{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010416666666666666,
      "grad_norm": 3.100854180799138,
      "learning_rate": 6.389441661416039e-08,
      "logits/chosen": -2.590585231781006,
      "logits/rejected": -2.5664222240448,
      "logps/chosen": -80.29847717285156,
      "logps/rejected": -53.10200881958008,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 2.781126507699089,
      "learning_rate": 6.389441661416038e-07,
      "logits/chosen": -2.5558536052703857,
      "logits/rejected": -2.5378901958465576,
      "logps/chosen": -87.89214324951172,
      "logps/rejected": -80.98480224609375,
      "loss": 0.6931,
      "rewards/accuracies": 0.2291666716337204,
      "rewards/chosen": 0.00010837005538633093,
      "rewards/margins": -0.00014457135694101453,
      "rewards/rejected": 0.0002529414196033031,
      "step": 10
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 2.553038645699022,
      "learning_rate": 5.762762398460686e-07,
      "logits/chosen": -2.5938525199890137,
      "logits/rejected": -2.543900966644287,
      "logps/chosen": -101.56424713134766,
      "logps/rejected": -88.41798400878906,
      "loss": 0.6914,
      "rewards/accuracies": 0.3375000059604645,
      "rewards/chosen": 0.00841432437300682,
      "rewards/margins": 0.0015086036873981357,
      "rewards/rejected": 0.006905719637870789,
      "step": 20
    },
    {
      "epoch": 0.3125,
      "grad_norm": 3.7950522400890523,
      "learning_rate": 5.136083135505332e-07,
      "logits/chosen": -2.456357002258301,
      "logits/rejected": -2.472012758255005,
      "logps/chosen": -66.62992095947266,
      "logps/rejected": -75.86373901367188,
      "loss": 0.6891,
      "rewards/accuracies": 0.32499998807907104,
      "rewards/chosen": 0.003802085295319557,
      "rewards/margins": 0.0082187969237566,
      "rewards/rejected": -0.004416711628437042,
      "step": 30
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 3.519596152843829,
      "learning_rate": 4.5094038725499785e-07,
      "logits/chosen": -2.5018997192382812,
      "logits/rejected": -2.4887325763702393,
      "logps/chosen": -71.3689956665039,
      "logps/rejected": -73.41954040527344,
      "loss": 0.6849,
      "rewards/accuracies": 0.3062500059604645,
      "rewards/chosen": 0.003661749418824911,
      "rewards/margins": 0.01640659011900425,
      "rewards/rejected": -0.012744839303195477,
      "step": 40
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 5.231502190809433,
      "learning_rate": 3.8827246095946254e-07,
      "logits/chosen": -2.3902275562286377,
      "logits/rejected": -2.4062817096710205,
      "logps/chosen": -49.79673385620117,
      "logps/rejected": -60.72575759887695,
      "loss": 0.6826,
      "rewards/accuracies": 0.22499999403953552,
      "rewards/chosen": 0.005200926214456558,
      "rewards/margins": 0.013756193220615387,
      "rewards/rejected": -0.008555267006158829,
      "step": 50
    },
    {
      "epoch": 0.625,
      "grad_norm": 4.689957831926571,
      "learning_rate": 3.256045346639272e-07,
      "logits/chosen": -2.4439873695373535,
      "logits/rejected": -2.4207093715667725,
      "logps/chosen": -86.81434631347656,
      "logps/rejected": -94.7623291015625,
      "loss": 0.6804,
      "rewards/accuracies": 0.3125,
      "rewards/chosen": -0.036475084722042084,
      "rewards/margins": 0.036166418343782425,
      "rewards/rejected": -0.07264150679111481,
      "step": 60
    },
    {
      "epoch": 0.7291666666666666,
      "grad_norm": 5.829443326665767,
      "learning_rate": 2.6293660836839186e-07,
      "logits/chosen": -2.3675405979156494,
      "logits/rejected": -2.348362445831299,
      "logps/chosen": -116.78021240234375,
      "logps/rejected": -112.79603576660156,
      "loss": 0.68,
      "rewards/accuracies": 0.3125,
      "rewards/chosen": -0.09623803943395615,
      "rewards/margins": 0.03254436329007149,
      "rewards/rejected": -0.12878240644931793,
      "step": 70
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 6.4331651891422785,
      "learning_rate": 2.0026868207285652e-07,
      "logits/chosen": -2.2932543754577637,
      "logits/rejected": -2.2299153804779053,
      "logps/chosen": -97.70858001708984,
      "logps/rejected": -105.18177795410156,
      "loss": 0.6695,
      "rewards/accuracies": 0.39375001192092896,
      "rewards/chosen": -0.05681135132908821,
      "rewards/margins": 0.06468762457370758,
      "rewards/rejected": -0.1214989647269249,
      "step": 80
    },
    {
      "epoch": 0.9375,
      "grad_norm": 5.087077256901478,
      "learning_rate": 1.376007557773212e-07,
      "logits/chosen": -2.2146198749542236,
      "logits/rejected": -2.2123677730560303,
      "logps/chosen": -61.2127571105957,
      "logps/rejected": -81.22966003417969,
      "loss": 0.6723,
      "rewards/accuracies": 0.26249998807907104,
      "rewards/chosen": -0.034062620252370834,
      "rewards/margins": 0.049583159387111664,
      "rewards/rejected": -0.0836457759141922,
      "step": 90
    },
    {
      "epoch": 1.0,
      "step": 96,
      "total_flos": 0.0,
      "train_loss": 0.6817257404327393,
      "train_runtime": 994.9537,
      "train_samples_per_second": 6.144,
      "train_steps_per_second": 0.096
    }
  ],
  "logging_steps": 10,
  "max_steps": 96,
  "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
}