{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003832078327681018,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.832078327681018e-05,
      "grad_norm": 3.426521062850952,
      "learning_rate": 1e-05,
      "loss": 10.2803,
      "step": 1
    },
    {
      "epoch": 3.832078327681018e-05,
      "eval_loss": 10.226699829101562,
      "eval_runtime": 198.1021,
      "eval_samples_per_second": 110.933,
      "eval_steps_per_second": 13.867,
      "step": 1
    },
    {
      "epoch": 7.664156655362036e-05,
      "grad_norm": 3.3724396228790283,
      "learning_rate": 2e-05,
      "loss": 10.1469,
      "step": 2
    },
    {
      "epoch": 0.00011496234983043054,
      "grad_norm": 3.1231155395507812,
      "learning_rate": 3e-05,
      "loss": 10.3281,
      "step": 3
    },
    {
      "epoch": 0.0001532831331072407,
      "grad_norm": 3.4462990760803223,
      "learning_rate": 4e-05,
      "loss": 10.0777,
      "step": 4
    },
    {
      "epoch": 0.00019160391638405088,
      "grad_norm": 3.0611374378204346,
      "learning_rate": 5e-05,
      "loss": 10.1656,
      "step": 5
    },
    {
      "epoch": 0.00022992469966086107,
      "grad_norm": 3.089136838912964,
      "learning_rate": 6e-05,
      "loss": 10.3253,
      "step": 6
    },
    {
      "epoch": 0.00026824548293767126,
      "grad_norm": 3.1562752723693848,
      "learning_rate": 7e-05,
      "loss": 10.1898,
      "step": 7
    },
    {
      "epoch": 0.0003065662662144814,
      "grad_norm": 3.3566901683807373,
      "learning_rate": 8e-05,
      "loss": 10.2334,
      "step": 8
    },
    {
      "epoch": 0.0003448870494912916,
      "grad_norm": 3.380046844482422,
      "learning_rate": 9e-05,
      "loss": 10.1106,
      "step": 9
    },
    {
      "epoch": 0.0003448870494912916,
      "eval_loss": 10.10090446472168,
      "eval_runtime": 198.2556,
      "eval_samples_per_second": 110.847,
      "eval_steps_per_second": 13.856,
      "step": 9
    },
    {
      "epoch": 0.00038320783276810176,
      "grad_norm": 3.2303075790405273,
      "learning_rate": 0.0001,
      "loss": 10.0097,
      "step": 10
    },
    {
      "epoch": 0.000421528616044912,
      "grad_norm": 2.8799538612365723,
      "learning_rate": 9.99695413509548e-05,
      "loss": 9.9966,
      "step": 11
    },
    {
      "epoch": 0.00045984939932172214,
      "grad_norm": 3.717454433441162,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.1469,
      "step": 12
    },
    {
      "epoch": 0.0004981701825985324,
      "grad_norm": 3.4059760570526123,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.1607,
      "step": 13
    },
    {
      "epoch": 0.0005364909658753425,
      "grad_norm": 3.6317834854125977,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.0034,
      "step": 14
    },
    {
      "epoch": 0.0005748117491521527,
      "grad_norm": 3.2543015480041504,
      "learning_rate": 9.924038765061042e-05,
      "loss": 9.8262,
      "step": 15
    },
    {
      "epoch": 0.0006131325324289629,
      "grad_norm": 3.1305909156799316,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.0142,
      "step": 16
    },
    {
      "epoch": 0.000651453315705773,
      "grad_norm": 2.911153554916382,
      "learning_rate": 9.851478631379982e-05,
      "loss": 9.6862,
      "step": 17
    },
    {
      "epoch": 0.0006897740989825832,
      "grad_norm": 2.923849105834961,
      "learning_rate": 9.806308479691595e-05,
      "loss": 9.6763,
      "step": 18
    },
    {
      "epoch": 0.0006897740989825832,
      "eval_loss": 9.730630874633789,
      "eval_runtime": 197.3292,
      "eval_samples_per_second": 111.367,
      "eval_steps_per_second": 13.921,
      "step": 18
    },
    {
      "epoch": 0.0007280948822593933,
      "grad_norm": 3.134058713912964,
      "learning_rate": 9.755282581475769e-05,
      "loss": 9.7739,
      "step": 19
    },
    {
      "epoch": 0.0007664156655362035,
      "grad_norm": 3.1884331703186035,
      "learning_rate": 9.698463103929542e-05,
      "loss": 9.5725,
      "step": 20
    },
    {
      "epoch": 0.0008047364488130138,
      "grad_norm": 3.215076446533203,
      "learning_rate": 9.635919272833938e-05,
      "loss": 9.8354,
      "step": 21
    },
    {
      "epoch": 0.000843057232089824,
      "grad_norm": 3.2122676372528076,
      "learning_rate": 9.567727288213005e-05,
      "loss": 9.6639,
      "step": 22
    },
    {
      "epoch": 0.0008813780153666341,
      "grad_norm": 3.1786868572235107,
      "learning_rate": 9.493970231495835e-05,
      "loss": 9.5412,
      "step": 23
    },
    {
      "epoch": 0.0009196987986434443,
      "grad_norm": 3.19095516204834,
      "learning_rate": 9.414737964294636e-05,
      "loss": 9.5994,
      "step": 24
    },
    {
      "epoch": 0.0009580195819202544,
      "grad_norm": 3.1054611206054688,
      "learning_rate": 9.330127018922194e-05,
      "loss": 9.5802,
      "step": 25
    },
    {
      "epoch": 0.0009963403651970647,
      "grad_norm": 3.075852155685425,
      "learning_rate": 9.24024048078213e-05,
      "loss": 9.5869,
      "step": 26
    },
    {
      "epoch": 0.0010346611484738748,
      "grad_norm": 3.107454776763916,
      "learning_rate": 9.145187862775209e-05,
      "loss": 9.2758,
      "step": 27
    },
    {
      "epoch": 0.0010346611484738748,
      "eval_loss": 9.356222152709961,
      "eval_runtime": 196.8567,
      "eval_samples_per_second": 111.635,
      "eval_steps_per_second": 13.954,
      "step": 27
    },
    {
      "epoch": 0.001072981931750685,
      "grad_norm": 3.239929437637329,
      "learning_rate": 9.045084971874738e-05,
      "loss": 9.3093,
      "step": 28
    },
    {
      "epoch": 0.001111302715027495,
      "grad_norm": 3.1697399616241455,
      "learning_rate": 8.940053768033609e-05,
      "loss": 9.4413,
      "step": 29
    },
    {
      "epoch": 0.0011496234983043054,
      "grad_norm": 2.983443260192871,
      "learning_rate": 8.83022221559489e-05,
      "loss": 9.2819,
      "step": 30
    },
    {
      "epoch": 0.0011879442815811154,
      "grad_norm": 2.9809553623199463,
      "learning_rate": 8.715724127386972e-05,
      "loss": 9.2256,
      "step": 31
    },
    {
      "epoch": 0.0012262650648579257,
      "grad_norm": 2.92080020904541,
      "learning_rate": 8.596699001693255e-05,
      "loss": 9.0488,
      "step": 32
    },
    {
      "epoch": 0.001264585848134736,
      "grad_norm": 2.7908945083618164,
      "learning_rate": 8.473291852294987e-05,
      "loss": 9.1336,
      "step": 33
    },
    {
      "epoch": 0.001302906631411546,
      "grad_norm": 2.688901662826538,
      "learning_rate": 8.345653031794292e-05,
      "loss": 9.0057,
      "step": 34
    },
    {
      "epoch": 0.0013412274146883563,
      "grad_norm": 2.6229913234710693,
      "learning_rate": 8.213938048432697e-05,
      "loss": 8.8516,
      "step": 35
    },
    {
      "epoch": 0.0013795481979651664,
      "grad_norm": 2.903886556625366,
      "learning_rate": 8.07830737662829e-05,
      "loss": 9.1772,
      "step": 36
    },
    {
      "epoch": 0.0013795481979651664,
      "eval_loss": 9.0332670211792,
      "eval_runtime": 200.6695,
      "eval_samples_per_second": 109.513,
      "eval_steps_per_second": 13.689,
      "step": 36
    },
    {
      "epoch": 0.0014178689812419766,
      "grad_norm": 2.304446220397949,
      "learning_rate": 7.938926261462366e-05,
      "loss": 9.0422,
      "step": 37
    },
    {
      "epoch": 0.0014561897645187867,
      "grad_norm": 2.6148622035980225,
      "learning_rate": 7.795964517353735e-05,
      "loss": 8.9424,
      "step": 38
    },
    {
      "epoch": 0.001494510547795597,
      "grad_norm": 2.5895235538482666,
      "learning_rate": 7.649596321166024e-05,
      "loss": 8.9902,
      "step": 39
    },
    {
      "epoch": 0.001532831331072407,
      "grad_norm": 2.4067177772521973,
      "learning_rate": 7.500000000000001e-05,
      "loss": 8.9559,
      "step": 40
    },
    {
      "epoch": 0.0015711521143492173,
      "grad_norm": 2.6639695167541504,
      "learning_rate": 7.347357813929454e-05,
      "loss": 8.8575,
      "step": 41
    },
    {
      "epoch": 0.0016094728976260276,
      "grad_norm": 2.2785677909851074,
      "learning_rate": 7.191855733945387e-05,
      "loss": 9.0544,
      "step": 42
    },
    {
      "epoch": 0.0016477936809028376,
      "grad_norm": 2.155168294906616,
      "learning_rate": 7.033683215379002e-05,
      "loss": 8.7763,
      "step": 43
    },
    {
      "epoch": 0.001686114464179648,
      "grad_norm": 2.451356887817383,
      "learning_rate": 6.873032967079561e-05,
      "loss": 8.9635,
      "step": 44
    },
    {
      "epoch": 0.001724435247456458,
      "grad_norm": 2.1244118213653564,
      "learning_rate": 6.710100716628344e-05,
      "loss": 8.7786,
      "step": 45
    },
    {
      "epoch": 0.001724435247456458,
      "eval_loss": 8.795065879821777,
      "eval_runtime": 198.6273,
      "eval_samples_per_second": 110.639,
      "eval_steps_per_second": 13.83,
      "step": 45
    },
    {
      "epoch": 0.0017627560307332682,
      "grad_norm": 2.1409757137298584,
      "learning_rate": 6.545084971874738e-05,
      "loss": 8.843,
      "step": 46
    },
    {
      "epoch": 0.0018010768140100783,
      "grad_norm": 2.1220507621765137,
      "learning_rate": 6.378186779084995e-05,
      "loss": 8.8037,
      "step": 47
    },
    {
      "epoch": 0.0018393975972868886,
      "grad_norm": 1.9951223134994507,
      "learning_rate": 6.209609477998338e-05,
      "loss": 8.7091,
      "step": 48
    },
    {
      "epoch": 0.0018777183805636986,
      "grad_norm": 2.0571706295013428,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 8.624,
      "step": 49
    },
    {
      "epoch": 0.001916039163840509,
      "grad_norm": 2.1683812141418457,
      "learning_rate": 5.868240888334653e-05,
      "loss": 8.7798,
      "step": 50
    },
    {
      "epoch": 0.001954359947117319,
      "grad_norm": 1.9748177528381348,
      "learning_rate": 5.695865504800327e-05,
      "loss": 8.669,
      "step": 51
    },
    {
      "epoch": 0.0019926807303941294,
      "grad_norm": 2.2210891246795654,
      "learning_rate": 5.522642316338268e-05,
      "loss": 8.7657,
      "step": 52
    },
    {
      "epoch": 0.0020310015136709393,
      "grad_norm": 1.8661513328552246,
      "learning_rate": 5.348782368720626e-05,
      "loss": 8.6206,
      "step": 53
    },
    {
      "epoch": 0.0020693222969477496,
      "grad_norm": 1.8140807151794434,
      "learning_rate": 5.174497483512506e-05,
      "loss": 8.7015,
      "step": 54
    },
    {
      "epoch": 0.0020693222969477496,
      "eval_loss": 8.63232421875,
      "eval_runtime": 197.1296,
      "eval_samples_per_second": 111.48,
      "eval_steps_per_second": 13.935,
      "step": 54
    },
    {
      "epoch": 0.00210764308022456,
      "grad_norm": 1.8564491271972656,
      "learning_rate": 5e-05,
      "loss": 8.6189,
      "step": 55
    },
    {
      "epoch": 0.00214596386350137,
      "grad_norm": 1.8724466562271118,
      "learning_rate": 4.825502516487497e-05,
      "loss": 8.48,
      "step": 56
    },
    {
      "epoch": 0.00218428464677818,
      "grad_norm": 1.7884173393249512,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 8.7433,
      "step": 57
    },
    {
      "epoch": 0.00222260543005499,
      "grad_norm": 1.7040969133377075,
      "learning_rate": 4.477357683661734e-05,
      "loss": 8.6235,
      "step": 58
    },
    {
      "epoch": 0.0022609262133318005,
      "grad_norm": 1.9406371116638184,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 8.6172,
      "step": 59
    },
    {
      "epoch": 0.0022992469966086108,
      "grad_norm": 1.7244473695755005,
      "learning_rate": 4.131759111665349e-05,
      "loss": 8.6254,
      "step": 60
    },
    {
      "epoch": 0.002337567779885421,
      "grad_norm": 1.6151647567749023,
      "learning_rate": 3.960441545911204e-05,
      "loss": 8.5338,
      "step": 61
    },
    {
      "epoch": 0.002375888563162231,
      "grad_norm": 1.602726697921753,
      "learning_rate": 3.790390522001662e-05,
      "loss": 8.6495,
      "step": 62
    },
    {
      "epoch": 0.002414209346439041,
      "grad_norm": 1.556414246559143,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 8.66,
      "step": 63
    },
    {
      "epoch": 0.002414209346439041,
      "eval_loss": 8.53507137298584,
      "eval_runtime": 197.1109,
      "eval_samples_per_second": 111.491,
      "eval_steps_per_second": 13.936,
      "step": 63
    },
    {
      "epoch": 0.0024525301297158514,
      "grad_norm": 1.8471159934997559,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 8.6437,
      "step": 64
    },
    {
      "epoch": 0.0024908509129926617,
      "grad_norm": 1.5061924457550049,
      "learning_rate": 3.289899283371657e-05,
      "loss": 8.4696,
      "step": 65
    },
    {
      "epoch": 0.002529171696269472,
      "grad_norm": 1.6884492635726929,
      "learning_rate": 3.12696703292044e-05,
      "loss": 8.5363,
      "step": 66
    },
    {
      "epoch": 0.002567492479546282,
      "grad_norm": 1.7472187280654907,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 8.3917,
      "step": 67
    },
    {
      "epoch": 0.002605813262823092,
      "grad_norm": 1.601895809173584,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 8.4395,
      "step": 68
    },
    {
      "epoch": 0.0026441340460999023,
      "grad_norm": 1.3957659006118774,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 8.6504,
      "step": 69
    },
    {
      "epoch": 0.0026824548293767126,
      "grad_norm": 1.4126591682434082,
      "learning_rate": 2.500000000000001e-05,
      "loss": 8.4654,
      "step": 70
    },
    {
      "epoch": 0.0027207756126535225,
      "grad_norm": 1.6027814149856567,
      "learning_rate": 2.350403678833976e-05,
      "loss": 8.4307,
      "step": 71
    },
    {
      "epoch": 0.0027590963959303327,
      "grad_norm": 1.5236140489578247,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 8.479,
      "step": 72
    },
    {
      "epoch": 0.0027590963959303327,
      "eval_loss": 8.478059768676758,
      "eval_runtime": 197.0774,
      "eval_samples_per_second": 111.509,
      "eval_steps_per_second": 13.939,
      "step": 72
    },
    {
      "epoch": 0.002797417179207143,
      "grad_norm": 1.574795126914978,
      "learning_rate": 2.061073738537635e-05,
      "loss": 8.3117,
      "step": 73
    },
    {
      "epoch": 0.0028357379624839533,
      "grad_norm": 1.6588678359985352,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 8.3155,
      "step": 74
    },
    {
      "epoch": 0.0028740587457607636,
      "grad_norm": 1.4572874307632446,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 8.4948,
      "step": 75
    },
    {
      "epoch": 0.0029123795290375734,
      "grad_norm": 1.3906676769256592,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 8.5319,
      "step": 76
    },
    {
      "epoch": 0.0029507003123143837,
      "grad_norm": 1.549890160560608,
      "learning_rate": 1.526708147705013e-05,
      "loss": 8.3946,
      "step": 77
    },
    {
      "epoch": 0.002989021095591194,
      "grad_norm": 1.4431867599487305,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 8.3487,
      "step": 78
    },
    {
      "epoch": 0.003027341878868004,
      "grad_norm": 1.5942152738571167,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 8.3657,
      "step": 79
    },
    {
      "epoch": 0.003065662662144814,
      "grad_norm": 1.3526906967163086,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 8.5344,
      "step": 80
    },
    {
      "epoch": 0.0031039834454216243,
      "grad_norm": 1.568245530128479,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 8.4987,
      "step": 81
    },
    {
      "epoch": 0.0031039834454216243,
      "eval_loss": 8.4481782913208,
      "eval_runtime": 197.166,
      "eval_samples_per_second": 111.459,
      "eval_steps_per_second": 13.932,
      "step": 81
    },
    {
      "epoch": 0.0031423042286984346,
      "grad_norm": 1.4625965356826782,
      "learning_rate": 9.549150281252633e-06,
      "loss": 8.3553,
      "step": 82
    },
    {
      "epoch": 0.003180625011975245,
      "grad_norm": 1.6190887689590454,
      "learning_rate": 8.548121372247918e-06,
      "loss": 8.4586,
      "step": 83
    },
    {
      "epoch": 0.003218945795252055,
      "grad_norm": 1.4923970699310303,
      "learning_rate": 7.597595192178702e-06,
      "loss": 8.3606,
      "step": 84
    },
    {
      "epoch": 0.003257266578528865,
      "grad_norm": 1.470651626586914,
      "learning_rate": 6.698729810778065e-06,
      "loss": 8.3707,
      "step": 85
    },
    {
      "epoch": 0.0032955873618056753,
      "grad_norm": 1.3880239725112915,
      "learning_rate": 5.852620357053651e-06,
      "loss": 8.5658,
      "step": 86
    },
    {
      "epoch": 0.0033339081450824855,
      "grad_norm": 1.5443851947784424,
      "learning_rate": 5.060297685041659e-06,
      "loss": 8.381,
      "step": 87
    },
    {
      "epoch": 0.003372228928359296,
      "grad_norm": 1.3600224256515503,
      "learning_rate": 4.322727117869951e-06,
      "loss": 8.4857,
      "step": 88
    },
    {
      "epoch": 0.0034105497116361056,
      "grad_norm": 1.3307414054870605,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 8.3026,
      "step": 89
    },
    {
      "epoch": 0.003448870494912916,
      "grad_norm": 1.3035300970077515,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 8.3625,
      "step": 90
    },
    {
      "epoch": 0.003448870494912916,
      "eval_loss": 8.436622619628906,
      "eval_runtime": 197.0498,
      "eval_samples_per_second": 111.525,
      "eval_steps_per_second": 13.941,
      "step": 90
    },
    {
      "epoch": 0.003487191278189726,
      "grad_norm": 1.4547570943832397,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 8.4409,
      "step": 91
    },
    {
      "epoch": 0.0035255120614665365,
      "grad_norm": 1.3213475942611694,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 8.4133,
      "step": 92
    },
    {
      "epoch": 0.0035638328447433467,
      "grad_norm": 1.3285075426101685,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 8.4509,
      "step": 93
    },
    {
      "epoch": 0.0036021536280201566,
      "grad_norm": 1.4316322803497314,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 8.4731,
      "step": 94
    },
    {
      "epoch": 0.003640474411296967,
      "grad_norm": 1.4853651523590088,
      "learning_rate": 7.596123493895991e-07,
      "loss": 8.4,
      "step": 95
    },
    {
      "epoch": 0.003678795194573777,
      "grad_norm": 1.407329797744751,
      "learning_rate": 4.865965629214819e-07,
      "loss": 8.4689,
      "step": 96
    },
    {
      "epoch": 0.0037171159778505874,
      "grad_norm": 1.4351682662963867,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 8.3587,
      "step": 97
    },
    {
      "epoch": 0.0037554367611273972,
      "grad_norm": 1.4511561393737793,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 8.4413,
      "step": 98
    },
    {
      "epoch": 0.0037937575444042075,
      "grad_norm": 1.4957984685897827,
      "learning_rate": 3.04586490452119e-08,
      "loss": 8.3962,
      "step": 99
    },
    {
      "epoch": 0.0037937575444042075,
      "eval_loss": 8.434378623962402,
      "eval_runtime": 197.6671,
      "eval_samples_per_second": 111.177,
      "eval_steps_per_second": 13.897,
      "step": 99
    },
    {
      "epoch": 0.003832078327681018,
      "grad_norm": 1.5082837343215942,
      "learning_rate": 0.0,
      "loss": 8.2469,
      "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": 27149520076800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}