{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06916825177243645,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006916825177243646,
      "grad_norm": 0.2954893708229065,
      "learning_rate": 0.0,
      "loss": 2.3812,
      "step": 1
    },
    {
      "epoch": 0.0013833650354487291,
      "grad_norm": 0.3372870683670044,
      "learning_rate": 1.3698630136986302e-06,
      "loss": 2.6562,
      "step": 2
    },
    {
      "epoch": 0.0020750475531730937,
      "grad_norm": 0.41708794236183167,
      "learning_rate": 2.7397260273972604e-06,
      "loss": 2.779,
      "step": 3
    },
    {
      "epoch": 0.0027667300708974583,
      "grad_norm": 0.48284393548965454,
      "learning_rate": 4.10958904109589e-06,
      "loss": 2.83,
      "step": 4
    },
    {
      "epoch": 0.0034584125886218224,
      "grad_norm": 0.328521728515625,
      "learning_rate": 5.479452054794521e-06,
      "loss": 2.3607,
      "step": 5
    },
    {
      "epoch": 0.004150095106346187,
      "grad_norm": 0.3413754403591156,
      "learning_rate": 6.849315068493151e-06,
      "loss": 1.9744,
      "step": 6
    },
    {
      "epoch": 0.0048417776240705515,
      "grad_norm": 0.43425995111465454,
      "learning_rate": 8.21917808219178e-06,
      "loss": 1.915,
      "step": 7
    },
    {
      "epoch": 0.0055334601417949165,
      "grad_norm": 0.45184195041656494,
      "learning_rate": 9.589041095890411e-06,
      "loss": 2.0002,
      "step": 8
    },
    {
      "epoch": 0.006225142659519281,
      "grad_norm": 0.3451146185398102,
      "learning_rate": 1.0958904109589042e-05,
      "loss": 2.5739,
      "step": 9
    },
    {
      "epoch": 0.006916825177243645,
      "grad_norm": 0.39400503039360046,
      "learning_rate": 1.2328767123287671e-05,
      "loss": 2.6139,
      "step": 10
    },
    {
      "epoch": 0.00760850769496801,
      "grad_norm": 0.4555888772010803,
      "learning_rate": 1.3698630136986302e-05,
      "loss": 2.4346,
      "step": 11
    },
    {
      "epoch": 0.008300190212692375,
      "grad_norm": 0.5475619435310364,
      "learning_rate": 1.5068493150684931e-05,
      "loss": 1.485,
      "step": 12
    },
    {
      "epoch": 0.008991872730416739,
      "grad_norm": 1.219076156616211,
      "learning_rate": 1.643835616438356e-05,
      "loss": 2.0555,
      "step": 13
    },
    {
      "epoch": 0.009683555248141103,
      "grad_norm": 0.3271433711051941,
      "learning_rate": 1.780821917808219e-05,
      "loss": 2.8418,
      "step": 14
    },
    {
      "epoch": 0.010375237765865467,
      "grad_norm": 0.3261394500732422,
      "learning_rate": 1.9178082191780822e-05,
      "loss": 2.287,
      "step": 15
    },
    {
      "epoch": 0.011066920283589833,
      "grad_norm": 0.39713796973228455,
      "learning_rate": 2.0547945205479453e-05,
      "loss": 2.7331,
      "step": 16
    },
    {
      "epoch": 0.011758602801314197,
      "grad_norm": 0.3226444125175476,
      "learning_rate": 2.1917808219178083e-05,
      "loss": 2.7307,
      "step": 17
    },
    {
      "epoch": 0.012450285319038561,
      "grad_norm": 0.4153122007846832,
      "learning_rate": 2.328767123287671e-05,
      "loss": 2.3229,
      "step": 18
    },
    {
      "epoch": 0.013141967836762926,
      "grad_norm": 0.29302462935447693,
      "learning_rate": 2.4657534246575342e-05,
      "loss": 2.2093,
      "step": 19
    },
    {
      "epoch": 0.01383365035448729,
      "grad_norm": 0.42535701394081116,
      "learning_rate": 2.6027397260273973e-05,
      "loss": 2.3698,
      "step": 20
    },
    {
      "epoch": 0.014525332872211656,
      "grad_norm": 0.33567023277282715,
      "learning_rate": 2.7397260273972603e-05,
      "loss": 2.6456,
      "step": 21
    },
    {
      "epoch": 0.01521701538993602,
      "grad_norm": 0.37375620007514954,
      "learning_rate": 2.8767123287671234e-05,
      "loss": 2.4148,
      "step": 22
    },
    {
      "epoch": 0.015908697907660384,
      "grad_norm": 0.2704203128814697,
      "learning_rate": 3.0136986301369862e-05,
      "loss": 1.6722,
      "step": 23
    },
    {
      "epoch": 0.01660038042538475,
      "grad_norm": 0.3946782946586609,
      "learning_rate": 3.1506849315068496e-05,
      "loss": 2.6759,
      "step": 24
    },
    {
      "epoch": 0.017292062943109112,
      "grad_norm": 0.368335098028183,
      "learning_rate": 3.287671232876712e-05,
      "loss": 2.6882,
      "step": 25
    },
    {
      "epoch": 0.017983745460833478,
      "grad_norm": 0.38029783964157104,
      "learning_rate": 3.424657534246575e-05,
      "loss": 2.6915,
      "step": 26
    },
    {
      "epoch": 0.01867542797855784,
      "grad_norm": 0.36253222823143005,
      "learning_rate": 3.561643835616438e-05,
      "loss": 2.1426,
      "step": 27
    },
    {
      "epoch": 0.019367110496282206,
      "grad_norm": 0.35769322514533997,
      "learning_rate": 3.698630136986301e-05,
      "loss": 2.6634,
      "step": 28
    },
    {
      "epoch": 0.020058793014006572,
      "grad_norm": 0.44577229022979736,
      "learning_rate": 3.8356164383561644e-05,
      "loss": 2.5996,
      "step": 29
    },
    {
      "epoch": 0.020750475531730934,
      "grad_norm": 0.5225628614425659,
      "learning_rate": 3.9726027397260274e-05,
      "loss": 2.5993,
      "step": 30
    },
    {
      "epoch": 0.0214421580494553,
      "grad_norm": 0.45649707317352295,
      "learning_rate": 4.1095890410958905e-05,
      "loss": 2.3344,
      "step": 31
    },
    {
      "epoch": 0.022133840567179666,
      "grad_norm": 0.31408172845840454,
      "learning_rate": 4.2465753424657536e-05,
      "loss": 2.343,
      "step": 32
    },
    {
      "epoch": 0.02282552308490403,
      "grad_norm": 0.3498693108558655,
      "learning_rate": 4.383561643835617e-05,
      "loss": 1.7196,
      "step": 33
    },
    {
      "epoch": 0.023517205602628394,
      "grad_norm": 0.5255292654037476,
      "learning_rate": 4.520547945205479e-05,
      "loss": 1.5354,
      "step": 34
    },
    {
      "epoch": 0.024208888120352757,
      "grad_norm": 0.3460487425327301,
      "learning_rate": 4.657534246575342e-05,
      "loss": 2.1435,
      "step": 35
    },
    {
      "epoch": 0.024900570638077123,
      "grad_norm": 0.47466233372688293,
      "learning_rate": 4.794520547945205e-05,
      "loss": 2.7025,
      "step": 36
    },
    {
      "epoch": 0.02559225315580149,
      "grad_norm": 0.39667466282844543,
      "learning_rate": 4.9315068493150684e-05,
      "loss": 2.2736,
      "step": 37
    },
    {
      "epoch": 0.02628393567352585,
      "grad_norm": 0.40798133611679077,
      "learning_rate": 5.068493150684932e-05,
      "loss": 1.4074,
      "step": 38
    },
    {
      "epoch": 0.026975618191250217,
      "grad_norm": 0.39603471755981445,
      "learning_rate": 5.2054794520547945e-05,
      "loss": 2.4354,
      "step": 39
    },
    {
      "epoch": 0.02766730070897458,
      "grad_norm": 0.5650593042373657,
      "learning_rate": 5.342465753424658e-05,
      "loss": 1.7307,
      "step": 40
    },
    {
      "epoch": 0.028358983226698945,
      "grad_norm": 0.7711919546127319,
      "learning_rate": 5.479452054794521e-05,
      "loss": 1.2067,
      "step": 41
    },
    {
      "epoch": 0.02905066574442331,
      "grad_norm": 0.46603119373321533,
      "learning_rate": 5.616438356164384e-05,
      "loss": 1.0539,
      "step": 42
    },
    {
      "epoch": 0.029742348262147673,
      "grad_norm": 0.2997550666332245,
      "learning_rate": 5.753424657534247e-05,
      "loss": 1.9997,
      "step": 43
    },
    {
      "epoch": 0.03043403077987204,
      "grad_norm": 0.4058617651462555,
      "learning_rate": 5.89041095890411e-05,
      "loss": 2.3323,
      "step": 44
    },
    {
      "epoch": 0.0311257132975964,
      "grad_norm": 0.3763635754585266,
      "learning_rate": 6.0273972602739724e-05,
      "loss": 1.8749,
      "step": 45
    },
    {
      "epoch": 0.03181739581532077,
      "grad_norm": 0.3507993221282959,
      "learning_rate": 6.164383561643835e-05,
      "loss": 2.3828,
      "step": 46
    },
    {
      "epoch": 0.03250907833304513,
      "grad_norm": 0.34240859746932983,
      "learning_rate": 6.301369863013699e-05,
      "loss": 2.3809,
      "step": 47
    },
    {
      "epoch": 0.0332007608507695,
      "grad_norm": 0.4183844029903412,
      "learning_rate": 6.438356164383562e-05,
      "loss": 2.2065,
      "step": 48
    },
    {
      "epoch": 0.03389244336849386,
      "grad_norm": 0.5209120512008667,
      "learning_rate": 6.575342465753424e-05,
      "loss": 2.061,
      "step": 49
    },
    {
      "epoch": 0.034584125886218224,
      "grad_norm": 0.6568111181259155,
      "learning_rate": 6.712328767123288e-05,
      "loss": 2.1576,
      "step": 50
    },
    {
      "epoch": 0.03527580840394259,
      "grad_norm": 0.5327390432357788,
      "learning_rate": 6.84931506849315e-05,
      "loss": 1.5562,
      "step": 51
    },
    {
      "epoch": 0.035967490921666956,
      "grad_norm": 0.6389997005462646,
      "learning_rate": 6.986301369863014e-05,
      "loss": 2.3966,
      "step": 52
    },
    {
      "epoch": 0.03665917343939132,
      "grad_norm": 0.6374388933181763,
      "learning_rate": 7.123287671232876e-05,
      "loss": 2.4013,
      "step": 53
    },
    {
      "epoch": 0.03735085595711568,
      "grad_norm": 0.4383719563484192,
      "learning_rate": 7.26027397260274e-05,
      "loss": 2.061,
      "step": 54
    },
    {
      "epoch": 0.03804253847484005,
      "grad_norm": 0.4306814670562744,
      "learning_rate": 7.397260273972603e-05,
      "loss": 2.4931,
      "step": 55
    },
    {
      "epoch": 0.03873422099256441,
      "grad_norm": 0.5693032145500183,
      "learning_rate": 7.534246575342466e-05,
      "loss": 2.2842,
      "step": 56
    },
    {
      "epoch": 0.039425903510288775,
      "grad_norm": 0.7792916297912598,
      "learning_rate": 7.671232876712329e-05,
      "loss": 1.8452,
      "step": 57
    },
    {
      "epoch": 0.040117586028013144,
      "grad_norm": 0.4936494827270508,
      "learning_rate": 7.808219178082192e-05,
      "loss": 1.8668,
      "step": 58
    },
    {
      "epoch": 0.040809268545737507,
      "grad_norm": 0.49626269936561584,
      "learning_rate": 7.945205479452055e-05,
      "loss": 1.9564,
      "step": 59
    },
    {
      "epoch": 0.04150095106346187,
      "grad_norm": 0.4702766537666321,
      "learning_rate": 8.082191780821919e-05,
      "loss": 2.419,
      "step": 60
    },
    {
      "epoch": 0.04219263358118624,
      "grad_norm": 0.6959900259971619,
      "learning_rate": 8.219178082191781e-05,
      "loss": 1.5835,
      "step": 61
    },
    {
      "epoch": 0.0428843160989106,
      "grad_norm": 0.5963976979255676,
      "learning_rate": 8.356164383561645e-05,
      "loss": 2.2932,
      "step": 62
    },
    {
      "epoch": 0.04357599861663496,
      "grad_norm": 0.4605785310268402,
      "learning_rate": 8.493150684931507e-05,
      "loss": 2.397,
      "step": 63
    },
    {
      "epoch": 0.04426768113435933,
      "grad_norm": 0.4479796588420868,
      "learning_rate": 8.630136986301371e-05,
      "loss": 2.0257,
      "step": 64
    },
    {
      "epoch": 0.044959363652083695,
      "grad_norm": 0.4342099726200104,
      "learning_rate": 8.767123287671233e-05,
      "loss": 1.9476,
      "step": 65
    },
    {
      "epoch": 0.04565104616980806,
      "grad_norm": 0.44643279910087585,
      "learning_rate": 8.904109589041096e-05,
      "loss": 2.4669,
      "step": 66
    },
    {
      "epoch": 0.04634272868753242,
      "grad_norm": 0.513254702091217,
      "learning_rate": 9.041095890410958e-05,
      "loss": 2.2581,
      "step": 67
    },
    {
      "epoch": 0.04703441120525679,
      "grad_norm": 0.6621958613395691,
      "learning_rate": 9.178082191780822e-05,
      "loss": 1.3013,
      "step": 68
    },
    {
      "epoch": 0.04772609372298115,
      "grad_norm": 0.43388229608535767,
      "learning_rate": 9.315068493150684e-05,
      "loss": 2.5325,
      "step": 69
    },
    {
      "epoch": 0.048417776240705514,
      "grad_norm": 0.539757490158081,
      "learning_rate": 9.452054794520548e-05,
      "loss": 1.76,
      "step": 70
    },
    {
      "epoch": 0.04910945875842988,
      "grad_norm": 0.33598029613494873,
      "learning_rate": 9.58904109589041e-05,
      "loss": 1.6931,
      "step": 71
    },
    {
      "epoch": 0.049801141276154245,
      "grad_norm": 0.8661749958992004,
      "learning_rate": 9.726027397260274e-05,
      "loss": 2.1326,
      "step": 72
    },
    {
      "epoch": 0.05049282379387861,
      "grad_norm": 0.5956202149391174,
      "learning_rate": 9.863013698630137e-05,
      "loss": 2.0554,
      "step": 73
    },
    {
      "epoch": 0.05118450631160298,
      "grad_norm": 0.7723128199577332,
      "learning_rate": 0.0001,
      "loss": 1.4837,
      "step": 74
    },
    {
      "epoch": 0.05187618882932734,
      "grad_norm": 0.5357879996299744,
      "learning_rate": 9.992716678805537e-05,
      "loss": 2.1688,
      "step": 75
    },
    {
      "epoch": 0.0525678713470517,
      "grad_norm": 0.48623108863830566,
      "learning_rate": 9.985433357611071e-05,
      "loss": 2.1567,
      "step": 76
    },
    {
      "epoch": 0.053259553864776064,
      "grad_norm": 0.4244164228439331,
      "learning_rate": 9.978150036416607e-05,
      "loss": 1.8235,
      "step": 77
    },
    {
      "epoch": 0.053951236382500434,
      "grad_norm": 0.6056337356567383,
      "learning_rate": 9.970866715222141e-05,
      "loss": 2.0154,
      "step": 78
    },
    {
      "epoch": 0.054642918900224796,
      "grad_norm": 0.5280382037162781,
      "learning_rate": 9.963583394027677e-05,
      "loss": 1.9959,
      "step": 79
    },
    {
      "epoch": 0.05533460141794916,
      "grad_norm": 0.44745901226997375,
      "learning_rate": 9.956300072833212e-05,
      "loss": 1.2171,
      "step": 80
    },
    {
      "epoch": 0.05602628393567353,
      "grad_norm": 0.7180289030075073,
      "learning_rate": 9.949016751638748e-05,
      "loss": 1.7036,
      "step": 81
    },
    {
      "epoch": 0.05671796645339789,
      "grad_norm": 0.6465222239494324,
      "learning_rate": 9.941733430444284e-05,
      "loss": 1.8992,
      "step": 82
    },
    {
      "epoch": 0.05740964897112225,
      "grad_norm": 0.4792153239250183,
      "learning_rate": 9.934450109249819e-05,
      "loss": 2.0712,
      "step": 83
    },
    {
      "epoch": 0.05810133148884662,
      "grad_norm": 0.47839808464050293,
      "learning_rate": 9.927166788055353e-05,
      "loss": 1.7548,
      "step": 84
    },
    {
      "epoch": 0.058793014006570984,
      "grad_norm": 0.7118557095527649,
      "learning_rate": 9.919883466860888e-05,
      "loss": 1.5835,
      "step": 85
    },
    {
      "epoch": 0.05948469652429535,
      "grad_norm": 0.5179592370986938,
      "learning_rate": 9.912600145666424e-05,
      "loss": 1.621,
      "step": 86
    },
    {
      "epoch": 0.060176379042019716,
      "grad_norm": 0.9235703349113464,
      "learning_rate": 9.905316824471959e-05,
      "loss": 0.8581,
      "step": 87
    },
    {
      "epoch": 0.06086806155974408,
      "grad_norm": 0.8734163045883179,
      "learning_rate": 9.898033503277495e-05,
      "loss": 2.2878,
      "step": 88
    },
    {
      "epoch": 0.06155974407746844,
      "grad_norm": 0.45049625635147095,
      "learning_rate": 9.890750182083031e-05,
      "loss": 2.2186,
      "step": 89
    },
    {
      "epoch": 0.0622514265951928,
      "grad_norm": 0.6119429469108582,
      "learning_rate": 9.883466860888566e-05,
      "loss": 2.2461,
      "step": 90
    },
    {
      "epoch": 0.06294310911291717,
      "grad_norm": 0.5095340013504028,
      "learning_rate": 9.876183539694101e-05,
      "loss": 2.2954,
      "step": 91
    },
    {
      "epoch": 0.06363479163064154,
      "grad_norm": 0.6094918251037598,
      "learning_rate": 9.868900218499635e-05,
      "loss": 2.3478,
      "step": 92
    },
    {
      "epoch": 0.0643264741483659,
      "grad_norm": 1.8420301675796509,
      "learning_rate": 9.861616897305172e-05,
      "loss": 2.213,
      "step": 93
    },
    {
      "epoch": 0.06501815666609026,
      "grad_norm": 0.6151532530784607,
      "learning_rate": 9.854333576110706e-05,
      "loss": 1.8737,
      "step": 94
    },
    {
      "epoch": 0.06570983918381462,
      "grad_norm": 0.5210903286933899,
      "learning_rate": 9.847050254916242e-05,
      "loss": 2.019,
      "step": 95
    },
    {
      "epoch": 0.066401521701539,
      "grad_norm": 0.535746693611145,
      "learning_rate": 9.839766933721779e-05,
      "loss": 2.399,
      "step": 96
    },
    {
      "epoch": 0.06709320421926336,
      "grad_norm": 0.8154505491256714,
      "learning_rate": 9.832483612527313e-05,
      "loss": 1.9442,
      "step": 97
    },
    {
      "epoch": 0.06778488673698772,
      "grad_norm": 0.521247923374176,
      "learning_rate": 9.825200291332848e-05,
      "loss": 2.5264,
      "step": 98
    },
    {
      "epoch": 0.06847656925471209,
      "grad_norm": 0.41544124484062195,
      "learning_rate": 9.817916970138383e-05,
      "loss": 1.8267,
      "step": 99
    },
    {
      "epoch": 0.06916825177243645,
      "grad_norm": 0.538253128528595,
      "learning_rate": 9.810633648943919e-05,
      "loss": 1.6463,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 1446,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3239229827579904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}