{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9872958257713249,
  "eval_steps": 100,
  "global_step": 68,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014519056261343012,
      "grad_norm": 2.5819620488760253,
      "learning_rate": 7.142857142857143e-07,
      "logits/chosen": 0.902682900428772,
      "logits/rejected": 0.8661031723022461,
      "logps/chosen": -125.2274169921875,
      "logps/rejected": -145.89674377441406,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.14519056261343014,
      "grad_norm": 3.2242486672937045,
      "learning_rate": 4.970219740227693e-06,
      "logits/chosen": 0.8677890300750732,
      "logits/rejected": 0.88941490650177,
      "logps/chosen": -120.65478515625,
      "logps/rejected": -149.0773468017578,
      "loss": 0.6925,
      "rewards/accuracies": 0.4097222089767456,
      "rewards/chosen": 0.0005513947107829154,
      "rewards/margins": -0.0005504629807546735,
      "rewards/rejected": 0.001101857633329928,
      "step": 10
    },
    {
      "epoch": 0.29038112522686027,
      "grad_norm": 4.0763010346326904,
      "learning_rate": 4.460299516441777e-06,
      "logits/chosen": 1.0478929281234741,
      "logits/rejected": 1.0530675649642944,
      "logps/chosen": -115.20359802246094,
      "logps/rejected": -142.4711456298828,
      "loss": 0.6887,
      "rewards/accuracies": 0.543749988079071,
      "rewards/chosen": -0.007147049065679312,
      "rewards/margins": 0.007046631071716547,
      "rewards/rejected": -0.014193681068718433,
      "step": 20
    },
    {
      "epoch": 0.4355716878402904,
      "grad_norm": 2.868995154924774,
      "learning_rate": 3.441819734087963e-06,
      "logits/chosen": 1.0493364334106445,
      "logits/rejected": 1.0137263536453247,
      "logps/chosen": -115.47831726074219,
      "logps/rejected": -145.4583282470703,
      "loss": 0.681,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.013122054748237133,
      "rewards/margins": 0.018696457147598267,
      "rewards/rejected": -0.031818509101867676,
      "step": 30
    },
    {
      "epoch": 0.5807622504537205,
      "grad_norm": 2.4635583297317165,
      "learning_rate": 2.1790041121336223e-06,
      "logits/chosen": 1.2130175828933716,
      "logits/rejected": 1.1768478155136108,
      "logps/chosen": -154.19398498535156,
      "logps/rejected": -181.88272094726562,
      "loss": 0.6762,
      "rewards/accuracies": 0.581250011920929,
      "rewards/chosen": -0.04483573138713837,
      "rewards/margins": 0.041850604116916656,
      "rewards/rejected": -0.08668633550405502,
      "step": 40
    },
    {
      "epoch": 0.7259528130671506,
      "grad_norm": 3.188683944287027,
      "learning_rate": 9.994642986290797e-07,
      "logits/chosen": 1.3518016338348389,
      "logits/rejected": 1.2714142799377441,
      "logps/chosen": -131.69985961914062,
      "logps/rejected": -161.8300018310547,
      "loss": 0.6622,
      "rewards/accuracies": 0.6499999761581421,
      "rewards/chosen": -0.011605720035731792,
      "rewards/margins": 0.06830872595310211,
      "rewards/rejected": -0.07991443574428558,
      "step": 50
    },
    {
      "epoch": 0.8711433756805808,
      "grad_norm": 3.3445679325076476,
      "learning_rate": 2.092077387824884e-07,
      "logits/chosen": 1.367594838142395,
      "logits/rejected": 1.2992292642593384,
      "logps/chosen": -121.10174560546875,
      "logps/rejected": -139.6844940185547,
      "loss": 0.6612,
      "rewards/accuracies": 0.612500011920929,
      "rewards/chosen": -0.017885591834783554,
      "rewards/margins": 0.07065734267234802,
      "rewards/rejected": -0.08854293823242188,
      "step": 60
    },
    {
      "epoch": 0.9872958257713249,
      "step": 68,
      "total_flos": 0.0,
      "train_loss": 0.6753217893488267,
      "train_runtime": 321.7901,
      "train_samples_per_second": 27.366,
      "train_steps_per_second": 0.211
    }
  ],
  "logging_steps": 10,
  "max_steps": 68,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}