{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3893575600259572,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12978585334198572,
      "grad_norm": 64.38245391845703,
      "learning_rate": 5e-07,
      "logits/chosen": -1.9029332399368286,
      "logits/rejected": -2.053706407546997,
      "logps/chosen": -40.4902458190918,
      "logps/rejected": -25.3558406829834,
      "loss": 0.5968,
      "rewards/accuracies": 0.800000011920929,
      "rewards/chosen": 0.17978771030902863,
      "rewards/margins": 0.2116149365901947,
      "rewards/rejected": -0.031827230006456375,
      "step": 25
    },
    {
      "epoch": 0.12978585334198572,
      "eval_logits/chosen": -1.9241564273834229,
      "eval_logits/rejected": -2.0354554653167725,
      "eval_logps/chosen": -38.01565933227539,
      "eval_logps/rejected": -26.247798919677734,
      "eval_loss": 0.454921156167984,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 0.4693543612957001,
      "eval_rewards/margins": 0.5530296564102173,
      "eval_rewards/rejected": -0.083675317466259,
      "eval_runtime": 140.2735,
      "eval_samples_per_second": 0.585,
      "eval_steps_per_second": 0.585,
      "step": 25
    },
    {
      "epoch": 0.25957170668397145,
      "grad_norm": 40.388370513916016,
      "learning_rate": 5e-07,
      "logits/chosen": -1.9818081855773926,
      "logits/rejected": -2.0913336277008057,
      "logps/chosen": -34.876155853271484,
      "logps/rejected": -27.348379135131836,
      "loss": 0.3498,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.7389992475509644,
      "rewards/margins": 0.8872407674789429,
      "rewards/rejected": -0.14824140071868896,
      "step": 50
    },
    {
      "epoch": 0.25957170668397145,
      "eval_logits/chosen": -2.0032734870910645,
      "eval_logits/rejected": -2.0942301750183105,
      "eval_logps/chosen": -32.67618942260742,
      "eval_logps/rejected": -27.68032455444336,
      "eval_loss": 0.2584493160247803,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.003301739692688,
      "eval_rewards/margins": 1.2302298545837402,
      "eval_rewards/rejected": -0.22692809998989105,
      "eval_runtime": 140.4996,
      "eval_samples_per_second": 0.584,
      "eval_steps_per_second": 0.584,
      "step": 50
    },
    {
      "epoch": 0.3893575600259572,
      "grad_norm": 29.64296531677246,
      "learning_rate": 5e-07,
      "logits/chosen": -2.0457983016967773,
      "logits/rejected": -2.112644910812378,
      "logps/chosen": -29.919565200805664,
      "logps/rejected": -29.504945755004883,
      "loss": 0.1989,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.2103655338287354,
      "rewards/margins": 1.545750379562378,
      "rewards/rejected": -0.33538496494293213,
      "step": 75
    },
    {
      "epoch": 0.3893575600259572,
      "eval_logits/chosen": -2.056947946548462,
      "eval_logits/rejected": -2.1299691200256348,
      "eval_logps/chosen": -28.753862380981445,
      "eval_logps/rejected": -30.1635684967041,
      "eval_loss": 0.14609307050704956,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 1.3955342769622803,
      "eval_rewards/margins": 1.8707866668701172,
      "eval_rewards/rejected": -0.4752523899078369,
      "eval_runtime": 140.5032,
      "eval_samples_per_second": 0.584,
      "eval_steps_per_second": 0.584,
      "step": 75
    }
  ],
  "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
}