{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07847753580537571,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015695507161075144,
      "grad_norm": 0.04355761408805847,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.845781326293945,
      "logits/rejected": 14.576438903808594,
      "logps/chosen": -0.31864267587661743,
      "logps/rejected": -0.24545662105083466,
      "loss": 1.0492,
      "rewards/accuracies": 0.25,
      "rewards/chosen": -0.47796401381492615,
      "rewards/margins": -0.10977902263402939,
      "rewards/rejected": -0.3681849539279938,
      "step": 10
    },
    {
      "epoch": 0.03139101432215029,
      "grad_norm": 0.04919258877635002,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 15.27595043182373,
      "logits/rejected": 14.872761726379395,
      "logps/chosen": -0.3344747722148895,
      "logps/rejected": -0.24258682131767273,
      "loss": 1.0487,
      "rewards/accuracies": 0.16249999403953552,
      "rewards/chosen": -0.5017121434211731,
      "rewards/margins": -0.1378319263458252,
      "rewards/rejected": -0.3638802468776703,
      "step": 20
    },
    {
      "epoch": 0.047086521483225424,
      "grad_norm": 0.049933061003685,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 15.913165092468262,
      "logits/rejected": 15.607622146606445,
      "logps/chosen": -0.3440183997154236,
      "logps/rejected": -0.2831566333770752,
      "loss": 1.0405,
      "rewards/accuracies": 0.1875,
      "rewards/chosen": -0.516027569770813,
      "rewards/margins": -0.09129264950752258,
      "rewards/rejected": -0.4247349202632904,
      "step": 30
    },
    {
      "epoch": 0.06278202864430057,
      "grad_norm": 0.05693503096699715,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 15.402900695800781,
      "logits/rejected": 14.99272632598877,
      "logps/chosen": -0.3297731578350067,
      "logps/rejected": -0.2746916711330414,
      "loss": 1.0369,
      "rewards/accuracies": 0.21250000596046448,
      "rewards/chosen": -0.49465981125831604,
      "rewards/margins": -0.08262218534946442,
      "rewards/rejected": -0.41203755140304565,
      "step": 40
    },
    {
      "epoch": 0.07847753580537571,
      "grad_norm": 0.05467928573489189,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 15.64543342590332,
      "logits/rejected": 15.632547378540039,
      "logps/chosen": -0.30952686071395874,
      "logps/rejected": -0.24847058951854706,
      "loss": 1.0367,
      "rewards/accuracies": 0.21250000596046448,
      "rewards/chosen": -0.46429023146629333,
      "rewards/margins": -0.09158438444137573,
      "rewards/rejected": -0.37270587682724,
      "step": 50
    },
    {
      "epoch": 0.07847753580537571,
      "eval_logits/chosen": 15.850138664245605,
      "eval_logits/rejected": 15.368529319763184,
      "eval_logps/chosen": -0.3222965598106384,
      "eval_logps/rejected": -0.26877468824386597,
      "eval_loss": 1.0326261520385742,
      "eval_rewards/accuracies": 0.26923078298568726,
      "eval_rewards/chosen": -0.4834447503089905,
      "eval_rewards/margins": -0.08028276264667511,
      "eval_rewards/rejected": -0.40316200256347656,
      "eval_runtime": 14.5044,
      "eval_samples_per_second": 28.405,
      "eval_steps_per_second": 3.585,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.2286877513652634e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}