{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 500,
  "global_step": 468,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 34.43344966418026,
      "learning_rate": 4.999373573764186e-07,
      "logits/chosen": -1.2502222061157227,
      "logits/rejected": -1.2531837224960327,
      "logps/chosen": -380.0782165527344,
      "logps/rejected": -386.2172546386719,
      "loss": 0.8964,
      "rewards/accuracies": 0.4950000047683716,
      "rewards/chosen": -0.023556923493742943,
      "rewards/margins": 0.005924960598349571,
      "rewards/rejected": -0.029481882229447365,
      "step": 50
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 37.45052221475562,
      "learning_rate": 4.807012604511541e-07,
      "logits/chosen": -1.2312381267547607,
      "logits/rejected": -1.2327096462249756,
      "logps/chosen": -395.3690490722656,
      "logps/rejected": -403.4739990234375,
      "loss": 0.8496,
      "rewards/accuracies": 0.5987499952316284,
      "rewards/chosen": -0.4553294777870178,
      "rewards/margins": 0.1346004605293274,
      "rewards/rejected": -0.5899299383163452,
      "step": 100
    },
    {
      "epoch": 0.32,
      "grad_norm": 35.36746039819262,
      "learning_rate": 4.2971971741276185e-07,
      "logits/chosen": -1.260800838470459,
      "logits/rejected": -1.2635284662246704,
      "logps/chosen": -376.4151306152344,
      "logps/rejected": -384.2753601074219,
      "loss": 0.8243,
      "rewards/accuracies": 0.5987499952316284,
      "rewards/chosen": -0.9694927930831909,
      "rewards/margins": 0.27553480863571167,
      "rewards/rejected": -1.2450276613235474,
      "step": 150
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 36.27189952514476,
      "learning_rate": 3.540079991103235e-07,
      "logits/chosen": -1.26079523563385,
      "logits/rejected": -1.2639491558074951,
      "logps/chosen": -394.5101623535156,
      "logps/rejected": -405.01641845703125,
      "loss": 0.8048,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -1.2865251302719116,
      "rewards/margins": 0.49585381150245667,
      "rewards/rejected": -1.7823787927627563,
      "step": 200
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 32.6541770215758,
      "learning_rate": 2.639843506318899e-07,
      "logits/chosen": -1.252700686454773,
      "logits/rejected": -1.263854742050171,
      "logps/chosen": -384.5255126953125,
      "logps/rejected": -390.5956726074219,
      "loss": 0.7906,
      "rewards/accuracies": 0.65625,
      "rewards/chosen": -1.3771264553070068,
      "rewards/margins": 0.43737706542015076,
      "rewards/rejected": -1.8145036697387695,
      "step": 250
    },
    {
      "epoch": 0.64,
      "grad_norm": 36.7055592501965,
      "learning_rate": 1.7203639775848423e-07,
      "logits/chosen": -1.2447404861450195,
      "logits/rejected": -1.2467286586761475,
      "logps/chosen": -384.63165283203125,
      "logps/rejected": -393.9804992675781,
      "loss": 0.7835,
      "rewards/accuracies": 0.699999988079071,
      "rewards/chosen": -1.325575590133667,
      "rewards/margins": 0.5131824016571045,
      "rewards/rejected": -1.8387579917907715,
      "step": 300
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 30.904620054592144,
      "learning_rate": 9.081655850224449e-08,
      "logits/chosen": -1.2564585208892822,
      "logits/rejected": -1.256412386894226,
      "logps/chosen": -383.8439025878906,
      "logps/rejected": -396.41839599609375,
      "loss": 0.7776,
      "rewards/accuracies": 0.6775000095367432,
      "rewards/chosen": -1.3743709325790405,
      "rewards/margins": 0.5735958814620972,
      "rewards/rejected": -1.9479665756225586,
      "step": 350
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 34.514970559024796,
      "learning_rate": 3.150101814011136e-08,
      "logits/chosen": -1.2832634449005127,
      "logits/rejected": -1.2844091653823853,
      "logps/chosen": -393.8801574707031,
      "logps/rejected": -403.3578186035156,
      "loss": 0.7851,
      "rewards/accuracies": 0.675000011920929,
      "rewards/chosen": -1.4652782678604126,
      "rewards/margins": 0.5471586585044861,
      "rewards/rejected": -2.012436866760254,
      "step": 400
    },
    {
      "epoch": 0.96,
      "grad_norm": 33.17626594386728,
      "learning_rate": 2.251839967945535e-09,
      "logits/chosen": -1.242918610572815,
      "logits/rejected": -1.2440977096557617,
      "logps/chosen": -381.6874084472656,
      "logps/rejected": -393.9809265136719,
      "loss": 0.7781,
      "rewards/accuracies": 0.6937500238418579,
      "rewards/chosen": -1.4276537895202637,
      "rewards/margins": 0.5591089129447937,
      "rewards/rejected": -1.9867626428604126,
      "step": 450
    },
    {
      "epoch": 0.9984,
      "step": 468,
      "total_flos": 160065019445248.0,
      "train_loss": 0.8088664193438668,
      "train_runtime": 8283.0284,
      "train_samples_per_second": 7.244,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 50,
  "max_steps": 468,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 160065019445248.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}