{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 1000,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 0.2610610014559749,
      "learning_rate": 2.0000000000000002e-07,
      "logits/chosen": -1.7501684427261353,
      "logits/rejected": -1.5946102142333984,
      "logps/chosen": -84.6928939819336,
      "logps/rejected": -66.21642303466797,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.22905427192235048,
      "learning_rate": 2.0000000000000003e-06,
      "logits/chosen": -1.743150234222412,
      "logits/rejected": -1.7186625003814697,
      "logps/chosen": -75.15956115722656,
      "logps/rejected": -78.51848602294922,
      "loss": 0.6929,
      "rewards/accuracies": 0.5694444179534912,
      "rewards/chosen": 0.0005810303264297545,
      "rewards/margins": 0.0006510103703476489,
      "rewards/rejected": -6.998008029768243e-05,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.22900106097369388,
      "learning_rate": 4.000000000000001e-06,
      "logits/chosen": -1.7664934396743774,
      "logits/rejected": -1.697330117225647,
      "logps/chosen": -77.00563049316406,
      "logps/rejected": -74.59007263183594,
      "loss": 0.6898,
      "rewards/accuracies": 0.9624999761581421,
      "rewards/chosen": 0.004773316439241171,
      "rewards/margins": 0.006489777471870184,
      "rewards/rejected": -0.001716460450552404,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.2398363937620789,
      "learning_rate": 4.993910125649561e-06,
      "logits/chosen": -1.670393705368042,
      "logits/rejected": -1.7334346771240234,
      "logps/chosen": -70.95411682128906,
      "logps/rejected": -81.66401672363281,
      "loss": 0.6758,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.021032074466347694,
      "rewards/margins": 0.03419991582632065,
      "rewards/rejected": -0.013167845085263252,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4134736462223887,
      "learning_rate": 4.9453690018345144e-06,
      "logits/chosen": -1.7007486820220947,
      "logits/rejected": -1.7079846858978271,
      "logps/chosen": -68.65242004394531,
      "logps/rejected": -83.7640609741211,
      "loss": 0.6394,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.06118398904800415,
      "rewards/margins": 0.11314834654331207,
      "rewards/rejected": -0.051964350044727325,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5811657939889897,
      "learning_rate": 4.849231551964771e-06,
      "logits/chosen": -1.680452585220337,
      "logits/rejected": -1.6310945749282837,
      "logps/chosen": -63.04345703125,
      "logps/rejected": -102.03121948242188,
      "loss": 0.5323,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.1268819272518158,
      "rewards/margins": 0.3797517418861389,
      "rewards/rejected": -0.2528698444366455,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.3746410656156246,
      "learning_rate": 4.707368982147318e-06,
      "logits/chosen": -1.6536400318145752,
      "logits/rejected": -1.496199607849121,
      "logps/chosen": -55.06901931762695,
      "logps/rejected": -124.32417297363281,
      "loss": 0.3761,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.2706597149372101,
      "rewards/margins": 0.8032084703445435,
      "rewards/rejected": -0.5325487852096558,
      "step": 60
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.2923014161860858,
      "learning_rate": 4.522542485937369e-06,
      "logits/chosen": -1.4761438369750977,
      "logits/rejected": -1.4017894268035889,
      "logps/chosen": -44.963287353515625,
      "logps/rejected": -186.46328735351562,
      "loss": 0.2624,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.33375969529151917,
      "rewards/margins": 1.4536139965057373,
      "rewards/rejected": -1.1198543310165405,
      "step": 70
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.1321053576972282,
      "learning_rate": 4.2983495008466285e-06,
      "logits/chosen": -1.4355762004852295,
      "logits/rejected": -1.3916115760803223,
      "logps/chosen": -38.39271926879883,
      "logps/rejected": -254.19973754882812,
      "loss": 0.2324,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.35416102409362793,
      "rewards/margins": 2.1357216835021973,
      "rewards/rejected": -1.7815606594085693,
      "step": 80
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.14508831317113868,
      "learning_rate": 4.039153688314146e-06,
      "logits/chosen": -1.5442588329315186,
      "logits/rejected": -1.526135802268982,
      "logps/chosen": -35.97533416748047,
      "logps/rejected": -263.40643310546875,
      "loss": 0.2095,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.41692012548446655,
      "rewards/margins": 2.3173232078552246,
      "rewards/rejected": -1.9004030227661133,
      "step": 90
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.44893168632741065,
      "learning_rate": 3.7500000000000005e-06,
      "logits/chosen": -1.2732983827590942,
      "logits/rejected": -1.2810883522033691,
      "logps/chosen": -31.883533477783203,
      "logps/rejected": -319.82061767578125,
      "loss": 0.1721,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.4404378831386566,
      "rewards/margins": 2.844158411026001,
      "rewards/rejected": -2.4037206172943115,
      "step": 100
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.6002566776493338,
      "learning_rate": 3.436516483539781e-06,
      "logits/chosen": -1.155807614326477,
      "logits/rejected": -1.1776975393295288,
      "logps/chosen": -31.725173950195312,
      "logps/rejected": -360.02349853515625,
      "loss": 0.1083,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.40672487020492554,
      "rewards/margins": 3.2172622680664062,
      "rewards/rejected": -2.810537338256836,
      "step": 110
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.15892065424589785,
      "learning_rate": 3.1048047389991693e-06,
      "logits/chosen": -1.228723406791687,
      "logits/rejected": -1.1159226894378662,
      "logps/chosen": -44.75030517578125,
      "logps/rejected": -419.255126953125,
      "loss": 0.0409,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.3626783490180969,
      "rewards/margins": 3.842852830886841,
      "rewards/rejected": -3.4801743030548096,
      "step": 120
    },
    {
      "epoch": 5.2,
      "grad_norm": 0.04827040736700255,
      "learning_rate": 2.761321158169134e-06,
      "logits/chosen": -1.0756232738494873,
      "logits/rejected": -1.0372257232666016,
      "logps/chosen": -64.86322021484375,
      "logps/rejected": -753.9734497070312,
      "loss": 0.0049,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.14987702667713165,
      "rewards/margins": 6.945639133453369,
      "rewards/rejected": -6.795762062072754,
      "step": 130
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.02673618186874915,
      "learning_rate": 2.4127512582437486e-06,
      "logits/chosen": -1.1154285669326782,
      "logits/rejected": -0.9958986043930054,
      "logps/chosen": -69.85175323486328,
      "logps/rejected": -913.9327392578125,
      "loss": 0.0029,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.10866590589284897,
      "rewards/margins": 8.513258934020996,
      "rewards/rejected": -8.404594421386719,
      "step": 140
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.017203740876186722,
      "learning_rate": 2.0658795558326745e-06,
      "logits/chosen": -1.0685889720916748,
      "logits/rejected": -1.033384919166565,
      "logps/chosen": -67.58888244628906,
      "logps/rejected": -917.8318481445312,
      "loss": 0.0024,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.08431224524974823,
      "rewards/margins": 8.512849807739258,
      "rewards/rejected": -8.42853832244873,
      "step": 150
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.015005056648195798,
      "learning_rate": 1.7274575140626318e-06,
      "logits/chosen": -1.1218775510787964,
      "logits/rejected": -1.0821073055267334,
      "logps/chosen": -61.10993576049805,
      "logps/rejected": -929.9596557617188,
      "loss": 0.0019,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.15528056025505066,
      "rewards/margins": 8.694746971130371,
      "rewards/rejected": -8.539467811584473,
      "step": 160
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.011209472305113497,
      "learning_rate": 1.4040721330273063e-06,
      "logits/chosen": -1.1669288873672485,
      "logits/rejected": -1.057388424873352,
      "logps/chosen": -59.08354568481445,
      "logps/rejected": -995.8665771484375,
      "loss": 0.0016,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.21780769526958466,
      "rewards/margins": 9.462162971496582,
      "rewards/rejected": -9.244354248046875,
      "step": 170
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.012213732988109802,
      "learning_rate": 1.1020177413231334e-06,
      "logits/chosen": -1.0734723806381226,
      "logits/rejected": -1.0714576244354248,
      "logps/chosen": -54.94775390625,
      "logps/rejected": -925.8068237304688,
      "loss": 0.0017,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.20917268097400665,
      "rewards/margins": 8.696084976196289,
      "rewards/rejected": -8.486912727355957,
      "step": 180
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.0137000842262227,
      "learning_rate": 8.271734841028553e-07,
      "logits/chosen": -1.1287630796432495,
      "logits/rejected": -1.0409098863601685,
      "logps/chosen": -55.30584716796875,
      "logps/rejected": -984.7487182617188,
      "loss": 0.0016,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.21431966125965118,
      "rewards/margins": 9.310848236083984,
      "rewards/rejected": -9.096528053283691,
      "step": 190
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.012982424059208061,
      "learning_rate": 5.848888922025553e-07,
      "logits/chosen": -1.1048905849456787,
      "logits/rejected": -1.0343353748321533,
      "logps/chosen": -55.2299919128418,
      "logps/rejected": -963.7037353515625,
      "loss": 0.0016,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.2215685397386551,
      "rewards/margins": 9.095995903015137,
      "rewards/rejected": -8.87442684173584,
      "step": 200
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.011333873276454402,
      "learning_rate": 3.798797596089351e-07,
      "logits/chosen": -1.0944920778274536,
      "logits/rejected": -0.9962091445922852,
      "logps/chosen": -53.680267333984375,
      "logps/rejected": -962.94775390625,
      "loss": 0.0015,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.24401147663593292,
      "rewards/margins": 9.146904945373535,
      "rewards/rejected": -8.902894973754883,
      "step": 210
    },
    {
      "epoch": 8.8,
      "grad_norm": 0.010235633073822109,
      "learning_rate": 2.1613635589349756e-07,
      "logits/chosen": -1.069654107093811,
      "logits/rejected": -1.0441746711730957,
      "logps/chosen": -53.099769592285156,
      "logps/rejected": -953.6365356445312,
      "loss": 0.0015,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.22151072323322296,
      "rewards/margins": 8.963228225708008,
      "rewards/rejected": -8.741719245910645,
      "step": 220
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.012374131573979113,
      "learning_rate": 9.684576015420277e-08,
      "logits/chosen": -1.023950219154358,
      "logits/rejected": -1.0566022396087646,
      "logps/chosen": -50.87507247924805,
      "logps/rejected": -911.796875,
      "loss": 0.0015,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.20660237967967987,
      "rewards/margins": 8.510995864868164,
      "rewards/rejected": -8.30439281463623,
      "step": 230
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.010557040037916637,
      "learning_rate": 2.4329828146074096e-08,
      "logits/chosen": -1.1207894086837769,
      "logits/rejected": -1.097846269607544,
      "logps/chosen": -54.16496658325195,
      "logps/rejected": -937.8318481445312,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.23018613457679749,
      "rewards/margins": 8.850129127502441,
      "rewards/rejected": -8.619942665100098,
      "step": 240
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.01132325198281179,
      "learning_rate": 0.0,
      "logits/chosen": -1.1102557182312012,
      "logits/rejected": -1.01675546169281,
      "logps/chosen": -56.481834411621094,
      "logps/rejected": -970.00634765625,
      "loss": 0.0015,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.22424273192882538,
      "rewards/margins": 9.186958312988281,
      "rewards/rejected": -8.962717056274414,
      "step": 250
    },
    {
      "epoch": 10.0,
      "step": 250,
      "total_flos": 0.0,
      "train_loss": 0.18631765481829643,
      "train_runtime": 3826.8955,
      "train_samples_per_second": 2.09,
      "train_steps_per_second": 0.065
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "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
}