{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05116398055768739,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005116398055768739,
      "grad_norm": 1.6488349437713623,
      "learning_rate": 1e-05,
      "loss": 2.1352,
      "step": 1
    },
    {
      "epoch": 0.0005116398055768739,
      "eval_loss": 1.228289008140564,
      "eval_runtime": 274.3879,
      "eval_samples_per_second": 5.999,
      "eval_steps_per_second": 0.751,
      "step": 1
    },
    {
      "epoch": 0.0010232796111537478,
      "grad_norm": 1.8014962673187256,
      "learning_rate": 2e-05,
      "loss": 2.439,
      "step": 2
    },
    {
      "epoch": 0.0015349194167306216,
      "grad_norm": 1.226792573928833,
      "learning_rate": 3e-05,
      "loss": 2.2876,
      "step": 3
    },
    {
      "epoch": 0.0020465592223074956,
      "grad_norm": 1.5848373174667358,
      "learning_rate": 4e-05,
      "loss": 2.1205,
      "step": 4
    },
    {
      "epoch": 0.0025581990278843694,
      "grad_norm": 3.6875414848327637,
      "learning_rate": 5e-05,
      "loss": 2.973,
      "step": 5
    },
    {
      "epoch": 0.0030698388334612432,
      "grad_norm": 1.861879587173462,
      "learning_rate": 6e-05,
      "loss": 2.2063,
      "step": 6
    },
    {
      "epoch": 0.003581478639038117,
      "grad_norm": 2.6092193126678467,
      "learning_rate": 7e-05,
      "loss": 2.5909,
      "step": 7
    },
    {
      "epoch": 0.004093118444614991,
      "grad_norm": 2.884692668914795,
      "learning_rate": 8e-05,
      "loss": 2.3501,
      "step": 8
    },
    {
      "epoch": 0.004604758250191865,
      "grad_norm": 1.9096957445144653,
      "learning_rate": 9e-05,
      "loss": 1.7905,
      "step": 9
    },
    {
      "epoch": 0.004604758250191865,
      "eval_loss": 1.1009039878845215,
      "eval_runtime": 274.3445,
      "eval_samples_per_second": 6.0,
      "eval_steps_per_second": 0.751,
      "step": 9
    },
    {
      "epoch": 0.005116398055768739,
      "grad_norm": 2.686815023422241,
      "learning_rate": 0.0001,
      "loss": 2.0176,
      "step": 10
    },
    {
      "epoch": 0.005628037861345613,
      "grad_norm": 1.8589001893997192,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.8315,
      "step": 11
    },
    {
      "epoch": 0.0061396776669224865,
      "grad_norm": 1.6375495195388794,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.8289,
      "step": 12
    },
    {
      "epoch": 0.00665131747249936,
      "grad_norm": 1.9399513006210327,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.5838,
      "step": 13
    },
    {
      "epoch": 0.007162957278076234,
      "grad_norm": 2.0972728729248047,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.514,
      "step": 14
    },
    {
      "epoch": 0.007674597083653108,
      "grad_norm": 2.4550724029541016,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8727,
      "step": 15
    },
    {
      "epoch": 0.008186236889229983,
      "grad_norm": 2.246565580368042,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.5098,
      "step": 16
    },
    {
      "epoch": 0.008697876694806856,
      "grad_norm": 2.1880674362182617,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.5074,
      "step": 17
    },
    {
      "epoch": 0.00920951650038373,
      "grad_norm": 2.00897216796875,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7004,
      "step": 18
    },
    {
      "epoch": 0.00920951650038373,
      "eval_loss": 0.8399195671081543,
      "eval_runtime": 274.0678,
      "eval_samples_per_second": 6.006,
      "eval_steps_per_second": 0.752,
      "step": 18
    },
    {
      "epoch": 0.009721156305960604,
      "grad_norm": 1.782171368598938,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3817,
      "step": 19
    },
    {
      "epoch": 0.010232796111537478,
      "grad_norm": 1.8624811172485352,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4014,
      "step": 20
    },
    {
      "epoch": 0.010744435917114352,
      "grad_norm": 2.667515516281128,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.771,
      "step": 21
    },
    {
      "epoch": 0.011256075722691225,
      "grad_norm": 2.9106290340423584,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.4126,
      "step": 22
    },
    {
      "epoch": 0.0117677155282681,
      "grad_norm": 2.704364776611328,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.3825,
      "step": 23
    },
    {
      "epoch": 0.012279355333844973,
      "grad_norm": 2.78434419631958,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5669,
      "step": 24
    },
    {
      "epoch": 0.012790995139421847,
      "grad_norm": 2.526869058609009,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.4226,
      "step": 25
    },
    {
      "epoch": 0.01330263494499872,
      "grad_norm": 1.8918830156326294,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3571,
      "step": 26
    },
    {
      "epoch": 0.013814274750575594,
      "grad_norm": 2.5752553939819336,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.2146,
      "step": 27
    },
    {
      "epoch": 0.013814274750575594,
      "eval_loss": 0.7836452126502991,
      "eval_runtime": 274.2003,
      "eval_samples_per_second": 6.003,
      "eval_steps_per_second": 0.751,
      "step": 27
    },
    {
      "epoch": 0.014325914556152468,
      "grad_norm": 2.8034920692443848,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6562,
      "step": 28
    },
    {
      "epoch": 0.014837554361729342,
      "grad_norm": 2.0168240070343018,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.3663,
      "step": 29
    },
    {
      "epoch": 0.015349194167306216,
      "grad_norm": 3.294177770614624,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5281,
      "step": 30
    },
    {
      "epoch": 0.01586083397288309,
      "grad_norm": 2.886345624923706,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.5451,
      "step": 31
    },
    {
      "epoch": 0.016372473778459965,
      "grad_norm": 1.7247331142425537,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0179,
      "step": 32
    },
    {
      "epoch": 0.01688411358403684,
      "grad_norm": 1.886189579963684,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.3923,
      "step": 33
    },
    {
      "epoch": 0.017395753389613713,
      "grad_norm": 2.080334424972534,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.2178,
      "step": 34
    },
    {
      "epoch": 0.017907393195190587,
      "grad_norm": 2.708214282989502,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2374,
      "step": 35
    },
    {
      "epoch": 0.01841903300076746,
      "grad_norm": 2.5027191638946533,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.0007,
      "step": 36
    },
    {
      "epoch": 0.01841903300076746,
      "eval_loss": 0.7541875243186951,
      "eval_runtime": 274.1248,
      "eval_samples_per_second": 6.005,
      "eval_steps_per_second": 0.751,
      "step": 36
    },
    {
      "epoch": 0.018930672806344334,
      "grad_norm": 1.938878059387207,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2976,
      "step": 37
    },
    {
      "epoch": 0.019442312611921208,
      "grad_norm": 2.1836838722229004,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.5049,
      "step": 38
    },
    {
      "epoch": 0.019953952417498082,
      "grad_norm": 2.365196704864502,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2362,
      "step": 39
    },
    {
      "epoch": 0.020465592223074956,
      "grad_norm": 1.9262018203735352,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7173,
      "step": 40
    },
    {
      "epoch": 0.02097723202865183,
      "grad_norm": 2.8925254344940186,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.3671,
      "step": 41
    },
    {
      "epoch": 0.021488871834228703,
      "grad_norm": 1.5692651271820068,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.1358,
      "step": 42
    },
    {
      "epoch": 0.022000511639805577,
      "grad_norm": 2.8360183238983154,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.3804,
      "step": 43
    },
    {
      "epoch": 0.02251215144538245,
      "grad_norm": 1.7869185209274292,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.2711,
      "step": 44
    },
    {
      "epoch": 0.023023791250959325,
      "grad_norm": 2.3221404552459717,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.7126,
      "step": 45
    },
    {
      "epoch": 0.023023791250959325,
      "eval_loss": 0.7342292070388794,
      "eval_runtime": 274.1224,
      "eval_samples_per_second": 6.005,
      "eval_steps_per_second": 0.751,
      "step": 45
    },
    {
      "epoch": 0.0235354310565362,
      "grad_norm": 4.136687278747559,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7686,
      "step": 46
    },
    {
      "epoch": 0.024047070862113072,
      "grad_norm": 2.2173714637756348,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.2285,
      "step": 47
    },
    {
      "epoch": 0.024558710667689946,
      "grad_norm": 2.4053614139556885,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.4621,
      "step": 48
    },
    {
      "epoch": 0.02507035047326682,
      "grad_norm": 2.109034299850464,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.4664,
      "step": 49
    },
    {
      "epoch": 0.025581990278843694,
      "grad_norm": 1.8373016119003296,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.2307,
      "step": 50
    },
    {
      "epoch": 0.026093630084420567,
      "grad_norm": 1.6459299325942993,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.1249,
      "step": 51
    },
    {
      "epoch": 0.02660526988999744,
      "grad_norm": 1.93509042263031,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.4258,
      "step": 52
    },
    {
      "epoch": 0.027116909695574315,
      "grad_norm": 3.230286121368408,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.4488,
      "step": 53
    },
    {
      "epoch": 0.02762854950115119,
      "grad_norm": 1.5479521751403809,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.0165,
      "step": 54
    },
    {
      "epoch": 0.02762854950115119,
      "eval_loss": 0.7164188623428345,
      "eval_runtime": 274.108,
      "eval_samples_per_second": 6.005,
      "eval_steps_per_second": 0.752,
      "step": 54
    },
    {
      "epoch": 0.028140189306728063,
      "grad_norm": 2.426544666290283,
      "learning_rate": 5e-05,
      "loss": 1.5535,
      "step": 55
    },
    {
      "epoch": 0.028651829112304936,
      "grad_norm": 1.6888998746871948,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.2925,
      "step": 56
    },
    {
      "epoch": 0.02916346891788181,
      "grad_norm": 1.6494107246398926,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.0268,
      "step": 57
    },
    {
      "epoch": 0.029675108723458684,
      "grad_norm": 2.0526039600372314,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.3885,
      "step": 58
    },
    {
      "epoch": 0.030186748529035558,
      "grad_norm": 2.0388901233673096,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.418,
      "step": 59
    },
    {
      "epoch": 0.03069838833461243,
      "grad_norm": 2.1916987895965576,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.2828,
      "step": 60
    },
    {
      "epoch": 0.031210028140189305,
      "grad_norm": 2.3835113048553467,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5845,
      "step": 61
    },
    {
      "epoch": 0.03172166794576618,
      "grad_norm": 2.7145097255706787,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.8305,
      "step": 62
    },
    {
      "epoch": 0.03223330775134305,
      "grad_norm": 1.8284953832626343,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.3383,
      "step": 63
    },
    {
      "epoch": 0.03223330775134305,
      "eval_loss": 0.708600640296936,
      "eval_runtime": 274.0602,
      "eval_samples_per_second": 6.006,
      "eval_steps_per_second": 0.752,
      "step": 63
    },
    {
      "epoch": 0.03274494755691993,
      "grad_norm": 2.4546236991882324,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4384,
      "step": 64
    },
    {
      "epoch": 0.0332565873624968,
      "grad_norm": 1.848671317100525,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.3614,
      "step": 65
    },
    {
      "epoch": 0.03376822716807368,
      "grad_norm": 1.7728267908096313,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.3155,
      "step": 66
    },
    {
      "epoch": 0.03427986697365055,
      "grad_norm": 2.5115482807159424,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.5332,
      "step": 67
    },
    {
      "epoch": 0.034791506779227425,
      "grad_norm": 2.179997682571411,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.1482,
      "step": 68
    },
    {
      "epoch": 0.035303146584804296,
      "grad_norm": 2.3714139461517334,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.2697,
      "step": 69
    },
    {
      "epoch": 0.03581478639038117,
      "grad_norm": 2.672269344329834,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6706,
      "step": 70
    },
    {
      "epoch": 0.03632642619595804,
      "grad_norm": 1.9255658388137817,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.1635,
      "step": 71
    },
    {
      "epoch": 0.03683806600153492,
      "grad_norm": 1.1116821765899658,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.8958,
      "step": 72
    },
    {
      "epoch": 0.03683806600153492,
      "eval_loss": 0.7018402814865112,
      "eval_runtime": 274.1606,
      "eval_samples_per_second": 6.004,
      "eval_steps_per_second": 0.751,
      "step": 72
    },
    {
      "epoch": 0.03734970580711179,
      "grad_norm": 1.3924734592437744,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0895,
      "step": 73
    },
    {
      "epoch": 0.03786134561268867,
      "grad_norm": 3.168287992477417,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.6212,
      "step": 74
    },
    {
      "epoch": 0.03837298541826554,
      "grad_norm": 2.118021249771118,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.2363,
      "step": 75
    },
    {
      "epoch": 0.038884625223842416,
      "grad_norm": 2.252734422683716,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.9702,
      "step": 76
    },
    {
      "epoch": 0.039396265029419286,
      "grad_norm": 1.5854482650756836,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.4033,
      "step": 77
    },
    {
      "epoch": 0.039907904834996163,
      "grad_norm": 2.2333011627197266,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.3619,
      "step": 78
    },
    {
      "epoch": 0.040419544640573034,
      "grad_norm": 2.2637572288513184,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.3294,
      "step": 79
    },
    {
      "epoch": 0.04093118444614991,
      "grad_norm": 2.184448003768921,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.3759,
      "step": 80
    },
    {
      "epoch": 0.04144282425172678,
      "grad_norm": 2.1181156635284424,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.4547,
      "step": 81
    },
    {
      "epoch": 0.04144282425172678,
      "eval_loss": 0.6984646916389465,
      "eval_runtime": 274.0143,
      "eval_samples_per_second": 6.007,
      "eval_steps_per_second": 0.752,
      "step": 81
    },
    {
      "epoch": 0.04195446405730366,
      "grad_norm": 2.124769926071167,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.711,
      "step": 82
    },
    {
      "epoch": 0.04246610386288053,
      "grad_norm": 2.768644332885742,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.4417,
      "step": 83
    },
    {
      "epoch": 0.042977743668457406,
      "grad_norm": 1.6614168882369995,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.1462,
      "step": 84
    },
    {
      "epoch": 0.04348938347403428,
      "grad_norm": 1.6592438220977783,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.1821,
      "step": 85
    },
    {
      "epoch": 0.044001023279611154,
      "grad_norm": 2.4975907802581787,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.5,
      "step": 86
    },
    {
      "epoch": 0.044512663085188024,
      "grad_norm": 1.9415825605392456,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.3181,
      "step": 87
    },
    {
      "epoch": 0.0450243028907649,
      "grad_norm": 1.8416827917099,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.1157,
      "step": 88
    },
    {
      "epoch": 0.04553594269634178,
      "grad_norm": 2.9629881381988525,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.6228,
      "step": 89
    },
    {
      "epoch": 0.04604758250191865,
      "grad_norm": 1.538602590560913,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.2217,
      "step": 90
    },
    {
      "epoch": 0.04604758250191865,
      "eval_loss": 0.6968083381652832,
      "eval_runtime": 274.0049,
      "eval_samples_per_second": 6.007,
      "eval_steps_per_second": 0.752,
      "step": 90
    },
    {
      "epoch": 0.046559222307495526,
      "grad_norm": 3.1427130699157715,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.4783,
      "step": 91
    },
    {
      "epoch": 0.0470708621130724,
      "grad_norm": 1.9339940547943115,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.3989,
      "step": 92
    },
    {
      "epoch": 0.047582501918649274,
      "grad_norm": 1.509247899055481,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.277,
      "step": 93
    },
    {
      "epoch": 0.048094141724226144,
      "grad_norm": 2.101160764694214,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.129,
      "step": 94
    },
    {
      "epoch": 0.04860578152980302,
      "grad_norm": 1.8684135675430298,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.397,
      "step": 95
    },
    {
      "epoch": 0.04911742133537989,
      "grad_norm": 2.9883639812469482,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.4069,
      "step": 96
    },
    {
      "epoch": 0.04962906114095677,
      "grad_norm": 2.2074315547943115,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.4236,
      "step": 97
    },
    {
      "epoch": 0.05014070094653364,
      "grad_norm": 2.8094723224639893,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.4329,
      "step": 98
    },
    {
      "epoch": 0.05065234075211052,
      "grad_norm": 1.6626664400100708,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.1333,
      "step": 99
    },
    {
      "epoch": 0.05065234075211052,
      "eval_loss": 0.6963222026824951,
      "eval_runtime": 274.0109,
      "eval_samples_per_second": 6.007,
      "eval_steps_per_second": 0.752,
      "step": 99
    },
    {
      "epoch": 0.05116398055768739,
      "grad_norm": 2.4238545894622803,
      "learning_rate": 0.0,
      "loss": 1.3018,
      "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": 1.313992467283968e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}