{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006439979392065945,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.58663918942126e-05,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.58663918942126e-05,
      "eval_loss": NaN,
      "eval_runtime": 212.7765,
      "eval_samples_per_second": 23.048,
      "eval_steps_per_second": 2.881,
      "step": 1
    },
    {
      "epoch": 0.0001717327837884252,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00025759917568263783,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0003434655675768504,
      "grad_norm": NaN,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.000429331959471063,
      "grad_norm": NaN,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005151983513652757,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0006010647432594882,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006869311351537008,
      "grad_norm": NaN,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0007727975270479134,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.000858663918942126,
      "grad_norm": NaN,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0009445303108363386,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0010303967027305513,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.001116263094624764,
      "grad_norm": NaN,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0012021294865189765,
      "grad_norm": NaN,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.001287995878413189,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0013738622703074017,
      "grad_norm": NaN,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0014597286622016143,
      "grad_norm": NaN,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0015455950540958269,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0016314614459900395,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.001717327837884252,
      "grad_norm": NaN,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0018031942297784646,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0018890606216726772,
      "grad_norm": NaN,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.00197492701356689,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.0020607934054611026,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.002146659797355315,
      "grad_norm": NaN,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.002146659797355315,
      "eval_loss": NaN,
      "eval_runtime": 212.7343,
      "eval_samples_per_second": 23.052,
      "eval_steps_per_second": 2.882,
      "step": 25
    },
    {
      "epoch": 0.002232526189249528,
      "grad_norm": NaN,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.00231839258114374,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.002404258973037953,
      "grad_norm": NaN,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.0024901253649321654,
      "grad_norm": NaN,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.002575991756826378,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0026618581487205905,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.0027477245406148034,
      "grad_norm": NaN,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.002833590932509016,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.0029194573244032285,
      "grad_norm": NaN,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0030053237162974413,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0030911901081916537,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0031770565000858665,
      "grad_norm": NaN,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.003262922891980079,
      "grad_norm": NaN,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0033487892838742917,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.003434655675768504,
      "grad_norm": NaN,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.003520522067662717,
      "grad_norm": NaN,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0036063884595569293,
      "grad_norm": NaN,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.003692254851451142,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0037781212433453545,
      "grad_norm": NaN,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.0038639876352395673,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.00394985402713378,
      "grad_norm": NaN,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0040357204190279924,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.004121586810922205,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.004207453202816418,
      "grad_norm": NaN,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.00429331959471063,
      "grad_norm": NaN,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.00429331959471063,
      "eval_loss": NaN,
      "eval_runtime": 212.7677,
      "eval_samples_per_second": 23.049,
      "eval_steps_per_second": 2.881,
      "step": 50
    },
    {
      "epoch": 0.004379185986604843,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.004465052378499056,
      "grad_norm": NaN,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.004550918770393268,
      "grad_norm": NaN,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.00463678516228748,
      "grad_norm": NaN,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.004722651554181693,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.004808517946075906,
      "grad_norm": NaN,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.004894384337970119,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.004980250729864331,
      "grad_norm": NaN,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.0050661171217585435,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.005151983513652756,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.005237849905546969,
      "grad_norm": NaN,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.005323716297441181,
      "grad_norm": NaN,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.005409582689335394,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.005495449081229607,
      "grad_norm": NaN,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.0055813154731238195,
      "grad_norm": NaN,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.005667181865018032,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.005753048256912244,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.005838914648806457,
      "grad_norm": NaN,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.00592478104070067,
      "grad_norm": NaN,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.006010647432594883,
      "grad_norm": NaN,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.006096513824489095,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.0061823802163833074,
      "grad_norm": NaN,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.00626824660827752,
      "grad_norm": NaN,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.006354113000171733,
      "grad_norm": NaN,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.006439979392065945,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.006439979392065945,
      "eval_loss": NaN,
      "eval_runtime": 212.7684,
      "eval_samples_per_second": 23.049,
      "eval_steps_per_second": 2.881,
      "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": 9933153317683200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}