{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9921671018276762,
  "eval_steps": 100,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5.000000000000001e-07,
      "logits/chosen": 0.8826487064361572,
      "logits/rejected": 0.921362042427063,
      "logps/chosen": -36.58121871948242,
      "logps/rejected": -54.902320861816406,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.1,
      "learning_rate": 5e-06,
      "logits/chosen": 0.8917223811149597,
      "logits/rejected": 0.875190019607544,
      "logps/chosen": -87.82333374023438,
      "logps/rejected": -96.38070678710938,
      "loss": 0.6934,
      "rewards/accuracies": 0.2361111044883728,
      "rewards/chosen": -0.00021312937315087765,
      "rewards/margins": -0.00011523600551299751,
      "rewards/rejected": -9.78933458100073e-05,
      "step": 10
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.83118057351089e-06,
      "logits/chosen": 0.780292272567749,
      "logits/rejected": 0.8473358154296875,
      "logps/chosen": -91.71416473388672,
      "logps/rejected": -85.1246566772461,
      "loss": 0.6932,
      "rewards/accuracies": 0.25,
      "rewards/chosen": 0.00043298042146489024,
      "rewards/margins": 0.00031665078131482005,
      "rewards/rejected": 0.00011632966197794303,
      "step": 20
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.3475222930516484e-06,
      "logits/chosen": 0.8648103475570679,
      "logits/rejected": 0.8488438725471497,
      "logps/chosen": -85.26679992675781,
      "logps/rejected": -78.0839614868164,
      "loss": 0.6929,
      "rewards/accuracies": 0.3125,
      "rewards/chosen": 0.0005245368229225278,
      "rewards/margins": 0.00098425371106714,
      "rewards/rejected": -0.0004597169754561037,
      "step": 30
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.6143458894413463e-06,
      "logits/chosen": 0.7656652927398682,
      "logits/rejected": 0.8423829078674316,
      "logps/chosen": -122.68544006347656,
      "logps/rejected": -108.7737045288086,
      "loss": 0.6931,
      "rewards/accuracies": 0.28125,
      "rewards/chosen": 0.00047112005995586514,
      "rewards/margins": 0.00047660223208367825,
      "rewards/rejected": -5.482271262735594e-06,
      "step": 40
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.730670898658255e-06,
      "logits/chosen": 0.8398499488830566,
      "logits/rejected": 0.8686380386352539,
      "logps/chosen": -65.76744079589844,
      "logps/rejected": -71.65315246582031,
      "loss": 0.6932,
      "rewards/accuracies": 0.23749999701976776,
      "rewards/chosen": -0.00012343151320237666,
      "rewards/margins": -0.0002229490492027253,
      "rewards/rejected": 9.951753600034863e-05,
      "step": 50
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.8158425248197931e-06,
      "logits/chosen": 0.814559817314148,
      "logits/rejected": 0.8853690028190613,
      "logps/chosen": -117.60276794433594,
      "logps/rejected": -110.95735168457031,
      "loss": 0.6931,
      "rewards/accuracies": 0.32499998807907104,
      "rewards/chosen": 0.0003024066681973636,
      "rewards/margins": 0.000562971574254334,
      "rewards/rejected": -0.0002605649351608008,
      "step": 60
    },
    {
      "epoch": 0.73,
      "learning_rate": 9.934134090518593e-07,
      "logits/chosen": 0.8051468133926392,
      "logits/rejected": 0.8624836802482605,
      "logps/chosen": -82.67887115478516,
      "logps/rejected": -83.9195327758789,
      "loss": 0.6932,
      "rewards/accuracies": 0.26249998807907104,
      "rewards/chosen": -0.00015662939404137433,
      "rewards/margins": -4.1384984797332436e-05,
      "rewards/rejected": -0.00011524439469212666,
      "step": 70
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.7445716067596506e-07,
      "logits/chosen": 0.7656813263893127,
      "logits/rejected": 0.8298920392990112,
      "logps/chosen": -105.78785705566406,
      "logps/rejected": -104.972900390625,
      "loss": 0.6931,
      "rewards/accuracies": 0.2750000059604645,
      "rewards/chosen": 0.0002620227460283786,
      "rewards/margins": 0.00032469426514580846,
      "rewards/rejected": -6.267154822126031e-05,
      "step": 80
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.256725079024554e-08,
      "logits/chosen": 0.8350532650947571,
      "logits/rejected": 0.8562027215957642,
      "logps/chosen": -77.66747283935547,
      "logps/rejected": -90.00565338134766,
      "loss": 0.6929,
      "rewards/accuracies": 0.30000001192092896,
      "rewards/chosen": 0.00024019060947466642,
      "rewards/margins": 0.0006700255908071995,
      "rewards/rejected": -0.0004298349958844483,
      "step": 90
    },
    {
      "epoch": 0.99,
      "step": 95,
      "total_flos": 0.0,
      "train_loss": 0.6931231824975265,
      "train_runtime": 1147.8486,
      "train_samples_per_second": 5.326,
      "train_steps_per_second": 0.083
    }
  ],
  "logging_steps": 10,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}