{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9874476987447699,
  "eval_steps": 500,
  "global_step": 59,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016736401673640166,
      "grad_norm": 12.245462384069063,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": -2.8317770957946777,
      "logits/rejected": -2.7326111793518066,
      "logps/chosen": -190.3253173828125,
      "logps/pi_response": -110.92029571533203,
      "logps/ref_response": -110.92029571533203,
      "logps/rejected": -223.7691192626953,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.16736401673640167,
      "grad_norm": 11.258294256737887,
      "learning_rate": 4.930057285201027e-07,
      "logits/chosen": -2.7557287216186523,
      "logits/rejected": -2.7092771530151367,
      "logps/chosen": -216.87799072265625,
      "logps/pi_response": -114.42035675048828,
      "logps/ref_response": -114.2578125,
      "logps/rejected": -264.3336486816406,
      "loss": 0.6848,
      "rewards/accuracies": 0.5486111044883728,
      "rewards/chosen": -0.02949061244726181,
      "rewards/margins": 0.02440599910914898,
      "rewards/rejected": -0.05389661341905594,
      "step": 10
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 26.158633449418044,
      "learning_rate": 4.187457503795526e-07,
      "logits/chosen": -2.7771294116973877,
      "logits/rejected": -2.7362141609191895,
      "logps/chosen": -254.28701782226562,
      "logps/pi_response": -111.6153335571289,
      "logps/ref_response": -113.4717788696289,
      "logps/rejected": -308.6377868652344,
      "loss": 0.6304,
      "rewards/accuracies": 0.6312500238418579,
      "rewards/chosen": -0.2588905096054077,
      "rewards/margins": 0.27992284297943115,
      "rewards/rejected": -0.5388133525848389,
      "step": 20
    },
    {
      "epoch": 0.502092050209205,
      "grad_norm": 15.587388407908863,
      "learning_rate": 2.8691164100062034e-07,
      "logits/chosen": -2.754197359085083,
      "logits/rejected": -2.718698024749756,
      "logps/chosen": -297.10418701171875,
      "logps/pi_response": -142.0721893310547,
      "logps/ref_response": -120.0687026977539,
      "logps/rejected": -351.3653259277344,
      "loss": 0.5839,
      "rewards/accuracies": 0.690625011920929,
      "rewards/chosen": -0.523945689201355,
      "rewards/margins": 0.4522995352745056,
      "rewards/rejected": -0.9762452840805054,
      "step": 30
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 16.430781172533628,
      "learning_rate": 1.4248369943086995e-07,
      "logits/chosen": -2.6763617992401123,
      "logits/rejected": -2.6239538192749023,
      "logps/chosen": -278.3578186035156,
      "logps/pi_response": -144.41726684570312,
      "logps/ref_response": -110.48355865478516,
      "logps/rejected": -363.93450927734375,
      "loss": 0.5503,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -0.5653710961341858,
      "rewards/margins": 0.5595625042915344,
      "rewards/rejected": -1.1249334812164307,
      "step": 40
    },
    {
      "epoch": 0.8368200836820083,
      "grad_norm": 18.753898859495603,
      "learning_rate": 3.473909705816111e-08,
      "logits/chosen": -2.624819040298462,
      "logits/rejected": -2.5662152767181396,
      "logps/chosen": -287.62396240234375,
      "logps/pi_response": -165.9267578125,
      "logps/ref_response": -112.31349182128906,
      "logps/rejected": -373.04034423828125,
      "loss": 0.5435,
      "rewards/accuracies": 0.71875,
      "rewards/chosen": -0.7290452122688293,
      "rewards/margins": 0.625941276550293,
      "rewards/rejected": -1.3549864292144775,
      "step": 50
    },
    {
      "epoch": 0.9874476987447699,
      "step": 59,
      "total_flos": 0.0,
      "train_loss": 0.587253408916926,
      "train_runtime": 2659.1015,
      "train_samples_per_second": 5.747,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 10,
  "max_steps": 59,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}