{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15808974886784685,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013174145738987238,
      "grad_norm": 0.5102696418762207,
      "learning_rate": 1.25e-07,
      "logits/chosen": 10.088521957397461,
      "logits/rejected": 10.263787269592285,
      "logps/chosen": -0.9118157029151917,
      "logps/rejected": -0.9621729850769043,
      "loss": 1.3897,
      "rewards/accuracies": 0.5234375,
      "rewards/chosen": -1.8236314058303833,
      "rewards/margins": 0.10071463882923126,
      "rewards/rejected": -1.9243459701538086,
      "step": 1
    },
    {
      "epoch": 0.026348291477974475,
      "grad_norm": 0.9815747141838074,
      "learning_rate": 2.5e-07,
      "logits/chosen": 10.592972755432129,
      "logits/rejected": 10.720216751098633,
      "logps/chosen": -0.945902943611145,
      "logps/rejected": -1.0317902565002441,
      "loss": 1.3077,
      "rewards/accuracies": 0.609375,
      "rewards/chosen": -1.89180588722229,
      "rewards/margins": 0.1717745065689087,
      "rewards/rejected": -2.0635805130004883,
      "step": 2
    },
    {
      "epoch": 0.03952243721696171,
      "grad_norm": 0.9049758315086365,
      "learning_rate": 3.75e-07,
      "logits/chosen": 10.041976928710938,
      "logits/rejected": 10.399316787719727,
      "logps/chosen": -1.0869810581207275,
      "logps/rejected": -1.1895216703414917,
      "loss": 1.346,
      "rewards/accuracies": 0.578125,
      "rewards/chosen": -2.173962116241455,
      "rewards/margins": 0.20508113503456116,
      "rewards/rejected": -2.3790433406829834,
      "step": 3
    },
    {
      "epoch": 0.05269658295594895,
      "grad_norm": 1.8911848068237305,
      "learning_rate": 5e-07,
      "logits/chosen": 10.243470191955566,
      "logits/rejected": 10.443375587463379,
      "logps/chosen": -0.966098427772522,
      "logps/rejected": -1.0040662288665771,
      "loss": 1.4032,
      "rewards/accuracies": 0.546875,
      "rewards/chosen": -1.932196855545044,
      "rewards/margins": 0.07593552023172379,
      "rewards/rejected": -2.0081324577331543,
      "step": 4
    },
    {
      "epoch": 0.06587072869493618,
      "grad_norm": 0.6135074496269226,
      "learning_rate": 6.249999999999999e-07,
      "logits/chosen": 10.439040184020996,
      "logits/rejected": 10.739177703857422,
      "logps/chosen": -0.9262609481811523,
      "logps/rejected": -0.9657196998596191,
      "loss": 1.3727,
      "rewards/accuracies": 0.5546875,
      "rewards/chosen": -1.8525218963623047,
      "rewards/margins": 0.07891744375228882,
      "rewards/rejected": -1.9314393997192383,
      "step": 5
    },
    {
      "epoch": 0.07904487443392343,
      "grad_norm": 0.5990542769432068,
      "learning_rate": 7.5e-07,
      "logits/chosen": 10.910269737243652,
      "logits/rejected": 11.204473495483398,
      "logps/chosen": -0.9439595341682434,
      "logps/rejected": -1.0420396327972412,
      "loss": 1.3491,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -1.8879190683364868,
      "rewards/margins": 0.196160227060318,
      "rewards/rejected": -2.0840792655944824,
      "step": 6
    },
    {
      "epoch": 0.09221902017291066,
      "grad_norm": 1.3676807880401611,
      "learning_rate": 8.75e-07,
      "logits/chosen": 9.873465538024902,
      "logits/rejected": 10.022269248962402,
      "logps/chosen": -0.8941428661346436,
      "logps/rejected": -1.0010743141174316,
      "loss": 1.3507,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -1.788285732269287,
      "rewards/margins": 0.21386288106441498,
      "rewards/rejected": -2.0021486282348633,
      "step": 7
    },
    {
      "epoch": 0.1053931659118979,
      "grad_norm": 1.7690002918243408,
      "learning_rate": 1e-06,
      "logits/chosen": 10.597719192504883,
      "logits/rejected": 10.780376434326172,
      "logps/chosen": -0.9080270528793335,
      "logps/rejected": -0.9909782409667969,
      "loss": 1.3305,
      "rewards/accuracies": 0.640625,
      "rewards/chosen": -1.816054105758667,
      "rewards/margins": 0.16590236127376556,
      "rewards/rejected": -1.9819564819335938,
      "step": 8
    },
    {
      "epoch": 0.11856731165088513,
      "grad_norm": 1.056247353553772,
      "learning_rate": 9.994504457428556e-07,
      "logits/chosen": 10.446786880493164,
      "logits/rejected": 10.839168548583984,
      "logps/chosen": -1.1091859340667725,
      "logps/rejected": -1.0694739818572998,
      "loss": 1.5127,
      "rewards/accuracies": 0.5390625,
      "rewards/chosen": -2.218371868133545,
      "rewards/margins": -0.07942387461662292,
      "rewards/rejected": -2.1389479637145996,
      "step": 9
    },
    {
      "epoch": 0.13174145738987236,
      "grad_norm": 2.076240062713623,
      "learning_rate": 9.97802991010949e-07,
      "logits/chosen": 10.343971252441406,
      "logits/rejected": 10.492179870605469,
      "logps/chosen": -0.9705042839050293,
      "logps/rejected": -0.9916192889213562,
      "loss": 1.4611,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -1.9410085678100586,
      "rewards/margins": 0.04223020374774933,
      "rewards/rejected": -1.9832385778427124,
      "step": 10
    },
    {
      "epoch": 0.14491560312885962,
      "grad_norm": 1.13358736038208,
      "learning_rate": 9.950612572673255e-07,
      "logits/chosen": 10.49313735961914,
      "logits/rejected": 10.680143356323242,
      "logps/chosen": -1.1081148386001587,
      "logps/rejected": -1.223841667175293,
      "loss": 1.3449,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -2.2162296772003174,
      "rewards/margins": 0.23145350813865662,
      "rewards/rejected": -2.447683334350586,
      "step": 11
    },
    {
      "epoch": 0.15808974886784685,
      "grad_norm": 1.1638388633728027,
      "learning_rate": 9.912312714377879e-07,
      "logits/chosen": 10.328557014465332,
      "logits/rejected": 10.365793228149414,
      "logps/chosen": -0.9249637722969055,
      "logps/rejected": -0.9842618703842163,
      "loss": 1.351,
      "rewards/accuracies": 0.6015625,
      "rewards/chosen": -1.849927544593811,
      "rewards/margins": 0.11859625577926636,
      "rewards/rejected": -1.9685237407684326,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 12,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}