{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.042973785990545764,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008594757198109154,
      "grad_norm": 0.05934199318289757,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.762972831726074,
      "logits/rejected": 15.199728012084961,
      "logps/chosen": -0.3259914815425873,
      "logps/rejected": -0.34297481179237366,
      "loss": 0.9377,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": -0.4889872074127197,
      "rewards/margins": 0.02547495998442173,
      "rewards/rejected": -0.5144621729850769,
      "step": 10
    },
    {
      "epoch": 0.017189514396218308,
      "grad_norm": 0.06342790275812149,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.351249694824219,
      "logits/rejected": 15.068448066711426,
      "logps/chosen": -0.2809392511844635,
      "logps/rejected": -0.3711296617984772,
      "loss": 0.9352,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.42140883207321167,
      "rewards/margins": 0.1352856159210205,
      "rewards/rejected": -0.5566944479942322,
      "step": 20
    },
    {
      "epoch": 0.02578427159432746,
      "grad_norm": 0.053961098194122314,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.636960983276367,
      "logits/rejected": 15.265243530273438,
      "logps/chosen": -0.2820780873298645,
      "logps/rejected": -0.34024301171302795,
      "loss": 0.9351,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.42311716079711914,
      "rewards/margins": 0.08724743127822876,
      "rewards/rejected": -0.5103646516799927,
      "step": 30
    },
    {
      "epoch": 0.034379028792436615,
      "grad_norm": 0.13506193459033966,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.4556884765625,
      "logits/rejected": 15.048967361450195,
      "logps/chosen": -0.2897028625011444,
      "logps/rejected": -0.34129124879837036,
      "loss": 0.922,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.43455424904823303,
      "rewards/margins": 0.07738252729177475,
      "rewards/rejected": -0.5119368433952332,
      "step": 40
    },
    {
      "epoch": 0.042973785990545764,
      "grad_norm": 0.05230574309825897,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.628789901733398,
      "logits/rejected": 15.307828903198242,
      "logps/chosen": -0.28786614537239075,
      "logps/rejected": -0.3513876795768738,
      "loss": 0.9201,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.4317992329597473,
      "rewards/margins": 0.09528233855962753,
      "rewards/rejected": -0.5270815491676331,
      "step": 50
    },
    {
      "epoch": 0.042973785990545764,
      "eval_logits/chosen": 14.234943389892578,
      "eval_logits/rejected": 15.258601188659668,
      "eval_logps/chosen": -0.2844341993331909,
      "eval_logps/rejected": -0.3695394694805145,
      "eval_loss": 0.9226060509681702,
      "eval_rewards/accuracies": 0.5157894492149353,
      "eval_rewards/chosen": -0.42665132880210876,
      "eval_rewards/margins": 0.1276579648256302,
      "eval_rewards/rejected": -0.5543092489242554,
      "eval_runtime": 25.9356,
      "eval_samples_per_second": 29.033,
      "eval_steps_per_second": 3.663,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.1369677154418688e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}