{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0784313725490196,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_logits/chosen": -2.3223893642425537,
      "eval_logits/rejected": -1.7441076040267944,
      "eval_logps/chosen": -205.81431579589844,
      "eval_logps/rejected": -160.84881591796875,
      "eval_loss": 0.6931471824645996,
      "eval_rewards/accuracies": 0.0,
      "eval_rewards/chosen": 0.0,
      "eval_rewards/margins": 0.0,
      "eval_rewards/rejected": 0.0,
      "eval_runtime": 13.1039,
      "eval_samples_per_second": 1.297,
      "eval_steps_per_second": 0.687,
      "step": 0
    },
    {
      "epoch": 0.026143790849673203,
      "grad_norm": 11.304482460021973,
      "learning_rate": 0.0,
      "logits/chosen": -2.2234325408935547,
      "logits/rejected": -2.2330026626586914,
      "logps/chosen": -251.4762420654297,
      "logps/rejected": -287.5872497558594,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.05228758169934641,
      "grad_norm": 11.91282844543457,
      "learning_rate": 2e-05,
      "logits/chosen": -2.2173714637756348,
      "logits/rejected": -2.2363157272338867,
      "logps/chosen": -227.2211151123047,
      "logps/rejected": -262.26251220703125,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 9.456698417663574,
      "learning_rate": 4e-05,
      "logits/chosen": -1.7777986526489258,
      "logits/rejected": -1.5732976198196411,
      "logps/chosen": -166.3558807373047,
      "logps/rejected": -206.31166076660156,
      "loss": 0.6976,
      "rewards/accuracies": 0.375,
      "rewards/chosen": 0.005008268635720015,
      "rewards/margins": -0.007055856287479401,
      "rewards/rejected": 0.012064123526215553,
      "step": 3
    },
    {
      "epoch": 0.0784313725490196,
      "eval_logits/chosen": -2.3259360790252686,
      "eval_logits/rejected": -1.7466574907302856,
      "eval_logps/chosen": -205.6438751220703,
      "eval_logps/rejected": -160.8700408935547,
      "eval_loss": 0.6828210353851318,
      "eval_rewards/accuracies": 0.6666666865348816,
      "eval_rewards/chosen": 0.017044195905327797,
      "eval_rewards/margins": 0.019166946411132812,
      "eval_rewards/rejected": -0.0021227519027888775,
      "eval_runtime": 12.9552,
      "eval_samples_per_second": 1.312,
      "eval_steps_per_second": 0.695,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}