{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 478,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.0416666666666666e-08,
      "logits/chosen": -2.8099329471588135,
      "logits/rejected": -2.7572641372680664,
      "logps/chosen": -241.48843383789062,
      "logps/rejected": -197.4517822265625,
      "loss": 0.7347,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0416666666666667e-07,
      "logits/chosen": -2.832111358642578,
      "logits/rejected": -2.8087170124053955,
      "logps/chosen": -292.73345947265625,
      "logps/rejected": -278.5730895996094,
      "loss": 0.731,
      "rewards/accuracies": 0.4236111044883728,
      "rewards/chosen": -0.00042624352499842644,
      "rewards/margins": -0.0005570763605646789,
      "rewards/rejected": 0.000130832806462422,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.0833333333333333e-07,
      "logits/chosen": -2.8119773864746094,
      "logits/rejected": -2.783511161804199,
      "logps/chosen": -290.25933837890625,
      "logps/rejected": -290.83258056640625,
      "loss": 0.7347,
      "rewards/accuracies": 0.6000000238418579,
      "rewards/chosen": 0.001403255038894713,
      "rewards/margins": 0.002630328293889761,
      "rewards/rejected": -0.0012270736042410135,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.1249999999999997e-07,
      "logits/chosen": -2.7597923278808594,
      "logits/rejected": -2.728569984436035,
      "logps/chosen": -246.2042694091797,
      "logps/rejected": -226.95529174804688,
      "loss": 0.728,
      "rewards/accuracies": 0.65625,
      "rewards/chosen": 0.0015784974675625563,
      "rewards/margins": 0.008332479745149612,
      "rewards/rejected": -0.0067539820447564125,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.1666666666666667e-07,
      "logits/chosen": -2.799250364303589,
      "logits/rejected": -2.7705955505371094,
      "logps/chosen": -298.7322082519531,
      "logps/rejected": -264.1480407714844,
      "loss": 0.7197,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": 0.007894225418567657,
      "rewards/margins": 0.03674033656716347,
      "rewards/rejected": -0.02884610928595066,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.999733114418725e-07,
      "logits/chosen": -2.7239151000976562,
      "logits/rejected": -2.7024989128112793,
      "logps/chosen": -277.66741943359375,
      "logps/rejected": -271.1574401855469,
      "loss": 0.7069,
      "rewards/accuracies": 0.668749988079071,
      "rewards/chosen": -0.002369915135204792,
      "rewards/margins": 0.07223416864871979,
      "rewards/rejected": -0.0746040791273117,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.990398100856366e-07,
      "logits/chosen": -2.7488715648651123,
      "logits/rejected": -2.7262396812438965,
      "logps/chosen": -261.4748229980469,
      "logps/rejected": -247.807861328125,
      "loss": 0.6795,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.023985665291547775,
      "rewards/margins": 0.1279429942369461,
      "rewards/rejected": -0.1519286334514618,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.967775735898179e-07,
      "logits/chosen": -2.7364790439605713,
      "logits/rejected": -2.70658802986145,
      "logps/chosen": -287.2948913574219,
      "logps/rejected": -270.7928466796875,
      "loss": 0.7083,
      "rewards/accuracies": 0.668749988079071,
      "rewards/chosen": -0.18872329592704773,
      "rewards/margins": 0.17036835849285126,
      "rewards/rejected": -0.3590916693210602,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.931986719649298e-07,
      "logits/chosen": -2.6997952461242676,
      "logits/rejected": -2.697025775909424,
      "logps/chosen": -298.27984619140625,
      "logps/rejected": -323.8697814941406,
      "loss": 0.6995,
      "rewards/accuracies": 0.6875,
      "rewards/chosen": -0.27548032999038696,
      "rewards/margins": 0.28797003626823425,
      "rewards/rejected": -0.5634504556655884,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.883222001996351e-07,
      "logits/chosen": -2.7339961528778076,
      "logits/rejected": -2.7010178565979004,
      "logps/chosen": -296.7826232910156,
      "logps/rejected": -312.85284423828125,
      "loss": 0.8219,
      "rewards/accuracies": 0.6937500238418579,
      "rewards/chosen": -0.41818127036094666,
      "rewards/margins": 0.36340323090553284,
      "rewards/rejected": -0.7815844416618347,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.821741763807186e-07,
      "logits/chosen": -2.715860605239868,
      "logits/rejected": -2.686281204223633,
      "logps/chosen": -333.1566467285156,
      "logps/rejected": -342.143310546875,
      "loss": 2.2447,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.4371761679649353,
      "rewards/margins": 0.3056567311286926,
      "rewards/rejected": -0.7428328990936279,
      "step": 100
    },
    {
      "epoch": 0.21,
      "eval_logits/chosen": -2.671812057495117,
      "eval_logits/rejected": -2.6597108840942383,
      "eval_logps/chosen": -285.50408935546875,
      "eval_logps/rejected": -325.74481201171875,
      "eval_loss": 12.741142272949219,
      "eval_rewards/accuracies": 0.75,
      "eval_rewards/chosen": -0.28464433550834656,
      "eval_rewards/margins": 0.39927127957344055,
      "eval_rewards/rejected": -0.6839155554771423,
      "eval_runtime": 53.1281,
      "eval_samples_per_second": 37.645,
      "eval_steps_per_second": 0.602,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.747874028753375e-07,
      "logits/chosen": -2.5364506244659424,
      "logits/rejected": -2.518993377685547,
      "logps/chosen": -321.1919860839844,
      "logps/rejected": -313.2504577636719,
      "loss": 2.392,
      "rewards/accuracies": 0.731249988079071,
      "rewards/chosen": -0.5109449028968811,
      "rewards/margins": 0.4034649729728699,
      "rewards/rejected": -0.9144099354743958,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.662012913161997e-07,
      "logits/chosen": -2.513144016265869,
      "logits/rejected": -2.483302593231201,
      "logps/chosen": -317.71197509765625,
      "logps/rejected": -354.447265625,
      "loss": 0.7845,
      "rewards/accuracies": 0.7437499761581421,
      "rewards/chosen": -0.4886089861392975,
      "rewards/margins": 0.42735376954078674,
      "rewards/rejected": -0.915962815284729,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.5646165232345103e-07,
      "logits/chosen": -2.38696026802063,
      "logits/rejected": -2.377903461456299,
      "logps/chosen": -329.28619384765625,
      "logps/rejected": -339.8948669433594,
      "loss": 0.9022,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -0.5479137897491455,
      "rewards/margins": 0.34450799226760864,
      "rewards/rejected": -0.8924217224121094,
      "step": 130
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.456204510851956e-07,
      "logits/chosen": -2.3478336334228516,
      "logits/rejected": -2.315876007080078,
      "logps/chosen": -339.808837890625,
      "logps/rejected": -381.429443359375,
      "loss": 29.8037,
      "rewards/accuracies": 0.71875,
      "rewards/chosen": -0.5917433500289917,
      "rewards/margins": 0.5149160623550415,
      "rewards/rejected": -1.1066595315933228,
      "step": 140
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.337355301007335e-07,
      "logits/chosen": -2.4338667392730713,
      "logits/rejected": -2.4544992446899414,
      "logps/chosen": -269.7679443359375,
      "logps/rejected": -317.58233642578125,
      "loss": 1.0584,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.4308902621269226,
      "rewards/margins": 0.38207167387008667,
      "rewards/rejected": -0.8129619359970093,
      "step": 150
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.2087030056579986e-07,
      "logits/chosen": -2.514054298400879,
      "logits/rejected": -2.484346866607666,
      "logps/chosen": -303.3541564941406,
      "logps/rejected": -321.21856689453125,
      "loss": 0.8359,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -0.47382301092147827,
      "rewards/margins": 0.2795892357826233,
      "rewards/rejected": -0.7534123659133911,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.070934040463998e-07,
      "logits/chosen": -2.496929883956909,
      "logits/rejected": -2.4770359992980957,
      "logps/chosen": -329.54736328125,
      "logps/rejected": -343.8206787109375,
      "loss": 4.1491,
      "rewards/accuracies": 0.7562500238418579,
      "rewards/chosen": -0.47380566596984863,
      "rewards/margins": 0.3627183437347412,
      "rewards/rejected": -0.8365238904953003,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.9247834624635404e-07,
      "logits/chosen": -2.5219836235046387,
      "logits/rejected": -2.5218372344970703,
      "logps/chosen": -325.4960632324219,
      "logps/rejected": -352.91546630859375,
      "loss": 4.4761,
      "rewards/accuracies": 0.7250000238418579,
      "rewards/chosen": -0.5631815195083618,
      "rewards/margins": 0.41213661432266235,
      "rewards/rejected": -0.9753181338310242,
      "step": 180
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.7710310482256523e-07,
      "logits/chosen": -2.543841600418091,
      "logits/rejected": -2.4971985816955566,
      "logps/chosen": -335.67486572265625,
      "logps/rejected": -353.8238830566406,
      "loss": 10897.8156,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.44279035925865173,
      "rewards/margins": 0.4546957015991211,
      "rewards/rejected": -0.8974860906600952,
      "step": 190
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.610497133404795e-07,
      "logits/chosen": -2.428988456726074,
      "logits/rejected": -2.4355721473693848,
      "logps/chosen": -354.25653076171875,
      "logps/rejected": -367.38916015625,
      "loss": 4.720340943901239e+22,
      "rewards/accuracies": 0.6937500238418579,
      "rewards/chosen": -0.5808899998664856,
      "rewards/margins": 0.4498439431190491,
      "rewards/rejected": -1.0307339429855347,
      "step": 200
    },
    {
      "epoch": 0.42,
      "eval_logits/chosen": -2.2813971042633057,
      "eval_logits/rejected": -2.236406087875366,
      "eval_logps/chosen": -400.4986877441406,
      "eval_logps/rejected": -450.00384521484375,
      "eval_loss": Infinity,
      "eval_rewards/accuracies": 0.69921875,
      "eval_rewards/chosen": -1.434590458869934,
      "eval_rewards/margins": 0.49191567301750183,
      "eval_rewards/rejected": -1.9265060424804688,
      "eval_runtime": 53.0955,
      "eval_samples_per_second": 37.668,
      "eval_steps_per_second": 0.603,
      "step": 200
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.4440382358952115e-07,
      "logits/chosen": -2.0168819427490234,
      "logits/rejected": -1.9473979473114014,
      "logps/chosen": -461.4383850097656,
      "logps/rejected": -495.66925048828125,
      "loss": 4.475516531174102e+21,
      "rewards/accuracies": 0.7124999761581421,
      "rewards/chosen": -1.8840515613555908,
      "rewards/margins": 0.5532835721969604,
      "rewards/rejected": -2.4373350143432617,
      "step": 210
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.272542485937368e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 40054194176.0,
      "rewards/accuracies": 0.11249999701976776,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 220
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.096924887558854e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 230
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.9181224366319943e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 240
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.7370891215954565e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 250
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.55479083351317e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 260
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.3722002126275822e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 270
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.19029145890313e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 280
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.0100351342479216e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 290
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.8323929841460178e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 300
    },
    {
      "epoch": 0.63,
      "eval_logits/chosen": NaN,
      "eval_logits/rejected": NaN,
      "eval_logps/chosen": NaN,
      "eval_logps/rejected": NaN,
      "eval_loss": NaN,
      "eval_rewards/accuracies": 0.0,
      "eval_rewards/chosen": NaN,
      "eval_rewards/margins": NaN,
      "eval_rewards/rejected": NaN,
      "eval_runtime": 51.7823,
      "eval_samples_per_second": 38.623,
      "eval_steps_per_second": 0.618,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.6583128063291573e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 310
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.488723393865766e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 320
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3245295796480788e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 330
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.1666074087171627e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 340
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.0157994641835734e-07,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 350
    },
    {
      "epoch": 0.75,
      "learning_rate": 8.729103716819111e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 360
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.387025063449081e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 370
    },
    {
      "epoch": 0.79,
      "learning_rate": 6.138919252022435e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 380
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.991445467064689e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 390
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.9507259776993954e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 400
    },
    {
      "epoch": 0.84,
      "eval_logits/chosen": NaN,
      "eval_logits/rejected": NaN,
      "eval_logps/chosen": NaN,
      "eval_logps/rejected": NaN,
      "eval_loss": NaN,
      "eval_rewards/accuracies": 0.0,
      "eval_rewards/chosen": NaN,
      "eval_rewards/margins": NaN,
      "eval_rewards/rejected": NaN,
      "eval_runtime": 51.801,
      "eval_samples_per_second": 38.609,
      "eval_steps_per_second": 0.618,
      "step": 400
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.022313472693447e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 410
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.2111614344599684e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 420
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.521597710086439e-08,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 430
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.57301420397924e-09,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 440
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.212833302556258e-09,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 450
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.158697848236607e-09,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 460
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.269029751107489e-10,
      "logits/chosen": NaN,
      "logits/rejected": NaN,
      "logps/chosen": NaN,
      "logps/rejected": NaN,
      "loss": 0.0,
      "rewards/accuracies": 0.0,
      "rewards/chosen": NaN,
      "rewards/margins": NaN,
      "rewards/rejected": NaN,
      "step": 470
    },
    {
      "epoch": 1.0,
      "step": 478,
      "total_flos": 0.0,
      "train_loss": 1.0811490788750324e+21,
      "train_runtime": 4273.3161,
      "train_samples_per_second": 14.306,
      "train_steps_per_second": 0.112
    }
  ],
  "logging_steps": 10,
  "max_steps": 478,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}