{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0028420932964492783,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.789457728599037e-05,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 3.789457728599037e-05,
      "eval_loss": NaN,
      "eval_runtime": 4088.0394,
      "eval_samples_per_second": 5.436,
      "eval_steps_per_second": 2.718,
      "step": 1
    },
    {
      "epoch": 7.578915457198075e-05,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00011368373185797112,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0001515783091439615,
      "grad_norm": NaN,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00018947288642995187,
      "grad_norm": NaN,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00022736746371594224,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00026526204100193264,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.000303156618287923,
      "grad_norm": NaN,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0003410511955739134,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00037894577285990373,
      "grad_norm": NaN,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00041684035014589413,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0004547349274318845,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0004926295047178749,
      "grad_norm": NaN,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0005305240820038653,
      "grad_norm": NaN,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0005684186592898556,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.000606313236575846,
      "grad_norm": NaN,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0006442078138618364,
      "grad_norm": NaN,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0006821023911478268,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0007199969684338172,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0007578915457198075,
      "grad_norm": NaN,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0007957861230057979,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0008336807002917883,
      "grad_norm": NaN,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0008715752775777787,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.000909469854863769,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0009473644321497594,
      "grad_norm": NaN,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0009473644321497594,
      "eval_loss": NaN,
      "eval_runtime": 4087.2977,
      "eval_samples_per_second": 5.437,
      "eval_steps_per_second": 2.719,
      "step": 25
    },
    {
      "epoch": 0.0009852590094357498,
      "grad_norm": NaN,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0010231535867217402,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0010610481640077306,
      "grad_norm": NaN,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.001098942741293721,
      "grad_norm": NaN,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0011368373185797111,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0011747318958657015,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.001212626473151692,
      "grad_norm": NaN,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0012505210504376823,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0012884156277236727,
      "grad_norm": NaN,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0013263102050096631,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0013642047822956535,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.001402099359581644,
      "grad_norm": NaN,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0014399939368676343,
      "grad_norm": NaN,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0014778885141536245,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.001515783091439615,
      "grad_norm": NaN,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0015536776687256053,
      "grad_norm": NaN,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0015915722460115957,
      "grad_norm": NaN,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0016294668232975861,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0016673614005835765,
      "grad_norm": NaN,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.001705255977869567,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0017431505551555573,
      "grad_norm": NaN,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0017810451324415475,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.001818939709727538,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0018568342870135283,
      "grad_norm": NaN,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0018947288642995187,
      "grad_norm": NaN,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0018947288642995187,
      "eval_loss": NaN,
      "eval_runtime": 4085.8714,
      "eval_samples_per_second": 5.439,
      "eval_steps_per_second": 2.72,
      "step": 50
    },
    {
      "epoch": 0.0019326234415855091,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.0019705180188714995,
      "grad_norm": NaN,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.00200841259615749,
      "grad_norm": NaN,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.0020463071734434803,
      "grad_norm": NaN,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.0020842017507294707,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.002122096328015461,
      "grad_norm": NaN,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.0021599909053014515,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.002197885482587442,
      "grad_norm": NaN,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.0022357800598734323,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.0022736746371594223,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.0023115692144454127,
      "grad_norm": NaN,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.002349463791731403,
      "grad_norm": NaN,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.0023873583690173935,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.002425252946303384,
      "grad_norm": NaN,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.0024631475235893743,
      "grad_norm": NaN,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.0025010421008753647,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.002538936678161355,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.0025768312554473455,
      "grad_norm": NaN,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.002614725832733336,
      "grad_norm": NaN,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.0026526204100193263,
      "grad_norm": NaN,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.0026905149873053167,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.002728409564591307,
      "grad_norm": NaN,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.0027663041418772975,
      "grad_norm": NaN,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.002804198719163288,
      "grad_norm": NaN,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.0028420932964492783,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.0028420932964492783,
      "eval_loss": NaN,
      "eval_runtime": 4087.7096,
      "eval_samples_per_second": 5.437,
      "eval_steps_per_second": 2.718,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 1.369132286041129e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}