{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08445945945945946,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008445945945945946,
      "grad_norm": 7.727255344390869,
      "learning_rate": 2e-05,
      "loss": 8.372,
      "step": 1
    },
    {
      "epoch": 0.0008445945945945946,
      "eval_loss": 8.063016891479492,
      "eval_runtime": 125.6054,
      "eval_samples_per_second": 3.973,
      "eval_steps_per_second": 1.99,
      "step": 1
    },
    {
      "epoch": 0.0016891891891891893,
      "grad_norm": 9.669200897216797,
      "learning_rate": 4e-05,
      "loss": 8.046,
      "step": 2
    },
    {
      "epoch": 0.002533783783783784,
      "grad_norm": 9.18079948425293,
      "learning_rate": 6e-05,
      "loss": 8.0321,
      "step": 3
    },
    {
      "epoch": 0.0033783783783783786,
      "grad_norm": 9.363329887390137,
      "learning_rate": 8e-05,
      "loss": 7.0182,
      "step": 4
    },
    {
      "epoch": 0.004222972972972973,
      "grad_norm": 9.816231727600098,
      "learning_rate": 0.0001,
      "loss": 7.7225,
      "step": 5
    },
    {
      "epoch": 0.005067567567567568,
      "grad_norm": 9.099088668823242,
      "learning_rate": 0.00012,
      "loss": 7.875,
      "step": 6
    },
    {
      "epoch": 0.0059121621621621625,
      "grad_norm": 9.296707153320312,
      "learning_rate": 0.00014,
      "loss": 5.6422,
      "step": 7
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 9.570911407470703,
      "learning_rate": 0.00016,
      "loss": 3.8105,
      "step": 8
    },
    {
      "epoch": 0.007601351351351352,
      "grad_norm": 8.131881713867188,
      "learning_rate": 0.00018,
      "loss": 2.0885,
      "step": 9
    },
    {
      "epoch": 0.008445945945945946,
      "grad_norm": 5.208433628082275,
      "learning_rate": 0.0002,
      "loss": 1.0562,
      "step": 10
    },
    {
      "epoch": 0.009290540540540541,
      "grad_norm": 10.91145133972168,
      "learning_rate": 0.0001999390827019096,
      "loss": 2.9782,
      "step": 11
    },
    {
      "epoch": 0.010135135135135136,
      "grad_norm": 17.846271514892578,
      "learning_rate": 0.00019975640502598244,
      "loss": 3.6074,
      "step": 12
    },
    {
      "epoch": 0.01097972972972973,
      "grad_norm": 8.735333442687988,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.805,
      "step": 13
    },
    {
      "epoch": 0.011824324324324325,
      "grad_norm": 6.351312637329102,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.1463,
      "step": 14
    },
    {
      "epoch": 0.01266891891891892,
      "grad_norm": 2.7280004024505615,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.2077,
      "step": 15
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 5.975780487060547,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.1476,
      "step": 16
    },
    {
      "epoch": 0.014358108108108109,
      "grad_norm": 5.841843605041504,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.0156,
      "step": 17
    },
    {
      "epoch": 0.015202702702702704,
      "grad_norm": 6.997043132781982,
      "learning_rate": 0.0001961261695938319,
      "loss": 0.6625,
      "step": 18
    },
    {
      "epoch": 0.016047297297297296,
      "grad_norm": 7.254495620727539,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.8055,
      "step": 19
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 5.706070423126221,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.3771,
      "step": 20
    },
    {
      "epoch": 0.017736486486486486,
      "grad_norm": 3.621236801147461,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.2341,
      "step": 21
    },
    {
      "epoch": 0.018581081081081082,
      "grad_norm": 1.3116642236709595,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0388,
      "step": 22
    },
    {
      "epoch": 0.019425675675675675,
      "grad_norm": 6.483520030975342,
      "learning_rate": 0.0001898794046299167,
      "loss": 0.7181,
      "step": 23
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 16.79340171813965,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.0507,
      "step": 24
    },
    {
      "epoch": 0.021114864864864864,
      "grad_norm": 3.9302544593811035,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8626,
      "step": 25
    },
    {
      "epoch": 0.021114864864864864,
      "eval_loss": 0.4980570375919342,
      "eval_runtime": 126.9443,
      "eval_samples_per_second": 3.931,
      "eval_steps_per_second": 1.969,
      "step": 25
    },
    {
      "epoch": 0.02195945945945946,
      "grad_norm": 3.3856303691864014,
      "learning_rate": 0.0001848048096156426,
      "loss": 0.3799,
      "step": 26
    },
    {
      "epoch": 0.022804054054054054,
      "grad_norm": 4.26168966293335,
      "learning_rate": 0.00018290375725550417,
      "loss": 0.5836,
      "step": 27
    },
    {
      "epoch": 0.02364864864864865,
      "grad_norm": 4.655025959014893,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6228,
      "step": 28
    },
    {
      "epoch": 0.024493243243243243,
      "grad_norm": 5.267085075378418,
      "learning_rate": 0.00017880107536067218,
      "loss": 0.354,
      "step": 29
    },
    {
      "epoch": 0.02533783783783784,
      "grad_norm": 3.4175171852111816,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.3025,
      "step": 30
    },
    {
      "epoch": 0.026182432432432432,
      "grad_norm": 3.4233884811401367,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.3893,
      "step": 31
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 0.795799195766449,
      "learning_rate": 0.0001719339800338651,
      "loss": 0.0842,
      "step": 32
    },
    {
      "epoch": 0.02787162162162162,
      "grad_norm": 2.771843671798706,
      "learning_rate": 0.00016946583704589973,
      "loss": 0.5852,
      "step": 33
    },
    {
      "epoch": 0.028716216216216218,
      "grad_norm": 2.5016746520996094,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.467,
      "step": 34
    },
    {
      "epoch": 0.02956081081081081,
      "grad_norm": 3.512495994567871,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.1078,
      "step": 35
    },
    {
      "epoch": 0.030405405405405407,
      "grad_norm": 2.59957218170166,
      "learning_rate": 0.0001615661475325658,
      "loss": 0.2617,
      "step": 36
    },
    {
      "epoch": 0.03125,
      "grad_norm": 1.0484542846679688,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0766,
      "step": 37
    },
    {
      "epoch": 0.03209459459459459,
      "grad_norm": 12.746214866638184,
      "learning_rate": 0.0001559192903470747,
      "loss": 0.3286,
      "step": 38
    },
    {
      "epoch": 0.032939189189189186,
      "grad_norm": 0.457368403673172,
      "learning_rate": 0.0001529919264233205,
      "loss": 0.0239,
      "step": 39
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 4.603786945343018,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.2592,
      "step": 40
    },
    {
      "epoch": 0.03462837837837838,
      "grad_norm": 4.357280731201172,
      "learning_rate": 0.00014694715627858908,
      "loss": 0.3277,
      "step": 41
    },
    {
      "epoch": 0.03547297297297297,
      "grad_norm": 5.606065273284912,
      "learning_rate": 0.00014383711467890774,
      "loss": 0.9881,
      "step": 42
    },
    {
      "epoch": 0.036317567567567564,
      "grad_norm": 0.958200216293335,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.0339,
      "step": 43
    },
    {
      "epoch": 0.037162162162162164,
      "grad_norm": 0.9110239744186401,
      "learning_rate": 0.00013746065934159123,
      "loss": 0.0388,
      "step": 44
    },
    {
      "epoch": 0.03800675675675676,
      "grad_norm": 10.007410049438477,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.1342,
      "step": 45
    },
    {
      "epoch": 0.03885135135135135,
      "grad_norm": 3.0555267333984375,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.1913,
      "step": 46
    },
    {
      "epoch": 0.03969594594594594,
      "grad_norm": 4.296360969543457,
      "learning_rate": 0.0001275637355816999,
      "loss": 0.2431,
      "step": 47
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 0.9275014400482178,
      "learning_rate": 0.00012419218955996676,
      "loss": 0.0389,
      "step": 48
    },
    {
      "epoch": 0.041385135135135136,
      "grad_norm": 0.2515358626842499,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.0064,
      "step": 49
    },
    {
      "epoch": 0.04222972972972973,
      "grad_norm": 0.12618118524551392,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.0036,
      "step": 50
    },
    {
      "epoch": 0.04222972972972973,
      "eval_loss": 0.24848654866218567,
      "eval_runtime": 127.0152,
      "eval_samples_per_second": 3.929,
      "eval_steps_per_second": 1.968,
      "step": 50
    },
    {
      "epoch": 0.04307432432432432,
      "grad_norm": 5.329013347625732,
      "learning_rate": 0.00011391731009600654,
      "loss": 0.2995,
      "step": 51
    },
    {
      "epoch": 0.04391891891891892,
      "grad_norm": 2.9597175121307373,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.1657,
      "step": 52
    },
    {
      "epoch": 0.044763513513513514,
      "grad_norm": 4.471776485443115,
      "learning_rate": 0.00010697564737441252,
      "loss": 0.2049,
      "step": 53
    },
    {
      "epoch": 0.04560810810810811,
      "grad_norm": 1.612620234489441,
      "learning_rate": 0.00010348994967025012,
      "loss": 0.0311,
      "step": 54
    },
    {
      "epoch": 0.0464527027027027,
      "grad_norm": 8.52501392364502,
      "learning_rate": 0.0001,
      "loss": 0.4772,
      "step": 55
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 11.812604904174805,
      "learning_rate": 9.651005032974994e-05,
      "loss": 0.6968,
      "step": 56
    },
    {
      "epoch": 0.04814189189189189,
      "grad_norm": 3.004138708114624,
      "learning_rate": 9.302435262558747e-05,
      "loss": 0.66,
      "step": 57
    },
    {
      "epoch": 0.048986486486486486,
      "grad_norm": 7.490670204162598,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.5833,
      "step": 58
    },
    {
      "epoch": 0.04983108108108108,
      "grad_norm": 3.6796233654022217,
      "learning_rate": 8.608268990399349e-05,
      "loss": 0.5957,
      "step": 59
    },
    {
      "epoch": 0.05067567567567568,
      "grad_norm": 0.1634790003299713,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.0041,
      "step": 60
    },
    {
      "epoch": 0.05152027027027027,
      "grad_norm": 6.999042510986328,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.4254,
      "step": 61
    },
    {
      "epoch": 0.052364864864864864,
      "grad_norm": 1.4367730617523193,
      "learning_rate": 7.580781044003324e-05,
      "loss": 0.0328,
      "step": 62
    },
    {
      "epoch": 0.05320945945945946,
      "grad_norm": 4.265451908111572,
      "learning_rate": 7.243626441830009e-05,
      "loss": 0.1511,
      "step": 63
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 2.716522693634033,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.2104,
      "step": 64
    },
    {
      "epoch": 0.05489864864864865,
      "grad_norm": 1.9555131196975708,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.1398,
      "step": 65
    },
    {
      "epoch": 0.05574324324324324,
      "grad_norm": 2.594125509262085,
      "learning_rate": 6.25393406584088e-05,
      "loss": 0.2959,
      "step": 66
    },
    {
      "epoch": 0.056587837837837836,
      "grad_norm": 4.196368217468262,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.2828,
      "step": 67
    },
    {
      "epoch": 0.057432432432432436,
      "grad_norm": 7.690390110015869,
      "learning_rate": 5.616288532109225e-05,
      "loss": 0.6751,
      "step": 68
    },
    {
      "epoch": 0.05827702702702703,
      "grad_norm": 5.08601713180542,
      "learning_rate": 5.305284372141095e-05,
      "loss": 0.7061,
      "step": 69
    },
    {
      "epoch": 0.05912162162162162,
      "grad_norm": 0.743725597858429,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0161,
      "step": 70
    },
    {
      "epoch": 0.059966216216216214,
      "grad_norm": 1.1107006072998047,
      "learning_rate": 4.700807357667952e-05,
      "loss": 0.0289,
      "step": 71
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 3.6318747997283936,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 0.2351,
      "step": 72
    },
    {
      "epoch": 0.06165540540540541,
      "grad_norm": 3.365870714187622,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.2887,
      "step": 73
    },
    {
      "epoch": 0.0625,
      "grad_norm": 2.29145884513855,
      "learning_rate": 3.843385246743417e-05,
      "loss": 0.2137,
      "step": 74
    },
    {
      "epoch": 0.0633445945945946,
      "grad_norm": 0.12063544243574142,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.0043,
      "step": 75
    },
    {
      "epoch": 0.0633445945945946,
      "eval_loss": 0.14590471982955933,
      "eval_runtime": 126.9422,
      "eval_samples_per_second": 3.931,
      "eval_steps_per_second": 1.969,
      "step": 75
    },
    {
      "epoch": 0.06418918918918919,
      "grad_norm": 0.20781630277633667,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0065,
      "step": 76
    },
    {
      "epoch": 0.06503378378378379,
      "grad_norm": 0.7386759519577026,
      "learning_rate": 3.053416295410026e-05,
      "loss": 0.0431,
      "step": 77
    },
    {
      "epoch": 0.06587837837837837,
      "grad_norm": 3.0190958976745605,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 0.2471,
      "step": 78
    },
    {
      "epoch": 0.06672297297297297,
      "grad_norm": 4.477311134338379,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.8406,
      "step": 79
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 0.9087244272232056,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.0187,
      "step": 80
    },
    {
      "epoch": 0.06841216216216216,
      "grad_norm": 2.032402276992798,
      "learning_rate": 2.119892463932781e-05,
      "loss": 0.3885,
      "step": 81
    },
    {
      "epoch": 0.06925675675675676,
      "grad_norm": 5.099620819091797,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.1469,
      "step": 82
    },
    {
      "epoch": 0.07010135135135136,
      "grad_norm": 1.4657068252563477,
      "learning_rate": 1.7096242744495837e-05,
      "loss": 0.0909,
      "step": 83
    },
    {
      "epoch": 0.07094594594594594,
      "grad_norm": 0.7036009430885315,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 0.0208,
      "step": 84
    },
    {
      "epoch": 0.07179054054054054,
      "grad_norm": 7.542021751403809,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.0755,
      "step": 85
    },
    {
      "epoch": 0.07263513513513513,
      "grad_norm": 0.7535510063171387,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 0.0495,
      "step": 86
    },
    {
      "epoch": 0.07347972972972973,
      "grad_norm": 2.493562936782837,
      "learning_rate": 1.0120595370083318e-05,
      "loss": 0.2186,
      "step": 87
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 3.849121332168579,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.2773,
      "step": 88
    },
    {
      "epoch": 0.07516891891891891,
      "grad_norm": 4.295147895812988,
      "learning_rate": 7.281614543321269e-06,
      "loss": 0.448,
      "step": 89
    },
    {
      "epoch": 0.07601351351351351,
      "grad_norm": 3.61863112449646,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.329,
      "step": 90
    },
    {
      "epoch": 0.07685810810810811,
      "grad_norm": 5.776922702789307,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.4583,
      "step": 91
    },
    {
      "epoch": 0.0777027027027027,
      "grad_norm": 2.3311469554901123,
      "learning_rate": 3.873830406168111e-06,
      "loss": 0.2086,
      "step": 92
    },
    {
      "epoch": 0.0785472972972973,
      "grad_norm": 0.32096993923187256,
      "learning_rate": 2.970427372400353e-06,
      "loss": 0.0184,
      "step": 93
    },
    {
      "epoch": 0.07939189189189189,
      "grad_norm": 0.9880800843238831,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0559,
      "step": 94
    },
    {
      "epoch": 0.08023648648648649,
      "grad_norm": 5.171363830566406,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.4847,
      "step": 95
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 3.456587314605713,
      "learning_rate": 9.731931258429638e-07,
      "loss": 0.2026,
      "step": 96
    },
    {
      "epoch": 0.08192567567567567,
      "grad_norm": 3.7345874309539795,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.5642,
      "step": 97
    },
    {
      "epoch": 0.08277027027027027,
      "grad_norm": 4.7123541831970215,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 0.4377,
      "step": 98
    },
    {
      "epoch": 0.08361486486486487,
      "grad_norm": 2.566887617111206,
      "learning_rate": 6.09172980904238e-08,
      "loss": 0.2207,
      "step": 99
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 1.7636704444885254,
      "learning_rate": 0.0,
      "loss": 0.0955,
      "step": 100
    },
    {
      "epoch": 0.08445945945945946,
      "eval_loss": 0.14757972955703735,
      "eval_runtime": 126.9347,
      "eval_samples_per_second": 3.931,
      "eval_steps_per_second": 1.97,
      "step": 100
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.32218823376896e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}