{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 2514.601414684904,
      "learning_rate": 3.125e-08,
      "logits/generated": -2.661752223968506,
      "logits/real": -2.483980894088745,
      "logps/generated": -429.17132568359375,
      "logps/real": -342.051025390625,
      "loss": 1.3612,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06369426751592357,
      "grad_norm": 0.31574006570864244,
      "learning_rate": 3.1249999999999997e-07,
      "logits/generated": -2.668369770050049,
      "logits/real": -2.424091339111328,
      "logps/generated": -450.4893798828125,
      "logps/real": -144.69952392578125,
      "loss": 0.4008,
      "rewards/accuracies": 0.8888888955116272,
      "rewards/generated": -2.1318063735961914,
      "rewards/margins": 21.866958618164062,
      "rewards/real": 19.735153198242188,
      "step": 10
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 0.005520241230176221,
      "learning_rate": 4.858156028368794e-07,
      "logits/generated": -2.692908763885498,
      "logits/real": -2.329023599624634,
      "logps/generated": -478.9815368652344,
      "logps/real": -0.014682354405522346,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.981024742126465,
      "rewards/margins": 39.18465805053711,
      "rewards/real": 34.203636169433594,
      "step": 20
    },
    {
      "epoch": 0.1910828025477707,
      "grad_norm": 0.002789639064368334,
      "learning_rate": 4.50354609929078e-07,
      "logits/generated": -2.705698013305664,
      "logits/real": -2.342294216156006,
      "logps/generated": -486.1914978027344,
      "logps/real": -0.004650969058275223,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -5.702020645141602,
      "rewards/margins": 39.90666198730469,
      "rewards/real": 34.20463943481445,
      "step": 30
    },
    {
      "epoch": 0.25477707006369427,
      "grad_norm": 0.0019297231936813803,
      "learning_rate": 4.148936170212766e-07,
      "logits/generated": -2.7122185230255127,
      "logits/real": -2.348639965057373,
      "logps/generated": -489.88970947265625,
      "logps/real": -0.002834505634382367,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.071843147277832,
      "rewards/margins": 40.27666473388672,
      "rewards/real": 34.2048225402832,
      "step": 40
    },
    {
      "epoch": 0.3184713375796178,
      "grad_norm": 0.0014726852980064813,
      "learning_rate": 3.7943262411347514e-07,
      "logits/generated": -2.71730375289917,
      "logits/real": -2.3547444343566895,
      "logps/generated": -492.354248046875,
      "logps/real": -0.0020735759753733873,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.318298816680908,
      "rewards/margins": 40.523193359375,
      "rewards/real": 34.20489501953125,
      "step": 50
    },
    {
      "epoch": 0.3821656050955414,
      "grad_norm": 0.0012108227405915682,
      "learning_rate": 3.4397163120567375e-07,
      "logits/generated": -2.7216479778289795,
      "logits/real": -2.359346866607666,
      "logps/generated": -493.62725830078125,
      "logps/real": -0.0016389258671551943,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.445591926574707,
      "rewards/margins": 40.65053176879883,
      "rewards/real": 34.20494079589844,
      "step": 60
    },
    {
      "epoch": 0.445859872611465,
      "grad_norm": 0.0010092968797445821,
      "learning_rate": 3.085106382978723e-07,
      "logits/generated": -2.7243549823760986,
      "logits/real": -2.3620219230651855,
      "logps/generated": -494.82586669921875,
      "logps/real": -0.0013623478589579463,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.565457820892334,
      "rewards/margins": 40.77042770385742,
      "rewards/real": 34.20496368408203,
      "step": 70
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 0.0008924667007579917,
      "learning_rate": 2.730496453900709e-07,
      "logits/generated": -2.726926565170288,
      "logits/real": -2.362954616546631,
      "logps/generated": -495.93377685546875,
      "logps/real": -0.0011800352949649096,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.676251411437988,
      "rewards/margins": 40.88123321533203,
      "rewards/real": 34.204986572265625,
      "step": 80
    },
    {
      "epoch": 0.5732484076433121,
      "grad_norm": 0.0008155704567801252,
      "learning_rate": 2.375886524822695e-07,
      "logits/generated": -2.72874116897583,
      "logits/real": -2.366927146911621,
      "logps/generated": -496.6890563964844,
      "logps/real": -0.0010528427083045244,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.751776218414307,
      "rewards/margins": 40.95677185058594,
      "rewards/real": 34.204994201660156,
      "step": 90
    },
    {
      "epoch": 0.6369426751592356,
      "grad_norm": 0.000725474761841383,
      "learning_rate": 2.0212765957446807e-07,
      "logits/generated": -2.7310385704040527,
      "logits/real": -2.369218349456787,
      "logps/generated": -497.72625732421875,
      "logps/real": -0.000954283110331744,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.855503082275391,
      "rewards/margins": 41.06051254272461,
      "rewards/real": 34.20500946044922,
      "step": 100
    },
    {
      "epoch": 0.6369426751592356,
      "eval_logits/generated": -2.661693572998047,
      "eval_logits/real": -2.609511137008667,
      "eval_logps/generated": -259.66143798828125,
      "eval_logps/real": -210.63931274414062,
      "eval_loss": 0.9619492292404175,
      "eval_rewards/accuracies": 0.890625,
      "eval_rewards/generated": -0.14410093426704407,
      "eval_rewards/margins": 0.3460058867931366,
      "eval_rewards/real": 0.20190495252609253,
      "eval_runtime": 37.6272,
      "eval_samples_per_second": 13.288,
      "eval_steps_per_second": 0.425,
      "step": 100
    },
    {
      "epoch": 0.7006369426751592,
      "grad_norm": 0.0006953242722311237,
      "learning_rate": 1.6666666666666665e-07,
      "logits/generated": -2.732168436050415,
      "logits/real": -2.370328426361084,
      "logps/generated": -497.7915954589844,
      "logps/real": -0.0008821273222565651,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.86203145980835,
      "rewards/margins": 41.06704330444336,
      "rewards/real": 34.20501708984375,
      "step": 110
    },
    {
      "epoch": 0.7643312101910829,
      "grad_norm": 0.0006463359840785572,
      "learning_rate": 1.3120567375886523e-07,
      "logits/generated": -2.7338597774505615,
      "logits/real": -2.3714773654937744,
      "logps/generated": -498.8688049316406,
      "logps/real": -0.0008279000176116824,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.969751834869385,
      "rewards/margins": 41.174774169921875,
      "rewards/real": 34.205020904541016,
      "step": 120
    },
    {
      "epoch": 0.8280254777070064,
      "grad_norm": 0.0006205498614208318,
      "learning_rate": 9.574468085106382e-08,
      "logits/generated": -2.7348275184631348,
      "logits/real": -2.3729214668273926,
      "logps/generated": -498.8643493652344,
      "logps/real": -0.0007825180655345321,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.969304084777832,
      "rewards/margins": 41.17433547973633,
      "rewards/real": 34.20502471923828,
      "step": 130
    },
    {
      "epoch": 0.89171974522293,
      "grad_norm": 0.0005942730744268325,
      "learning_rate": 6.02836879432624e-08,
      "logits/generated": -2.7360432147979736,
      "logits/real": -2.374084949493408,
      "logps/generated": -499.4146423339844,
      "logps/real": -0.0007567574502900243,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -7.024338722229004,
      "rewards/margins": 41.229366302490234,
      "rewards/real": 34.20502471923828,
      "step": 140
    },
    {
      "epoch": 0.9554140127388535,
      "grad_norm": 0.0005956400007297931,
      "learning_rate": 2.4822695035460993e-08,
      "logits/generated": -2.73626708984375,
      "logits/real": -2.374666690826416,
      "logps/generated": -499.5492248535156,
      "logps/real": -0.0007398539455607533,
      "loss": 0.0,
      "rewards/accuracies": 1.0,
      "rewards/generated": -7.0377936363220215,
      "rewards/margins": 41.242820739746094,
      "rewards/real": 34.20502471923828,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 157,
      "total_flos": 0.0,
      "train_loss": 0.03164779691052703,
      "train_runtime": 1178.5993,
      "train_samples_per_second": 4.242,
      "train_steps_per_second": 0.133
    }
  ],
  "logging_steps": 10,
  "max_steps": 157,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}