{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04103405826836274,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008206811653672548,
      "grad_norm": 0.07778492569923401,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": -2.053281307220459,
      "logits/rejected": -2.495474338531494,
      "logps/chosen": -0.3126755356788635,
      "logps/rejected": -0.3312620520591736,
      "loss": 7.6211,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.4690132737159729,
      "rewards/margins": 0.027879873290657997,
      "rewards/rejected": -0.49689316749572754,
      "step": 10
    },
    {
      "epoch": 0.016413623307345096,
      "grad_norm": 0.07773654907941818,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": -2.0624098777770996,
      "logits/rejected": -2.4424185752868652,
      "logps/chosen": -0.26926660537719727,
      "logps/rejected": -0.2978014051914215,
      "loss": 7.5195,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.4038998484611511,
      "rewards/margins": 0.04280223697423935,
      "rewards/rejected": -0.44670209288597107,
      "step": 20
    },
    {
      "epoch": 0.024620434961017644,
      "grad_norm": 0.07357177883386612,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": -2.068427562713623,
      "logits/rejected": -2.486642360687256,
      "logps/chosen": -0.29993391036987305,
      "logps/rejected": -0.34360918402671814,
      "loss": 7.4913,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.4499008059501648,
      "rewards/margins": 0.06551288068294525,
      "rewards/rejected": -0.5154137015342712,
      "step": 30
    },
    {
      "epoch": 0.03282724661469019,
      "grad_norm": 0.14212799072265625,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": -2.015650987625122,
      "logits/rejected": -2.3838727474212646,
      "logps/chosen": -0.2911723852157593,
      "logps/rejected": -0.30521970987319946,
      "loss": 7.5217,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.4367586076259613,
      "rewards/margins": 0.021070968359708786,
      "rewards/rejected": -0.4578295648097992,
      "step": 40
    },
    {
      "epoch": 0.04103405826836274,
      "grad_norm": 0.08107248693704605,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": -2.1150989532470703,
      "logits/rejected": -2.4338631629943848,
      "logps/chosen": -0.26249754428863525,
      "logps/rejected": -0.3132360577583313,
      "loss": 7.519,
      "rewards/accuracies": 0.5375000238418579,
      "rewards/chosen": -0.3937462866306305,
      "rewards/margins": 0.07610772550106049,
      "rewards/rejected": -0.4698540270328522,
      "step": 50
    },
    {
      "epoch": 0.04103405826836274,
      "eval_logits/chosen": -2.0232737064361572,
      "eval_logits/rejected": -2.4952735900878906,
      "eval_logps/chosen": -0.27974528074264526,
      "eval_logps/rejected": -0.3420677185058594,
      "eval_loss": 0.9291417598724365,
      "eval_rewards/accuracies": 0.49494948983192444,
      "eval_rewards/chosen": -0.41961798071861267,
      "eval_rewards/margins": 0.09348361939191818,
      "eval_rewards/rejected": -0.5131015777587891,
      "eval_runtime": 26.0563,
      "eval_samples_per_second": 30.242,
      "eval_steps_per_second": 3.799,
      "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": 1.8304469433738854e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}