{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.053304904051172705,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010660980810234541,
      "grad_norm": 0.051327500492334366,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.755006790161133,
      "logits/rejected": 14.735244750976562,
      "logps/chosen": -0.29377540946006775,
      "logps/rejected": -0.30969956517219543,
      "loss": 0.952,
      "rewards/accuracies": 0.4375,
      "rewards/chosen": -0.44066309928894043,
      "rewards/margins": 0.023886267095804214,
      "rewards/rejected": -0.46454939246177673,
      "step": 10
    },
    {
      "epoch": 0.021321961620469083,
      "grad_norm": 0.04346882924437523,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.513801574707031,
      "logits/rejected": 14.946454048156738,
      "logps/chosen": -0.27995699644088745,
      "logps/rejected": -0.30138006806373596,
      "loss": 0.9726,
      "rewards/accuracies": 0.4124999940395355,
      "rewards/chosen": -0.4199354648590088,
      "rewards/margins": 0.03213457390666008,
      "rewards/rejected": -0.45207005739212036,
      "step": 20
    },
    {
      "epoch": 0.031982942430703626,
      "grad_norm": 0.05228634551167488,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.266324043273926,
      "logits/rejected": 14.423965454101562,
      "logps/chosen": -0.2919609546661377,
      "logps/rejected": -0.32358455657958984,
      "loss": 0.9622,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.43794146180152893,
      "rewards/margins": 0.047435395419597626,
      "rewards/rejected": -0.48537683486938477,
      "step": 30
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 0.05487598106265068,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.965211868286133,
      "logits/rejected": 15.058088302612305,
      "logps/chosen": -0.277716726064682,
      "logps/rejected": -0.3055034577846527,
      "loss": 0.9403,
      "rewards/accuracies": 0.4000000059604645,
      "rewards/chosen": -0.4165751039981842,
      "rewards/margins": 0.04168009012937546,
      "rewards/rejected": -0.4582551419734955,
      "step": 40
    },
    {
      "epoch": 0.053304904051172705,
      "grad_norm": 0.057255037128925323,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.539288520812988,
      "logits/rejected": 15.174041748046875,
      "logps/chosen": -0.26362231373786926,
      "logps/rejected": -0.3325727581977844,
      "loss": 0.9588,
      "rewards/accuracies": 0.4749999940395355,
      "rewards/chosen": -0.3954334557056427,
      "rewards/margins": 0.10342560708522797,
      "rewards/rejected": -0.49885907769203186,
      "step": 50
    },
    {
      "epoch": 0.053304904051172705,
      "eval_logits/chosen": 14.618952751159668,
      "eval_logits/rejected": 15.176809310913086,
      "eval_logps/chosen": -0.2685677409172058,
      "eval_logps/rejected": -0.3283654451370239,
      "eval_loss": 0.9551004767417908,
      "eval_rewards/accuracies": 0.5131579041481018,
      "eval_rewards/chosen": -0.4028516113758087,
      "eval_rewards/margins": 0.08969658613204956,
      "eval_rewards/rejected": -0.4925481975078583,
      "eval_runtime": 21.4453,
      "eval_samples_per_second": 28.305,
      "eval_steps_per_second": 3.544,
      "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": 1.207668074044457e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}