{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6394884092725819,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0639488409272582,
      "grad_norm": 34.1801643371582,
      "learning_rate": 2.8125e-07,
      "logits/chosen": -3.5118160247802734,
      "logits/rejected": -5.780074596405029,
      "logps/chosen": -185.06735229492188,
      "logps/rejected": -44.872135162353516,
      "loss": 0.6948,
      "rewards/accuracies": 0.3812499940395355,
      "rewards/chosen": -0.00896346103399992,
      "rewards/margins": -0.0022051387932151556,
      "rewards/rejected": -0.006758322007954121,
      "step": 10
    },
    {
      "epoch": 0.1278976818545164,
      "grad_norm": 31.33914566040039,
      "learning_rate": 4.893617021276595e-07,
      "logits/chosen": -3.459812641143799,
      "logits/rejected": -5.795159816741943,
      "logps/chosen": -184.6004180908203,
      "logps/rejected": -45.62327575683594,
      "loss": 0.6527,
      "rewards/accuracies": 0.8374999761581421,
      "rewards/chosen": 0.012581730261445045,
      "rewards/margins": 0.08460129797458649,
      "rewards/rejected": -0.072019562125206,
      "step": 20
    },
    {
      "epoch": 0.19184652278177458,
      "grad_norm": 25.785869598388672,
      "learning_rate": 4.5390070921985813e-07,
      "logits/chosen": -3.524862289428711,
      "logits/rejected": -5.835035800933838,
      "logps/chosen": -185.87277221679688,
      "logps/rejected": -48.05480194091797,
      "loss": 0.5261,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.04550371319055557,
      "rewards/margins": 0.37238603830337524,
      "rewards/rejected": -0.32688233256340027,
      "step": 30
    },
    {
      "epoch": 0.2557953637090328,
      "grad_norm": 17.68821144104004,
      "learning_rate": 4.184397163120567e-07,
      "logits/chosen": -3.496417999267578,
      "logits/rejected": -5.88121223449707,
      "logps/chosen": -182.35060119628906,
      "logps/rejected": -51.58687210083008,
      "loss": 0.3762,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.11964114010334015,
      "rewards/margins": 0.7925335168838501,
      "rewards/rejected": -0.6728923320770264,
      "step": 40
    },
    {
      "epoch": 0.31974420463629094,
      "grad_norm": 13.102643966674805,
      "learning_rate": 3.829787234042553e-07,
      "logits/chosen": -3.518444776535034,
      "logits/rejected": -5.8981804847717285,
      "logps/chosen": -182.53024291992188,
      "logps/rejected": -55.42652130126953,
      "loss": 0.2457,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.2259349524974823,
      "rewards/margins": 1.2894086837768555,
      "rewards/rejected": -1.0634738206863403,
      "step": 50
    },
    {
      "epoch": 0.38369304556354916,
      "grad_norm": 7.4990034103393555,
      "learning_rate": 3.475177304964539e-07,
      "logits/chosen": -3.5364508628845215,
      "logits/rejected": -5.861163139343262,
      "logps/chosen": -182.3606719970703,
      "logps/rejected": -59.04890823364258,
      "loss": 0.1486,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.42806726694107056,
      "rewards/margins": 1.8459545373916626,
      "rewards/rejected": -1.4178870916366577,
      "step": 60
    },
    {
      "epoch": 0.44764188649080733,
      "grad_norm": 4.712187767028809,
      "learning_rate": 3.1205673758865245e-07,
      "logits/chosen": -3.4948315620422363,
      "logits/rejected": -5.790167331695557,
      "logps/chosen": -179.1177215576172,
      "logps/rejected": -62.539405822753906,
      "loss": 0.086,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.6628400683403015,
      "rewards/margins": 2.428367853164673,
      "rewards/rejected": -1.7655279636383057,
      "step": 70
    },
    {
      "epoch": 0.5115907274180655,
      "grad_norm": 2.8228342533111572,
      "learning_rate": 2.7659574468085106e-07,
      "logits/chosen": -3.5341973304748535,
      "logits/rejected": -5.6943488121032715,
      "logps/chosen": -176.5838165283203,
      "logps/rejected": -65.91018676757812,
      "loss": 0.0486,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 0.9148324728012085,
      "rewards/margins": 3.0173087120056152,
      "rewards/rejected": -2.1024765968322754,
      "step": 80
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 1.7507271766662598,
      "learning_rate": 2.411347517730496e-07,
      "logits/chosen": -3.482938289642334,
      "logits/rejected": -5.569075584411621,
      "logps/chosen": -171.7285919189453,
      "logps/rejected": -69.48970031738281,
      "loss": 0.0275,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.1483333110809326,
      "rewards/margins": 3.605067014694214,
      "rewards/rejected": -2.456733465194702,
      "step": 90
    },
    {
      "epoch": 0.6394884092725819,
      "grad_norm": 1.236215353012085,
      "learning_rate": 2.0567375886524822e-07,
      "logits/chosen": -3.5123608112335205,
      "logits/rejected": -5.456024646759033,
      "logps/chosen": -171.9407958984375,
      "logps/rejected": -73.64480590820312,
      "loss": 0.0153,
      "rewards/accuracies": 1.0,
      "rewards/chosen": 1.32476007938385,
      "rewards/margins": 4.2044148445129395,
      "rewards/rejected": -2.8796544075012207,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 157,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}