{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.5555555555555554,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 37.69427401780438,
      "learning_rate": 7.407407407407407e-07,
      "loss": 3.3424,
      "step": 20
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 14.88534997200217,
      "learning_rate": 1.4814814814814815e-06,
      "loss": 1.4123,
      "step": 40
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 8.911512449667354,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.3828,
      "step": 60
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 7.63936054251728,
      "learning_rate": 2.962962962962963e-06,
      "loss": 0.1952,
      "step": 80
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 8.719508343316141,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.2151,
      "step": 100
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 3.652230684843914,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.1807,
      "step": 120
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.803486909222409,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.1998,
      "step": 140
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 5.683925517413812,
      "learning_rate": 5.925925925925926e-06,
      "loss": 0.2007,
      "step": 160
    },
    {
      "epoch": 0.8,
      "grad_norm": 5.671264277200244,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1823,
      "step": 180
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 5.281924383594261,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.2291,
      "step": 200
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.1828269511461258,
      "eval_runtime": 8.8421,
      "eval_samples_per_second": 22.619,
      "eval_steps_per_second": 5.655,
      "step": 200
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 2.2722939108252085,
      "learning_rate": 8.148148148148148e-06,
      "loss": 0.1731,
      "step": 220
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 2.0906758425548317,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.1711,
      "step": 240
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 6.978596990843908,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.2049,
      "step": 260
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 3.6743331117766505,
      "learning_rate": 9.999582149277188e-06,
      "loss": 0.1922,
      "step": 280
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 1.9815412342738243,
      "learning_rate": 9.996239762521152e-06,
      "loss": 0.1656,
      "step": 300
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 7.061934705422651,
      "learning_rate": 9.989557223505661e-06,
      "loss": 0.1966,
      "step": 320
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 2.941290886263295,
      "learning_rate": 9.979538999730047e-06,
      "loss": 0.1608,
      "step": 340
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.643733136494985,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.171,
      "step": 360
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 3.543866617747764,
      "learning_rate": 9.949524513498636e-06,
      "loss": 0.1779,
      "step": 380
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 3.178266950243424,
      "learning_rate": 9.929548316723983e-06,
      "loss": 0.195,
      "step": 400
    },
    {
      "epoch": 1.7777777777777777,
      "eval_loss": 0.16687195003032684,
      "eval_runtime": 8.6479,
      "eval_samples_per_second": 23.127,
      "eval_steps_per_second": 5.782,
      "step": 400
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 5.20687251609928,
      "learning_rate": 9.906276553136924e-06,
      "loss": 0.1675,
      "step": 420
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 1.2698407364204303,
      "learning_rate": 9.879724780684518e-06,
      "loss": 0.169,
      "step": 440
    },
    {
      "epoch": 2.0444444444444443,
      "grad_norm": 0.9580164829323206,
      "learning_rate": 9.849910750108718e-06,
      "loss": 0.1225,
      "step": 460
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 1.9949193423922398,
      "learning_rate": 9.816854393079402e-06,
      "loss": 0.1063,
      "step": 480
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 5.346736325447602,
      "learning_rate": 9.7805778088694e-06,
      "loss": 0.1116,
      "step": 500
    },
    {
      "epoch": 2.311111111111111,
      "grad_norm": 4.28662690357361,
      "learning_rate": 9.741105249580383e-06,
      "loss": 0.1053,
      "step": 520
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.9465352734274741,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.1069,
      "step": 540
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 2.655625957871827,
      "learning_rate": 9.652679879607843e-06,
      "loss": 0.1015,
      "step": 560
    },
    {
      "epoch": 2.5777777777777775,
      "grad_norm": 19.89512752629162,
      "learning_rate": 9.603786184221693e-06,
      "loss": 0.1052,
      "step": 580
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 1.7316001929181462,
      "learning_rate": 9.551814704830734e-06,
      "loss": 0.096,
      "step": 600
    },
    {
      "epoch": 2.6666666666666665,
      "eval_loss": 0.16640160977840424,
      "eval_runtime": 8.6785,
      "eval_samples_per_second": 23.045,
      "eval_steps_per_second": 5.761,
      "step": 600
    },
    {
      "epoch": 2.7555555555555555,
      "grad_norm": 4.520411658514228,
      "learning_rate": 9.496800186095466e-06,
      "loss": 0.1555,
      "step": 620
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 2.053823726339468,
      "learning_rate": 9.438779407049282e-06,
      "loss": 0.1199,
      "step": 640
    },
    {
      "epoch": 2.9333333333333336,
      "grad_norm": 2.305382285885107,
      "learning_rate": 9.377791156510456e-06,
      "loss": 0.1199,
      "step": 660
    },
    {
      "epoch": 3.022222222222222,
      "grad_norm": 1.0397507056066575,
      "learning_rate": 9.313876207150544e-06,
      "loss": 0.0812,
      "step": 680
    },
    {
      "epoch": 3.111111111111111,
      "grad_norm": 1.2727327131324244,
      "learning_rate": 9.247077288236488e-06,
      "loss": 0.0716,
      "step": 700
    },
    {
      "epoch": 3.2,
      "grad_norm": 2.1523549330040077,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.093,
      "step": 720
    },
    {
      "epoch": 3.2888888888888888,
      "grad_norm": 5.864509224189539,
      "learning_rate": 9.105008069106093e-06,
      "loss": 0.092,
      "step": 740
    },
    {
      "epoch": 3.3777777777777778,
      "grad_norm": 3.844288077679731,
      "learning_rate": 9.029832746882372e-06,
      "loss": 0.0864,
      "step": 760
    },
    {
      "epoch": 3.466666666666667,
      "grad_norm": 9.187901961444704,
      "learning_rate": 8.951963347593797e-06,
      "loss": 0.0867,
      "step": 780
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 1.7296873275889046,
      "learning_rate": 8.871451929520662e-06,
      "loss": 0.0692,
      "step": 800
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.1792396605014801,
      "eval_runtime": 8.674,
      "eval_samples_per_second": 23.057,
      "eval_steps_per_second": 5.764,
      "step": 800
    }
  ],
  "logging_steps": 20,
  "max_steps": 2700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 13273461227520.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}