{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992429977289932,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.941176470588235e-08,
      "logits/chosen": -0.36791229248046875,
      "logits/rejected": 1.366540551185608,
      "logps/chosen": -143.6042022705078,
      "logps/rejected": -273.9673156738281,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.941176470588235e-07,
      "logits/chosen": -0.5245670676231384,
      "logits/rejected": 1.248136281967163,
      "logps/chosen": -224.94821166992188,
      "logps/rejected": -359.60687255859375,
      "loss": 0.6689,
      "rewards/accuracies": 0.6597222089767456,
      "rewards/chosen": -0.021773571148514748,
      "rewards/margins": 0.06528930366039276,
      "rewards/rejected": -0.08706288039684296,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.994932636402031e-07,
      "logits/chosen": -0.00770964939147234,
      "logits/rejected": 1.8876569271087646,
      "logps/chosen": -248.1709442138672,
      "logps/rejected": -470.3589782714844,
      "loss": 0.5867,
      "rewards/accuracies": 0.7875000238418579,
      "rewards/chosen": -0.5789338946342468,
      "rewards/margins": 0.8933883905410767,
      "rewards/rejected": -1.4723222255706787,
      "step": 20
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.905416503522123e-07,
      "logits/chosen": -0.027714919298887253,
      "logits/rejected": 1.730603814125061,
      "logps/chosen": -320.3919677734375,
      "logps/rejected": -555.4063720703125,
      "loss": 0.5422,
      "rewards/accuracies": 0.71875,
      "rewards/chosen": -0.9962596893310547,
      "rewards/margins": 1.338209867477417,
      "rewards/rejected": -2.3344695568084717,
      "step": 30
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.707922373336523e-07,
      "logits/chosen": 0.3444180190563202,
      "logits/rejected": 1.8734357357025146,
      "logps/chosen": -267.8757019042969,
      "logps/rejected": -508.5665588378906,
      "loss": 0.4963,
      "rewards/accuracies": 0.824999988079071,
      "rewards/chosen": -0.6485141515731812,
      "rewards/margins": 1.0762808322906494,
      "rewards/rejected": -1.7247949838638306,
      "step": 40
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.4113156629677313e-07,
      "logits/chosen": 0.37747180461883545,
      "logits/rejected": 2.4962353706359863,
      "logps/chosen": -263.87420654296875,
      "logps/rejected": -523.7318115234375,
      "loss": 0.4954,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": -0.6324308514595032,
      "rewards/margins": 1.1557624340057373,
      "rewards/rejected": -1.7881933450698853,
      "step": 50
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.0289109058972283e-07,
      "logits/chosen": 0.44958215951919556,
      "logits/rejected": 2.4981770515441895,
      "logps/chosen": -306.72894287109375,
      "logps/rejected": -533.3639526367188,
      "loss": 0.4826,
      "rewards/accuracies": 0.7749999761581421,
      "rewards/chosen": -0.7705734372138977,
      "rewards/margins": 1.0842384099960327,
      "rewards/rejected": -1.8548120260238647,
      "step": 60
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.577874068920446e-07,
      "logits/chosen": 0.39437779784202576,
      "logits/rejected": 1.8338779211044312,
      "logps/chosen": -271.2483215332031,
      "logps/rejected": -511.545654296875,
      "loss": 0.4825,
      "rewards/accuracies": 0.8187500238418579,
      "rewards/chosen": -0.6353504657745361,
      "rewards/margins": 1.111212134361267,
      "rewards/rejected": -1.7465627193450928,
      "step": 70
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.078451980100854e-07,
      "logits/chosen": 0.38897716999053955,
      "logits/rejected": 2.2546534538269043,
      "logps/chosen": -290.3913879394531,
      "logps/rejected": -523.7283935546875,
      "loss": 0.4871,
      "rewards/accuracies": 0.793749988079071,
      "rewards/chosen": -0.7725954055786133,
      "rewards/margins": 1.1881004571914673,
      "rewards/rejected": -1.9606958627700806,
      "step": 80
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.553063458334059e-07,
      "logits/chosen": 0.24224960803985596,
      "logits/rejected": 2.18202543258667,
      "logps/chosen": -291.9999694824219,
      "logps/rejected": -528.9313354492188,
      "loss": 0.4659,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -0.6901915669441223,
      "rewards/margins": 1.1535792350769043,
      "rewards/rejected": -1.8437706232070923,
      "step": 90
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.0252929432814287e-07,
      "logits/chosen": 0.29941219091415405,
      "logits/rejected": 2.375978708267212,
      "logps/chosen": -254.08950805664062,
      "logps/rejected": -499.0948181152344,
      "loss": 0.4401,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": -0.6152492165565491,
      "rewards/margins": 1.0863755941390991,
      "rewards/rejected": -1.7016246318817139,
      "step": 100
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.5188318011445906e-07,
      "logits/chosen": 0.29582899808883667,
      "logits/rejected": 2.588685989379883,
      "logps/chosen": -301.9359436035156,
      "logps/rejected": -512.3338012695312,
      "loss": 0.4591,
      "rewards/accuracies": 0.8125,
      "rewards/chosen": -0.8254504203796387,
      "rewards/margins": 1.0966691970825195,
      "rewards/rejected": -1.9221197366714478,
      "step": 110
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.0564148305586295e-07,
      "logits/chosen": 0.34316009283065796,
      "logits/rejected": 2.3965556621551514,
      "logps/chosen": -301.0910339355469,
      "logps/rejected": -507.458251953125,
      "loss": 0.4652,
      "rewards/accuracies": 0.762499988079071,
      "rewards/chosen": -0.8790184855461121,
      "rewards/margins": 0.9550568461418152,
      "rewards/rejected": -1.8340752124786377,
      "step": 120
    },
    {
      "epoch": 0.79,
      "learning_rate": 6.587997083462196e-08,
      "logits/chosen": 0.7106651067733765,
      "logits/rejected": 2.231572389602661,
      "logps/chosen": -312.9052734375,
      "logps/rejected": -524.6278686523438,
      "loss": 0.4696,
      "rewards/accuracies": 0.7562500238418579,
      "rewards/chosen": -0.8491412401199341,
      "rewards/margins": 1.0410358905792236,
      "rewards/rejected": -1.8901771306991577,
      "step": 130
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.438351873250492e-08,
      "logits/chosen": 0.49447330832481384,
      "logits/rejected": 2.810368537902832,
      "logps/chosen": -259.0260925292969,
      "logps/rejected": -522.2190551757812,
      "loss": 0.4652,
      "rewards/accuracies": 0.8500000238418579,
      "rewards/chosen": -0.7394121885299683,
      "rewards/margins": 1.2198739051818848,
      "rewards/rejected": -1.959286093711853,
      "step": 140
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.256598743236703e-08,
      "logits/chosen": 0.6611243486404419,
      "logits/rejected": 2.3112754821777344,
      "logps/chosen": -326.75994873046875,
      "logps/rejected": -526.3076171875,
      "loss": 0.4862,
      "rewards/accuracies": 0.7875000238418579,
      "rewards/chosen": -0.9679144620895386,
      "rewards/margins": 1.0426340103149414,
      "rewards/rejected": -2.0105483531951904,
      "step": 150
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.406755487774386e-09,
      "logits/chosen": 0.5118433833122253,
      "logits/rejected": 2.144733428955078,
      "logps/chosen": -298.64678955078125,
      "logps/rejected": -506.86346435546875,
      "loss": 0.4578,
      "rewards/accuracies": 0.7875000238418579,
      "rewards/chosen": -0.8880035281181335,
      "rewards/margins": 0.9844219088554382,
      "rewards/rejected": -1.8724254369735718,
      "step": 160
    },
    {
      "epoch": 1.0,
      "step": 165,
      "total_flos": 0.0,
      "train_loss": 0.49529894770997945,
      "train_runtime": 10046.2235,
      "train_samples_per_second": 2.104,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}