{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5067567567567568,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 1.165550708770752,
      "learning_rate": 1e-05,
      "loss": 3.626,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "eval_loss": 3.7272541522979736,
      "eval_runtime": 4.139,
      "eval_samples_per_second": 30.2,
      "eval_steps_per_second": 3.866,
      "step": 1
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 1.0644617080688477,
      "learning_rate": 2e-05,
      "loss": 3.8724,
      "step": 2
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 1.1389989852905273,
      "learning_rate": 3e-05,
      "loss": 3.5915,
      "step": 3
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.0900439023971558,
      "learning_rate": 4e-05,
      "loss": 3.7253,
      "step": 4
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 1.1674542427062988,
      "learning_rate": 5e-05,
      "loss": 3.6544,
      "step": 5
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.027275800704956,
      "learning_rate": 6e-05,
      "loss": 3.3359,
      "step": 6
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 1.348042607307434,
      "learning_rate": 7e-05,
      "loss": 3.7027,
      "step": 7
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.2195662260055542,
      "learning_rate": 8e-05,
      "loss": 3.4344,
      "step": 8
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 1.1674548387527466,
      "learning_rate": 9e-05,
      "loss": 3.4253,
      "step": 9
    },
    {
      "epoch": 0.060810810810810814,
      "eval_loss": 3.543837070465088,
      "eval_runtime": 3.5109,
      "eval_samples_per_second": 35.603,
      "eval_steps_per_second": 4.557,
      "step": 9
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 1.3922748565673828,
      "learning_rate": 0.0001,
      "loss": 3.643,
      "step": 10
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 1.216573715209961,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.5204,
      "step": 11
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.1309475898742676,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.113,
      "step": 12
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 1.4442179203033447,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.0735,
      "step": 13
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 1.3493503332138062,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.2508,
      "step": 14
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.3219938278198242,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.1881,
      "step": 15
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.606813669204712,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.004,
      "step": 16
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 1.4070640802383423,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.5799,
      "step": 17
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.4162650108337402,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6839,
      "step": 18
    },
    {
      "epoch": 0.12162162162162163,
      "eval_loss": 2.5524935722351074,
      "eval_runtime": 3.5211,
      "eval_samples_per_second": 35.501,
      "eval_steps_per_second": 4.544,
      "step": 18
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 1.2180479764938354,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.632,
      "step": 19
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.2392053604125977,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.543,
      "step": 20
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.225856900215149,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.3457,
      "step": 21
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 1.4014432430267334,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.4257,
      "step": 22
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 1.1311300992965698,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.9219,
      "step": 23
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.2671700716018677,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.3732,
      "step": 24
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 0.9614380598068237,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2316,
      "step": 25
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 1.0399982929229736,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.0554,
      "step": 26
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 1.2994896173477173,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.1411,
      "step": 27
    },
    {
      "epoch": 0.18243243243243243,
      "eval_loss": 2.0132856369018555,
      "eval_runtime": 3.5135,
      "eval_samples_per_second": 35.577,
      "eval_steps_per_second": 4.554,
      "step": 27
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.0128037929534912,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.8349,
      "step": 28
    },
    {
      "epoch": 0.19594594594594594,
      "grad_norm": 1.0621966123580933,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.7304,
      "step": 29
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 0.9444336891174316,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.8391,
      "step": 30
    },
    {
      "epoch": 0.20945945945945946,
      "grad_norm": 1.013601541519165,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.9608,
      "step": 31
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.1101553440093994,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.9638,
      "step": 32
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 0.9574841856956482,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.0326,
      "step": 33
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 0.9780818223953247,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.7894,
      "step": 34
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 1.0742874145507812,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.9416,
      "step": 35
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.9108137488365173,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.861,
      "step": 36
    },
    {
      "epoch": 0.24324324324324326,
      "eval_loss": 1.8477528095245361,
      "eval_runtime": 3.5122,
      "eval_samples_per_second": 35.59,
      "eval_steps_per_second": 4.556,
      "step": 36
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.9335376024246216,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8027,
      "step": 37
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 1.0257062911987305,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.8306,
      "step": 38
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 0.8713502883911133,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.5814,
      "step": 39
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.0091434717178345,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5569,
      "step": 40
    },
    {
      "epoch": 0.27702702702702703,
      "grad_norm": 0.9113713502883911,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.7839,
      "step": 41
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 0.8845016360282898,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.6395,
      "step": 42
    },
    {
      "epoch": 0.2905405405405405,
      "grad_norm": 0.9751928448677063,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.0989,
      "step": 43
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 1.0509858131408691,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6493,
      "step": 44
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 1.0471868515014648,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.6431,
      "step": 45
    },
    {
      "epoch": 0.30405405405405406,
      "eval_loss": 1.7883583307266235,
      "eval_runtime": 3.5109,
      "eval_samples_per_second": 35.604,
      "eval_steps_per_second": 4.557,
      "step": 45
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 1.315850019454956,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5634,
      "step": 46
    },
    {
      "epoch": 0.31756756756756754,
      "grad_norm": 0.9055303335189819,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.7563,
      "step": 47
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.9029581546783447,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.822,
      "step": 48
    },
    {
      "epoch": 0.3310810810810811,
      "grad_norm": 0.8379126191139221,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.5573,
      "step": 49
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 1.1745027303695679,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.062,
      "step": 50
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 1.1078695058822632,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.1678,
      "step": 51
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 0.9430006742477417,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.8513,
      "step": 52
    },
    {
      "epoch": 0.3581081081081081,
      "grad_norm": 0.9669394493103027,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8486,
      "step": 53
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 0.9533030390739441,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.8129,
      "step": 54
    },
    {
      "epoch": 0.36486486486486486,
      "eval_loss": 1.7548061609268188,
      "eval_runtime": 3.5366,
      "eval_samples_per_second": 35.345,
      "eval_steps_per_second": 4.524,
      "step": 54
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 0.8269166350364685,
      "learning_rate": 5e-05,
      "loss": 1.6914,
      "step": 55
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.9480825662612915,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.8577,
      "step": 56
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 0.9473639130592346,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.9744,
      "step": 57
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 0.9393849968910217,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.8944,
      "step": 58
    },
    {
      "epoch": 0.39864864864864863,
      "grad_norm": 0.848622739315033,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.619,
      "step": 59
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 0.9589544534683228,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.8031,
      "step": 60
    },
    {
      "epoch": 0.41216216216216217,
      "grad_norm": 0.9193155169487,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.57,
      "step": 61
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 0.8888735175132751,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.5869,
      "step": 62
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 0.9404612183570862,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8206,
      "step": 63
    },
    {
      "epoch": 0.42567567567567566,
      "eval_loss": 1.7357913255691528,
      "eval_runtime": 3.5129,
      "eval_samples_per_second": 35.583,
      "eval_steps_per_second": 4.555,
      "step": 63
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.8742846846580505,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.5211,
      "step": 64
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 0.9241499304771423,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.082,
      "step": 65
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 0.9210823774337769,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.7166,
      "step": 66
    },
    {
      "epoch": 0.4527027027027027,
      "grad_norm": 0.8455032706260681,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.5984,
      "step": 67
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 0.9703152775764465,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.8997,
      "step": 68
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 1.0417201519012451,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.6946,
      "step": 69
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 0.8623643517494202,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.8819,
      "step": 70
    },
    {
      "epoch": 0.4797297297297297,
      "grad_norm": 0.8981446027755737,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.7159,
      "step": 71
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 0.8115476965904236,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.3985,
      "step": 72
    },
    {
      "epoch": 0.4864864864864865,
      "eval_loss": 1.719651699066162,
      "eval_runtime": 3.5221,
      "eval_samples_per_second": 35.49,
      "eval_steps_per_second": 4.543,
      "step": 72
    },
    {
      "epoch": 0.49324324324324326,
      "grad_norm": 0.8665674328804016,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5179,
      "step": 73
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.9210397005081177,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.7493,
      "step": 74
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 0.8442562222480774,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8021,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7771734228860928.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}