{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7936507936507936,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007936507936507936,
      "grad_norm": 0.5723141431808472,
      "learning_rate": 1e-05,
      "loss": 0.7819,
      "step": 1
    },
    {
      "epoch": 0.007936507936507936,
      "eval_loss": 0.7385377883911133,
      "eval_runtime": 12.4951,
      "eval_samples_per_second": 8.483,
      "eval_steps_per_second": 1.12,
      "step": 1
    },
    {
      "epoch": 0.015873015873015872,
      "grad_norm": 0.5577658414840698,
      "learning_rate": 2e-05,
      "loss": 0.5743,
      "step": 2
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.5924695730209351,
      "learning_rate": 3e-05,
      "loss": 0.7856,
      "step": 3
    },
    {
      "epoch": 0.031746031746031744,
      "grad_norm": 1.1029717922210693,
      "learning_rate": 4e-05,
      "loss": 1.0336,
      "step": 4
    },
    {
      "epoch": 0.03968253968253968,
      "grad_norm": 0.5817142128944397,
      "learning_rate": 5e-05,
      "loss": 0.6727,
      "step": 5
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.9134500622749329,
      "learning_rate": 6e-05,
      "loss": 0.7168,
      "step": 6
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.8548192977905273,
      "learning_rate": 7e-05,
      "loss": 0.7588,
      "step": 7
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.9592969417572021,
      "learning_rate": 8e-05,
      "loss": 0.5431,
      "step": 8
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.4753745496273041,
      "learning_rate": 9e-05,
      "loss": 0.4157,
      "step": 9
    },
    {
      "epoch": 0.07142857142857142,
      "eval_loss": 0.4517921805381775,
      "eval_runtime": 11.8008,
      "eval_samples_per_second": 8.982,
      "eval_steps_per_second": 1.186,
      "step": 9
    },
    {
      "epoch": 0.07936507936507936,
      "grad_norm": 0.5649997591972351,
      "learning_rate": 0.0001,
      "loss": 0.4264,
      "step": 10
    },
    {
      "epoch": 0.0873015873015873,
      "grad_norm": 0.6885582208633423,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.4388,
      "step": 11
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.3964652419090271,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3397,
      "step": 12
    },
    {
      "epoch": 0.10317460317460317,
      "grad_norm": 0.6276869177818298,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.3906,
      "step": 13
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.5640867948532104,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.2939,
      "step": 14
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.8967375159263611,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.3472,
      "step": 15
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.7164875864982605,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2494,
      "step": 16
    },
    {
      "epoch": 0.1349206349206349,
      "grad_norm": 0.4000527262687683,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.245,
      "step": 17
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.480807363986969,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.2695,
      "step": 18
    },
    {
      "epoch": 0.14285714285714285,
      "eval_loss": 0.263343870639801,
      "eval_runtime": 11.7919,
      "eval_samples_per_second": 8.989,
      "eval_steps_per_second": 1.187,
      "step": 18
    },
    {
      "epoch": 0.15079365079365079,
      "grad_norm": 0.5784887671470642,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2667,
      "step": 19
    },
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.3400481939315796,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2797,
      "step": 20
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.8097524642944336,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3259,
      "step": 21
    },
    {
      "epoch": 0.1746031746031746,
      "grad_norm": 0.45467671751976013,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.2423,
      "step": 22
    },
    {
      "epoch": 0.18253968253968253,
      "grad_norm": 0.4269068241119385,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.2045,
      "step": 23
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.5358132123947144,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2549,
      "step": 24
    },
    {
      "epoch": 0.1984126984126984,
      "grad_norm": 0.6622316241264343,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2531,
      "step": 25
    },
    {
      "epoch": 0.20634920634920634,
      "grad_norm": 0.36567825078964233,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.2373,
      "step": 26
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.3651120662689209,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.231,
      "step": 27
    },
    {
      "epoch": 0.21428571428571427,
      "eval_loss": 0.23956447839736938,
      "eval_runtime": 11.7941,
      "eval_samples_per_second": 8.988,
      "eval_steps_per_second": 1.187,
      "step": 27
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.5219882726669312,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2168,
      "step": 28
    },
    {
      "epoch": 0.23015873015873015,
      "grad_norm": 0.3878607153892517,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.2452,
      "step": 29
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.3680654466152191,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2422,
      "step": 30
    },
    {
      "epoch": 0.24603174603174602,
      "grad_norm": 0.29995450377464294,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2249,
      "step": 31
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.4001246392726898,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2622,
      "step": 32
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 0.28822505474090576,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2116,
      "step": 33
    },
    {
      "epoch": 0.2698412698412698,
      "grad_norm": 0.25429052114486694,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2007,
      "step": 34
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.29249072074890137,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2173,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.30489400029182434,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2127,
      "step": 36
    },
    {
      "epoch": 0.2857142857142857,
      "eval_loss": 0.22131845355033875,
      "eval_runtime": 11.7833,
      "eval_samples_per_second": 8.996,
      "eval_steps_per_second": 1.188,
      "step": 36
    },
    {
      "epoch": 0.29365079365079366,
      "grad_norm": 0.4536025822162628,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2486,
      "step": 37
    },
    {
      "epoch": 0.30158730158730157,
      "grad_norm": 0.21147893369197845,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2094,
      "step": 38
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 0.21347074210643768,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2146,
      "step": 39
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.4815422594547272,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1892,
      "step": 40
    },
    {
      "epoch": 0.3253968253968254,
      "grad_norm": 0.30590173602104187,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2208,
      "step": 41
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5233677625656128,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2463,
      "step": 42
    },
    {
      "epoch": 0.3412698412698413,
      "grad_norm": 0.3786214590072632,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2107,
      "step": 43
    },
    {
      "epoch": 0.3492063492063492,
      "grad_norm": 0.3967248797416687,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.187,
      "step": 44
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.4329782724380493,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2235,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "eval_loss": 0.20556718111038208,
      "eval_runtime": 11.7406,
      "eval_samples_per_second": 9.029,
      "eval_steps_per_second": 1.192,
      "step": 45
    },
    {
      "epoch": 0.36507936507936506,
      "grad_norm": 0.5757659673690796,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.223,
      "step": 46
    },
    {
      "epoch": 0.373015873015873,
      "grad_norm": 0.3994109332561493,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2308,
      "step": 47
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.2843783497810364,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2052,
      "step": 48
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.4453858733177185,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.1988,
      "step": 49
    },
    {
      "epoch": 0.3968253968253968,
      "grad_norm": 0.4066433608531952,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2084,
      "step": 50
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 0.42400673031806946,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2285,
      "step": 51
    },
    {
      "epoch": 0.4126984126984127,
      "grad_norm": 0.5643566250801086,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2119,
      "step": 52
    },
    {
      "epoch": 0.42063492063492064,
      "grad_norm": 0.4981585144996643,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2294,
      "step": 53
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.40946900844573975,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2237,
      "step": 54
    },
    {
      "epoch": 0.42857142857142855,
      "eval_loss": 0.20218834280967712,
      "eval_runtime": 11.8148,
      "eval_samples_per_second": 8.972,
      "eval_steps_per_second": 1.185,
      "step": 54
    },
    {
      "epoch": 0.4365079365079365,
      "grad_norm": 0.7285588979721069,
      "learning_rate": 5e-05,
      "loss": 0.2249,
      "step": 55
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.4775647222995758,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2223,
      "step": 56
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 0.4595770537853241,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1801,
      "step": 57
    },
    {
      "epoch": 0.4603174603174603,
      "grad_norm": 0.34900394082069397,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1862,
      "step": 58
    },
    {
      "epoch": 0.46825396825396826,
      "grad_norm": 0.5798309445381165,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2086,
      "step": 59
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.4363901615142822,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.2127,
      "step": 60
    },
    {
      "epoch": 0.48412698412698413,
      "grad_norm": 0.3747006952762604,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2035,
      "step": 61
    },
    {
      "epoch": 0.49206349206349204,
      "grad_norm": 0.4907454550266266,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2025,
      "step": 62
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.42181912064552307,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2209,
      "step": 63
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.1936516910791397,
      "eval_runtime": 11.7483,
      "eval_samples_per_second": 9.023,
      "eval_steps_per_second": 1.192,
      "step": 63
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.4980236887931824,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2029,
      "step": 64
    },
    {
      "epoch": 0.5158730158730159,
      "grad_norm": 0.3584940433502197,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1888,
      "step": 65
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 0.4028421938419342,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1871,
      "step": 66
    },
    {
      "epoch": 0.5317460317460317,
      "grad_norm": 0.4666447341442108,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.204,
      "step": 67
    },
    {
      "epoch": 0.5396825396825397,
      "grad_norm": 0.3785227835178375,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.1973,
      "step": 68
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 0.4338895380496979,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2053,
      "step": 69
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.3227415978908539,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1659,
      "step": 70
    },
    {
      "epoch": 0.5634920634920635,
      "grad_norm": 0.3305239975452423,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.1687,
      "step": 71
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.5412036180496216,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1706,
      "step": 72
    },
    {
      "epoch": 0.5714285714285714,
      "eval_loss": 0.1866018921136856,
      "eval_runtime": 11.7603,
      "eval_samples_per_second": 9.013,
      "eval_steps_per_second": 1.19,
      "step": 72
    },
    {
      "epoch": 0.5793650793650794,
      "grad_norm": 0.33903056383132935,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1653,
      "step": 73
    },
    {
      "epoch": 0.5873015873015873,
      "grad_norm": 0.4676951467990875,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2113,
      "step": 74
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.36672213673591614,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1957,
      "step": 75
    },
    {
      "epoch": 0.6031746031746031,
      "grad_norm": 0.34517067670822144,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1601,
      "step": 76
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.4209977686405182,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2038,
      "step": 77
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.37364357709884644,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.1732,
      "step": 78
    },
    {
      "epoch": 0.626984126984127,
      "grad_norm": 0.4351928234100342,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1906,
      "step": 79
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.41745811700820923,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2098,
      "step": 80
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.4128893315792084,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1775,
      "step": 81
    },
    {
      "epoch": 0.6428571428571429,
      "eval_loss": 0.18361014127731323,
      "eval_runtime": 11.7937,
      "eval_samples_per_second": 8.988,
      "eval_steps_per_second": 1.187,
      "step": 81
    },
    {
      "epoch": 0.6507936507936508,
      "grad_norm": 0.3903600573539734,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1877,
      "step": 82
    },
    {
      "epoch": 0.6587301587301587,
      "grad_norm": 0.4527701735496521,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.1946,
      "step": 83
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.370411217212677,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1821,
      "step": 84
    },
    {
      "epoch": 0.6746031746031746,
      "grad_norm": 0.44652992486953735,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.1745,
      "step": 85
    },
    {
      "epoch": 0.6825396825396826,
      "grad_norm": 0.3680137097835541,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.1663,
      "step": 86
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 0.5062569975852966,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2003,
      "step": 87
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.36240339279174805,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1886,
      "step": 88
    },
    {
      "epoch": 0.7063492063492064,
      "grad_norm": 0.5011777877807617,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2218,
      "step": 89
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.39543071389198303,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2025,
      "step": 90
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.17969763278961182,
      "eval_runtime": 11.7457,
      "eval_samples_per_second": 9.025,
      "eval_steps_per_second": 1.192,
      "step": 90
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.5232609510421753,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2011,
      "step": 91
    },
    {
      "epoch": 0.7301587301587301,
      "grad_norm": 0.7661548852920532,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2548,
      "step": 92
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 0.35290607810020447,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1839,
      "step": 93
    },
    {
      "epoch": 0.746031746031746,
      "grad_norm": 0.34179702401161194,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.1623,
      "step": 94
    },
    {
      "epoch": 0.753968253968254,
      "grad_norm": 0.4746062457561493,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2129,
      "step": 95
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.540755569934845,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2118,
      "step": 96
    },
    {
      "epoch": 0.7698412698412699,
      "grad_norm": 0.38110673427581787,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1797,
      "step": 97
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.5135464072227478,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1675,
      "step": 98
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.3694540560245514,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1878,
      "step": 99
    },
    {
      "epoch": 0.7857142857142857,
      "eval_loss": 0.17945602536201477,
      "eval_runtime": 11.7379,
      "eval_samples_per_second": 9.031,
      "eval_steps_per_second": 1.193,
      "step": 99
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.31265389919281006,
      "learning_rate": 0.0,
      "loss": 0.1826,
      "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": 7.641439020672614e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}