{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8e-05,
      "grad_norm": 6.928949356079102,
      "learning_rate": 0.0,
      "loss": 12.014674186706543,
      "step": 1
    },
    {
      "epoch": 0.00016,
      "grad_norm": 8.920316696166992,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 15.713064193725586,
      "step": 2
    },
    {
      "epoch": 0.00024,
      "grad_norm": 8.561675071716309,
      "learning_rate": 6.666666666666667e-05,
      "loss": 13.12899398803711,
      "step": 3
    },
    {
      "epoch": 0.00032,
      "grad_norm": 8.729342460632324,
      "learning_rate": 0.0001,
      "loss": 16.589990615844727,
      "step": 4
    },
    {
      "epoch": 0.0004,
      "grad_norm": 7.973804950714111,
      "learning_rate": 0.00013333333333333334,
      "loss": 13.032384872436523,
      "step": 5
    },
    {
      "epoch": 0.00048,
      "grad_norm": 6.11670446395874,
      "learning_rate": 0.0001666666666666667,
      "loss": 8.09074592590332,
      "step": 6
    },
    {
      "epoch": 0.00056,
      "grad_norm": 12.821895599365234,
      "learning_rate": 0.0002,
      "loss": 13.565499305725098,
      "step": 7
    },
    {
      "epoch": 0.00064,
      "grad_norm": Infinity,
      "learning_rate": 0.00019998688836656323,
      "loss": 9.580286026000977,
      "step": 8
    },
    {
      "epoch": 0.00072,
      "grad_norm": 10.717191696166992,
      "learning_rate": 0.00019998688836656323,
      "loss": 11.118619918823242,
      "step": 9
    },
    {
      "epoch": 0.0008,
      "grad_norm": 15.189062118530273,
      "learning_rate": 0.00019994755690455152,
      "loss": 10.562832832336426,
      "step": 10
    },
    {
      "epoch": 0.00088,
      "grad_norm": 11.298067092895508,
      "learning_rate": 0.0001998820159279591,
      "loss": 8.768858909606934,
      "step": 11
    },
    {
      "epoch": 0.00096,
      "grad_norm": 10.482418060302734,
      "learning_rate": 0.00019979028262377118,
      "loss": 6.118743419647217,
      "step": 12
    },
    {
      "epoch": 0.00104,
      "grad_norm": 13.8955078125,
      "learning_rate": 0.00019967238104745696,
      "loss": 6.71580696105957,
      "step": 13
    },
    {
      "epoch": 0.00112,
      "grad_norm": 8.358887672424316,
      "learning_rate": 0.0001995283421166614,
      "loss": 6.379769325256348,
      "step": 14
    },
    {
      "epoch": 0.0012,
      "grad_norm": 11.862845420837402,
      "learning_rate": 0.00019935820360309777,
      "loss": 6.037031173706055,
      "step": 15
    },
    {
      "epoch": 0.00128,
      "grad_norm": 8.839066505432129,
      "learning_rate": 0.00019916201012264254,
      "loss": 5.507349014282227,
      "step": 16
    },
    {
      "epoch": 0.00136,
      "grad_norm": 8.00528621673584,
      "learning_rate": 0.00019893981312363562,
      "loss": 5.974639892578125,
      "step": 17
    },
    {
      "epoch": 0.00144,
      "grad_norm": 5.869845867156982,
      "learning_rate": 0.00019869167087338907,
      "loss": 5.14662504196167,
      "step": 18
    },
    {
      "epoch": 0.00152,
      "grad_norm": 7.9579997062683105,
      "learning_rate": 0.00019841764844290744,
      "loss": 5.114725112915039,
      "step": 19
    },
    {
      "epoch": 0.0016,
      "grad_norm": 6.74857234954834,
      "learning_rate": 0.0001981178176898239,
      "loss": 4.387443542480469,
      "step": 20
    },
    {
      "epoch": 0.00168,
      "grad_norm": 4.906152725219727,
      "learning_rate": 0.00019779225723955707,
      "loss": 3.8158411979675293,
      "step": 21
    },
    {
      "epoch": 0.00176,
      "grad_norm": 4.70120906829834,
      "learning_rate": 0.00019744105246469263,
      "loss": 3.4386539459228516,
      "step": 22
    },
    {
      "epoch": 0.00184,
      "grad_norm": 3.952915906906128,
      "learning_rate": 0.00019706429546259593,
      "loss": 3.0041065216064453,
      "step": 23
    },
    {
      "epoch": 0.00192,
      "grad_norm": 15.562743186950684,
      "learning_rate": 0.00019666208503126112,
      "loss": 4.854756832122803,
      "step": 24
    },
    {
      "epoch": 0.002,
      "grad_norm": 4.657861709594727,
      "learning_rate": 0.00019623452664340306,
      "loss": 3.153581142425537,
      "step": 25
    },
    {
      "epoch": 0.00208,
      "grad_norm": 7.487373352050781,
      "learning_rate": 0.00019578173241879872,
      "loss": 3.5299084186553955,
      "step": 26
    },
    {
      "epoch": 0.00216,
      "grad_norm": 6.073024749755859,
      "learning_rate": 0.0001953038210948861,
      "loss": 2.894967555999756,
      "step": 27
    },
    {
      "epoch": 0.00224,
      "grad_norm": 8.635567665100098,
      "learning_rate": 0.00019480091799562704,
      "loss": 3.047236680984497,
      "step": 28
    },
    {
      "epoch": 0.00232,
      "grad_norm": 6.574955463409424,
      "learning_rate": 0.00019427315499864344,
      "loss": 3.163996696472168,
      "step": 29
    },
    {
      "epoch": 0.0024,
      "grad_norm": 8.933237075805664,
      "learning_rate": 0.00019372067050063438,
      "loss": 3.112985372543335,
      "step": 30
    },
    {
      "epoch": 0.00248,
      "grad_norm": 6.229989528656006,
      "learning_rate": 0.00019314360938108425,
      "loss": 3.183608055114746,
      "step": 31
    },
    {
      "epoch": 0.00256,
      "grad_norm": 4.343419551849365,
      "learning_rate": 0.00019254212296427044,
      "loss": 1.5173087120056152,
      "step": 32
    },
    {
      "epoch": 0.00264,
      "grad_norm": 4.703884601593018,
      "learning_rate": 0.00019191636897958122,
      "loss": 2.5797841548919678,
      "step": 33
    },
    {
      "epoch": 0.00272,
      "grad_norm": 4.645837783813477,
      "learning_rate": 0.00019126651152015403,
      "loss": 3.0819389820098877,
      "step": 34
    },
    {
      "epoch": 0.0028,
      "grad_norm": 4.055941581726074,
      "learning_rate": 0.0001905927209998447,
      "loss": 2.445788860321045,
      "step": 35
    },
    {
      "epoch": 0.00288,
      "grad_norm": 3.485275983810425,
      "learning_rate": 0.00018989517410853955,
      "loss": 2.1609947681427,
      "step": 36
    },
    {
      "epoch": 0.00296,
      "grad_norm": 2.7206485271453857,
      "learning_rate": 0.00018917405376582145,
      "loss": 1.184091567993164,
      "step": 37
    },
    {
      "epoch": 0.00304,
      "grad_norm": 4.22371244430542,
      "learning_rate": 0.00018842954907300236,
      "loss": 2.033668279647827,
      "step": 38
    },
    {
      "epoch": 0.00312,
      "grad_norm": 6.188478469848633,
      "learning_rate": 0.0001876618552635348,
      "loss": 3.973464012145996,
      "step": 39
    },
    {
      "epoch": 0.0032,
      "grad_norm": 5.991054058074951,
      "learning_rate": 0.00018687117365181512,
      "loss": 3.453714370727539,
      "step": 40
    },
    {
      "epoch": 0.00328,
      "grad_norm": 3.2771706581115723,
      "learning_rate": 0.00018605771158039253,
      "loss": 2.016055107116699,
      "step": 41
    },
    {
      "epoch": 0.00336,
      "grad_norm": 2.86710262298584,
      "learning_rate": 0.00018522168236559695,
      "loss": 1.0825953483581543,
      "step": 42
    },
    {
      "epoch": 0.00344,
      "grad_norm": 3.313237190246582,
      "learning_rate": 0.00018436330524160047,
      "loss": 2.536651134490967,
      "step": 43
    },
    {
      "epoch": 0.00352,
      "grad_norm": 4.080451488494873,
      "learning_rate": 0.00018348280530292713,
      "loss": 3.4808599948883057,
      "step": 44
    },
    {
      "epoch": 0.0036,
      "grad_norm": 3.049909830093384,
      "learning_rate": 0.00018258041344542566,
      "loss": 2.493288516998291,
      "step": 45
    },
    {
      "epoch": 0.00368,
      "grad_norm": 6.047203540802002,
      "learning_rate": 0.0001816563663057211,
      "loss": 3.421189308166504,
      "step": 46
    },
    {
      "epoch": 0.00376,
      "grad_norm": 6.8579206466674805,
      "learning_rate": 0.00018071090619916093,
      "loss": 4.0107502937316895,
      "step": 47
    },
    {
      "epoch": 0.00384,
      "grad_norm": 8.001409530639648,
      "learning_rate": 0.00017974428105627208,
      "loss": 1.8383188247680664,
      "step": 48
    },
    {
      "epoch": 0.00392,
      "grad_norm": 5.185579776763916,
      "learning_rate": 0.00017875674435774547,
      "loss": 2.074155807495117,
      "step": 49
    },
    {
      "epoch": 0.004,
      "grad_norm": 3.5374512672424316,
      "learning_rate": 0.00017774855506796496,
      "loss": 1.4657212495803833,
      "step": 50
    },
    {
      "epoch": 0.00408,
      "grad_norm": 3.688544750213623,
      "learning_rate": 0.00017671997756709863,
      "loss": 1.6368293762207031,
      "step": 51
    },
    {
      "epoch": 0.00416,
      "grad_norm": 5.878078937530518,
      "learning_rate": 0.00017567128158176953,
      "loss": 2.581313133239746,
      "step": 52
    },
    {
      "epoch": 0.00424,
      "grad_norm": 4.422114372253418,
      "learning_rate": 0.0001746027421143246,
      "loss": 2.660783290863037,
      "step": 53
    },
    {
      "epoch": 0.00432,
      "grad_norm": 5.147724151611328,
      "learning_rate": 0.00017351463937072004,
      "loss": 2.2990241050720215,
      "step": 54
    },
    {
      "epoch": 0.0044,
      "grad_norm": 6.18672513961792,
      "learning_rate": 0.00017240725868704218,
      "loss": 1.4074926376342773,
      "step": 55
    },
    {
      "epoch": 0.00448,
      "grad_norm": 5.2075042724609375,
      "learning_rate": 0.00017128089045468294,
      "loss": 1.5134844779968262,
      "step": 56
    },
    {
      "epoch": 0.00456,
      "grad_norm": 3.1878983974456787,
      "learning_rate": 0.00017013583004418993,
      "loss": 2.699907064437866,
      "step": 57
    },
    {
      "epoch": 0.00464,
      "grad_norm": 3.742098093032837,
      "learning_rate": 0.00016897237772781044,
      "loss": 1.6386728286743164,
      "step": 58
    },
    {
      "epoch": 0.00472,
      "grad_norm": 2.6552226543426514,
      "learning_rate": 0.00016779083860075033,
      "loss": 1.1386427879333496,
      "step": 59
    },
    {
      "epoch": 0.0048,
      "grad_norm": 2.4843499660491943,
      "learning_rate": 0.00016659152250116812,
      "loss": 0.8249317407608032,
      "step": 60
    },
    {
      "epoch": 0.00488,
      "grad_norm": 4.540428161621094,
      "learning_rate": 0.00016537474392892528,
      "loss": 3.6220569610595703,
      "step": 61
    },
    {
      "epoch": 0.00496,
      "grad_norm": 4.440019130706787,
      "learning_rate": 0.000164140821963114,
      "loss": 2.0882022380828857,
      "step": 62
    },
    {
      "epoch": 0.00504,
      "grad_norm": 5.714387893676758,
      "learning_rate": 0.00016289008017838445,
      "loss": 2.471445083618164,
      "step": 63
    },
    {
      "epoch": 0.00512,
      "grad_norm": 3.9814000129699707,
      "learning_rate": 0.00016162284656009274,
      "loss": 1.4108766317367554,
      "step": 64
    },
    {
      "epoch": 0.0052,
      "grad_norm": 2.511936664581299,
      "learning_rate": 0.00016033945341829248,
      "loss": 1.2236822843551636,
      "step": 65
    },
    {
      "epoch": 0.00528,
      "grad_norm": 3.3108081817626953,
      "learning_rate": 0.00015904023730059228,
      "loss": 1.9047954082489014,
      "step": 66
    },
    {
      "epoch": 0.00536,
      "grad_norm": 3.4142255783081055,
      "learning_rate": 0.00015772553890390197,
      "loss": 1.8660364151000977,
      "step": 67
    },
    {
      "epoch": 0.00544,
      "grad_norm": 5.404369831085205,
      "learning_rate": 0.00015639570298509064,
      "loss": 2.1426186561584473,
      "step": 68
    },
    {
      "epoch": 0.00552,
      "grad_norm": 4.093230724334717,
      "learning_rate": 0.00015505107827058036,
      "loss": 1.168108344078064,
      "step": 69
    },
    {
      "epoch": 0.0056,
      "grad_norm": 2.660120725631714,
      "learning_rate": 0.0001536920173648984,
      "loss": 2.291879892349243,
      "step": 70
    },
    {
      "epoch": 0.00568,
      "grad_norm": 4.722398281097412,
      "learning_rate": 0.000152318876658213,
      "loss": 2.181743860244751,
      "step": 71
    },
    {
      "epoch": 0.00576,
      "grad_norm": 2.6253931522369385,
      "learning_rate": 0.00015093201623287631,
      "loss": 1.9663147926330566,
      "step": 72
    },
    {
      "epoch": 0.00584,
      "grad_norm": 3.9038803577423096,
      "learning_rate": 0.00014953179976899878,
      "loss": 2.0541481971740723,
      "step": 73
    },
    {
      "epoch": 0.00592,
      "grad_norm": 6.097304821014404,
      "learning_rate": 0.00014811859444908052,
      "loss": 1.653533935546875,
      "step": 74
    },
    {
      "epoch": 0.006,
      "grad_norm": 3.6705079078674316,
      "learning_rate": 0.00014669277086172406,
      "loss": 1.9317748546600342,
      "step": 75
    },
    {
      "epoch": 0.00608,
      "grad_norm": 4.832096576690674,
      "learning_rate": 0.00014525470290445392,
      "loss": 1.969446063041687,
      "step": 76
    },
    {
      "epoch": 0.00616,
      "grad_norm": 3.0651421546936035,
      "learning_rate": 0.00014380476768566824,
      "loss": 1.0908013582229614,
      "step": 77
    },
    {
      "epoch": 0.00624,
      "grad_norm": 2.731213092803955,
      "learning_rate": 0.00014234334542574906,
      "loss": 1.504532814025879,
      "step": 78
    },
    {
      "epoch": 0.00632,
      "grad_norm": 2.8738863468170166,
      "learning_rate": 0.00014087081935735564,
      "loss": 1.8904380798339844,
      "step": 79
    },
    {
      "epoch": 0.0064,
      "grad_norm": 3.4613351821899414,
      "learning_rate": 0.00013938757562492873,
      "loss": 2.320128917694092,
      "step": 80
    },
    {
      "epoch": 0.00648,
      "grad_norm": 2.597461462020874,
      "learning_rate": 0.00013789400318343068,
      "loss": 0.9850823879241943,
      "step": 81
    },
    {
      "epoch": 0.00656,
      "grad_norm": 4.481573104858398,
      "learning_rate": 0.00013639049369634876,
      "loss": 1.219327688217163,
      "step": 82
    },
    {
      "epoch": 0.00664,
      "grad_norm": 5.184344291687012,
      "learning_rate": 0.00013487744143298822,
      "loss": 2.01560640335083,
      "step": 83
    },
    {
      "epoch": 0.00672,
      "grad_norm": 3.655848979949951,
      "learning_rate": 0.00013335524316508208,
      "loss": 1.3672316074371338,
      "step": 84
    },
    {
      "epoch": 0.0068,
      "grad_norm": 2.1263749599456787,
      "learning_rate": 0.0001318242980627444,
      "loss": 0.8222290277481079,
      "step": 85
    },
    {
      "epoch": 0.00688,
      "grad_norm": 2.7781271934509277,
      "learning_rate": 0.00013028500758979506,
      "loss": 1.3532121181488037,
      "step": 86
    },
    {
      "epoch": 0.00696,
      "grad_norm": 3.8022267818450928,
      "learning_rate": 0.00012873777539848283,
      "loss": 1.483093023300171,
      "step": 87
    },
    {
      "epoch": 0.00704,
      "grad_norm": 4.301313400268555,
      "learning_rate": 0.0001271830072236343,
      "loss": 2.149625778198242,
      "step": 88
    },
    {
      "epoch": 0.00712,
      "grad_norm": 1.896973729133606,
      "learning_rate": 0.00012562111077625722,
      "loss": 1.3007004261016846,
      "step": 89
    },
    {
      "epoch": 0.0072,
      "grad_norm": 3.8339455127716064,
      "learning_rate": 0.00012405249563662537,
      "loss": 2.0180318355560303,
      "step": 90
    },
    {
      "epoch": 0.00728,
      "grad_norm": 2.7834441661834717,
      "learning_rate": 0.00012247757314687297,
      "loss": 0.9584566354751587,
      "step": 91
    },
    {
      "epoch": 0.00736,
      "grad_norm": 4.279788017272949,
      "learning_rate": 0.00012089675630312754,
      "loss": 2.384021759033203,
      "step": 92
    },
    {
      "epoch": 0.00744,
      "grad_norm": 2.1873183250427246,
      "learning_rate": 0.00011931045964720881,
      "loss": 1.5363960266113281,
      "step": 93
    },
    {
      "epoch": 0.00752,
      "grad_norm": 2.2680325508117676,
      "learning_rate": 0.0001177190991579223,
      "loss": 1.9146153926849365,
      "step": 94
    },
    {
      "epoch": 0.0076,
      "grad_norm": 6.569868564605713,
      "learning_rate": 0.00011612309214197599,
      "loss": 3.304594039916992,
      "step": 95
    },
    {
      "epoch": 0.00768,
      "grad_norm": 2.8254189491271973,
      "learning_rate": 0.00011452285712454904,
      "loss": 1.9783649444580078,
      "step": 96
    },
    {
      "epoch": 0.00776,
      "grad_norm": 2.8782193660736084,
      "learning_rate": 0.00011291881373954065,
      "loss": 1.1415950059890747,
      "step": 97
    },
    {
      "epoch": 0.00784,
      "grad_norm": 4.276658058166504,
      "learning_rate": 0.00011131138261952845,
      "loss": 1.7967627048492432,
      "step": 98
    },
    {
      "epoch": 0.00792,
      "grad_norm": 1.8674637079238892,
      "learning_rate": 0.00010970098528546481,
      "loss": 1.3417999744415283,
      "step": 99
    },
    {
      "epoch": 0.008,
      "grad_norm": 2.835909366607666,
      "learning_rate": 0.00010808804403614043,
      "loss": 2.7765414714813232,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 612887561183232.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}