{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25396825396825395,
  "eval_steps": 50,
  "global_step": 200,
  "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
    }
  ],
  "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": 4.8604806577022566e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}