{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05329780146568954,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010659560293137908,
      "grad_norm": 0.2118789255619049,
      "learning_rate": 5e-05,
      "loss": 10.3788,
      "step": 1
    },
    {
      "epoch": 0.0010659560293137908,
      "eval_loss": 10.37948989868164,
      "eval_runtime": 0.1071,
      "eval_samples_per_second": 466.984,
      "eval_steps_per_second": 121.416,
      "step": 1
    },
    {
      "epoch": 0.0021319120586275817,
      "grad_norm": 0.2286320924758911,
      "learning_rate": 0.0001,
      "loss": 10.3851,
      "step": 2
    },
    {
      "epoch": 0.0031978680879413725,
      "grad_norm": 0.21430334448814392,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3848,
      "step": 3
    },
    {
      "epoch": 0.004263824117255163,
      "grad_norm": 0.22832240164279938,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.3828,
      "step": 4
    },
    {
      "epoch": 0.005329780146568954,
      "grad_norm": 0.21788468956947327,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3802,
      "step": 5
    },
    {
      "epoch": 0.006395736175882745,
      "grad_norm": 0.20640529692173004,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3797,
      "step": 6
    },
    {
      "epoch": 0.007461692205196536,
      "grad_norm": 0.2152969092130661,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3823,
      "step": 7
    },
    {
      "epoch": 0.008527648234510327,
      "grad_norm": 0.21746909618377686,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3793,
      "step": 8
    },
    {
      "epoch": 0.009593604263824117,
      "grad_norm": 0.21747761964797974,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3822,
      "step": 9
    },
    {
      "epoch": 0.010659560293137908,
      "grad_norm": 0.23156635463237762,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3759,
      "step": 10
    },
    {
      "epoch": 0.011725516322451699,
      "grad_norm": 0.23956775665283203,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3713,
      "step": 11
    },
    {
      "epoch": 0.01279147235176549,
      "grad_norm": 0.247402623295784,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3753,
      "step": 12
    },
    {
      "epoch": 0.01385742838107928,
      "grad_norm": 0.24369311332702637,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3697,
      "step": 13
    },
    {
      "epoch": 0.014923384410393072,
      "grad_norm": 0.22514982521533966,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3721,
      "step": 14
    },
    {
      "epoch": 0.015989340439706862,
      "grad_norm": 0.2375071495771408,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3686,
      "step": 15
    },
    {
      "epoch": 0.017055296469020653,
      "grad_norm": 0.2357599139213562,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3702,
      "step": 16
    },
    {
      "epoch": 0.018121252498334444,
      "grad_norm": 0.2340744137763977,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.363,
      "step": 17
    },
    {
      "epoch": 0.019187208527648235,
      "grad_norm": 0.25050875544548035,
      "learning_rate": 7.75e-05,
      "loss": 10.3633,
      "step": 18
    },
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 0.26678064465522766,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.3597,
      "step": 19
    },
    {
      "epoch": 0.021319120586275817,
      "grad_norm": 0.2650009095668793,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3602,
      "step": 20
    },
    {
      "epoch": 0.022385076615589607,
      "grad_norm": 0.2694423496723175,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3619,
      "step": 21
    },
    {
      "epoch": 0.023451032644903398,
      "grad_norm": 0.31218400597572327,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.3583,
      "step": 22
    },
    {
      "epoch": 0.02451698867421719,
      "grad_norm": 0.2973407208919525,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.3511,
      "step": 23
    },
    {
      "epoch": 0.02558294470353098,
      "grad_norm": 0.3031325936317444,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3545,
      "step": 24
    },
    {
      "epoch": 0.02664890073284477,
      "grad_norm": 0.3626728951931,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3463,
      "step": 25
    },
    {
      "epoch": 0.02664890073284477,
      "eval_loss": 10.344112396240234,
      "eval_runtime": 0.1159,
      "eval_samples_per_second": 431.357,
      "eval_steps_per_second": 112.153,
      "step": 25
    },
    {
      "epoch": 0.02771485676215856,
      "grad_norm": 0.29466956853866577,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.3486,
      "step": 26
    },
    {
      "epoch": 0.028780812791472352,
      "grad_norm": 0.31241559982299805,
      "learning_rate": 5.205685918464356e-05,
      "loss": 10.347,
      "step": 27
    },
    {
      "epoch": 0.029846768820786143,
      "grad_norm": 0.2826091945171356,
      "learning_rate": 4.912632135009769e-05,
      "loss": 10.3492,
      "step": 28
    },
    {
      "epoch": 0.030912724850099934,
      "grad_norm": 0.3171038329601288,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 10.3494,
      "step": 29
    },
    {
      "epoch": 0.031978680879413725,
      "grad_norm": 0.304294615983963,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.3456,
      "step": 30
    },
    {
      "epoch": 0.03304463690872751,
      "grad_norm": 0.3247598111629486,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3515,
      "step": 31
    },
    {
      "epoch": 0.034110592938041306,
      "grad_norm": 0.3589993119239807,
      "learning_rate": 3.777924554357096e-05,
      "loss": 10.346,
      "step": 32
    },
    {
      "epoch": 0.035176548967355094,
      "grad_norm": 0.36132293939590454,
      "learning_rate": 3.509700894014496e-05,
      "loss": 10.3411,
      "step": 33
    },
    {
      "epoch": 0.03624250499666889,
      "grad_norm": 0.3835195302963257,
      "learning_rate": 3.250000000000001e-05,
      "loss": 10.3379,
      "step": 34
    },
    {
      "epoch": 0.037308461025982675,
      "grad_norm": 0.3723469376564026,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 10.3345,
      "step": 35
    },
    {
      "epoch": 0.03837441705529647,
      "grad_norm": 0.3813835680484772,
      "learning_rate": 2.760573569460757e-05,
      "loss": 10.3435,
      "step": 36
    },
    {
      "epoch": 0.03944037308461026,
      "grad_norm": 0.40655070543289185,
      "learning_rate": 2.53294383204969e-05,
      "loss": 10.3404,
      "step": 37
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 0.3889438211917877,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 10.3424,
      "step": 38
    },
    {
      "epoch": 0.04157228514323784,
      "grad_norm": 0.3690129518508911,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.339,
      "step": 39
    },
    {
      "epoch": 0.04263824117255163,
      "grad_norm": 0.36811506748199463,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 10.337,
      "step": 40
    },
    {
      "epoch": 0.04370419720186542,
      "grad_norm": 0.3503737449645996,
      "learning_rate": 1.758386744638546e-05,
      "loss": 10.3365,
      "step": 41
    },
    {
      "epoch": 0.044770153231179215,
      "grad_norm": 0.3476838171482086,
      "learning_rate": 1.602885682970026e-05,
      "loss": 10.3357,
      "step": 42
    },
    {
      "epoch": 0.045836109260493,
      "grad_norm": 0.40502050518989563,
      "learning_rate": 1.464072663102903e-05,
      "loss": 10.326,
      "step": 43
    },
    {
      "epoch": 0.046902065289806796,
      "grad_norm": 0.37952473759651184,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 10.3307,
      "step": 44
    },
    {
      "epoch": 0.047968021319120584,
      "grad_norm": 0.3985709846019745,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 10.3376,
      "step": 45
    },
    {
      "epoch": 0.04903397734843438,
      "grad_norm": 0.3946983516216278,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 10.3341,
      "step": 46
    },
    {
      "epoch": 0.050099933377748165,
      "grad_norm": 0.37759777903556824,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 10.3338,
      "step": 47
    },
    {
      "epoch": 0.05116588940706196,
      "grad_norm": 0.40839263796806335,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 10.3287,
      "step": 48
    },
    {
      "epoch": 0.05223184543637575,
      "grad_norm": 0.42501384019851685,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 10.3254,
      "step": 49
    },
    {
      "epoch": 0.05329780146568954,
      "grad_norm": 0.4669570028781891,
      "learning_rate": 1e-05,
      "loss": 10.3262,
      "step": 50
    },
    {
      "epoch": 0.05329780146568954,
      "eval_loss": 10.321706771850586,
      "eval_runtime": 0.1212,
      "eval_samples_per_second": 412.623,
      "eval_steps_per_second": 107.282,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 84675463741440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}