{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.75,
  "eval_steps": 500,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.625,
      "grad_norm": 6.125,
      "learning_rate": 4.1332457142857145e-06,
      "logits/chosen": -4.040154457092285,
      "logits/rejected": -3.8396897315979004,
      "logps/chosen": -26.683429718017578,
      "logps/rejected": -26.878021240234375,
      "loss": 1.0018,
      "rewards/accuracies": 0.47187501192092896,
      "rewards/chosen": -0.09798367321491241,
      "rewards/margins": -0.0074737281538546085,
      "rewards/rejected": -0.09050994366407394,
      "step": 5
    },
    {
      "epoch": 0.875,
      "eval_logits/chosen": -3.9245500564575195,
      "eval_logits/rejected": -3.882066011428833,
      "eval_logps/chosen": -28.090627670288086,
      "eval_logps/rejected": -30.770191192626953,
      "eval_loss": 0.9992011189460754,
      "eval_rewards/accuracies": 0.5550000071525574,
      "eval_rewards/chosen": -0.007961263880133629,
      "eval_rewards/margins": 0.003196741919964552,
      "eval_rewards/rejected": -0.011158007197082043,
      "eval_runtime": 2.2911,
      "eval_samples_per_second": 87.295,
      "eval_steps_per_second": 87.295,
      "step": 7
    },
    {
      "epoch": 1.25,
      "grad_norm": 6.21875,
      "learning_rate": 9.299802857142857e-06,
      "logits/chosen": -4.034914970397949,
      "logits/rejected": -3.825766086578369,
      "logps/chosen": -26.990406036376953,
      "logps/rejected": -27.383045196533203,
      "loss": 0.9995,
      "rewards/accuracies": 0.48750001192092896,
      "rewards/chosen": -0.09668578207492828,
      "rewards/margins": 0.0020204861648380756,
      "rewards/rejected": -0.09870626777410507,
      "step": 10
    },
    {
      "epoch": 1.75,
      "eval_logits/chosen": -3.9060890674591064,
      "eval_logits/rejected": -3.860724449157715,
      "eval_logps/chosen": -28.430126190185547,
      "eval_logps/rejected": -31.278379440307617,
      "eval_loss": 0.9930404424667358,
      "eval_rewards/accuracies": 0.5950000286102295,
      "eval_rewards/chosen": -0.0588860809803009,
      "eval_rewards/margins": 0.02849973924458027,
      "eval_rewards/rejected": -0.08738581836223602,
      "eval_runtime": 2.2914,
      "eval_samples_per_second": 87.282,
      "eval_steps_per_second": 87.282,
      "step": 14
    }
  ],
  "logging_steps": 5,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "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": 64,
  "trial_name": null,
  "trial_params": null
}