{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2306805074971165,
      "grad_norm": 0.1563875675201416,
      "learning_rate": 4.9514994664236535e-05,
      "logits/chosen": -0.03814176842570305,
      "logits/rejected": -0.1161862164735794,
      "logps/chosen": -86.28071594238281,
      "logps/rejected": -165.0573272705078,
      "loss": 0.2976,
      "rewards/accuracies": 0.8399999737739563,
      "rewards/chosen": 1.2352830171585083,
      "rewards/margins": 7.974934101104736,
      "rewards/rejected": -6.739651679992676,
      "step": 25
    },
    {
      "epoch": 0.461361014994233,
      "grad_norm": 0.0002876661019399762,
      "learning_rate": 4.595642583205011e-05,
      "logits/chosen": 0.09085014462471008,
      "logits/rejected": -0.024974705651402473,
      "logps/chosen": -75.26371002197266,
      "logps/rejected": -177.68812561035156,
      "loss": 0.0515,
      "rewards/accuracies": 0.9775000214576721,
      "rewards/chosen": 3.720491409301758,
      "rewards/margins": 14.312078475952148,
      "rewards/rejected": -10.591588020324707,
      "step": 50
    },
    {
      "epoch": 0.6920415224913494,
      "grad_norm": 0.13601072132587433,
      "learning_rate": 3.941700805287168e-05,
      "logits/chosen": 0.12366016209125519,
      "logits/rejected": -0.007848848588764668,
      "logps/chosen": -80.43215942382812,
      "logps/rejected": -185.66546630859375,
      "loss": 0.0342,
      "rewards/accuracies": 0.9900000095367432,
      "rewards/chosen": 2.8130407333374023,
      "rewards/margins": 17.123788833618164,
      "rewards/rejected": -14.310747146606445,
      "step": 75
    },
    {
      "epoch": 0.922722029988466,
      "grad_norm": 3.1388745307922363,
      "learning_rate": 3.0826910276178916e-05,
      "logits/chosen": -0.015246749855577946,
      "logits/rejected": -0.15489181876182556,
      "logps/chosen": -67.32815551757812,
      "logps/rejected": -182.48895263671875,
      "loss": 0.0549,
      "rewards/accuracies": 0.9800000190734863,
      "rewards/chosen": 4.961977481842041,
      "rewards/margins": 16.877761840820312,
      "rewards/rejected": -11.915783882141113,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 218,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 109,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}