{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011131725417439703,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001484230055658627,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0001484230055658627,
      "eval_loss": NaN,
      "eval_runtime": 611.4372,
      "eval_samples_per_second": 9.28,
      "eval_steps_per_second": 4.64,
      "step": 1
    },
    {
      "epoch": 0.0002968460111317254,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0004452690166975881,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005936920222634508,
      "grad_norm": NaN,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0007421150278293135,
      "grad_norm": NaN,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008905380333951762,
      "grad_norm": NaN,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.001038961038961039,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0011873840445269016,
      "grad_norm": NaN,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0013358070500927644,
      "grad_norm": NaN,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.001484230055658627,
      "grad_norm": NaN,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0016326530612244899,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0017810760667903525,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0019294990723562153,
      "grad_norm": NaN,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.002077922077922078,
      "grad_norm": NaN,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0022263450834879408,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.002374768089053803,
      "grad_norm": NaN,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.002523191094619666,
      "grad_norm": NaN,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.002671614100185529,
      "grad_norm": NaN,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0028200371057513916,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.002968460111317254,
      "grad_norm": NaN,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.003116883116883117,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0032653061224489797,
      "grad_norm": NaN,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.003413729128014842,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.003562152133580705,
      "grad_norm": NaN,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0037105751391465678,
      "grad_norm": NaN,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0037105751391465678,
      "eval_loss": NaN,
      "eval_runtime": 611.4127,
      "eval_samples_per_second": 9.28,
      "eval_steps_per_second": 4.64,
      "step": 25
    },
    {
      "epoch": 0.0038589981447124306,
      "grad_norm": NaN,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.004007421150278293,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.004155844155844156,
      "grad_norm": NaN,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.004304267161410019,
      "grad_norm": NaN,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0044526901669758815,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.004601113172541744,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.004749536178107606,
      "grad_norm": NaN,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.004897959183673469,
      "grad_norm": NaN,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.005046382189239332,
      "grad_norm": NaN,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.005194805194805195,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.005343228200371058,
      "grad_norm": NaN,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.0054916512059369205,
      "grad_norm": NaN,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.005640074211502783,
      "grad_norm": NaN,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.005788497217068645,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.005936920222634508,
      "grad_norm": NaN,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.006085343228200371,
      "grad_norm": NaN,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.006233766233766234,
      "grad_norm": NaN,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.006382189239332097,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.006530612244897959,
      "grad_norm": NaN,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.006679035250463822,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.006827458256029684,
      "grad_norm": NaN,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.006975881261595547,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.00712430426716141,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.007272727272727273,
      "grad_norm": NaN,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0074211502782931356,
      "grad_norm": NaN,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0074211502782931356,
      "eval_loss": NaN,
      "eval_runtime": 612.3488,
      "eval_samples_per_second": 9.266,
      "eval_steps_per_second": 4.633,
      "step": 50
    },
    {
      "epoch": 0.007569573283858998,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.007717996289424861,
      "grad_norm": NaN,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.007866419294990724,
      "grad_norm": NaN,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.008014842300556586,
      "grad_norm": NaN,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.00816326530612245,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.008311688311688312,
      "grad_norm": NaN,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.008460111317254174,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.008608534322820037,
      "grad_norm": NaN,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.0087569573283859,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.008905380333951763,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.009053803339517625,
      "grad_norm": NaN,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.009202226345083489,
      "grad_norm": NaN,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.00935064935064935,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.009499072356215213,
      "grad_norm": NaN,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.009647495361781076,
      "grad_norm": NaN,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.009795918367346938,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.009944341372912802,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.010092764378478664,
      "grad_norm": NaN,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.010241187384044528,
      "grad_norm": NaN,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": NaN,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.010538033395176252,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.010686456400742115,
      "grad_norm": NaN,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.010834879406307977,
      "grad_norm": NaN,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.010983302411873841,
      "grad_norm": NaN,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.011131725417439703,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.011131725417439703,
      "eval_loss": NaN,
      "eval_runtime": 612.3545,
      "eval_samples_per_second": 9.266,
      "eval_steps_per_second": 4.633,
      "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": 9.877262206972723e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}