{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03252561392096276,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003252561392096276,
      "grad_norm": 0.14763297140598297,
      "learning_rate": 1e-05,
      "loss": 1.3107,
      "step": 1
    },
    {
      "epoch": 0.0003252561392096276,
      "eval_loss": 0.6128472089767456,
      "eval_runtime": 782.4336,
      "eval_samples_per_second": 3.309,
      "eval_steps_per_second": 0.414,
      "step": 1
    },
    {
      "epoch": 0.0006505122784192552,
      "grad_norm": 0.15804411470890045,
      "learning_rate": 2e-05,
      "loss": 1.2744,
      "step": 2
    },
    {
      "epoch": 0.0009757684176288828,
      "grad_norm": 0.20896154642105103,
      "learning_rate": 3e-05,
      "loss": 1.2737,
      "step": 3
    },
    {
      "epoch": 0.0013010245568385104,
      "grad_norm": 0.16174398362636566,
      "learning_rate": 4e-05,
      "loss": 1.2305,
      "step": 4
    },
    {
      "epoch": 0.0016262806960481379,
      "grad_norm": 0.2118031233549118,
      "learning_rate": 5e-05,
      "loss": 1.2944,
      "step": 5
    },
    {
      "epoch": 0.0019515368352577655,
      "grad_norm": 0.23166026175022125,
      "learning_rate": 6e-05,
      "loss": 1.3836,
      "step": 6
    },
    {
      "epoch": 0.002276792974467393,
      "grad_norm": 0.24533332884311676,
      "learning_rate": 7e-05,
      "loss": 1.351,
      "step": 7
    },
    {
      "epoch": 0.002602049113677021,
      "grad_norm": 0.22335144877433777,
      "learning_rate": 8e-05,
      "loss": 1.2094,
      "step": 8
    },
    {
      "epoch": 0.002927305252886648,
      "grad_norm": 0.17421536147594452,
      "learning_rate": 9e-05,
      "loss": 1.0518,
      "step": 9
    },
    {
      "epoch": 0.002927305252886648,
      "eval_loss": 0.5979532599449158,
      "eval_runtime": 784.5573,
      "eval_samples_per_second": 3.3,
      "eval_steps_per_second": 0.413,
      "step": 9
    },
    {
      "epoch": 0.0032525613920962758,
      "grad_norm": 0.23275502026081085,
      "learning_rate": 0.0001,
      "loss": 1.156,
      "step": 10
    },
    {
      "epoch": 0.0035778175313059034,
      "grad_norm": 0.2948048710823059,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.3445,
      "step": 11
    },
    {
      "epoch": 0.003903073670515531,
      "grad_norm": 0.2602439522743225,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.2708,
      "step": 12
    },
    {
      "epoch": 0.004228329809725159,
      "grad_norm": 0.27609723806381226,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.1945,
      "step": 13
    },
    {
      "epoch": 0.004553585948934786,
      "grad_norm": 0.2293613851070404,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1564,
      "step": 14
    },
    {
      "epoch": 0.004878842088144414,
      "grad_norm": 0.22937771677970886,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.1253,
      "step": 15
    },
    {
      "epoch": 0.005204098227354042,
      "grad_norm": 0.18859991431236267,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.1374,
      "step": 16
    },
    {
      "epoch": 0.0055293543665636685,
      "grad_norm": 0.1891753226518631,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.0756,
      "step": 17
    },
    {
      "epoch": 0.005854610505773296,
      "grad_norm": 0.1989993453025818,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1617,
      "step": 18
    },
    {
      "epoch": 0.005854610505773296,
      "eval_loss": 0.5764406323432922,
      "eval_runtime": 784.0595,
      "eval_samples_per_second": 3.302,
      "eval_steps_per_second": 0.413,
      "step": 18
    },
    {
      "epoch": 0.006179866644982924,
      "grad_norm": 0.22392453253269196,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1877,
      "step": 19
    },
    {
      "epoch": 0.0065051227841925515,
      "grad_norm": 0.3026638627052307,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.4219,
      "step": 20
    },
    {
      "epoch": 0.006830378923402179,
      "grad_norm": 0.25882938504219055,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.3057,
      "step": 21
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": 0.1638745367527008,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0829,
      "step": 22
    },
    {
      "epoch": 0.0074808912018214345,
      "grad_norm": 0.2118702530860901,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.0412,
      "step": 23
    },
    {
      "epoch": 0.007806147341031062,
      "grad_norm": 0.18744254112243652,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.0664,
      "step": 24
    },
    {
      "epoch": 0.00813140348024069,
      "grad_norm": 0.20246753096580505,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1876,
      "step": 25
    },
    {
      "epoch": 0.008456659619450317,
      "grad_norm": 0.41961824893951416,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.26,
      "step": 26
    },
    {
      "epoch": 0.008781915758659945,
      "grad_norm": 0.21500089764595032,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.1012,
      "step": 27
    },
    {
      "epoch": 0.008781915758659945,
      "eval_loss": 0.5579646825790405,
      "eval_runtime": 783.8198,
      "eval_samples_per_second": 3.303,
      "eval_steps_per_second": 0.413,
      "step": 27
    },
    {
      "epoch": 0.009107171897869573,
      "grad_norm": 0.24031320214271545,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1712,
      "step": 28
    },
    {
      "epoch": 0.0094324280370792,
      "grad_norm": 0.3059426546096802,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1868,
      "step": 29
    },
    {
      "epoch": 0.009757684176288828,
      "grad_norm": 0.23784655332565308,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1079,
      "step": 30
    },
    {
      "epoch": 0.010082940315498456,
      "grad_norm": 0.22733500599861145,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1338,
      "step": 31
    },
    {
      "epoch": 0.010408196454708083,
      "grad_norm": 0.24907109141349792,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0192,
      "step": 32
    },
    {
      "epoch": 0.01073345259391771,
      "grad_norm": 0.2515224516391754,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.0843,
      "step": 33
    },
    {
      "epoch": 0.011058708733127337,
      "grad_norm": 0.2625855505466461,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.085,
      "step": 34
    },
    {
      "epoch": 0.011383964872336965,
      "grad_norm": 0.2575761079788208,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.1539,
      "step": 35
    },
    {
      "epoch": 0.011709221011546592,
      "grad_norm": 0.29588720202445984,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1184,
      "step": 36
    },
    {
      "epoch": 0.011709221011546592,
      "eval_loss": 0.5465654134750366,
      "eval_runtime": 783.8133,
      "eval_samples_per_second": 3.303,
      "eval_steps_per_second": 0.413,
      "step": 36
    },
    {
      "epoch": 0.01203447715075622,
      "grad_norm": 0.3065912425518036,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.1541,
      "step": 37
    },
    {
      "epoch": 0.012359733289965848,
      "grad_norm": 0.26761195063591003,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.1795,
      "step": 38
    },
    {
      "epoch": 0.012684989429175475,
      "grad_norm": 0.2772088348865509,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.0239,
      "step": 39
    },
    {
      "epoch": 0.013010245568385103,
      "grad_norm": 0.32695820927619934,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0768,
      "step": 40
    },
    {
      "epoch": 0.01333550170759473,
      "grad_norm": 0.2808251976966858,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.1167,
      "step": 41
    },
    {
      "epoch": 0.013660757846804358,
      "grad_norm": 0.3229953944683075,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.1411,
      "step": 42
    },
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 0.37887775897979736,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.0486,
      "step": 43
    },
    {
      "epoch": 0.014311270125223614,
      "grad_norm": 0.26884517073631287,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0855,
      "step": 44
    },
    {
      "epoch": 0.014636526264433241,
      "grad_norm": 0.2808413803577423,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.0628,
      "step": 45
    },
    {
      "epoch": 0.014636526264433241,
      "eval_loss": 0.5379300713539124,
      "eval_runtime": 783.7901,
      "eval_samples_per_second": 3.303,
      "eval_steps_per_second": 0.413,
      "step": 45
    },
    {
      "epoch": 0.014961782403642869,
      "grad_norm": 0.3325427174568176,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.007,
      "step": 46
    },
    {
      "epoch": 0.015287038542852497,
      "grad_norm": 0.31275928020477295,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.2218,
      "step": 47
    },
    {
      "epoch": 0.015612294682062124,
      "grad_norm": 0.30787625908851624,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.0805,
      "step": 48
    },
    {
      "epoch": 0.01593755082127175,
      "grad_norm": 0.280702143907547,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.0439,
      "step": 49
    },
    {
      "epoch": 0.01626280696048138,
      "grad_norm": 0.34143200516700745,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.1203,
      "step": 50
    },
    {
      "epoch": 0.016588063099691006,
      "grad_norm": 0.35546672344207764,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.2668,
      "step": 51
    },
    {
      "epoch": 0.016913319238900635,
      "grad_norm": 0.2736748158931732,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.0887,
      "step": 52
    },
    {
      "epoch": 0.01723857537811026,
      "grad_norm": 0.27704671025276184,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.1158,
      "step": 53
    },
    {
      "epoch": 0.01756383151731989,
      "grad_norm": 0.33320048451423645,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.2026,
      "step": 54
    },
    {
      "epoch": 0.01756383151731989,
      "eval_loss": 0.5289172530174255,
      "eval_runtime": 783.8207,
      "eval_samples_per_second": 3.303,
      "eval_steps_per_second": 0.413,
      "step": 54
    },
    {
      "epoch": 0.017889087656529516,
      "grad_norm": 0.28806421160697937,
      "learning_rate": 5e-05,
      "loss": 1.0224,
      "step": 55
    },
    {
      "epoch": 0.018214343795739146,
      "grad_norm": 0.3748149275779724,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.045,
      "step": 56
    },
    {
      "epoch": 0.01853959993494877,
      "grad_norm": 0.28911730647087097,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.1132,
      "step": 57
    },
    {
      "epoch": 0.0188648560741584,
      "grad_norm": 0.2615390121936798,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.898,
      "step": 58
    },
    {
      "epoch": 0.019190112213368027,
      "grad_norm": 0.26514431834220886,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.0557,
      "step": 59
    },
    {
      "epoch": 0.019515368352577656,
      "grad_norm": 0.3049844801425934,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.0511,
      "step": 60
    },
    {
      "epoch": 0.019840624491787282,
      "grad_norm": 0.3749238848686218,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0863,
      "step": 61
    },
    {
      "epoch": 0.02016588063099691,
      "grad_norm": 0.2859311103820801,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9929,
      "step": 62
    },
    {
      "epoch": 0.020491136770206538,
      "grad_norm": 0.2842947542667389,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9925,
      "step": 63
    },
    {
      "epoch": 0.020491136770206538,
      "eval_loss": 0.523247480392456,
      "eval_runtime": 783.5638,
      "eval_samples_per_second": 3.304,
      "eval_steps_per_second": 0.413,
      "step": 63
    },
    {
      "epoch": 0.020816392909416167,
      "grad_norm": 0.2733912765979767,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0786,
      "step": 64
    },
    {
      "epoch": 0.021141649048625793,
      "grad_norm": 0.29001614451408386,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.0672,
      "step": 65
    },
    {
      "epoch": 0.02146690518783542,
      "grad_norm": 0.35740548372268677,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.0932,
      "step": 66
    },
    {
      "epoch": 0.021792161327045048,
      "grad_norm": 0.2935461699962616,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8891,
      "step": 67
    },
    {
      "epoch": 0.022117417466254674,
      "grad_norm": 0.2859397828578949,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.0254,
      "step": 68
    },
    {
      "epoch": 0.022442673605464303,
      "grad_norm": 0.29368773102760315,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.9727,
      "step": 69
    },
    {
      "epoch": 0.02276792974467393,
      "grad_norm": 0.34601661562919617,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0418,
      "step": 70
    },
    {
      "epoch": 0.02309318588388356,
      "grad_norm": 0.27021434903144836,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.9738,
      "step": 71
    },
    {
      "epoch": 0.023418442023093185,
      "grad_norm": 0.3417051434516907,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0822,
      "step": 72
    },
    {
      "epoch": 0.023418442023093185,
      "eval_loss": 0.5194622874259949,
      "eval_runtime": 784.0065,
      "eval_samples_per_second": 3.302,
      "eval_steps_per_second": 0.413,
      "step": 72
    },
    {
      "epoch": 0.023743698162302814,
      "grad_norm": 0.32264044880867004,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.941,
      "step": 73
    },
    {
      "epoch": 0.02406895430151244,
      "grad_norm": 0.634362518787384,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.2005,
      "step": 74
    },
    {
      "epoch": 0.02439421044072207,
      "grad_norm": 0.3109305202960968,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.012,
      "step": 75
    },
    {
      "epoch": 0.024719466579931695,
      "grad_norm": 0.4276930093765259,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.0689,
      "step": 76
    },
    {
      "epoch": 0.025044722719141325,
      "grad_norm": 0.3671048581600189,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.2221,
      "step": 77
    },
    {
      "epoch": 0.02536997885835095,
      "grad_norm": 0.3389880061149597,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.9975,
      "step": 78
    },
    {
      "epoch": 0.02569523499756058,
      "grad_norm": 0.3353745639324188,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.9682,
      "step": 79
    },
    {
      "epoch": 0.026020491136770206,
      "grad_norm": 0.3157464861869812,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.0898,
      "step": 80
    },
    {
      "epoch": 0.026345747275979835,
      "grad_norm": 0.31050676107406616,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.9718,
      "step": 81
    },
    {
      "epoch": 0.026345747275979835,
      "eval_loss": 0.5167155265808105,
      "eval_runtime": 783.7942,
      "eval_samples_per_second": 3.303,
      "eval_steps_per_second": 0.413,
      "step": 81
    },
    {
      "epoch": 0.02667100341518946,
      "grad_norm": 0.28341951966285706,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9535,
      "step": 82
    },
    {
      "epoch": 0.02699625955439909,
      "grad_norm": 0.34261542558670044,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.0475,
      "step": 83
    },
    {
      "epoch": 0.027321515693608717,
      "grad_norm": 0.2891163229942322,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.0398,
      "step": 84
    },
    {
      "epoch": 0.027646771832818346,
      "grad_norm": 0.30140769481658936,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.0461,
      "step": 85
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 0.3153305947780609,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0026,
      "step": 86
    },
    {
      "epoch": 0.028297284111237598,
      "grad_norm": 0.2923007905483246,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.0061,
      "step": 87
    },
    {
      "epoch": 0.028622540250447227,
      "grad_norm": 0.310686856508255,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.0761,
      "step": 88
    },
    {
      "epoch": 0.028947796389656853,
      "grad_norm": 0.3076779544353485,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0248,
      "step": 89
    },
    {
      "epoch": 0.029273052528866483,
      "grad_norm": 0.3605354130268097,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0372,
      "step": 90
    },
    {
      "epoch": 0.029273052528866483,
      "eval_loss": 0.5154066681861877,
      "eval_runtime": 783.8332,
      "eval_samples_per_second": 3.303,
      "eval_steps_per_second": 0.413,
      "step": 90
    },
    {
      "epoch": 0.02959830866807611,
      "grad_norm": 0.34296754002571106,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.9784,
      "step": 91
    },
    {
      "epoch": 0.029923564807285738,
      "grad_norm": 0.283575177192688,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.8804,
      "step": 92
    },
    {
      "epoch": 0.030248820946495364,
      "grad_norm": 0.3156563639640808,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.0238,
      "step": 93
    },
    {
      "epoch": 0.030574077085704993,
      "grad_norm": 0.30818790197372437,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.9902,
      "step": 94
    },
    {
      "epoch": 0.03089933322491462,
      "grad_norm": 0.3115820586681366,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.9174,
      "step": 95
    },
    {
      "epoch": 0.03122458936412425,
      "grad_norm": 0.305444598197937,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.9995,
      "step": 96
    },
    {
      "epoch": 0.031549845503333875,
      "grad_norm": 0.37256306409835815,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.9834,
      "step": 97
    },
    {
      "epoch": 0.0318751016425435,
      "grad_norm": 0.32575827836990356,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.0356,
      "step": 98
    },
    {
      "epoch": 0.03220035778175313,
      "grad_norm": 0.4277135133743286,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0836,
      "step": 99
    },
    {
      "epoch": 0.03220035778175313,
      "eval_loss": 0.5151550769805908,
      "eval_runtime": 784.0298,
      "eval_samples_per_second": 3.302,
      "eval_steps_per_second": 0.413,
      "step": 99
    },
    {
      "epoch": 0.03252561392096276,
      "grad_norm": 0.35957303643226624,
      "learning_rate": 0.0,
      "loss": 1.0562,
      "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": 2.4502623654641664e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}