{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9872958257713249,
  "eval_steps": 100,
  "global_step": 68,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014519056261343012,
      "grad_norm": 2.4859837489271306,
      "learning_rate": 7.142857142857143e-07,
      "logits/chosen": 0.09337720274925232,
      "logits/rejected": 0.09554587304592133,
      "logps/chosen": -152.76107788085938,
      "logps/rejected": -188.5344696044922,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.14519056261343014,
      "grad_norm": 1.9129959728137063,
      "learning_rate": 4.970219740227693e-06,
      "logits/chosen": 0.5112766027450562,
      "logits/rejected": 0.892162561416626,
      "logps/chosen": -149.86944580078125,
      "logps/rejected": -192.12844848632812,
      "loss": 0.6935,
      "rewards/accuracies": 0.3958333432674408,
      "rewards/chosen": -0.0032075627241283655,
      "rewards/margins": -0.0028414721600711346,
      "rewards/rejected": -0.0003660905349534005,
      "step": 10
    },
    {
      "epoch": 0.29038112522686027,
      "grad_norm": 6.387926383082319,
      "learning_rate": 4.460299516441777e-06,
      "logits/chosen": 0.7456380128860474,
      "logits/rejected": 0.9128583073616028,
      "logps/chosen": -145.0723876953125,
      "logps/rejected": -185.00823974609375,
      "loss": 0.692,
      "rewards/accuracies": 0.5249999761581421,
      "rewards/chosen": -0.002810679841786623,
      "rewards/margins": -0.0024495997931808233,
      "rewards/rejected": -0.00036108028143644333,
      "step": 20
    },
    {
      "epoch": 0.4355716878402904,
      "grad_norm": 2.851603494816296,
      "learning_rate": 3.441819734087963e-06,
      "logits/chosen": 0.6626991033554077,
      "logits/rejected": 0.8471162915229797,
      "logps/chosen": -145.3153076171875,
      "logps/rejected": -191.17898559570312,
      "loss": 0.6882,
      "rewards/accuracies": 0.53125,
      "rewards/chosen": -0.002587886294350028,
      "rewards/margins": 0.008108791895210743,
      "rewards/rejected": -0.010696678422391415,
      "step": 30
    },
    {
      "epoch": 0.5807622504537205,
      "grad_norm": 2.4335402011634337,
      "learning_rate": 2.1790041121336223e-06,
      "logits/chosen": 0.8962385058403015,
      "logits/rejected": 1.0721851587295532,
      "logps/chosen": -192.60690307617188,
      "logps/rejected": -232.34994506835938,
      "loss": 0.6874,
      "rewards/accuracies": 0.543749988079071,
      "rewards/chosen": -0.022678321227431297,
      "rewards/margins": 0.01420576311647892,
      "rewards/rejected": -0.03688408061861992,
      "step": 40
    },
    {
      "epoch": 0.7259528130671506,
      "grad_norm": 4.774287308012212,
      "learning_rate": 9.994642986290797e-07,
      "logits/chosen": 0.9905160665512085,
      "logits/rejected": 1.3741340637207031,
      "logps/chosen": -162.32839965820312,
      "logps/rejected": -209.26821899414062,
      "loss": 0.6823,
      "rewards/accuracies": 0.59375,
      "rewards/chosen": -0.002683633007109165,
      "rewards/margins": 0.022018445655703545,
      "rewards/rejected": -0.024702081456780434,
      "step": 50
    },
    {
      "epoch": 0.8711433756805808,
      "grad_norm": 3.010894871763621,
      "learning_rate": 2.092077387824884e-07,
      "logits/chosen": 0.9261436462402344,
      "logits/rejected": 1.0222227573394775,
      "logps/chosen": -149.97549438476562,
      "logps/rejected": -182.0010528564453,
      "loss": 0.6835,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.006383872590959072,
      "rewards/margins": 0.01851298287510872,
      "rewards/rejected": -0.024896854534745216,
      "step": 60
    },
    {
      "epoch": 0.9872958257713249,
      "step": 68,
      "total_flos": 0.0,
      "train_loss": 0.6879464878755457,
      "train_runtime": 373.787,
      "train_samples_per_second": 23.559,
      "train_steps_per_second": 0.182
    }
  ],
  "logging_steps": 10,
  "max_steps": 68,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}