{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016874789065136685,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016874789065136686,
      "grad_norm": 13.266812324523926,
      "learning_rate": 1e-05,
      "loss": 19.9559,
      "step": 1
    },
    {
      "epoch": 0.00016874789065136686,
      "eval_loss": 19.823026657104492,
      "eval_runtime": 624.9335,
      "eval_samples_per_second": 7.985,
      "eval_steps_per_second": 0.999,
      "step": 1
    },
    {
      "epoch": 0.0003374957813027337,
      "grad_norm": 15.035416603088379,
      "learning_rate": 2e-05,
      "loss": 21.5673,
      "step": 2
    },
    {
      "epoch": 0.0005062436719541006,
      "grad_norm": 12.844522476196289,
      "learning_rate": 3e-05,
      "loss": 20.0941,
      "step": 3
    },
    {
      "epoch": 0.0006749915626054674,
      "grad_norm": 88.11199188232422,
      "learning_rate": 4e-05,
      "loss": 20.1455,
      "step": 4
    },
    {
      "epoch": 0.0008437394532568343,
      "grad_norm": 16.133426666259766,
      "learning_rate": 5e-05,
      "loss": 19.227,
      "step": 5
    },
    {
      "epoch": 0.0010124873439082012,
      "grad_norm": 16.455032348632812,
      "learning_rate": 6e-05,
      "loss": 19.8539,
      "step": 6
    },
    {
      "epoch": 0.001181235234559568,
      "grad_norm": 18.83427619934082,
      "learning_rate": 7e-05,
      "loss": 19.5651,
      "step": 7
    },
    {
      "epoch": 0.0013499831252109348,
      "grad_norm": 18.673877716064453,
      "learning_rate": 8e-05,
      "loss": 16.1982,
      "step": 8
    },
    {
      "epoch": 0.0015187310158623017,
      "grad_norm": 24.28838348388672,
      "learning_rate": 9e-05,
      "loss": 15.5664,
      "step": 9
    },
    {
      "epoch": 0.0015187310158623017,
      "eval_loss": 13.202075958251953,
      "eval_runtime": 625.2006,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 0.998,
      "step": 9
    },
    {
      "epoch": 0.0016874789065136687,
      "grad_norm": 24.719589233398438,
      "learning_rate": 0.0001,
      "loss": 13.1658,
      "step": 10
    },
    {
      "epoch": 0.0018562267971650355,
      "grad_norm": 25.70557975769043,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.7528,
      "step": 11
    },
    {
      "epoch": 0.0020249746878164025,
      "grad_norm": 23.93406867980957,
      "learning_rate": 9.987820251299122e-05,
      "loss": 7.6002,
      "step": 12
    },
    {
      "epoch": 0.0021937225784677693,
      "grad_norm": 23.907575607299805,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.2926,
      "step": 13
    },
    {
      "epoch": 0.002362470469119136,
      "grad_norm": 26.39476203918457,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.66,
      "step": 14
    },
    {
      "epoch": 0.002531218359770503,
      "grad_norm": 24.314708709716797,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5953,
      "step": 15
    },
    {
      "epoch": 0.0026999662504218697,
      "grad_norm": 16.123825073242188,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5627,
      "step": 16
    },
    {
      "epoch": 0.0028687141410732365,
      "grad_norm": 12.633217811584473,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2861,
      "step": 17
    },
    {
      "epoch": 0.0030374620317246033,
      "grad_norm": 0.947323739528656,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0246,
      "step": 18
    },
    {
      "epoch": 0.0030374620317246033,
      "eval_loss": 0.022907478734850883,
      "eval_runtime": 625.1731,
      "eval_samples_per_second": 7.982,
      "eval_steps_per_second": 0.998,
      "step": 18
    },
    {
      "epoch": 0.00320620992237597,
      "grad_norm": 1.5885169506072998,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0205,
      "step": 19
    },
    {
      "epoch": 0.0033749578130273373,
      "grad_norm": 0.3169364929199219,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0045,
      "step": 20
    },
    {
      "epoch": 0.003543705703678704,
      "grad_norm": 0.15564976632595062,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0029,
      "step": 21
    },
    {
      "epoch": 0.003712453594330071,
      "grad_norm": 0.23578593134880066,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.003,
      "step": 22
    },
    {
      "epoch": 0.0038812014849814377,
      "grad_norm": 0.09976252913475037,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0018,
      "step": 23
    },
    {
      "epoch": 0.004049949375632805,
      "grad_norm": 0.027458133175969124,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0009,
      "step": 24
    },
    {
      "epoch": 0.004218697266284171,
      "grad_norm": 0.019286803901195526,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0007,
      "step": 25
    },
    {
      "epoch": 0.004387445156935539,
      "grad_norm": 0.015429716557264328,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0006,
      "step": 26
    },
    {
      "epoch": 0.004556193047586905,
      "grad_norm": 0.014270446263253689,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0005,
      "step": 27
    },
    {
      "epoch": 0.004556193047586905,
      "eval_loss": 0.00048640690511092544,
      "eval_runtime": 625.2079,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 0.998,
      "step": 27
    },
    {
      "epoch": 0.004724940938238272,
      "grad_norm": 0.013738259673118591,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0005,
      "step": 28
    },
    {
      "epoch": 0.0048936888288896386,
      "grad_norm": 0.011623798869550228,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0004,
      "step": 29
    },
    {
      "epoch": 0.005062436719541006,
      "grad_norm": 0.010492907837033272,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0004,
      "step": 30
    },
    {
      "epoch": 0.005231184610192373,
      "grad_norm": 0.0082252724096179,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0003,
      "step": 31
    },
    {
      "epoch": 0.005399932500843739,
      "grad_norm": 0.00736565887928009,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0003,
      "step": 32
    },
    {
      "epoch": 0.005568680391495107,
      "grad_norm": 0.006228178273886442,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0003,
      "step": 33
    },
    {
      "epoch": 0.005737428282146473,
      "grad_norm": 0.006074465811252594,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0003,
      "step": 34
    },
    {
      "epoch": 0.00590617617279784,
      "grad_norm": 0.005153958685696125,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0002,
      "step": 35
    },
    {
      "epoch": 0.006074924063449207,
      "grad_norm": 0.004693693481385708,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0002,
      "step": 36
    },
    {
      "epoch": 0.006074924063449207,
      "eval_loss": 0.00021085055777803063,
      "eval_runtime": 625.4436,
      "eval_samples_per_second": 7.978,
      "eval_steps_per_second": 0.998,
      "step": 36
    },
    {
      "epoch": 0.006243671954100574,
      "grad_norm": 0.004258438479155302,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0002,
      "step": 37
    },
    {
      "epoch": 0.00641241984475194,
      "grad_norm": 0.003934090957045555,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0002,
      "step": 38
    },
    {
      "epoch": 0.0065811677354033074,
      "grad_norm": 0.0036359785590320826,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0002,
      "step": 39
    },
    {
      "epoch": 0.006749915626054675,
      "grad_norm": 0.0035507134161889553,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0002,
      "step": 40
    },
    {
      "epoch": 0.006918663516706041,
      "grad_norm": 0.0032880627550184727,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0002,
      "step": 41
    },
    {
      "epoch": 0.007087411407357408,
      "grad_norm": 0.0030914421658962965,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0002,
      "step": 42
    },
    {
      "epoch": 0.007256159298008775,
      "grad_norm": 0.003022991819307208,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0002,
      "step": 43
    },
    {
      "epoch": 0.007424907188660142,
      "grad_norm": 0.002991467248648405,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0002,
      "step": 44
    },
    {
      "epoch": 0.007593655079311508,
      "grad_norm": 0.002782425144687295,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.007593655079311508,
      "eval_loss": 0.00013746670447289944,
      "eval_runtime": 625.8113,
      "eval_samples_per_second": 7.974,
      "eval_steps_per_second": 0.997,
      "step": 45
    },
    {
      "epoch": 0.0077624029699628755,
      "grad_norm": 0.0028392772655934095,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.007931150860614243,
      "grad_norm": 0.0026526101864874363,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.00809989875126561,
      "grad_norm": 0.002278174040839076,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0001,
      "step": 48
    },
    {
      "epoch": 0.008268646641916975,
      "grad_norm": 0.002606036141514778,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0001,
      "step": 49
    },
    {
      "epoch": 0.008437394532568343,
      "grad_norm": 0.0025056349113583565,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0001,
      "step": 50
    },
    {
      "epoch": 0.00860614242321971,
      "grad_norm": 0.0027577311266213655,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0001,
      "step": 51
    },
    {
      "epoch": 0.008774890313871077,
      "grad_norm": 0.002076483564451337,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0001,
      "step": 52
    },
    {
      "epoch": 0.008943638204522443,
      "grad_norm": 0.002053693402558565,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0001,
      "step": 53
    },
    {
      "epoch": 0.00911238609517381,
      "grad_norm": 0.001942686503753066,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0001,
      "step": 54
    },
    {
      "epoch": 0.00911238609517381,
      "eval_loss": 0.00010649749310687184,
      "eval_runtime": 625.3193,
      "eval_samples_per_second": 7.98,
      "eval_steps_per_second": 0.998,
      "step": 54
    },
    {
      "epoch": 0.009281133985825177,
      "grad_norm": 0.002150897169485688,
      "learning_rate": 5e-05,
      "loss": 0.0001,
      "step": 55
    },
    {
      "epoch": 0.009449881876476544,
      "grad_norm": 0.0019327056361362338,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0001,
      "step": 56
    },
    {
      "epoch": 0.009618629767127912,
      "grad_norm": 0.0019373386166989803,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0001,
      "step": 57
    },
    {
      "epoch": 0.009787377657779277,
      "grad_norm": 0.001666673575527966,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0001,
      "step": 58
    },
    {
      "epoch": 0.009956125548430644,
      "grad_norm": 0.0018461407162249088,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0001,
      "step": 59
    },
    {
      "epoch": 0.010124873439082012,
      "grad_norm": 0.001814463990740478,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0001,
      "step": 60
    },
    {
      "epoch": 0.010293621329733379,
      "grad_norm": 0.0016477357130497694,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0001,
      "step": 61
    },
    {
      "epoch": 0.010462369220384746,
      "grad_norm": 0.0017269348027184606,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0001,
      "step": 62
    },
    {
      "epoch": 0.010631117111036112,
      "grad_norm": 0.0015631854766979814,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0001,
      "step": 63
    },
    {
      "epoch": 0.010631117111036112,
      "eval_loss": 9.104237688006833e-05,
      "eval_runtime": 625.134,
      "eval_samples_per_second": 7.982,
      "eval_steps_per_second": 0.998,
      "step": 63
    },
    {
      "epoch": 0.010799865001687479,
      "grad_norm": 0.001599570270627737,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0001,
      "step": 64
    },
    {
      "epoch": 0.010968612892338846,
      "grad_norm": 0.0015619302866980433,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0001,
      "step": 65
    },
    {
      "epoch": 0.011137360782990213,
      "grad_norm": 0.001559612574055791,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0001,
      "step": 66
    },
    {
      "epoch": 0.011306108673641579,
      "grad_norm": 0.0014832329470664263,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0001,
      "step": 67
    },
    {
      "epoch": 0.011474856564292946,
      "grad_norm": 0.0015647419495508075,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0001,
      "step": 68
    },
    {
      "epoch": 0.011643604454944313,
      "grad_norm": 0.0015791577752679586,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0001,
      "step": 69
    },
    {
      "epoch": 0.01181235234559568,
      "grad_norm": 0.0014235398266464472,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0001,
      "step": 70
    },
    {
      "epoch": 0.011981100236247048,
      "grad_norm": 0.0014568621991202235,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0001,
      "step": 71
    },
    {
      "epoch": 0.012149848126898413,
      "grad_norm": 0.001490483176894486,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0001,
      "step": 72
    },
    {
      "epoch": 0.012149848126898413,
      "eval_loss": 8.287984383059666e-05,
      "eval_runtime": 625.1903,
      "eval_samples_per_second": 7.982,
      "eval_steps_per_second": 0.998,
      "step": 72
    },
    {
      "epoch": 0.01231859601754978,
      "grad_norm": 0.001367215532809496,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0001,
      "step": 73
    },
    {
      "epoch": 0.012487343908201148,
      "grad_norm": 0.0014116012025624514,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0001,
      "step": 74
    },
    {
      "epoch": 0.012656091798852515,
      "grad_norm": 0.0014055395731702447,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0001,
      "step": 75
    },
    {
      "epoch": 0.01282483968950388,
      "grad_norm": 0.0014061018591746688,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0001,
      "step": 76
    },
    {
      "epoch": 0.012993587580155248,
      "grad_norm": 0.0013402934418991208,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0001,
      "step": 77
    },
    {
      "epoch": 0.013162335470806615,
      "grad_norm": 0.0014890744350850582,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0001,
      "step": 78
    },
    {
      "epoch": 0.013331083361457982,
      "grad_norm": 0.0014930571196600795,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0001,
      "step": 79
    },
    {
      "epoch": 0.01349983125210935,
      "grad_norm": 0.0013904611114412546,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0001,
      "step": 80
    },
    {
      "epoch": 0.013668579142760715,
      "grad_norm": 0.0014016530476510525,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0001,
      "step": 81
    },
    {
      "epoch": 0.013668579142760715,
      "eval_loss": 7.960916991578415e-05,
      "eval_runtime": 625.247,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 0.998,
      "step": 81
    },
    {
      "epoch": 0.013837327033412082,
      "grad_norm": 0.0013044956140220165,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0001,
      "step": 82
    },
    {
      "epoch": 0.01400607492406345,
      "grad_norm": 0.0013390292879194021,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0001,
      "step": 83
    },
    {
      "epoch": 0.014174822814714817,
      "grad_norm": 0.0013420628383755684,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0001,
      "step": 84
    },
    {
      "epoch": 0.014343570705366182,
      "grad_norm": 0.0012917967978864908,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0001,
      "step": 85
    },
    {
      "epoch": 0.01451231859601755,
      "grad_norm": 0.0012750140158459544,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0001,
      "step": 86
    },
    {
      "epoch": 0.014681066486668917,
      "grad_norm": 0.0013294611126184464,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0001,
      "step": 87
    },
    {
      "epoch": 0.014849814377320284,
      "grad_norm": 0.0012809195322915912,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0001,
      "step": 88
    },
    {
      "epoch": 0.015018562267971651,
      "grad_norm": 0.001249048626050353,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0001,
      "step": 89
    },
    {
      "epoch": 0.015187310158623017,
      "grad_norm": 0.0013068304397165775,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0001,
      "step": 90
    },
    {
      "epoch": 0.015187310158623017,
      "eval_loss": 7.809953240212053e-05,
      "eval_runtime": 625.207,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 0.998,
      "step": 90
    },
    {
      "epoch": 0.015356058049274384,
      "grad_norm": 0.0013493247097358108,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0001,
      "step": 91
    },
    {
      "epoch": 0.015524805939925751,
      "grad_norm": 0.0012746276333928108,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0001,
      "step": 92
    },
    {
      "epoch": 0.015693553830577116,
      "grad_norm": 0.0012948549119755626,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0001,
      "step": 93
    },
    {
      "epoch": 0.015862301721228485,
      "grad_norm": 0.0013543089153245091,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.01603104961187985,
      "grad_norm": 0.001380831585265696,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0001,
      "step": 95
    },
    {
      "epoch": 0.01619979750253122,
      "grad_norm": 0.0013931747525930405,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0001,
      "step": 96
    },
    {
      "epoch": 0.016368545393182585,
      "grad_norm": 0.0013471550773829222,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0001,
      "step": 97
    },
    {
      "epoch": 0.01653729328383395,
      "grad_norm": 0.0012436999240890145,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0001,
      "step": 98
    },
    {
      "epoch": 0.01670604117448532,
      "grad_norm": 0.0013065434759482741,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0001,
      "step": 99
    },
    {
      "epoch": 0.01670604117448532,
      "eval_loss": 7.7750941272825e-05,
      "eval_runtime": 625.196,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 0.998,
      "step": 99
    },
    {
      "epoch": 0.016874789065136685,
      "grad_norm": 0.0013825303176417947,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "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": 1.483775372427264e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}