{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9989528795811519,
  "eval_steps": 200,
  "global_step": 477,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "beta_dpo/beta_used": 0.10024853050708771,
      "beta_dpo/beta_used_raw": 0.10024853050708771,
      "beta_dpo/gap_mean": -0.0031278375536203384,
      "beta_dpo/gap_std": 0.09185527265071869,
      "beta_dpo/mask_keep_frac": 0.75,
      "epoch": 0.0020942408376963353,
      "grad_norm": 80.06067657470703,
      "learning_rate": 0.0,
      "logits/chosen": -0.6103914976119995,
      "logits/rejected": -0.6099507808685303,
      "loss": 1.3869,
      "step": 1
    },
    {
      "beta_dpo/beta_used": 0.10045824944972992,
      "beta_dpo/beta_used_raw": 0.10045824944972992,
      "beta_dpo/gap_mean": 0.0029368107207119465,
      "beta_dpo/gap_std": 0.47314706444740295,
      "beta_dpo/mask_keep_frac": 0.7916666865348816,
      "epoch": 0.020942408376963352,
      "grad_norm": 72.42662811279297,
      "learning_rate": 9.375e-08,
      "logits/chosen": -0.6866854429244995,
      "logits/rejected": -0.668829083442688,
      "loss": 1.386,
      "step": 10
    },
    {
      "beta_dpo/beta_used": 0.10218687355518341,
      "beta_dpo/beta_used_raw": 0.10218687355518341,
      "beta_dpo/gap_mean": 0.05031166225671768,
      "beta_dpo/gap_std": 0.731455385684967,
      "beta_dpo/mask_keep_frac": 0.7749999761581421,
      "epoch": 0.041884816753926704,
      "grad_norm": 77.65188598632812,
      "learning_rate": 1.9791666666666664e-07,
      "logits/chosen": -0.6419292688369751,
      "logits/rejected": -0.6541769504547119,
      "loss": 1.3785,
      "step": 20
    },
    {
      "beta_dpo/beta_used": 0.10061170160770416,
      "beta_dpo/beta_used_raw": 0.10061170160770416,
      "beta_dpo/gap_mean": 0.0937122255563736,
      "beta_dpo/gap_std": 0.7656054496765137,
      "beta_dpo/mask_keep_frac": 0.8062499761581421,
      "epoch": 0.06282722513089005,
      "grad_norm": 74.03604125976562,
      "learning_rate": 3.020833333333333e-07,
      "logits/chosen": -0.6690393686294556,
      "logits/rejected": -0.6756961941719055,
      "loss": 1.3767,
      "step": 30
    },
    {
      "beta_dpo/beta_used": 0.10513947159051895,
      "beta_dpo/beta_used_raw": 0.10513947159051895,
      "beta_dpo/gap_mean": 0.3032568395137787,
      "beta_dpo/gap_std": 0.9986203908920288,
      "beta_dpo/mask_keep_frac": 0.856249988079071,
      "epoch": 0.08376963350785341,
      "grad_norm": 68.4834976196289,
      "learning_rate": 4.0625e-07,
      "logits/chosen": -0.6429699659347534,
      "logits/rejected": -0.6495934724807739,
      "loss": 1.3467,
      "step": 40
    },
    {
      "beta_dpo/beta_used": 0.104192815721035,
      "beta_dpo/beta_used_raw": 0.104192815721035,
      "beta_dpo/gap_mean": 0.7923426032066345,
      "beta_dpo/gap_std": 1.8291547298431396,
      "beta_dpo/mask_keep_frac": 0.762499988079071,
      "epoch": 0.10471204188481675,
      "grad_norm": 71.59126281738281,
      "learning_rate": 4.999932966293553e-07,
      "logits/chosen": -0.7035672068595886,
      "logits/rejected": -0.7120343446731567,
      "loss": 1.3039,
      "step": 50
    },
    {
      "beta_dpo/beta_used": 0.10957477241754532,
      "beta_dpo/beta_used_raw": 0.10957477241754532,
      "beta_dpo/gap_mean": 1.5687782764434814,
      "beta_dpo/gap_std": 3.4623851776123047,
      "beta_dpo/mask_keep_frac": 0.84375,
      "epoch": 0.1256544502617801,
      "grad_norm": 82.82760620117188,
      "learning_rate": 4.991893270335525e-07,
      "logits/chosen": -0.6742374897003174,
      "logits/rejected": -0.6726926565170288,
      "loss": 1.2274,
      "step": 60
    },
    {
      "beta_dpo/beta_used": 0.10323189198970795,
      "beta_dpo/beta_used_raw": 0.10323189198970795,
      "beta_dpo/gap_mean": 2.4878456592559814,
      "beta_dpo/gap_std": 5.3841118812561035,
      "beta_dpo/mask_keep_frac": 0.737500011920929,
      "epoch": 0.14659685863874344,
      "grad_norm": 79.24715423583984,
      "learning_rate": 4.970496218214204e-07,
      "logits/chosen": -0.7053920030593872,
      "logits/rejected": -0.7138158679008484,
      "loss": 1.1847,
      "step": 70
    },
    {
      "beta_dpo/beta_used": 0.10442471504211426,
      "beta_dpo/beta_used_raw": 0.10279443114995956,
      "beta_dpo/gap_mean": 3.6363892555236816,
      "beta_dpo/gap_std": 7.359000205993652,
      "beta_dpo/mask_keep_frac": 0.831250011920929,
      "epoch": 0.16753926701570682,
      "grad_norm": 40.18954849243164,
      "learning_rate": 4.935856505068998e-07,
      "logits/chosen": -0.7026282548904419,
      "logits/rejected": -0.70656818151474,
      "loss": 1.1297,
      "step": 80
    },
    {
      "beta_dpo/beta_used": 0.09297941625118256,
      "beta_dpo/beta_used_raw": 0.0927402526140213,
      "beta_dpo/gap_mean": 4.5779619216918945,
      "beta_dpo/gap_std": 9.087356567382812,
      "beta_dpo/mask_keep_frac": 0.7875000238418579,
      "epoch": 0.18848167539267016,
      "grad_norm": 45.59261703491211,
      "learning_rate": 4.8881598109976e-07,
      "logits/chosen": -0.6874291896820068,
      "logits/rejected": -0.7057452201843262,
      "loss": 1.1141,
      "step": 90
    },
    {
      "beta_dpo/beta_used": 0.10471361875534058,
      "beta_dpo/beta_used_raw": 0.10211487114429474,
      "beta_dpo/gap_mean": 5.183230400085449,
      "beta_dpo/gap_std": 10.404474258422852,
      "beta_dpo/mask_keep_frac": 0.8187500238418579,
      "epoch": 0.2094240837696335,
      "grad_norm": 66.85250854492188,
      "learning_rate": 4.827661805750437e-07,
      "logits/chosen": -0.6732321977615356,
      "logits/rejected": -0.6987311840057373,
      "loss": 1.1044,
      "step": 100
    },
    {
      "beta_dpo/beta_used": 0.1166844591498375,
      "beta_dpo/beta_used_raw": 0.1166844591498375,
      "beta_dpo/gap_mean": 6.204737663269043,
      "beta_dpo/gap_std": 11.558156967163086,
      "beta_dpo/mask_keep_frac": 0.8062499761581421,
      "epoch": 0.23036649214659685,
      "grad_norm": 54.56244659423828,
      "learning_rate": 4.75468677825789e-07,
      "logits/chosen": -0.7261234521865845,
      "logits/rejected": -0.7450467348098755,
      "loss": 1.0282,
      "step": 110
    },
    {
      "beta_dpo/beta_used": 0.08581940829753876,
      "beta_dpo/beta_used_raw": 0.0759856328368187,
      "beta_dpo/gap_mean": 6.777069091796875,
      "beta_dpo/gap_std": 12.461393356323242,
      "beta_dpo/mask_keep_frac": 0.800000011920929,
      "epoch": 0.2513089005235602,
      "grad_norm": 54.73094940185547,
      "learning_rate": 4.669625898336438e-07,
      "logits/chosen": -0.7630956768989563,
      "logits/rejected": -0.776543378829956,
      "loss": 1.1069,
      "step": 120
    },
    {
      "beta_dpo/beta_used": 0.10493312776088715,
      "beta_dpo/beta_used_raw": 0.09375782310962677,
      "beta_dpo/gap_mean": 7.0316290855407715,
      "beta_dpo/gap_std": 13.4308500289917,
      "beta_dpo/mask_keep_frac": 0.800000011920929,
      "epoch": 0.27225130890052357,
      "grad_norm": 53.551025390625,
      "learning_rate": 4.5729351198915705e-07,
      "logits/chosen": -0.7406284809112549,
      "logits/rejected": -0.7330573201179504,
      "loss": 1.091,
      "step": 130
    },
    {
      "beta_dpo/beta_used": 0.0665307343006134,
      "beta_dpo/beta_used_raw": 0.04071963578462601,
      "beta_dpo/gap_mean": 7.776385307312012,
      "beta_dpo/gap_std": 14.402565002441406,
      "beta_dpo/mask_keep_frac": 0.824999988079071,
      "epoch": 0.2931937172774869,
      "grad_norm": 107.44986724853516,
      "learning_rate": 4.4651327368569684e-07,
      "logits/chosen": -0.7388048768043518,
      "logits/rejected": -0.7451251745223999,
      "loss": 1.1576,
      "step": 140
    },
    {
      "beta_dpo/beta_used": 0.07846825569868088,
      "beta_dpo/beta_used_raw": 0.06488198786973953,
      "beta_dpo/gap_mean": 8.364961624145508,
      "beta_dpo/gap_std": 14.984090805053711,
      "beta_dpo/mask_keep_frac": 0.7875000238418579,
      "epoch": 0.31413612565445026,
      "grad_norm": 38.963260650634766,
      "learning_rate": 4.346796604970912e-07,
      "logits/chosen": -0.768231213092804,
      "logits/rejected": -0.7551404237747192,
      "loss": 1.1224,
      "step": 150
    },
    {
      "beta_dpo/beta_used": 0.11797045171260834,
      "beta_dpo/beta_used_raw": 0.09938563406467438,
      "beta_dpo/gap_mean": 9.785693168640137,
      "beta_dpo/gap_std": 15.681970596313477,
      "beta_dpo/mask_keep_frac": 0.856249988079071,
      "epoch": 0.33507853403141363,
      "grad_norm": 80.62310028076172,
      "learning_rate": 4.218561044282098e-07,
      "logits/chosen": -0.7575253844261169,
      "logits/rejected": -0.7614981532096863,
      "loss": 1.0544,
      "step": 160
    },
    {
      "beta_dpo/beta_used": 0.07409517467021942,
      "beta_dpo/beta_used_raw": 0.04705094173550606,
      "beta_dpo/gap_mean": 10.035483360290527,
      "beta_dpo/gap_std": 16.284427642822266,
      "beta_dpo/mask_keep_frac": 0.8187500238418579,
      "epoch": 0.35602094240837695,
      "grad_norm": 65.990966796875,
      "learning_rate": 4.081113438988443e-07,
      "logits/chosen": -0.7660126090049744,
      "logits/rejected": -0.7755380868911743,
      "loss": 1.0875,
      "step": 170
    },
    {
      "beta_dpo/beta_used": 0.07568483054637909,
      "beta_dpo/beta_used_raw": 0.06118815019726753,
      "beta_dpo/gap_mean": 9.977958679199219,
      "beta_dpo/gap_std": 16.553037643432617,
      "beta_dpo/mask_keep_frac": 0.793749988079071,
      "epoch": 0.3769633507853403,
      "grad_norm": 56.092166900634766,
      "learning_rate": 3.935190552834828e-07,
      "logits/chosen": -0.7195374965667725,
      "logits/rejected": -0.7341417074203491,
      "loss": 1.0689,
      "step": 180
    },
    {
      "beta_dpo/beta_used": 0.10011672973632812,
      "beta_dpo/beta_used_raw": 0.08130989223718643,
      "beta_dpo/gap_mean": 10.884498596191406,
      "beta_dpo/gap_std": 17.649686813354492,
      "beta_dpo/mask_keep_frac": 0.768750011920929,
      "epoch": 0.39790575916230364,
      "grad_norm": 47.546146392822266,
      "learning_rate": 3.781574579820464e-07,
      "logits/chosen": -0.7710455060005188,
      "logits/rejected": -0.783000648021698,
      "loss": 1.0703,
      "step": 190
    },
    {
      "beta_dpo/beta_used": 0.03816061466932297,
      "beta_dpo/beta_used_raw": 0.01525220274925232,
      "beta_dpo/gap_mean": 10.375402450561523,
      "beta_dpo/gap_std": 17.245559692382812,
      "beta_dpo/mask_keep_frac": 0.831250011920929,
      "epoch": 0.418848167539267,
      "grad_norm": 40.988670349121094,
      "learning_rate": 3.621088951385353e-07,
      "logits/chosen": -0.7636905312538147,
      "logits/rejected": -0.7812480330467224,
      "loss": 1.1971,
      "step": 200
    },
    {
      "epoch": 0.418848167539267,
      "eval_beta_dpo/beta_used": 0.12430721521377563,
      "eval_beta_dpo/beta_used_raw": 0.09974151104688644,
      "eval_beta_dpo/gap_mean": 11.01975154876709,
      "eval_beta_dpo/gap_std": 18.638986587524414,
      "eval_beta_dpo/mask_keep_frac": 1.0,
      "eval_logits/chosen": -0.7570037245750427,
      "eval_logits/rejected": -0.7552843689918518,
      "eval_loss": 0.6548933386802673,
      "eval_runtime": 51.0397,
      "eval_samples_per_second": 39.185,
      "eval_steps_per_second": 0.627,
      "step": 200
    },
    {
      "beta_dpo/beta_used": 0.09783867746591568,
      "beta_dpo/beta_used_raw": 0.09206344187259674,
      "beta_dpo/gap_mean": 11.258265495300293,
      "beta_dpo/gap_std": 19.141300201416016,
      "beta_dpo/mask_keep_frac": 0.831250011920929,
      "epoch": 0.4397905759162304,
      "grad_norm": 106.01080322265625,
      "learning_rate": 3.454593922550693e-07,
      "logits/chosen": -0.7539916038513184,
      "logits/rejected": -0.7599259614944458,
      "loss": 1.0859,
      "step": 210
    },
    {
      "beta_dpo/beta_used": 0.13818596303462982,
      "beta_dpo/beta_used_raw": 0.118813656270504,
      "beta_dpo/gap_mean": 11.77585220336914,
      "beta_dpo/gap_std": 19.773366928100586,
      "beta_dpo/mask_keep_frac": 0.824999988079071,
      "epoch": 0.4607329842931937,
      "grad_norm": 128.11996459960938,
      "learning_rate": 3.2829819606729477e-07,
      "logits/chosen": -0.7987761497497559,
      "logits/rejected": -0.7768310308456421,
      "loss": 1.0097,
      "step": 220
    },
    {
      "beta_dpo/beta_used": 0.0800265297293663,
      "beta_dpo/beta_used_raw": 0.06512973457574844,
      "beta_dpo/gap_mean": 12.928131103515625,
      "beta_dpo/gap_std": 20.115745544433594,
      "beta_dpo/mask_keep_frac": 0.75,
      "epoch": 0.4816753926701571,
      "grad_norm": 41.492034912109375,
      "learning_rate": 3.1071729615293424e-07,
      "logits/chosen": -0.7944627404212952,
      "logits/rejected": -0.7826088070869446,
      "loss": 1.0617,
      "step": 230
    },
    {
      "beta_dpo/beta_used": 0.07821373641490936,
      "beta_dpo/beta_used_raw": 0.05508134886622429,
      "beta_dpo/gap_mean": 13.714938163757324,
      "beta_dpo/gap_std": 21.715341567993164,
      "beta_dpo/mask_keep_frac": 0.7749999761581421,
      "epoch": 0.5026178010471204,
      "grad_norm": 55.7053108215332,
      "learning_rate": 2.9281093183781403e-07,
      "logits/chosen": -0.7329837083816528,
      "logits/rejected": -0.7595623731613159,
      "loss": 1.1275,
      "step": 240
    },
    {
      "beta_dpo/beta_used": 0.08778323978185654,
      "beta_dpo/beta_used_raw": 0.048361603170633316,
      "beta_dpo/gap_mean": 13.810220718383789,
      "beta_dpo/gap_std": 22.46774673461914,
      "beta_dpo/mask_keep_frac": 0.800000011920929,
      "epoch": 0.5235602094240838,
      "grad_norm": 53.13675308227539,
      "learning_rate": 2.7467508704251135e-07,
      "logits/chosen": -0.787535548210144,
      "logits/rejected": -0.7830525636672974,
      "loss": 1.1019,
      "step": 250
    },
    {
      "beta_dpo/beta_used": 0.11194082349538803,
      "beta_dpo/beta_used_raw": 0.06594248861074448,
      "beta_dpo/gap_mean": 13.73353099822998,
      "beta_dpo/gap_std": 22.698503494262695,
      "beta_dpo/mask_keep_frac": 0.824999988079071,
      "epoch": 0.5445026178010471,
      "grad_norm": 0.9119361042976379,
      "learning_rate": 2.5640697577740815e-07,
      "logits/chosen": -0.7817746996879578,
      "logits/rejected": -0.7839881181716919,
      "loss": 1.1687,
      "step": 260
    },
    {
      "beta_dpo/beta_used": 0.09284855425357819,
      "beta_dpo/beta_used_raw": 0.08311768621206284,
      "beta_dpo/gap_mean": 13.976015090942383,
      "beta_dpo/gap_std": 22.33526039123535,
      "beta_dpo/mask_keep_frac": 0.8187500238418579,
      "epoch": 0.5654450261780105,
      "grad_norm": 136.4973602294922,
      "learning_rate": 2.381045210440644e-07,
      "logits/chosen": -0.7521445155143738,
      "logits/rejected": -0.7410815954208374,
      "loss": 1.0209,
      "step": 270
    },
    {
      "beta_dpo/beta_used": 0.10686023533344269,
      "beta_dpo/beta_used_raw": 0.06296978890895844,
      "beta_dpo/gap_mean": 14.858721733093262,
      "beta_dpo/gap_std": 22.79940414428711,
      "beta_dpo/mask_keep_frac": 0.824999988079071,
      "epoch": 0.5863874345549738,
      "grad_norm": 38.58131790161133,
      "learning_rate": 2.1986582993616925e-07,
      "logits/chosen": -0.7521171569824219,
      "logits/rejected": -0.7675251364707947,
      "loss": 1.058,
      "step": 280
    },
    {
      "beta_dpo/beta_used": 0.06835642457008362,
      "beta_dpo/beta_used_raw": 0.012238355353474617,
      "beta_dpo/gap_mean": 13.978078842163086,
      "beta_dpo/gap_std": 23.335269927978516,
      "beta_dpo/mask_keep_frac": 0.8374999761581421,
      "epoch": 0.6073298429319371,
      "grad_norm": 1.274525761604309,
      "learning_rate": 2.0178866775369774e-07,
      "logits/chosen": -0.7752319574356079,
      "logits/rejected": -0.7829610109329224,
      "loss": 1.2126,
      "step": 290
    },
    {
      "beta_dpo/beta_used": 0.08970650285482407,
      "beta_dpo/beta_used_raw": 0.0673152282834053,
      "beta_dpo/gap_mean": 13.71714973449707,
      "beta_dpo/gap_std": 23.238323211669922,
      "beta_dpo/mask_keep_frac": 0.75,
      "epoch": 0.6282722513089005,
      "grad_norm": 60.473148345947266,
      "learning_rate": 1.839699339491937e-07,
      "logits/chosen": -0.7769112586975098,
      "logits/rejected": -0.7637456655502319,
      "loss": 1.1287,
      "step": 300
    },
    {
      "beta_dpo/beta_used": 0.0964554101228714,
      "beta_dpo/beta_used_raw": 0.06809216737747192,
      "beta_dpo/gap_mean": 14.4856595993042,
      "beta_dpo/gap_std": 23.187442779541016,
      "beta_dpo/mask_keep_frac": 0.8125,
      "epoch": 0.6492146596858639,
      "grad_norm": 30.574621200561523,
      "learning_rate": 1.6650514271527465e-07,
      "logits/chosen": -0.7852055430412292,
      "logits/rejected": -0.7743746638298035,
      "loss": 1.1436,
      "step": 310
    },
    {
      "beta_dpo/beta_used": 0.0930468887090683,
      "beta_dpo/beta_used_raw": 0.057879697531461716,
      "beta_dpo/gap_mean": 15.27861213684082,
      "beta_dpo/gap_std": 23.997211456298828,
      "beta_dpo/mask_keep_frac": 0.8125,
      "epoch": 0.6701570680628273,
      "grad_norm": 266.17156982421875,
      "learning_rate": 1.4948791099758052e-07,
      "logits/chosen": -0.8031824827194214,
      "logits/rejected": -0.7853301763534546,
      "loss": 1.2318,
      "step": 320
    },
    {
      "beta_dpo/beta_used": 0.08731904625892639,
      "beta_dpo/beta_used_raw": 0.05920511484146118,
      "beta_dpo/gap_mean": 15.062555313110352,
      "beta_dpo/gap_std": 24.421737670898438,
      "beta_dpo/mask_keep_frac": 0.824999988079071,
      "epoch": 0.6910994764397905,
      "grad_norm": 54.84642791748047,
      "learning_rate": 1.3300945667758012e-07,
      "logits/chosen": -0.7694008946418762,
      "logits/rejected": -0.7609071135520935,
      "loss": 1.058,
      "step": 330
    },
    {
      "beta_dpo/beta_used": 0.07772944122552872,
      "beta_dpo/beta_used_raw": 0.04176778346300125,
      "beta_dpo/gap_mean": 15.674954414367676,
      "beta_dpo/gap_std": 25.302011489868164,
      "beta_dpo/mask_keep_frac": 0.762499988079071,
      "epoch": 0.7120418848167539,
      "grad_norm": 162.36752319335938,
      "learning_rate": 1.1715810961514072e-07,
      "logits/chosen": -0.8045889139175415,
      "logits/rejected": -0.8078791499137878,
      "loss": 1.1423,
      "step": 340
    },
    {
      "beta_dpo/beta_used": 0.09465853869915009,
      "beta_dpo/beta_used_raw": 0.03491034358739853,
      "beta_dpo/gap_mean": 15.350746154785156,
      "beta_dpo/gap_std": 25.115270614624023,
      "beta_dpo/mask_keep_frac": 0.7562500238418579,
      "epoch": 0.7329842931937173,
      "grad_norm": 122.0066146850586,
      "learning_rate": 1.0201883817182949e-07,
      "logits/chosen": -0.7979413866996765,
      "logits/rejected": -0.8106569051742554,
      "loss": 1.1516,
      "step": 350
    },
    {
      "beta_dpo/beta_used": 0.07950497418642044,
      "beta_dpo/beta_used_raw": 0.021852362900972366,
      "beta_dpo/gap_mean": 15.205873489379883,
      "beta_dpo/gap_std": 25.209131240844727,
      "beta_dpo/mask_keep_frac": 0.800000011920929,
      "epoch": 0.7539267015706806,
      "grad_norm": 93.26220703125,
      "learning_rate": 8.76727937529367e-08,
      "logits/chosen": -0.7563246488571167,
      "logits/rejected": -0.7660932540893555,
      "loss": 1.24,
      "step": 360
    },
    {
      "beta_dpo/beta_used": 0.10245828330516815,
      "beta_dpo/beta_used_raw": 0.05802968889474869,
      "beta_dpo/gap_mean": 16.286312103271484,
      "beta_dpo/gap_std": 25.74993896484375,
      "beta_dpo/mask_keep_frac": 0.768750011920929,
      "epoch": 0.774869109947644,
      "grad_norm": 143.22608947753906,
      "learning_rate": 7.419687580962222e-08,
      "logits/chosen": -0.7966378331184387,
      "logits/rejected": -0.8195791244506836,
      "loss": 1.1759,
      "step": 370
    },
    {
      "beta_dpo/beta_used": 0.04838007315993309,
      "beta_dpo/beta_used_raw": -0.006214796099811792,
      "beta_dpo/gap_mean": 15.983156204223633,
      "beta_dpo/gap_std": 24.809345245361328,
      "beta_dpo/mask_keep_frac": 0.7437499761581421,
      "epoch": 0.7958115183246073,
      "grad_norm": 36.29342269897461,
      "learning_rate": 6.166331963291519e-08,
      "logits/chosen": -0.7881544828414917,
      "logits/rejected": -0.786669909954071,
      "loss": 1.2336,
      "step": 380
    },
    {
      "beta_dpo/beta_used": 0.07021647691726685,
      "beta_dpo/beta_used_raw": 0.00572154950350523,
      "beta_dpo/gap_mean": 16.157865524291992,
      "beta_dpo/gap_std": 25.035715103149414,
      "beta_dpo/mask_keep_frac": 0.793749988079071,
      "epoch": 0.8167539267015707,
      "grad_norm": 27.86089324951172,
      "learning_rate": 5.013930914912476e-08,
      "logits/chosen": -0.8044806718826294,
      "logits/rejected": -0.8055523633956909,
      "loss": 1.1986,
      "step": 390
    },
    {
      "beta_dpo/beta_used": 0.0964551717042923,
      "beta_dpo/beta_used_raw": 0.04246100038290024,
      "beta_dpo/gap_mean": 16.26091766357422,
      "beta_dpo/gap_std": 25.67080307006836,
      "beta_dpo/mask_keep_frac": 0.793749988079071,
      "epoch": 0.837696335078534,
      "grad_norm": 203.63230895996094,
      "learning_rate": 3.968661679220467e-08,
      "logits/chosen": -0.8050006628036499,
      "logits/rejected": -0.7917808890342712,
      "loss": 1.2165,
      "step": 400
    },
    {
      "epoch": 0.837696335078534,
      "eval_beta_dpo/beta_used": 0.1434057652950287,
      "eval_beta_dpo/beta_used_raw": 0.09862707555294037,
      "eval_beta_dpo/gap_mean": 15.923084259033203,
      "eval_beta_dpo/gap_std": 25.965980529785156,
      "eval_beta_dpo/mask_keep_frac": 1.0,
      "eval_logits/chosen": -0.8034595847129822,
      "eval_logits/rejected": -0.7974430322647095,
      "eval_loss": 0.7667602896690369,
      "eval_runtime": 50.9741,
      "eval_samples_per_second": 39.236,
      "eval_steps_per_second": 0.628,
      "step": 400
    },
    {
      "beta_dpo/beta_used": 0.09968056529760361,
      "beta_dpo/beta_used_raw": 0.04236916825175285,
      "beta_dpo/gap_mean": 16.500282287597656,
      "beta_dpo/gap_std": 26.050161361694336,
      "beta_dpo/mask_keep_frac": 0.793749988079071,
      "epoch": 0.8586387434554974,
      "grad_norm": 82.50851440429688,
      "learning_rate": 3.036127238347164e-08,
      "logits/chosen": -0.827735424041748,
      "logits/rejected": -0.8203527331352234,
      "loss": 1.2025,
      "step": 410
    },
    {
      "beta_dpo/beta_used": 0.0970761626958847,
      "beta_dpo/beta_used_raw": 0.058871395885944366,
      "beta_dpo/gap_mean": 16.738262176513672,
      "beta_dpo/gap_std": 26.436817169189453,
      "beta_dpo/mask_keep_frac": 0.7562500238418579,
      "epoch": 0.8795811518324608,
      "grad_norm": 277.814453125,
      "learning_rate": 2.2213262793589482e-08,
      "logits/chosen": -0.7558459639549255,
      "logits/rejected": -0.7355632185935974,
      "loss": 1.1919,
      "step": 420
    },
    {
      "beta_dpo/beta_used": 0.07494507730007172,
      "beta_dpo/beta_used_raw": 0.037638500332832336,
      "beta_dpo/gap_mean": 17.993297576904297,
      "beta_dpo/gap_std": 27.201208114624023,
      "beta_dpo/mask_keep_frac": 0.84375,
      "epoch": 0.900523560209424,
      "grad_norm": 1.1577889919281006,
      "learning_rate": 1.5286263996730026e-08,
      "logits/chosen": -0.8132478594779968,
      "logits/rejected": -0.8199571371078491,
      "loss": 1.1747,
      "step": 430
    },
    {
      "beta_dpo/beta_used": 0.046172745525836945,
      "beta_dpo/beta_used_raw": -0.05054600164294243,
      "beta_dpo/gap_mean": 16.831357955932617,
      "beta_dpo/gap_std": 27.087594985961914,
      "beta_dpo/mask_keep_frac": 0.793749988079071,
      "epoch": 0.9214659685863874,
      "grad_norm": 8.6950101852417,
      "learning_rate": 9.617406953185136e-09,
      "logits/chosen": -0.8208335638046265,
      "logits/rejected": -0.8280296325683594,
      "loss": 1.2337,
      "step": 440
    },
    {
      "beta_dpo/beta_used": 0.11133173853158951,
      "beta_dpo/beta_used_raw": 0.07020476460456848,
      "beta_dpo/gap_mean": 16.71297264099121,
      "beta_dpo/gap_std": 26.49554443359375,
      "beta_dpo/mask_keep_frac": 0.824999988079071,
      "epoch": 0.9424083769633508,
      "grad_norm": 108.31566619873047,
      "learning_rate": 5.2370785753763356e-09,
      "logits/chosen": -0.7833819389343262,
      "logits/rejected": -0.7876101732254028,
      "loss": 1.171,
      "step": 450
    },
    {
      "beta_dpo/beta_used": 0.06652946025133133,
      "beta_dpo/beta_used_raw": -0.015655241906642914,
      "beta_dpo/gap_mean": 17.124013900756836,
      "beta_dpo/gap_std": 27.718246459960938,
      "beta_dpo/mask_keep_frac": 0.8062499761581421,
      "epoch": 0.9633507853403142,
      "grad_norm": 70.03536224365234,
      "learning_rate": 2.168758844148272e-09,
      "logits/chosen": -0.8030775785446167,
      "logits/rejected": -0.8030357360839844,
      "loss": 1.2041,
      "step": 460
    },
    {
      "beta_dpo/beta_used": 0.12787500023841858,
      "beta_dpo/beta_used_raw": 0.10427769273519516,
      "beta_dpo/gap_mean": 17.284704208374023,
      "beta_dpo/gap_std": 27.71035385131836,
      "beta_dpo/mask_keep_frac": 0.862500011920929,
      "epoch": 0.9842931937172775,
      "grad_norm": 215.3680877685547,
      "learning_rate": 4.288949484559934e-10,
      "logits/chosen": -0.7909310460090637,
      "logits/rejected": -0.7838017344474792,
      "loss": 1.2015,
      "step": 470
    },
    {
      "epoch": 0.9989528795811519,
      "step": 477,
      "total_flos": 0.0,
      "train_loss": 1.1642480231431045,
      "train_runtime": 4421.8255,
      "train_samples_per_second": 13.826,
      "train_steps_per_second": 0.108
    }
  ],
  "logging_steps": 10,
  "max_steps": 477,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}