{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6877637130801688,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 0.4396141469478607,
      "learning_rate": 8.620689655172415e-07,
      "logits/chosen": 1.6453087329864502,
      "logits/rejected": 1.694819450378418,
      "logps/chosen": -74.5937728881836,
      "logps/rejected": -83.19783782958984,
      "loss": 0.6928,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": 0.003385844174772501,
      "rewards/margins": 0.004794469103217125,
      "rewards/rejected": -0.0014086246956139803,
      "step": 10
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": 3.18404483795166,
      "learning_rate": 1.724137931034483e-06,
      "logits/chosen": 1.7945035696029663,
      "logits/rejected": 1.8347476720809937,
      "logps/chosen": -95.46636199951172,
      "logps/rejected": -101.22709655761719,
      "loss": 0.6933,
      "rewards/accuracies": 0.4625000059604645,
      "rewards/chosen": -0.0005593777750618756,
      "rewards/margins": -0.002013001125305891,
      "rewards/rejected": 0.0014536241069436073,
      "step": 20
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.48596081137657166,
      "learning_rate": 2.5862068965517246e-06,
      "logits/chosen": 1.774155616760254,
      "logits/rejected": 1.8374344110488892,
      "logps/chosen": -82.01265716552734,
      "logps/rejected": -84.23635864257812,
      "loss": 0.6948,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.0031326995231211185,
      "rewards/margins": -0.00463916826993227,
      "rewards/rejected": 0.0015064675826579332,
      "step": 30
    },
    {
      "epoch": 1.350210970464135,
      "grad_norm": 0.5144609808921814,
      "learning_rate": 3.448275862068966e-06,
      "logits/chosen": 1.838865876197815,
      "logits/rejected": 1.9505430459976196,
      "logps/chosen": -73.50071716308594,
      "logps/rejected": -88.8648452758789,
      "loss": 0.6928,
      "rewards/accuracies": 0.42500001192092896,
      "rewards/chosen": -0.0035957477521151304,
      "rewards/margins": -0.008830643258988857,
      "rewards/rejected": 0.005234894808381796,
      "step": 40
    },
    {
      "epoch": 1.6877637130801688,
      "grad_norm": 0.48295095562934875,
      "learning_rate": 4.310344827586207e-06,
      "logits/chosen": 1.8197529315948486,
      "logits/rejected": 1.8459796905517578,
      "logps/chosen": -83.36590576171875,
      "logps/rejected": -70.26930236816406,
      "loss": 0.6929,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.0030026868917047977,
      "rewards/margins": -0.006082554347813129,
      "rewards/rejected": 0.003079867223277688,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 580,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7011436887526605e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}