{
  "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": 178.77286563875307,
      "learning_rate": 1.7600461536419332e-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": 160.97877202778918,
      "learning_rate": 1.760046153641933e-07,
      "logits/chosen": -2.555966377258301,
      "logits/rejected": -2.5380208492279053,
      "logps/chosen": -87.92900848388672,
      "logps/rejected": -81.04818725585938,
      "loss": 0.6931,
      "rewards/accuracies": 0.2013888955116272,
      "rewards/chosen": -0.0037568057887256145,
      "rewards/margins": -0.0011305783409625292,
      "rewards/rejected": -0.0026262274477630854,
      "step": 10
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 135.4750421201187,
      "learning_rate": 1.671668693916127e-07,
      "logits/chosen": -2.6140284538269043,
      "logits/rejected": -2.5652213096618652,
      "logps/chosen": -103.2249755859375,
      "logps/rejected": -89.80636596679688,
      "loss": 0.6837,
      "rewards/accuracies": 0.3375000059604645,
      "rewards/chosen": 0.0341915600001812,
      "rewards/margins": 0.01302550919353962,
      "rewards/rejected": 0.021166052669286728,
      "step": 20
    },
    {
      "epoch": 0.3125,
      "grad_norm": 183.23637457075452,
      "learning_rate": 1.5832912341903208e-07,
      "logits/chosen": -2.518775701522827,
      "logits/rejected": -2.5330777168273926,
      "logps/chosen": -67.13838958740234,
      "logps/rejected": -74.79261779785156,
      "loss": 0.6768,
      "rewards/accuracies": 0.3062500059604645,
      "rewards/chosen": 0.08110855519771576,
      "rewards/margins": 0.044944558292627335,
      "rewards/rejected": 0.036163996905088425,
      "step": 30
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 117.61800068052908,
      "learning_rate": 1.4949137744645144e-07,
      "logits/chosen": -2.5774178504943848,
      "logits/rejected": -2.5653040409088135,
      "logps/chosen": -71.62496948242188,
      "logps/rejected": -70.44197082519531,
      "loss": 0.6712,
      "rewards/accuracies": 0.26875001192092896,
      "rewards/chosen": 0.14154085516929626,
      "rewards/margins": 0.06791118532419205,
      "rewards/rejected": 0.07362965494394302,
      "step": 40
    },
    {
      "epoch": 0.5208333333333334,
      "grad_norm": 134.94145476491178,
      "learning_rate": 1.4065363147387083e-07,
      "logits/chosen": -2.491271495819092,
      "logits/rejected": -2.503357410430908,
      "logps/chosen": -50.327152252197266,
      "logps/rejected": -58.57765579223633,
      "loss": 0.6631,
      "rewards/accuracies": 0.23125000298023224,
      "rewards/chosen": 0.15576013922691345,
      "rewards/margins": 0.0658084824681282,
      "rewards/rejected": 0.08995168656110764,
      "step": 50
    },
    {
      "epoch": 0.625,
      "grad_norm": 132.63437591048415,
      "learning_rate": 1.3181588550129022e-07,
      "logits/chosen": -2.5763726234436035,
      "logits/rejected": -2.557838201522827,
      "logps/chosen": -78.12178039550781,
      "logps/rejected": -78.89440155029297,
      "loss": 0.6587,
      "rewards/accuracies": 0.32499998807907104,
      "rewards/chosen": 0.25709980726242065,
      "rewards/margins": 0.1368531435728073,
      "rewards/rejected": 0.12024664878845215,
      "step": 60
    },
    {
      "epoch": 0.7291666666666666,
      "grad_norm": 131.450312242274,
      "learning_rate": 1.229781395287096e-07,
      "logits/chosen": -2.5564064979553223,
      "logits/rejected": -2.5472121238708496,
      "logps/chosen": -94.9344253540039,
      "logps/rejected": -84.7915267944336,
      "loss": 0.6471,
      "rewards/accuracies": 0.3499999940395355,
      "rewards/chosen": 0.3827608525753021,
      "rewards/margins": 0.20402593910694122,
      "rewards/rejected": 0.1787349283695221,
      "step": 70
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 204.1138249065331,
      "learning_rate": 1.1414039355612898e-07,
      "logits/chosen": -2.5576930046081543,
      "logits/rejected": -2.5041146278381348,
      "logps/chosen": -84.25480651855469,
      "logps/rejected": -78.98388671875,
      "loss": 0.6283,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": 0.37731510400772095,
      "rewards/margins": 0.2691493034362793,
      "rewards/rejected": 0.10816575586795807,
      "step": 80
    },
    {
      "epoch": 0.9375,
      "grad_norm": 173.37555247860905,
      "learning_rate": 1.0530264758354837e-07,
      "logits/chosen": -2.4902758598327637,
      "logits/rejected": -2.484860420227051,
      "logps/chosen": -53.16009521484375,
      "logps/rejected": -63.27381134033203,
      "loss": 0.6453,
      "rewards/accuracies": 0.26875001192092896,
      "rewards/chosen": 0.2224617451429367,
      "rewards/margins": 0.16971835494041443,
      "rewards/rejected": 0.052743397653102875,
      "step": 90
    },
    {
      "epoch": 1.0,
      "step": 96,
      "total_flos": 0.0,
      "train_loss": 0.6600211213032404,
      "train_runtime": 962.6608,
      "train_samples_per_second": 6.35,
      "train_steps_per_second": 0.1
    }
  ],
  "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
}