/chosen": 2.074075126647949,
      "step": 90
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 55.25,
      "kl": 30.880172729492188,
      "learning_rate": 8.68e-07,
      "logits/chosen": 1800670822.4,
      "logps/chosen": -1629.187109375,
      "loss": 0.4936,
      "rewards/chosen": 3.1399845123291015,
      "step": 100
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 47.75,
      "kl": 42.36182403564453,
      "learning_rate": 8.546666666666666e-07,
      "logits/chosen": 1819451801.6,
      "logps/chosen": -1631.21865234375,
      "loss": 0.4832,
      "rewards/chosen": 4.322412109375,
      "step": 110
    },
    {
      "epoch": 1.6,
      "grad_norm": 65.0,
      "kl": 29.110525131225586,
      "learning_rate": 8.413333333333333e-07,
      "logits/chosen": 1786882220.2616823,
      "logits/rejected": 1767476998.0093896,
      "logps/chosen": -1454.260660046729,
      "logps/rejected": -1486.950850938967,
      "loss": 0.4809,
      "rewards/chosen": 4.8924052871276285,
      "rewards/margins": 2.9423321882151434,
      "rewards/rejected": 1.9500730989124853,
      "step": 120
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 68.0,
      "kl": 10.5321044921875,
      "learning_rate": 8.28e-07,
      "logits/rejected": 1757802086.4,
      "logps/rejected": -1584.4416015625,
      "loss": 0.4952,
      "rewards/rejected": 1.1045079231262207,
      "step": 130
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 74.5,
      "kl": 2.656236171722412,
      "learning_rate": 8.146666666666666e-07,
      "logits/rejected": 1784456601.6,
      "logps/rejected": -1606.92255859375,
      "loss": 0.4411,
      "rewards/rejected": 0.04395853877067566,
      "step": 140
    },
    {
      "epoch": 2.0,
      "grad_norm": 47.25,
      "kl": 0.02235652133822441,
      "learning_rate": 8.013333333333333e-07,
      "logits/rejected": 1755790950.4,
      "logps/rejected": -1492.91025390625,
      "loss": 0.3227,
      "rewards/rejected": -0.965308952331543,
      "step": 150
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 74.5,
      "kl": 22.667367935180664,
      "learning_rate": 7.88e-07,
      "logits/chosen": 1760644710.4,
      "logps/chosen": -1561.63623046875,
      "loss": 0.5121,
      "rewards/chosen": 2.2527976989746095,
      "step": 160
    },
    {
      "epoch": 2.2666666666666666,
      "grad_norm": 75.5,
      "kl": 35.21966552734375,
      "learning_rate": 7.746666666666666e-07,
      "logits/chosen": 1774286233.6,
      "logps/chosen": -1643.762109375,
      "loss": 0.4987,
      "rewards/chosen": 3.5484432220458983,
      "step": 170
    },
    {
      "epoch": 2.4,
      "grad_norm": 52.25,
      "kl": 43.11100387573242,
      "learning_rate": 7.613333333333333e-07,
      "logits/chosen": 1786122035.2,
      "logps/chosen": -1576.08076171875,
      "loss": 0.4918,
      "rewards/chosen": 4.371388244628906,
      "step": 180
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 49.75,
      "kl": 43.39256286621094,
      "learning_rate": 7.48e-07,
      "logits/chosen": 1780707128.5692885,
      "logits/rejected": 1751267212.0754716,
      "logps/chosen": -1593.653675093633,
      "logps/rejected": -1665.3343160377358,
      "loss": 0.481,
      "rewards/chosen": 5.09666597173455,
      "rewards/margins": 3.9583941361195003,
      "rewards/rejected": 1.13827183561505,
      "step": 190
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 63.5,
      "kl": 5.4629011154174805,
      "learning_rate": 7.346666666666666e-07,
      "logits/rejected": 1737874841.6,
      "logps/rejected": -1520.10458984375,
      "loss": 0.4785,
      "rewards/rejected": 0.5283474445343017,
      "step": 200
    },
    {
      "epoch": 2.8,
      "grad_norm": 59.25,
      "kl": 1.2280102968215942,
      "learning_rate": 7.213333333333334e-07,
      "logits/rejected": 1761185177.6,
      "logps/rejected": -1594.97919921875,
      "loss": 0.4105,
      "rewards/rejected": -0.23803796768188476,
      "step": 210
    },
    {
      "epoch": 2.9333333333333336,
      "grad_norm": 70.5,
      "kl": 0.0,
      "learning_rate": 7.079999999999999e-07,
      "logits/rejected": 1738660864.0,
      "logps/rejected": -1625.093359375,
      "loss": 0.2885,
      "rewards/rejected": -1.2162075996398927,
      "step": 220
    },
    {
      "epoch": 3.066666666666667,
      "grad_norm": 75.5,
      "kl": 14.01048469543457,
      "learning_rate": 6.946666666666666e-07,
      "logits/chosen": 1750113075.2,
      "logits/rejected": 1743708160.0,
      "logps/chosen": -1658.2826171875,
      "logps/rejected": -1375.04150390625,
      "loss": 0.3769,
      "rewards/chosen": 2.9034093856811523,
      "rewards/margins": 4.364873313903809,
      "rewards/rejected": -1.4614639282226562,
      "step": 230
    },
    {
      "epoch": 3.2,
      "grad_norm": 63.0,
      "kl": 37.20917510986328,
      "learning_rate": 6.813333333333333e-07,
      "logits/chosen": 1746606899.2,
      "logps/chosen": -1536.5771484375,
      "loss": 0.4982,
      "rewards/chosen": 3.75426025390625,
      "step": 240
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 54.5,
      "kl": 43.48841094970703,
      "learning_rate": 6.68e-07,
      "logits/chosen": 1757109657.6,
      "logps/chosen": -1617.16201171875,
      "loss": 0.5003,
      "rewards/chosen": 4.342501831054688,
      "step": 250
    },
    {
      "epoch": 3.466666666666667,
      "grad_norm": 52.5,
      "kl": 51.4334716796875,
      "learning_rate": 6.546666666666665e-07,
      "logits/chosen": 1780435148.8,
      "logps/chosen": -1622.2716796875,
      "loss": 0.4796,
      "rewards/chosen": 5.217120742797851,
      "step": 260
    },
    {
      "epoch": 3.6,
      "grad_norm": 67.5,
      "kl": 19.67037582397461,
      "learning_rate": 6.413333333333333e-07,
      "logits/chosen": 1755938050.3925233,
      "logits/rejected": 1727550343.8122065,
      "logps/chosen": -1448.7593457943926,
      "logps/rejected": -1504.9633215962442,
      "loss": 0.4334,
      "rewards/chosen": 5.442524277161215,
      "rewards/margins": 5.293697337761961,
      "rewards/rejected": 0.1488269393992536,
      "step": 270
    },
    {
      "epoch": 3.7333333333333334,
      "grad_norm": 51.75,
      "kl": 0.6852197647094727,
      "learning_rate": 6.28e-07,
      "logits/rejected": 1722981785.6,
      "logps/rejected": -1600.43251953125,
      "loss": 0.3926,
      "rewards/rejected": -0.49457273483276365,
      "step": 280
    },
    {
      "epoch": 3.8666666666666667,
      "grad_norm": 49.0,
      "kl": 0.2839541435241699,
      "learning_rate": 6.146666666666667e-07,
      "logits/rejected": 1752589516.8,
      "logps/rejected": -1619.22822265625,
      "loss": 0.2889,
      "rewards/rejected": -1.1866175651550293,
      "step": 290
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.0,
      "kl": 0.0,
      "learning_rate": 6.013333333333334e-07,
      "logits/rejected": 1728595353.6,
      "logps/rejected": -1498.5271484375,
      "loss": 0.2549,
      "rewards/rejected": -1.526987361907959,
      "step": 300
    },
    {
      "epoch": 4.133333333333334,
      "grad_norm": 54.0,
      "kl": 39.12127685546875,
      "learning_rate": 5.879999999999999e-07,
      "logits/chosen": 1737360384.0,
      "logps/chosen": -1544.43232421875,
      "loss": 0.4935,
      "rewards/chosen": 3.9731983184814452,
      "step": 310
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 172.0,
      "kl": 46.1120491027832,
      "learning_rate": 5.746666666666667e-07,
      "logits/chosen": 1747944038.4,
      "logps/chosen": -1632.6375,
      "loss": 0.4933,
      "rewards/chosen": 4.660909652709961,
      "step": 320
    },
    {
      "epoch": 4.4,
      "grad_norm": 60.0,
      "kl": 50.143592834472656,
      "learning_rate": 5.613333333333333e-07,
      "logits/chosen": 1759613952.0,
      "logps/chosen": -1568.59072265625,
      "loss": 0.4785,
      "rewards/chosen": 5.1204078674316404,
      "step": 330
    },
    {
      "epoch": 4.533333333333333,
      "grad_norm": 42.5,
      "kl": 45.67478942871094,
      "learning_rate": 5.48e-07,
      "logits/chosen": 1756831406.5018728,
      "logits/rejected": 1722636635.7735848,
      "logps/chosen": -1589.1077949438202,
      "logps/rejected": -1681.454304245283,
      "loss": 0.4447,
      "rewards/chosen": 5.551258558637641,
      "rewards/margins": 6.024997390931457,
      "rewards/rejected": -0.47373883229381636,
      "step": 340
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 217.0,
      "kl": 0.32102876901626587,
      "learning_rate": 5.346666666666666e-07,
      "logits/rejected": 1712375193.6,
      "logps/rejected": -1534.0259765625,
      "loss": 0.338,
      "rewards/rejected": -0.8637893676757813,
      "step": 350
    },
    {
      "epoch": 4.8,
      "grad_norm": 47.0,
      "kl": 0.029415320605039597,
      "learning_rate": 5.213333333333333e-07,
      "logits/rejected": 1739532697.6,
      "logps/rejected": -1605.47685546875,
      "loss": 0.2836,
      "rewards/rejected": -1.2877922058105469,
      "step": 360
    },
    {
      "epoch": 4.933333333333334,
      "grad_norm": 50.5,
      "kl": 0.0,
      "learning_rate": 5.079999999999999e-07,
      "logits/rejected": 1720070963.2,
      "logps/rejected": -1630.8001953125,
      "loss": 0.2262,
      "rewards/rejected": -1.7868902206420898,
      "step": 370
    },
    {
      "epoch": 5.066666666666666,
      "grad_norm": 70.5,
      "kl": 21.522884368896484,
      "learning_rate": 4.946666666666666e-07,
      "logits/chosen": 1738568908.8,
      "logits/rejected": 1726313472.0,
      "logps/chosen": -1644.7123046875,
      "logps/rejected": -1377.4642578125,
      "loss": 0.3804,
      "rewards/chosen": 4.260452651977539,
      "rewards/margins": 5.9641773223876955,
      "rewards/rejected": -1.7037246704101563,
      "step": 380
    },
    {
      "epoch": 5.2,
      "grad_norm": 49.75,
      "kl": 47.77645492553711,
      "learning_rate": 4.813333333333334e-07,
      "logits/chosen": 1732489625.6,
      "logps/chosen": -1525.93984375,
      "loss": 0.4944,
      "rewards/chosen": 4.817991256713867,
      "step": 390
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 50.25,
      "kl": 49.042144775390625,
      "learning_rate": 4.68e-07,
      "logits/chosen": 1741244620.8,
      "logps/chosen": -1609.87353515625,
      "loss": 0.4644,
      "rewards/chosen": 5.071358489990234,
      "step": 400
    },
    {
      "epoch": 5.466666666666667,
      "grad_norm": 48.0,
      "kl": 55.76483154296875,
      "learning_rate": 4.5466666666666666e-07,
      "logits/chosen": 1760807936.0,
      "logps/chosen": -1618.9923828125,
      "loss": 0.5002,
      "rewards/chosen": 5.545055770874024,
      "step": 410
    },
    {
      "epoch": 5.6,
      "grad_norm": 50.0,
      "kl": 18.410531997680664,
      "learning_rate": 4.413333333333333e-07,
      "logits/chosen": 1736117544.672897,
      "logits/rejected": 1708876583.6619718,
      "logps/chosen": -1447.1404789719627,
      "logps/rejected": -1516.6236795774648,
      "loss": 0.3554,
      "rewards/chosen": 5.60440890588493,
      "rewards/margins": 6.6215995436077515,
      "rewards/rejected": -1.0171906377228213,
      "step": 420
    },
    {
      "epoch": 5.733333333333333,
      "grad_norm": 39.25,
      "kl": 0.028980541974306107,
      "learning_rate": 4.2799999999999997e-07,
      "logits/rejected": 1704340684.8,
      "logps/rejected": -1610.3271484375,
      "loss": 0.269,
      "rewards/rejected": -1.4840303421020509,
      "step": 430
    },
    {
      "epoch": 5.866666666666667,
      "grad_norm": 53.5,
      "kl": 0.0,
      "learning_rate": 4.146666666666667e-07,
      "logits/rejected": 1737012224.0,
      "logps/rejected": -1625.72900390625,
      "loss": 0.2277,
      "rewards/rejected": -1.8366947174072266,
      "step": 440
    },
    {
      "epoch": 6.0,
      "grad_norm": 39.25,
      "kl": 0.0,
      "learning_rate": 4.0133333333333333e-07,
      "logits/rejected": 1715832217.6,
      "logps/rejected": -1501.8396484375,
      "loss": 0.2283,
      "rewards/rejected": -1.8582498550415039,
      "step": 450
    },
    {
      "epoch": 6.133333333333334,
      "grad_norm": 55.25,
      "kl": 47.387760162353516,
      "learning_rate": 3.88e-07,
      "logits/chosen": 1729806540.8,
      "logps/chosen": -1536.3201171875,
      "loss": 0.4921,
      "rewards/chosen": 4.784424209594727,
      "step": 460
    },
    {
      "epoch": 6.266666666666667,
      "grad_norm": 77.0,
      "kl": 51.74030685424805,
      "learning_rate": 3.7466666666666663e-07,
      "logits/chosen": 1736568832.0,
      "logps/chosen": -1627.24794921875,
      "loss": 0.4934,
      "rewards/chosen": 5.199858093261719,
      "step": 470
    },
    {
      "epoch": 6.4,
      "grad_norm": 61.75,
      "kl": 53.5655517578125,
      "learning_rate": 3.6133333333333334e-07,
      "logits/chosen": 1746720563.2,
      "logps/chosen": -1565.3529296875,
      "loss": 0.4801,
      "rewards/chosen": 5.444185256958008,
      "step": 480
    },
    {
      "epoch": 6.533333333333333,
      "grad_norm": 40.75,
      "kl": 47.25954055786133,
      "learning_rate": 3.4799999999999994e-07,
      "logits/chosen": 1744727741.8426967,
      "logits/rejected": 1706023105.2075472,
      "logps/chosen": -1587.4740168539327,
      "logps/rejected": -1689.911704009434,
      "loss": 0.4287,
      "rewards/chosen": 5.714643957016619,
      "rewards/margins": 7.034099805566516,
      "rewards/rejected": -1.3194558485498968,
      "step": 490
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 58.0,
      "kl": 0.0,
      "learning_rate": 3.3466666666666665e-07,
      "logits/rejected": 1700372172.8,
      "logps/rejected": -1541.06552734375,
      "loss": 0.265,
      "rewards/rejected": -1.5677401542663574,
      "step": 500
    },
    {
      "epoch": 6.8,
      "grad_norm": 39.75,
      "kl": 0.0,
      "learning_rate": 3.2133333333333335e-07,
      "logits/rejected": 1729151795.2,
      "logps/rejected": -1609.8298828125,
      "loss": 0.2389,
      "rewards/rejected": -1.7230974197387696,
      "step": 510
    },
    {
      "epoch": 6.933333333333334,
      "grad_norm": 42.0,
      "kl": 0.0,
      "learning_rate": 3.08e-07,
      "logits/rejected": 1712730828.8,
      "logps/rejected": -1633.16318359375,
      "loss": 0.2112,
      "rewards/rejected": -2.023202896118164,
      "step": 520
    },
    {
      "epoch": 7.066666666666666,
      "grad_norm": 64.5,
      "kl": 25.04488754272461,
      "learning_rate": 2.9466666666666666e-07,
      "logits/chosen": 1731994419.2,
      "logits/rejected": 1720656691.2,
      "logps/chosen": -1637.28173828125,
      "logps/rejected": -1377.9115234375,
      "loss": 0.3763,
      "rewards/chosen": 5.003516006469726,
      "rewards/margins": 6.7519731521606445,
      "rewards/rejected": -1.748457145690918,
      "step": 530
    },
    {
      "epoch": 7.2,
      "grad_norm": 56.0,
      "kl": 52.43037033081055,
      "learning_rate": 2.813333333333333e-07,
      "logits/chosen": 1726875648.0,
      "logps/chosen": -1521.06044921875,
      "loss": 0.4829,
      "rewards/chosen": 5.305931854248047,
      "step": 540
    },
    {
      "epoch": 7.333333333333333,
      "grad_norm": 50.0,
      "kl": 51.872047424316406,
      "learning_rate": 2.68e-07,
      "logits/chosen": 1734085222.4,
      "logps/chosen": -1607.64345703125,
      "loss": 0.4712,
      "rewards/chosen": 5.294354629516602,
      "step": 550
    },
    {
      "epoch": 7.466666666666667,
      "grad_norm": 51.0,
      "kl": 55.77549362182617,
      "learning_rate": 2.546666666666666e-07,
      "logits/chosen": 1753063219.2,
      "logps/chosen": -1617.415625,
      "loss": 0.4773,
      "rewards/chosen": 5.702725982666015,
      "step": 560
    },
    {
      "epoch": 7.6,
      "grad_norm": 43.75,
      "kl": 18.287708282470703,
      "learning_rate": 2.413333333333333e-07,
      "logits/chosen": 1731032073.5700934,
      "logits/rejected": 1702629587.5305164,
      "logps/chosen": -1447.9690420560748,
      "logps/rejected": -1521.8135269953052,
      "loss": 0.3238,
      "rewards/chosen": 5.521567086193049,
      "rewards/margins": 7.057752337348419,
      "rewards/rejected": -1.5361852511553697,
      "step": 570
    },
    {
      "epoch": 7.733333333333333,
      "grad_norm": 41.0,
      "kl": 0.0,
      "learning_rate": 2.28e-07,
      "logits/rejected": 1697045913.6,
      "logps/rejected": -1615.4837890625,
      "loss": 0.2158,
      "rewards/rejected": -1.9997014999389648,
      "step": 580
    },
    {
      "epoch": 7.866666666666667,
      "grad_norm": 38.75,
      "kl": 0.0,
      "learning_rate": 2.1466666666666666e-07,
      "logits/rejected": 1732887756.8,
      "logps/rejected": -1627.6578125,
      "loss": 0.206,
      "rewards/rejected": -2.029564094543457,
      "step": 590
    },
    {
      "epoch": 8.0,
      "grad_norm": 43.25,
      "kl": 0.0,
      "learning_rate": 2.0133333333333334e-07,
      "logits/rejected": 1715685171.2,
      "logps/rejected": -1501.2095703125,
      "loss": 0.241,
      "rewards/rejected": -1.795237922668457,
      "step": 600
    },
    {
      "epoch": 8.133333333333333,
      "grad_norm": 55.0,
      "kl": 51.67559051513672,
      "learning_rate": 1.88e-07,
      "logits/chosen": 1727099904.0,
      "logps/chosen": -1532.07939453125,
      "loss": 0.4961,
      "rewards/chosen": 5.208480453491211,
      "step": 610
    },
    {
      "epoch": 8.266666666666667,
      "grad_norm": 64.5,
      "kl": 54.74528884887695,
      "learning_rate": 1.7466666666666667e-07,
      "logits/chosen": 1733115904.0,
      "logps/chosen": -1624.519921875,
      "loss": 0.5013,
      "rewards/chosen": 5.472665786743164,
      "step": 620
    },
    {
      "epoch": 8.4,
      "grad_norm": 54.75,
      "kl": 54.551849365234375,
      "learning_rate": 1.6133333333333332e-07,
      "logits/chosen": 1742884659.2,
      "logps/chosen": -1564.97412109375,
      "loss": 0.4915,
      "rewards/chosen": 5.482054138183594,
      "step": 630
    },
    {
      "epoch": 8.533333333333333,
      "grad_norm": 30.625,
      "kl": 46.306522369384766,
      "learning_rate": 1.4799999999999998e-07,
      "logits/chosen": 1739496766.3220973,
      "logits/rejected": 1702134687.3962264,
      "logps/chosen": -1588.0999531835207,
      "logps/rejected": -1696.4740566037735,
      "loss": 0.4184,
      "rewards/chosen": 5.652020515127575,
      "rewards/margins": 7.627730826153518,
      "rewards/rejected": -1.9757103110259433,
      "step": 640
    },
    {
      "epoch": 8.666666666666666,
      "grad_norm": 56.5,
      "kl": 0.0,
      "learning_rate": 1.3466666666666665e-07,
      "logits/rejected": 1696173260.8,
      "logps/rejected": -1544.7572265625,
      "loss": 0.2282,
      "rewards/rejected": -1.9369186401367187,
      "step": 650
    },
    {
      "epoch": 8.8,
      "grad_norm": 36.75,
      "kl": 0.0,
      "learning_rate": 1.2133333333333333e-07,
      "logits/rejected": 1725317120.0,
      "logps/rejected": -1612.53291015625,
      "loss": 0.2132,
      "rewards/rejected": -1.9934148788452148,
      "step": 660
    },
    {
      "epoch": 8.933333333333334,
      "grad_norm": 43.25,
      "kl": 0.0,
      "learning_rate": 1.0799999999999999e-07,
      "logits/rejected": 1711136563.2,
      "logps/rejected": -1633.72958984375,
      "loss": 0.2084,
      "rewards/rejected": -2.079827880859375,
      "step": 670
    },
    {
      "epoch": 9.066666666666666,
      "grad_norm": 74.5,
      "kl": 26.150564193725586,
      "learning_rate": 9.466666666666665e-08,
      "logits/chosen": 1734777036.8,
      "logits/rejected": 1720304844.8,
      "logps/chosen": -1634.3982421875,
      "logps/rejected": -1376.32314453125,
      "loss": 0.3847,
      "rewards/chosen": 5.2918556213378904,
      "rewards/margins": 6.881484413146973,
      "rewards/rejected": -1.5896287918090821,
      "step": 680
    },
    {
      "epoch": 9.2,
      "grad_norm": 45.0,
      "kl": 54.32807540893555,
      "learning_rate": 8.133333333333332e-08,
      "logits/chosen": 1726023270.4,
      "logps/chosen": -1519.271875,
      "loss": 0.4882,
      "rewards/chosen": 5.484774017333985,
      "step": 690
    },
    {
      "epoch": 9.333333333333334,
      "grad_norm": 51.75,
      "kl": 53.640716552734375,
      "learning_rate": 6.8e-08,
      "logits/chosen": 1733355929.6,
      "logps/chosen": -1606.2349609375,
      "loss": 0.4805,
      "rewards/chosen": 5.435222625732422,
      "step": 700
    },
    {
      "epoch": 9.466666666666667,
      "grad_norm": 46.75,
      "kl": 56.87353515625,
      "learning_rate": 5.4666666666666666e-08,
      "logits/chosen": 1751316684.8,
      "logps/chosen": -1617.39033203125,
      "loss": 0.4885,
      "rewards/chosen": 5.705249786376953,
      "step": 710
    },
    {
      "epoch": 9.6,
      "grad_norm": 38.25,
      "kl": 17.8724308013916,
      "learning_rate": 4.133333333333333e-08,
      "logits/chosen": 1729312212.9345794,
      "logits/rejected": 1699881844.5821595,
      "logps/chosen": -1447.3971962616822,
      "logps/rejected": -1524.6291079812206,
      "loss": 0.2937,
      "rewards/chosen": 5.578735921984521,
      "rewards/margins": 7.396489386947476,
      "rewards/rejected": -1.8177534649629548,
      "step": 720
    },
    {
      "epoch": 9.733333333333333,
      "grad_norm": 30.375,
      "kl": 0.0,
      "learning_rate": 2.8e-08,
      "logits/rejected": 1695596134.4,
      "logps/rejected": -1616.91201171875,
      "loss": 0.2028,
      "rewards/rejected": -2.142536735534668,
      "step": 730
    },
    {
      "epoch": 9.866666666666667,
      "grad_norm": 42.5,
      "kl": 0.0,
      "learning_rate": 1.4666666666666666e-08,
      "logits/rejected": 1732339097.6,
      "logps/rejected": -1627.45458984375,
      "loss": 0.211,
      "rewards/rejected": -2.0092498779296877,
      "step": 740
    },
    {
      "epoch": 10.0,
      "grad_norm": 42.0,
      "kl": 0.0,
      "learning_rate": 1.3333333333333333e-09,
      "logits/rejected": 1714343731.2,
      "logps/rejected": -1500.21591796875,
      "loss": 0.2487,
      "rewards/rejected": -1.6958515167236328,
      "step": 750
    }
  ],
  "logging_steps": 10,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}