{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003283640901031063,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.2836409010310635e-05,
      "grad_norm": 0.039061568677425385,
      "learning_rate": 1e-05,
      "loss": 10.374,
      "step": 1
    },
    {
      "epoch": 3.2836409010310635e-05,
      "eval_loss": 10.37774658203125,
      "eval_runtime": 169.5857,
      "eval_samples_per_second": 151.227,
      "eval_steps_per_second": 18.905,
      "step": 1
    },
    {
      "epoch": 6.567281802062127e-05,
      "grad_norm": 0.04970359802246094,
      "learning_rate": 2e-05,
      "loss": 10.3808,
      "step": 2
    },
    {
      "epoch": 9.85092270309319e-05,
      "grad_norm": 0.051377296447753906,
      "learning_rate": 3e-05,
      "loss": 10.3791,
      "step": 3
    },
    {
      "epoch": 0.00013134563604124254,
      "grad_norm": 0.040986333042383194,
      "learning_rate": 4e-05,
      "loss": 10.3831,
      "step": 4
    },
    {
      "epoch": 0.00016418204505155317,
      "grad_norm": 0.04276856407523155,
      "learning_rate": 5e-05,
      "loss": 10.3766,
      "step": 5
    },
    {
      "epoch": 0.0001970184540618638,
      "grad_norm": 0.03917916491627693,
      "learning_rate": 6e-05,
      "loss": 10.3777,
      "step": 6
    },
    {
      "epoch": 0.00022985486307217442,
      "grad_norm": 0.054591104388237,
      "learning_rate": 7e-05,
      "loss": 10.3798,
      "step": 7
    },
    {
      "epoch": 0.0002626912720824851,
      "grad_norm": 0.04181118682026863,
      "learning_rate": 8e-05,
      "loss": 10.3828,
      "step": 8
    },
    {
      "epoch": 0.0002955276810927957,
      "grad_norm": 0.039910946041345596,
      "learning_rate": 9e-05,
      "loss": 10.3794,
      "step": 9
    },
    {
      "epoch": 0.0002955276810927957,
      "eval_loss": 10.377296447753906,
      "eval_runtime": 170.6195,
      "eval_samples_per_second": 150.311,
      "eval_steps_per_second": 18.79,
      "step": 9
    },
    {
      "epoch": 0.00032836409010310633,
      "grad_norm": 0.057242438197135925,
      "learning_rate": 0.0001,
      "loss": 10.3841,
      "step": 10
    },
    {
      "epoch": 0.00036120049911341694,
      "grad_norm": 0.06191801652312279,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3803,
      "step": 11
    },
    {
      "epoch": 0.0003940369081237276,
      "grad_norm": 0.06025468185544014,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3891,
      "step": 12
    },
    {
      "epoch": 0.00042687331713403825,
      "grad_norm": 0.04083796963095665,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3679,
      "step": 13
    },
    {
      "epoch": 0.00045970972614434885,
      "grad_norm": 0.04752117395401001,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3791,
      "step": 14
    },
    {
      "epoch": 0.0004925461351546594,
      "grad_norm": 0.063045933842659,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.383,
      "step": 15
    },
    {
      "epoch": 0.0005253825441649702,
      "grad_norm": 0.03456421196460724,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3785,
      "step": 16
    },
    {
      "epoch": 0.0005582189531752808,
      "grad_norm": 0.04961790144443512,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3833,
      "step": 17
    },
    {
      "epoch": 0.0005910553621855914,
      "grad_norm": 0.05567217618227005,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3881,
      "step": 18
    },
    {
      "epoch": 0.0005910553621855914,
      "eval_loss": 10.37619400024414,
      "eval_runtime": 170.4028,
      "eval_samples_per_second": 150.502,
      "eval_steps_per_second": 18.814,
      "step": 18
    },
    {
      "epoch": 0.0006238917711959021,
      "grad_norm": 0.038412440568208694,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3748,
      "step": 19
    },
    {
      "epoch": 0.0006567281802062127,
      "grad_norm": 0.04399815946817398,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3757,
      "step": 20
    },
    {
      "epoch": 0.0006895645892165233,
      "grad_norm": 0.03764853626489639,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3762,
      "step": 21
    },
    {
      "epoch": 0.0007224009982268339,
      "grad_norm": 0.052127059549093246,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3771,
      "step": 22
    },
    {
      "epoch": 0.0007552374072371446,
      "grad_norm": 0.03697521612048149,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.374,
      "step": 23
    },
    {
      "epoch": 0.0007880738162474552,
      "grad_norm": 0.04965825751423836,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3714,
      "step": 24
    },
    {
      "epoch": 0.0008209102252577658,
      "grad_norm": 0.038044273853302,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3757,
      "step": 25
    },
    {
      "epoch": 0.0008537466342680765,
      "grad_norm": 0.04307650402188301,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3715,
      "step": 26
    },
    {
      "epoch": 0.0008865830432783871,
      "grad_norm": 0.041188716888427734,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3712,
      "step": 27
    },
    {
      "epoch": 0.0008865830432783871,
      "eval_loss": 10.375112533569336,
      "eval_runtime": 170.1694,
      "eval_samples_per_second": 150.709,
      "eval_steps_per_second": 18.84,
      "step": 27
    },
    {
      "epoch": 0.0009194194522886977,
      "grad_norm": 0.03614542633295059,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3765,
      "step": 28
    },
    {
      "epoch": 0.0009522558612990083,
      "grad_norm": 0.0354689322412014,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3743,
      "step": 29
    },
    {
      "epoch": 0.000985092270309319,
      "grad_norm": 0.0464780293405056,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3809,
      "step": 30
    },
    {
      "epoch": 0.0010179286793196296,
      "grad_norm": 0.05983458459377289,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3758,
      "step": 31
    },
    {
      "epoch": 0.0010507650883299403,
      "grad_norm": 0.04344520345330238,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3735,
      "step": 32
    },
    {
      "epoch": 0.0010836014973402508,
      "grad_norm": 0.041173264384269714,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3722,
      "step": 33
    },
    {
      "epoch": 0.0011164379063505615,
      "grad_norm": 0.041133031249046326,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3769,
      "step": 34
    },
    {
      "epoch": 0.0011492743153608722,
      "grad_norm": 0.06315415352582932,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.378,
      "step": 35
    },
    {
      "epoch": 0.0011821107243711827,
      "grad_norm": 0.04024801030755043,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.373,
      "step": 36
    },
    {
      "epoch": 0.0011821107243711827,
      "eval_loss": 10.374061584472656,
      "eval_runtime": 170.5991,
      "eval_samples_per_second": 150.329,
      "eval_steps_per_second": 18.793,
      "step": 36
    },
    {
      "epoch": 0.0012149471333814934,
      "grad_norm": 0.042859919369220734,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3751,
      "step": 37
    },
    {
      "epoch": 0.0012477835423918041,
      "grad_norm": 0.04361676052212715,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.3766,
      "step": 38
    },
    {
      "epoch": 0.0012806199514021146,
      "grad_norm": 0.053741976618766785,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3753,
      "step": 39
    },
    {
      "epoch": 0.0013134563604124253,
      "grad_norm": 0.0702785924077034,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3751,
      "step": 40
    },
    {
      "epoch": 0.0013462927694227358,
      "grad_norm": 0.06600352376699448,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3788,
      "step": 41
    },
    {
      "epoch": 0.0013791291784330465,
      "grad_norm": 0.037580136209726334,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3778,
      "step": 42
    },
    {
      "epoch": 0.0014119655874433572,
      "grad_norm": 0.05780002847313881,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.375,
      "step": 43
    },
    {
      "epoch": 0.0014448019964536677,
      "grad_norm": 0.04174739867448807,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.3758,
      "step": 44
    },
    {
      "epoch": 0.0014776384054639784,
      "grad_norm": 0.053912002593278885,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3738,
      "step": 45
    },
    {
      "epoch": 0.0014776384054639784,
      "eval_loss": 10.373043060302734,
      "eval_runtime": 170.5618,
      "eval_samples_per_second": 150.362,
      "eval_steps_per_second": 18.797,
      "step": 45
    },
    {
      "epoch": 0.0015104748144742892,
      "grad_norm": 0.044272515922784805,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3758,
      "step": 46
    },
    {
      "epoch": 0.0015433112234845997,
      "grad_norm": 0.04709697142243385,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3749,
      "step": 47
    },
    {
      "epoch": 0.0015761476324949104,
      "grad_norm": 0.04305019602179527,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.364,
      "step": 48
    },
    {
      "epoch": 0.001608984041505221,
      "grad_norm": 0.049739986658096313,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3708,
      "step": 49
    },
    {
      "epoch": 0.0016418204505155316,
      "grad_norm": 0.04268916696310043,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3697,
      "step": 50
    },
    {
      "epoch": 0.0016746568595258423,
      "grad_norm": 0.042693495750427246,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3793,
      "step": 51
    },
    {
      "epoch": 0.001707493268536153,
      "grad_norm": 0.045006535947322845,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.3675,
      "step": 52
    },
    {
      "epoch": 0.0017403296775464635,
      "grad_norm": 0.04501199349761009,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3753,
      "step": 53
    },
    {
      "epoch": 0.0017731660865567742,
      "grad_norm": 0.04330871254205704,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.374,
      "step": 54
    },
    {
      "epoch": 0.0017731660865567742,
      "eval_loss": 10.37214469909668,
      "eval_runtime": 170.1851,
      "eval_samples_per_second": 150.695,
      "eval_steps_per_second": 18.838,
      "step": 54
    },
    {
      "epoch": 0.0018060024955670847,
      "grad_norm": 0.05513521283864975,
      "learning_rate": 5e-05,
      "loss": 10.367,
      "step": 55
    },
    {
      "epoch": 0.0018388389045773954,
      "grad_norm": 0.048482492566108704,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3717,
      "step": 56
    },
    {
      "epoch": 0.001871675313587706,
      "grad_norm": 0.0455101802945137,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3688,
      "step": 57
    },
    {
      "epoch": 0.0019045117225980166,
      "grad_norm": 0.04642629623413086,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3778,
      "step": 58
    },
    {
      "epoch": 0.0019373481316083273,
      "grad_norm": 0.0608275830745697,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3782,
      "step": 59
    },
    {
      "epoch": 0.001970184540618638,
      "grad_norm": 0.049797091633081436,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3706,
      "step": 60
    },
    {
      "epoch": 0.0020030209496289487,
      "grad_norm": 0.0518428236246109,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3705,
      "step": 61
    },
    {
      "epoch": 0.002035857358639259,
      "grad_norm": 0.04151507094502449,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3754,
      "step": 62
    },
    {
      "epoch": 0.0020686937676495697,
      "grad_norm": 0.047984637320041656,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3595,
      "step": 63
    },
    {
      "epoch": 0.0020686937676495697,
      "eval_loss": 10.37141227722168,
      "eval_runtime": 170.6032,
      "eval_samples_per_second": 150.325,
      "eval_steps_per_second": 18.792,
      "step": 63
    },
    {
      "epoch": 0.0021015301766598806,
      "grad_norm": 0.049031127244234085,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3674,
      "step": 64
    },
    {
      "epoch": 0.002134366585670191,
      "grad_norm": 0.051563944667577744,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.376,
      "step": 65
    },
    {
      "epoch": 0.0021672029946805016,
      "grad_norm": 0.04762021079659462,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3799,
      "step": 66
    },
    {
      "epoch": 0.0022000394036908125,
      "grad_norm": 0.06098484992980957,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3745,
      "step": 67
    },
    {
      "epoch": 0.002232875812701123,
      "grad_norm": 0.04760457202792168,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3699,
      "step": 68
    },
    {
      "epoch": 0.0022657122217114335,
      "grad_norm": 0.05251610651612282,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3793,
      "step": 69
    },
    {
      "epoch": 0.0022985486307217444,
      "grad_norm": 0.05606340244412422,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3652,
      "step": 70
    },
    {
      "epoch": 0.002331385039732055,
      "grad_norm": 0.04817664250731468,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.374,
      "step": 71
    },
    {
      "epoch": 0.0023642214487423654,
      "grad_norm": 0.047362156212329865,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3679,
      "step": 72
    },
    {
      "epoch": 0.0023642214487423654,
      "eval_loss": 10.370889663696289,
      "eval_runtime": 170.6022,
      "eval_samples_per_second": 150.326,
      "eval_steps_per_second": 18.792,
      "step": 72
    },
    {
      "epoch": 0.0023970578577526764,
      "grad_norm": 0.05063464865088463,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3752,
      "step": 73
    },
    {
      "epoch": 0.002429894266762987,
      "grad_norm": 0.05633007362484932,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3643,
      "step": 74
    },
    {
      "epoch": 0.0024627306757732973,
      "grad_norm": 0.06308276206254959,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3707,
      "step": 75
    },
    {
      "epoch": 0.0024955670847836083,
      "grad_norm": 0.05032104626297951,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.3751,
      "step": 76
    },
    {
      "epoch": 0.0025284034937939188,
      "grad_norm": 0.06600265204906464,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.3799,
      "step": 77
    },
    {
      "epoch": 0.0025612399028042293,
      "grad_norm": 0.05626071244478226,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3706,
      "step": 78
    },
    {
      "epoch": 0.0025940763118145397,
      "grad_norm": 0.04748469963669777,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.369,
      "step": 79
    },
    {
      "epoch": 0.0026269127208248507,
      "grad_norm": 0.04868736118078232,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3713,
      "step": 80
    },
    {
      "epoch": 0.002659749129835161,
      "grad_norm": 0.04755145311355591,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3695,
      "step": 81
    },
    {
      "epoch": 0.002659749129835161,
      "eval_loss": 10.370580673217773,
      "eval_runtime": 170.173,
      "eval_samples_per_second": 150.705,
      "eval_steps_per_second": 18.84,
      "step": 81
    },
    {
      "epoch": 0.0026925855388454717,
      "grad_norm": 0.04993366450071335,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3709,
      "step": 82
    },
    {
      "epoch": 0.0027254219478557826,
      "grad_norm": 0.047633569687604904,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.3658,
      "step": 83
    },
    {
      "epoch": 0.002758258356866093,
      "grad_norm": 0.049595627933740616,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.3725,
      "step": 84
    },
    {
      "epoch": 0.0027910947658764036,
      "grad_norm": 0.04706868901848793,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3715,
      "step": 85
    },
    {
      "epoch": 0.0028239311748867145,
      "grad_norm": 0.047884490340948105,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.364,
      "step": 86
    },
    {
      "epoch": 0.002856767583897025,
      "grad_norm": 0.04975724220275879,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3678,
      "step": 87
    },
    {
      "epoch": 0.0028896039929073355,
      "grad_norm": 0.052582498639822006,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.3702,
      "step": 88
    },
    {
      "epoch": 0.0029224404019176464,
      "grad_norm": 0.05560288950800896,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.3735,
      "step": 89
    },
    {
      "epoch": 0.002955276810927957,
      "grad_norm": 0.061860982328653336,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3729,
      "step": 90
    },
    {
      "epoch": 0.002955276810927957,
      "eval_loss": 10.370454788208008,
      "eval_runtime": 170.5443,
      "eval_samples_per_second": 150.377,
      "eval_steps_per_second": 18.799,
      "step": 90
    },
    {
      "epoch": 0.0029881132199382674,
      "grad_norm": 0.0577683299779892,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3711,
      "step": 91
    },
    {
      "epoch": 0.0030209496289485783,
      "grad_norm": 0.05124616622924805,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.3703,
      "step": 92
    },
    {
      "epoch": 0.003053786037958889,
      "grad_norm": 0.052736300975084305,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3715,
      "step": 93
    },
    {
      "epoch": 0.0030866224469691993,
      "grad_norm": 0.05762464180588722,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.3688,
      "step": 94
    },
    {
      "epoch": 0.0031194588559795102,
      "grad_norm": 0.0635187178850174,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3695,
      "step": 95
    },
    {
      "epoch": 0.0031522952649898207,
      "grad_norm": 0.05708334967494011,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.366,
      "step": 96
    },
    {
      "epoch": 0.003185131674000131,
      "grad_norm": 0.05262709781527519,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.3671,
      "step": 97
    },
    {
      "epoch": 0.003217968083010442,
      "grad_norm": 0.06074366718530655,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.3769,
      "step": 98
    },
    {
      "epoch": 0.0032508044920207526,
      "grad_norm": 0.04959198087453842,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3706,
      "step": 99
    },
    {
      "epoch": 0.0032508044920207526,
      "eval_loss": 10.370431900024414,
      "eval_runtime": 170.5901,
      "eval_samples_per_second": 150.337,
      "eval_steps_per_second": 18.794,
      "step": 99
    },
    {
      "epoch": 0.003283640901031063,
      "grad_norm": 0.050457920879125595,
      "learning_rate": 0.0,
      "loss": 10.375,
      "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": 5230244659200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}