{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.985781990521327,
  "eval_steps": 100,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 1063.3979842677222,
      "learning_rate": 8.333333333333333e-08,
      "logits/chosen": 123.11854553222656,
      "logits/rejected": 97.00198364257812,
      "logps/chosen": -425.18585205078125,
      "logps/rejected": -424.1869201660156,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.19,
      "grad_norm": 1346.5075049308593,
      "learning_rate": 4.907293218369498e-07,
      "logits/chosen": 117.30894470214844,
      "logits/rejected": 136.13665771484375,
      "logps/chosen": -440.2249450683594,
      "logps/rejected": -523.478759765625,
      "loss": 1.549,
      "rewards/accuracies": 0.5416666865348816,
      "rewards/chosen": 1.265385627746582,
      "rewards/margins": 1.0109217166900635,
      "rewards/rejected": 0.2544640600681305,
      "step": 10
    },
    {
      "epoch": 0.38,
      "grad_norm": 809.9127862531388,
      "learning_rate": 3.941700805287168e-07,
      "logits/chosen": 126.48260498046875,
      "logits/rejected": 134.13934326171875,
      "logps/chosen": -427.7540588378906,
      "logps/rejected": -498.09625244140625,
      "loss": 1.4687,
      "rewards/accuracies": 0.643750011920929,
      "rewards/chosen": -0.5957807302474976,
      "rewards/margins": 3.638510227203369,
      "rewards/rejected": -4.234290599822998,
      "step": 20
    },
    {
      "epoch": 0.57,
      "grad_norm": 949.0759148823992,
      "learning_rate": 2.3293939665883228e-07,
      "logits/chosen": 124.88182067871094,
      "logits/rejected": 128.2673797607422,
      "logps/chosen": -467.4933166503906,
      "logps/rejected": -528.9049682617188,
      "loss": 1.514,
      "rewards/accuracies": 0.71875,
      "rewards/chosen": -4.949261665344238,
      "rewards/margins": 3.726797580718994,
      "rewards/rejected": -8.676058769226074,
      "step": 30
    },
    {
      "epoch": 0.76,
      "grad_norm": 844.5086167522245,
      "learning_rate": 7.936171419533652e-08,
      "logits/chosen": 124.84774017333984,
      "logits/rejected": 119.7896957397461,
      "logps/chosen": -481.734130859375,
      "logps/rejected": -502.24835205078125,
      "loss": 1.4623,
      "rewards/accuracies": 0.6625000238418579,
      "rewards/chosen": -3.4210944175720215,
      "rewards/margins": 3.572343111038208,
      "rewards/rejected": -6.99343729019165,
      "step": 40
    },
    {
      "epoch": 0.95,
      "grad_norm": 1014.9882130910677,
      "learning_rate": 2.328513490917311e-09,
      "logits/chosen": 134.2489776611328,
      "logits/rejected": 134.7040557861328,
      "logps/chosen": -490.24871826171875,
      "logps/rejected": -506.75469970703125,
      "loss": 1.3461,
      "rewards/accuracies": 0.643750011920929,
      "rewards/chosen": -2.9704134464263916,
      "rewards/margins": 3.232123613357544,
      "rewards/rejected": -6.202536582946777,
      "step": 50
    },
    {
      "epoch": 0.99,
      "step": 52,
      "total_flos": 0.0,
      "train_loss": 1.4415429693001967,
      "train_runtime": 577.5791,
      "train_samples_per_second": 11.687,
      "train_steps_per_second": 0.09
    }
  ],
  "logging_steps": 10,
  "max_steps": 52,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}