{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19900497512437812,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03980099502487562,
      "grad_norm": 1.5459058284759521,
      "learning_rate": 4.980474401576887e-07,
      "logits/chosen": -1.4838274717330933,
      "logits/rejected": -1.5693057775497437,
      "logps/chosen": -190.30685424804688,
      "logps/rejected": -190.12179565429688,
      "loss": 0.7107,
      "rewards/accuracies": 0.49312499165534973,
      "rewards/chosen": -0.8337415456771851,
      "rewards/margins": 0.0017802910879254341,
      "rewards/rejected": -0.8355217576026917,
      "step": 100
    },
    {
      "epoch": 0.07960199004975124,
      "grad_norm": 1.247958779335022,
      "learning_rate": 4.922202605502572e-07,
      "logits/chosen": -1.4577226638793945,
      "logits/rejected": -1.544972538948059,
      "logps/chosen": -191.1748504638672,
      "logps/rejected": -191.21063232421875,
      "loss": 0.7063,
      "rewards/accuracies": 0.5017187595367432,
      "rewards/chosen": -0.7915948629379272,
      "rewards/margins": 0.004952423740178347,
      "rewards/rejected": -0.7965472340583801,
      "step": 200
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 1.1431488990783691,
      "learning_rate": 4.82609484512869e-07,
      "logits/chosen": -1.4753738641738892,
      "logits/rejected": -1.5457732677459717,
      "logps/chosen": -189.42088317871094,
      "logps/rejected": -190.7891082763672,
      "loss": 0.7009,
      "rewards/accuracies": 0.5146874785423279,
      "rewards/chosen": -0.7856764197349548,
      "rewards/margins": 0.013686330057680607,
      "rewards/rejected": -0.7993627190589905,
      "step": 300
    },
    {
      "epoch": 0.15920398009950248,
      "grad_norm": 1.1773804426193237,
      "learning_rate": 4.6936523696827614e-07,
      "logits/chosen": -1.4836928844451904,
      "logits/rejected": -1.5391887426376343,
      "logps/chosen": -191.47879028320312,
      "logps/rejected": -192.72312927246094,
      "loss": 0.7031,
      "rewards/accuracies": 0.4935937523841858,
      "rewards/chosen": -0.7633911967277527,
      "rewards/margins": 0.00844556000083685,
      "rewards/rejected": -0.7718366384506226,
      "step": 400
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.1332217454910278,
      "learning_rate": 4.5269439940365644e-07,
      "logits/chosen": -1.5031734704971313,
      "logits/rejected": -1.5771981477737427,
      "logps/chosen": -188.72503662109375,
      "logps/rejected": -188.9233856201172,
      "loss": 0.6982,
      "rewards/accuracies": 0.5159375071525574,
      "rewards/chosen": -0.7517531514167786,
      "rewards/margins": 0.017128920182585716,
      "rewards/rejected": -0.7688820362091064,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 2512,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}