{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06349206349206349,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 0.04716634005308151,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.883691787719727,
      "logits/rejected": 15.016583442687988,
      "logps/chosen": -0.29512909054756165,
      "logps/rejected": -0.30033987760543823,
      "loss": 1.0007,
      "rewards/accuracies": 0.36250001192092896,
      "rewards/chosen": -0.4426936209201813,
      "rewards/margins": 0.007816222496330738,
      "rewards/rejected": -0.45050984621047974,
      "step": 10
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 0.04392225295305252,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.705224990844727,
      "logits/rejected": 14.737253189086914,
      "logps/chosen": -0.3201700747013092,
      "logps/rejected": -0.280050128698349,
      "loss": 0.9984,
      "rewards/accuracies": 0.26249998807907104,
      "rewards/chosen": -0.4802550673484802,
      "rewards/margins": -0.060179851949214935,
      "rewards/rejected": -0.4200752377510071,
      "step": 20
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.04989476501941681,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 15.147977828979492,
      "logits/rejected": 15.080279350280762,
      "logps/chosen": -0.3157380223274231,
      "logps/rejected": -0.2997627556324005,
      "loss": 0.9991,
      "rewards/accuracies": 0.2874999940395355,
      "rewards/chosen": -0.47360706329345703,
      "rewards/margins": -0.023962898179888725,
      "rewards/rejected": -0.44964417815208435,
      "step": 30
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 0.054729390889406204,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 15.301165580749512,
      "logits/rejected": 15.276555061340332,
      "logps/chosen": -0.30470195412635803,
      "logps/rejected": -0.29767152667045593,
      "loss": 0.9849,
      "rewards/accuracies": 0.36250001192092896,
      "rewards/chosen": -0.45705294609069824,
      "rewards/margins": -0.010545584373176098,
      "rewards/rejected": -0.44650736451148987,
      "step": 40
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.06035450100898743,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.600168228149414,
      "logits/rejected": 14.7944917678833,
      "logps/chosen": -0.32278841733932495,
      "logps/rejected": -0.3014402687549591,
      "loss": 0.9991,
      "rewards/accuracies": 0.3499999940395355,
      "rewards/chosen": -0.48418259620666504,
      "rewards/margins": -0.03202226758003235,
      "rewards/rejected": -0.4521603584289551,
      "step": 50
    },
    {
      "epoch": 0.06349206349206349,
      "eval_logits/chosen": 15.261337280273438,
      "eval_logits/rejected": 15.51547908782959,
      "eval_logps/chosen": -0.3022651970386505,
      "eval_logps/rejected": -0.3061661124229431,
      "eval_loss": 0.9846106171607971,
      "eval_rewards/accuracies": 0.40625,
      "eval_rewards/chosen": -0.4533977508544922,
      "eval_rewards/margins": 0.005851435009390116,
      "eval_rewards/rejected": -0.45924919843673706,
      "eval_runtime": 18.4033,
      "eval_samples_per_second": 27.712,
      "eval_steps_per_second": 3.478,
      "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": 1.195225510838272e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}