{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12978585334198572,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12978585334198572,
      "grad_norm": 0.0001288286439375952,
      "learning_rate": 9.985564567238237e-05,
      "logits/chosen": -2.892515182495117,
      "logits/rejected": -2.8839669227600098,
      "logps/chosen": -65.34242248535156,
      "logps/rejected": -120.23748779296875,
      "loss": 0.2047,
      "rewards/accuracies": 0.7599999904632568,
      "rewards/chosen": -2.3054304122924805,
      "rewards/margins": 7.21456241607666,
      "rewards/rejected": -9.519991874694824,
      "step": 25
    },
    {
      "epoch": 0.12978585334198572,
      "eval_logits/chosen": -3.1952435970306396,
      "eval_logits/rejected": -3.1321091651916504,
      "eval_logps/chosen": -126.43878936767578,
      "eval_logps/rejected": -265.6844177246094,
      "eval_loss": 4.6241984819062054e-07,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": -8.37295913696289,
      "eval_rewards/margins": 15.654376983642578,
      "eval_rewards/rejected": -24.02733612060547,
      "eval_runtime": 140.1846,
      "eval_samples_per_second": 0.585,
      "eval_steps_per_second": 0.585,
      "step": 25
    }
  ],
  "logging_steps": 25,
  "max_steps": 384,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}