{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9924812030075187,
  "eval_steps": 100,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 0.11394428461790085,
      "learning_rate": 1.25e-06,
      "logits/chosen": 53.32560348510742,
      "logits/rejected": 52.14335632324219,
      "logps/chosen": -207.40060424804688,
      "logps/rejected": -210.90672302246094,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.10490746051073074,
      "learning_rate": 4.49023266426411e-06,
      "logits/chosen": 53.276390075683594,
      "logits/rejected": 52.504600524902344,
      "logps/chosen": -217.22320556640625,
      "logps/rejected": -226.3312530517578,
      "loss": 0.6927,
      "rewards/accuracies": 0.5069444179534912,
      "rewards/chosen": 0.0014083709102123976,
      "rewards/margins": 0.0025196613278239965,
      "rewards/rejected": -0.001111290417611599,
      "step": 10
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.10140777379274368,
      "learning_rate": 2.0955450086180883e-06,
      "logits/chosen": 57.7002067565918,
      "logits/rejected": 52.5445556640625,
      "logps/chosen": -243.323974609375,
      "logps/rejected": -219.4124755859375,
      "loss": 0.6927,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": 0.001665401621721685,
      "rewards/margins": 0.003051209496334195,
      "rewards/rejected": -0.0013858078746125102,
      "step": 20
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.08208052068948746,
      "learning_rate": 1.3086707204299415e-07,
      "logits/chosen": 54.466644287109375,
      "logits/rejected": 52.3039665222168,
      "logps/chosen": -239.034912109375,
      "logps/rejected": -239.99618530273438,
      "loss": 0.692,
      "rewards/accuracies": 0.48124998807907104,
      "rewards/chosen": -0.003810341702774167,
      "rewards/margins": -0.0013501467183232307,
      "rewards/rejected": -0.0024601949844509363,
      "step": 30
    },
    {
      "epoch": 0.9924812030075187,
      "step": 33,
      "total_flos": 0.0,
      "train_loss": 0.6927223205566406,
      "train_runtime": 34619.6666,
      "train_samples_per_second": 0.123,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 10,
  "max_steps": 33,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}