{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04189359028068706,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00041893590280687055,
      "grad_norm": 8.333969116210938,
      "learning_rate": 2e-05,
      "loss": 3.3261,
      "step": 1
    },
    {
      "epoch": 0.0008378718056137411,
      "grad_norm": 7.348582744598389,
      "learning_rate": 1.9998324256388776e-05,
      "loss": 3.2312,
      "step": 2
    },
    {
      "epoch": 0.0012568077084206116,
      "grad_norm": 3.1899449825286865,
      "learning_rate": 1.9996648512777547e-05,
      "loss": 2.9318,
      "step": 3
    },
    {
      "epoch": 0.0016757436112274822,
      "grad_norm": 2.177359104156494,
      "learning_rate": 1.9994972769166317e-05,
      "loss": 2.8876,
      "step": 4
    },
    {
      "epoch": 0.0020946795140343527,
      "grad_norm": 2.1708009243011475,
      "learning_rate": 1.999329702555509e-05,
      "loss": 3.068,
      "step": 5
    },
    {
      "epoch": 0.0025136154168412233,
      "grad_norm": 1.77362060546875,
      "learning_rate": 1.9991621281943865e-05,
      "loss": 2.6598,
      "step": 6
    },
    {
      "epoch": 0.002932551319648094,
      "grad_norm": 1.709831714630127,
      "learning_rate": 1.9989945538332636e-05,
      "loss": 2.767,
      "step": 7
    },
    {
      "epoch": 0.0033514872224549644,
      "grad_norm": 1.5493128299713135,
      "learning_rate": 1.998826979472141e-05,
      "loss": 2.7182,
      "step": 8
    },
    {
      "epoch": 0.003770423125261835,
      "grad_norm": 1.39557945728302,
      "learning_rate": 1.998659405111018e-05,
      "loss": 2.8695,
      "step": 9
    },
    {
      "epoch": 0.0041893590280687055,
      "grad_norm": 1.1357755661010742,
      "learning_rate": 1.9984918307498955e-05,
      "loss": 2.5497,
      "step": 10
    },
    {
      "epoch": 0.004608294930875576,
      "grad_norm": 1.0683544874191284,
      "learning_rate": 1.9983242563887726e-05,
      "loss": 2.7363,
      "step": 11
    },
    {
      "epoch": 0.005027230833682447,
      "grad_norm": 0.9199109673500061,
      "learning_rate": 1.99815668202765e-05,
      "loss": 2.4438,
      "step": 12
    },
    {
      "epoch": 0.005446166736489317,
      "grad_norm": 0.9708887338638306,
      "learning_rate": 1.997989107666527e-05,
      "loss": 2.6098,
      "step": 13
    },
    {
      "epoch": 0.005865102639296188,
      "grad_norm": 0.9026995301246643,
      "learning_rate": 1.9978215333054045e-05,
      "loss": 2.4444,
      "step": 14
    },
    {
      "epoch": 0.006284038542103058,
      "grad_norm": 1.2418183088302612,
      "learning_rate": 1.9976539589442816e-05,
      "loss": 2.5436,
      "step": 15
    },
    {
      "epoch": 0.006702974444909929,
      "grad_norm": 0.8761052489280701,
      "learning_rate": 1.997486384583159e-05,
      "loss": 2.3926,
      "step": 16
    },
    {
      "epoch": 0.007121910347716799,
      "grad_norm": 0.8849633932113647,
      "learning_rate": 1.997318810222036e-05,
      "loss": 2.5935,
      "step": 17
    },
    {
      "epoch": 0.00754084625052367,
      "grad_norm": 0.8368175029754639,
      "learning_rate": 1.9971512358609135e-05,
      "loss": 2.4684,
      "step": 18
    },
    {
      "epoch": 0.007959782153330541,
      "grad_norm": 0.697807788848877,
      "learning_rate": 1.9969836614997905e-05,
      "loss": 2.3537,
      "step": 19
    },
    {
      "epoch": 0.008378718056137411,
      "grad_norm": 0.7476556301116943,
      "learning_rate": 1.996816087138668e-05,
      "loss": 2.4659,
      "step": 20
    },
    {
      "epoch": 0.008797653958944282,
      "grad_norm": 0.7885666489601135,
      "learning_rate": 1.9966485127775454e-05,
      "loss": 2.4466,
      "step": 21
    },
    {
      "epoch": 0.009216589861751152,
      "grad_norm": 0.7271686792373657,
      "learning_rate": 1.9964809384164224e-05,
      "loss": 2.3659,
      "step": 22
    },
    {
      "epoch": 0.009635525764558023,
      "grad_norm": 0.7286465764045715,
      "learning_rate": 1.9963133640552995e-05,
      "loss": 2.4473,
      "step": 23
    },
    {
      "epoch": 0.010054461667364893,
      "grad_norm": 0.8572853207588196,
      "learning_rate": 1.996145789694177e-05,
      "loss": 2.3595,
      "step": 24
    },
    {
      "epoch": 0.010473397570171765,
      "grad_norm": 0.8283334374427795,
      "learning_rate": 1.9959782153330543e-05,
      "loss": 2.5291,
      "step": 25
    },
    {
      "epoch": 0.010892333472978634,
      "grad_norm": 0.6586313843727112,
      "learning_rate": 1.9958106409719314e-05,
      "loss": 2.3985,
      "step": 26
    },
    {
      "epoch": 0.011311269375785506,
      "grad_norm": 0.6430657505989075,
      "learning_rate": 1.9956430666108085e-05,
      "loss": 2.3578,
      "step": 27
    },
    {
      "epoch": 0.011730205278592375,
      "grad_norm": 0.6550448536872864,
      "learning_rate": 1.995475492249686e-05,
      "loss": 2.4077,
      "step": 28
    },
    {
      "epoch": 0.012149141181399247,
      "grad_norm": 0.7592840194702148,
      "learning_rate": 1.9953079178885633e-05,
      "loss": 2.5008,
      "step": 29
    },
    {
      "epoch": 0.012568077084206116,
      "grad_norm": 0.7858672738075256,
      "learning_rate": 1.9951403435274407e-05,
      "loss": 2.4674,
      "step": 30
    },
    {
      "epoch": 0.012987012987012988,
      "grad_norm": 0.6130352020263672,
      "learning_rate": 1.9949727691663178e-05,
      "loss": 2.3526,
      "step": 31
    },
    {
      "epoch": 0.013405948889819858,
      "grad_norm": 0.6684207320213318,
      "learning_rate": 1.994805194805195e-05,
      "loss": 2.3732,
      "step": 32
    },
    {
      "epoch": 0.013824884792626729,
      "grad_norm": 0.8275600671768188,
      "learning_rate": 1.9946376204440723e-05,
      "loss": 2.135,
      "step": 33
    },
    {
      "epoch": 0.014243820695433599,
      "grad_norm": 0.5858725309371948,
      "learning_rate": 1.9944700460829494e-05,
      "loss": 2.1368,
      "step": 34
    },
    {
      "epoch": 0.01466275659824047,
      "grad_norm": 0.7133444547653198,
      "learning_rate": 1.9943024717218268e-05,
      "loss": 2.304,
      "step": 35
    },
    {
      "epoch": 0.01508169250104734,
      "grad_norm": 0.5466803312301636,
      "learning_rate": 1.994134897360704e-05,
      "loss": 2.1682,
      "step": 36
    },
    {
      "epoch": 0.015500628403854211,
      "grad_norm": 0.5196086168289185,
      "learning_rate": 1.9939673229995813e-05,
      "loss": 2.1546,
      "step": 37
    },
    {
      "epoch": 0.015919564306661083,
      "grad_norm": 0.5088497400283813,
      "learning_rate": 1.9937997486384583e-05,
      "loss": 2.1018,
      "step": 38
    },
    {
      "epoch": 0.016338500209467952,
      "grad_norm": 0.6117899417877197,
      "learning_rate": 1.9936321742773358e-05,
      "loss": 2.2346,
      "step": 39
    },
    {
      "epoch": 0.016757436112274822,
      "grad_norm": 0.5710458159446716,
      "learning_rate": 1.993464599916213e-05,
      "loss": 2.2147,
      "step": 40
    },
    {
      "epoch": 0.01717637201508169,
      "grad_norm": 0.5152861475944519,
      "learning_rate": 1.9932970255550902e-05,
      "loss": 2.2716,
      "step": 41
    },
    {
      "epoch": 0.017595307917888565,
      "grad_norm": 0.6851192712783813,
      "learning_rate": 1.9931294511939673e-05,
      "loss": 2.3158,
      "step": 42
    },
    {
      "epoch": 0.018014243820695434,
      "grad_norm": 0.5485531687736511,
      "learning_rate": 1.9929618768328447e-05,
      "loss": 2.2679,
      "step": 43
    },
    {
      "epoch": 0.018433179723502304,
      "grad_norm": 0.48592010140419006,
      "learning_rate": 1.992794302471722e-05,
      "loss": 2.1303,
      "step": 44
    },
    {
      "epoch": 0.018852115626309174,
      "grad_norm": 0.5533665418624878,
      "learning_rate": 1.9926267281105992e-05,
      "loss": 2.1981,
      "step": 45
    },
    {
      "epoch": 0.019271051529116047,
      "grad_norm": 0.5932656526565552,
      "learning_rate": 1.9924591537494763e-05,
      "loss": 2.3737,
      "step": 46
    },
    {
      "epoch": 0.019689987431922917,
      "grad_norm": 0.5236673951148987,
      "learning_rate": 1.9922915793883537e-05,
      "loss": 2.2694,
      "step": 47
    },
    {
      "epoch": 0.020108923334729786,
      "grad_norm": 0.5357316732406616,
      "learning_rate": 1.992124005027231e-05,
      "loss": 2.2368,
      "step": 48
    },
    {
      "epoch": 0.020527859237536656,
      "grad_norm": 0.5500349998474121,
      "learning_rate": 1.9919564306661082e-05,
      "loss": 2.213,
      "step": 49
    },
    {
      "epoch": 0.02094679514034353,
      "grad_norm": 0.48040810227394104,
      "learning_rate": 1.9917888563049853e-05,
      "loss": 2.1892,
      "step": 50
    },
    {
      "epoch": 0.0213657310431504,
      "grad_norm": 0.5716186165809631,
      "learning_rate": 1.9916212819438627e-05,
      "loss": 2.2039,
      "step": 51
    },
    {
      "epoch": 0.02178466694595727,
      "grad_norm": 0.5564374923706055,
      "learning_rate": 1.99145370758274e-05,
      "loss": 2.1411,
      "step": 52
    },
    {
      "epoch": 0.022203602848764138,
      "grad_norm": 0.4996980130672455,
      "learning_rate": 1.9912861332216175e-05,
      "loss": 2.1521,
      "step": 53
    },
    {
      "epoch": 0.02262253875157101,
      "grad_norm": 0.5239240527153015,
      "learning_rate": 1.9911185588604946e-05,
      "loss": 2.0742,
      "step": 54
    },
    {
      "epoch": 0.02304147465437788,
      "grad_norm": 0.4403076767921448,
      "learning_rate": 1.9909509844993716e-05,
      "loss": 1.9841,
      "step": 55
    },
    {
      "epoch": 0.02346041055718475,
      "grad_norm": 0.5169032216072083,
      "learning_rate": 1.990783410138249e-05,
      "loss": 2.0327,
      "step": 56
    },
    {
      "epoch": 0.02387934645999162,
      "grad_norm": 0.4901898503303528,
      "learning_rate": 1.9906158357771265e-05,
      "loss": 2.0063,
      "step": 57
    },
    {
      "epoch": 0.024298282362798494,
      "grad_norm": 0.6581910252571106,
      "learning_rate": 1.9904482614160035e-05,
      "loss": 2.1385,
      "step": 58
    },
    {
      "epoch": 0.024717218265605363,
      "grad_norm": 0.4522070586681366,
      "learning_rate": 1.9902806870548806e-05,
      "loss": 1.9944,
      "step": 59
    },
    {
      "epoch": 0.025136154168412233,
      "grad_norm": 0.5315820574760437,
      "learning_rate": 1.990113112693758e-05,
      "loss": 2.1579,
      "step": 60
    },
    {
      "epoch": 0.025555090071219103,
      "grad_norm": 0.4661259353160858,
      "learning_rate": 1.9899455383326354e-05,
      "loss": 2.1193,
      "step": 61
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 0.4940222203731537,
      "learning_rate": 1.9897779639715125e-05,
      "loss": 2.0844,
      "step": 62
    },
    {
      "epoch": 0.026392961876832845,
      "grad_norm": 0.46520665287971497,
      "learning_rate": 1.98961038961039e-05,
      "loss": 1.9306,
      "step": 63
    },
    {
      "epoch": 0.026811897779639715,
      "grad_norm": 0.5645989179611206,
      "learning_rate": 1.989442815249267e-05,
      "loss": 2.1236,
      "step": 64
    },
    {
      "epoch": 0.027230833682446585,
      "grad_norm": 0.47880157828330994,
      "learning_rate": 1.989275240888144e-05,
      "loss": 2.0206,
      "step": 65
    },
    {
      "epoch": 0.027649769585253458,
      "grad_norm": 0.6371349692344666,
      "learning_rate": 1.9891076665270215e-05,
      "loss": 2.019,
      "step": 66
    },
    {
      "epoch": 0.028068705488060328,
      "grad_norm": 0.5742272734642029,
      "learning_rate": 1.988940092165899e-05,
      "loss": 2.0899,
      "step": 67
    },
    {
      "epoch": 0.028487641390867197,
      "grad_norm": 0.5579768419265747,
      "learning_rate": 1.988772517804776e-05,
      "loss": 2.081,
      "step": 68
    },
    {
      "epoch": 0.028906577293674067,
      "grad_norm": 0.5897182822227478,
      "learning_rate": 1.988604943443653e-05,
      "loss": 1.9601,
      "step": 69
    },
    {
      "epoch": 0.02932551319648094,
      "grad_norm": 0.46881428360939026,
      "learning_rate": 1.9884373690825305e-05,
      "loss": 1.9085,
      "step": 70
    },
    {
      "epoch": 0.02974444909928781,
      "grad_norm": 0.6095844507217407,
      "learning_rate": 1.988269794721408e-05,
      "loss": 1.9762,
      "step": 71
    },
    {
      "epoch": 0.03016338500209468,
      "grad_norm": 0.599513053894043,
      "learning_rate": 1.988102220360285e-05,
      "loss": 1.8723,
      "step": 72
    },
    {
      "epoch": 0.03058232090490155,
      "grad_norm": 0.585457980632782,
      "learning_rate": 1.987934645999162e-05,
      "loss": 1.9209,
      "step": 73
    },
    {
      "epoch": 0.031001256807708422,
      "grad_norm": 0.42224225401878357,
      "learning_rate": 1.9877670716380394e-05,
      "loss": 1.9186,
      "step": 74
    },
    {
      "epoch": 0.03142019271051529,
      "grad_norm": 0.4566991329193115,
      "learning_rate": 1.987599497276917e-05,
      "loss": 2.018,
      "step": 75
    },
    {
      "epoch": 0.031839128613322165,
      "grad_norm": 0.47718995809555054,
      "learning_rate": 1.9874319229157943e-05,
      "loss": 2.0119,
      "step": 76
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.4412285089492798,
      "learning_rate": 1.9872643485546713e-05,
      "loss": 1.9211,
      "step": 77
    },
    {
      "epoch": 0.032677000418935905,
      "grad_norm": 0.4711454212665558,
      "learning_rate": 1.9870967741935484e-05,
      "loss": 1.9051,
      "step": 78
    },
    {
      "epoch": 0.03309593632174277,
      "grad_norm": 0.4665948450565338,
      "learning_rate": 1.9869291998324258e-05,
      "loss": 1.9571,
      "step": 79
    },
    {
      "epoch": 0.033514872224549644,
      "grad_norm": 0.46011775732040405,
      "learning_rate": 1.9867616254713032e-05,
      "loss": 1.9599,
      "step": 80
    },
    {
      "epoch": 0.03393380812735652,
      "grad_norm": 0.46272069215774536,
      "learning_rate": 1.9865940511101803e-05,
      "loss": 1.9161,
      "step": 81
    },
    {
      "epoch": 0.03435274403016338,
      "grad_norm": 0.5554195046424866,
      "learning_rate": 1.9864264767490574e-05,
      "loss": 2.0202,
      "step": 82
    },
    {
      "epoch": 0.034771679932970256,
      "grad_norm": 0.5324104428291321,
      "learning_rate": 1.9862589023879348e-05,
      "loss": 1.9356,
      "step": 83
    },
    {
      "epoch": 0.03519061583577713,
      "grad_norm": 0.5279750823974609,
      "learning_rate": 1.9860913280268122e-05,
      "loss": 1.9511,
      "step": 84
    },
    {
      "epoch": 0.035609551738583996,
      "grad_norm": 0.5002080202102661,
      "learning_rate": 1.9859237536656893e-05,
      "loss": 1.9248,
      "step": 85
    },
    {
      "epoch": 0.03602848764139087,
      "grad_norm": 0.5625497102737427,
      "learning_rate": 1.9857561793045667e-05,
      "loss": 2.0023,
      "step": 86
    },
    {
      "epoch": 0.036447423544197735,
      "grad_norm": 0.6030247807502747,
      "learning_rate": 1.9855886049434438e-05,
      "loss": 1.893,
      "step": 87
    },
    {
      "epoch": 0.03686635944700461,
      "grad_norm": 0.4760509729385376,
      "learning_rate": 1.9854210305823212e-05,
      "loss": 1.8902,
      "step": 88
    },
    {
      "epoch": 0.03728529534981148,
      "grad_norm": 0.6618624925613403,
      "learning_rate": 1.9852534562211983e-05,
      "loss": 1.9173,
      "step": 89
    },
    {
      "epoch": 0.03770423125261835,
      "grad_norm": 0.47204822301864624,
      "learning_rate": 1.9850858818600757e-05,
      "loss": 1.9266,
      "step": 90
    },
    {
      "epoch": 0.03812316715542522,
      "grad_norm": 0.5421533584594727,
      "learning_rate": 1.9849183074989527e-05,
      "loss": 1.9796,
      "step": 91
    },
    {
      "epoch": 0.038542103058232094,
      "grad_norm": 0.48972201347351074,
      "learning_rate": 1.98475073313783e-05,
      "loss": 1.91,
      "step": 92
    },
    {
      "epoch": 0.03896103896103896,
      "grad_norm": 0.5566658973693848,
      "learning_rate": 1.9845831587767072e-05,
      "loss": 1.8992,
      "step": 93
    },
    {
      "epoch": 0.03937997486384583,
      "grad_norm": 0.4685937464237213,
      "learning_rate": 1.9844155844155846e-05,
      "loss": 1.9231,
      "step": 94
    },
    {
      "epoch": 0.0397989107666527,
      "grad_norm": 0.6744531393051147,
      "learning_rate": 1.9842480100544617e-05,
      "loss": 1.9109,
      "step": 95
    },
    {
      "epoch": 0.04021784666945957,
      "grad_norm": 0.6984325051307678,
      "learning_rate": 1.984080435693339e-05,
      "loss": 1.9566,
      "step": 96
    },
    {
      "epoch": 0.040636782572266446,
      "grad_norm": 0.6627328991889954,
      "learning_rate": 1.9839128613322162e-05,
      "loss": 1.9933,
      "step": 97
    },
    {
      "epoch": 0.04105571847507331,
      "grad_norm": 0.4586343765258789,
      "learning_rate": 1.9837452869710936e-05,
      "loss": 1.7939,
      "step": 98
    },
    {
      "epoch": 0.041474654377880185,
      "grad_norm": 0.6211162805557251,
      "learning_rate": 1.983577712609971e-05,
      "loss": 1.9164,
      "step": 99
    },
    {
      "epoch": 0.04189359028068706,
      "grad_norm": 0.9397639632225037,
      "learning_rate": 1.983410138248848e-05,
      "loss": 2.0262,
      "step": 100
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 11935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.051799292837888e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}