{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9345794392523364,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 3.475229024887085,
      "learning_rate": 1e-05,
      "loss": 4.7496,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 2.4821035861968994,
      "eval_runtime": 8.6429,
      "eval_samples_per_second": 10.413,
      "eval_steps_per_second": 1.388,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 4.237077713012695,
      "learning_rate": 2e-05,
      "loss": 4.756,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 3.3195765018463135,
      "learning_rate": 3e-05,
      "loss": 4.1589,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 3.983478307723999,
      "learning_rate": 4e-05,
      "loss": 3.9572,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 3.835078239440918,
      "learning_rate": 5e-05,
      "loss": 4.6358,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 3.3207688331604004,
      "learning_rate": 6e-05,
      "loss": 4.4949,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 4.351305961608887,
      "learning_rate": 7e-05,
      "loss": 4.3616,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 4.54740571975708,
      "learning_rate": 8e-05,
      "loss": 4.5251,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 6.202987194061279,
      "learning_rate": 9e-05,
      "loss": 4.2042,
      "step": 9
    },
    {
      "epoch": 0.08411214953271028,
      "eval_loss": 2.0572032928466797,
      "eval_runtime": 8.8167,
      "eval_samples_per_second": 10.208,
      "eval_steps_per_second": 1.361,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 4.361314296722412,
      "learning_rate": 0.0001,
      "loss": 3.791,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 5.193600654602051,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.1392,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 3.730332136154175,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.1271,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 3.418407678604126,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.9921,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 3.397888660430908,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.4537,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 3.643331289291382,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.1209,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 4.123091697692871,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7798,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 4.18911075592041,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.4373,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 5.305290222167969,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.4688,
      "step": 18
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 0.5362531542778015,
      "eval_runtime": 8.8425,
      "eval_samples_per_second": 10.178,
      "eval_steps_per_second": 1.357,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 4.885643482208252,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9024,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 4.518307685852051,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0553,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 3.145583391189575,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.685,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 2.9263885021209717,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.52,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 4.0514726638793945,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5227,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 3.7129552364349365,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.4578,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 2.919783592224121,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.3577,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 3.2541680335998535,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.383,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 2.778571367263794,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.3865,
      "step": 27
    },
    {
      "epoch": 0.2523364485981308,
      "eval_loss": 0.21326401829719543,
      "eval_runtime": 8.8619,
      "eval_samples_per_second": 10.156,
      "eval_steps_per_second": 1.354,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 4.196018695831299,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4486,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 4.145666599273682,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.4204,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 2.7288219928741455,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3265,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 2.6117634773254395,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.3738,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 3.820230484008789,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3816,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 1.249776005744934,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.263,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 1.3800694942474365,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2968,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 1.2462210655212402,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2924,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 1.8340442180633545,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2891,
      "step": 36
    },
    {
      "epoch": 0.3364485981308411,
      "eval_loss": 0.15187448263168335,
      "eval_runtime": 8.8701,
      "eval_samples_per_second": 10.146,
      "eval_steps_per_second": 1.353,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 1.1207772493362427,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2535,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.8222551941871643,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.232,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 1.3257524967193604,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.3135,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 1.2347744703292847,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2617,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 1.18996000289917,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.2631,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.9912763237953186,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2337,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 1.4678013324737549,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2809,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 1.3919346332550049,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.2653,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 1.550614833831787,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2985,
      "step": 45
    },
    {
      "epoch": 0.4205607476635514,
      "eval_loss": 0.13848339021205902,
      "eval_runtime": 8.8715,
      "eval_samples_per_second": 10.145,
      "eval_steps_per_second": 1.353,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 1.1843987703323364,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2799,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 1.0948872566223145,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2766,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 0.6759229898452759,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2409,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 0.7522386908531189,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.2441,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.9243168234825134,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2522,
      "step": 50
    },
    {
      "epoch": 0.4766355140186916,
      "grad_norm": 1.0649523735046387,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2433,
      "step": 51
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": 1.03244948387146,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2643,
      "step": 52
    },
    {
      "epoch": 0.4953271028037383,
      "grad_norm": 1.1822388172149658,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2851,
      "step": 53
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": 1.0989553928375244,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2547,
      "step": 54
    },
    {
      "epoch": 0.5046728971962616,
      "eval_loss": 0.12161575257778168,
      "eval_runtime": 8.8601,
      "eval_samples_per_second": 10.158,
      "eval_steps_per_second": 1.354,
      "step": 54
    },
    {
      "epoch": 0.514018691588785,
      "grad_norm": 0.84681636095047,
      "learning_rate": 5e-05,
      "loss": 0.2252,
      "step": 55
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 0.9115450978279114,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2447,
      "step": 56
    },
    {
      "epoch": 0.5327102803738317,
      "grad_norm": 0.5815334916114807,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2272,
      "step": 57
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": 0.7288433909416199,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2088,
      "step": 58
    },
    {
      "epoch": 0.5514018691588785,
      "grad_norm": 0.5948763489723206,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2356,
      "step": 59
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 1.3248896598815918,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3241,
      "step": 60
    },
    {
      "epoch": 0.5700934579439252,
      "grad_norm": 0.7061538100242615,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2592,
      "step": 61
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": 0.5691075921058655,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2186,
      "step": 62
    },
    {
      "epoch": 0.5887850467289719,
      "grad_norm": 0.7251190543174744,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2087,
      "step": 63
    },
    {
      "epoch": 0.5887850467289719,
      "eval_loss": 0.13431856036186218,
      "eval_runtime": 8.8607,
      "eval_samples_per_second": 10.157,
      "eval_steps_per_second": 1.354,
      "step": 63
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 0.6317557096481323,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2656,
      "step": 64
    },
    {
      "epoch": 0.6074766355140186,
      "grad_norm": 1.0805617570877075,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2749,
      "step": 65
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": 1.092241644859314,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2476,
      "step": 66
    },
    {
      "epoch": 0.6261682242990654,
      "grad_norm": 0.7364262938499451,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2146,
      "step": 67
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": 1.5130839347839355,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2876,
      "step": 68
    },
    {
      "epoch": 0.6448598130841121,
      "grad_norm": 0.5146616697311401,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.225,
      "step": 69
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.7840948700904846,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2188,
      "step": 70
    },
    {
      "epoch": 0.6635514018691588,
      "grad_norm": 0.8238986134529114,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2358,
      "step": 71
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 0.6461347937583923,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2586,
      "step": 72
    },
    {
      "epoch": 0.6728971962616822,
      "eval_loss": 0.12448190152645111,
      "eval_runtime": 8.8646,
      "eval_samples_per_second": 10.153,
      "eval_steps_per_second": 1.354,
      "step": 72
    },
    {
      "epoch": 0.6822429906542056,
      "grad_norm": 1.080885410308838,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2784,
      "step": 73
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": 0.7682233452796936,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2554,
      "step": 74
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": 0.8654624819755554,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2422,
      "step": 75
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": 0.5746442079544067,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2505,
      "step": 76
    },
    {
      "epoch": 0.719626168224299,
      "grad_norm": 0.8767488598823547,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.247,
      "step": 77
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": 0.7167015075683594,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.2451,
      "step": 78
    },
    {
      "epoch": 0.7383177570093458,
      "grad_norm": 1.2198740243911743,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2493,
      "step": 79
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.6779648065567017,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2161,
      "step": 80
    },
    {
      "epoch": 0.7570093457943925,
      "grad_norm": 0.7529325485229492,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2551,
      "step": 81
    },
    {
      "epoch": 0.7570093457943925,
      "eval_loss": 0.12358495593070984,
      "eval_runtime": 8.88,
      "eval_samples_per_second": 10.135,
      "eval_steps_per_second": 1.351,
      "step": 81
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": 0.740033745765686,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2112,
      "step": 82
    },
    {
      "epoch": 0.7757009345794392,
      "grad_norm": 0.8699694275856018,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2286,
      "step": 83
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": 0.439491331577301,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.228,
      "step": 84
    },
    {
      "epoch": 0.794392523364486,
      "grad_norm": 0.6666630506515503,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2204,
      "step": 85
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": 0.44219282269477844,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2274,
      "step": 86
    },
    {
      "epoch": 0.8130841121495327,
      "grad_norm": 0.6741518974304199,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2334,
      "step": 87
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 0.5375016927719116,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2219,
      "step": 88
    },
    {
      "epoch": 0.8317757009345794,
      "grad_norm": 0.5032656192779541,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2078,
      "step": 89
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.6404811143875122,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2303,
      "step": 90
    },
    {
      "epoch": 0.8411214953271028,
      "eval_loss": 0.12498477101325989,
      "eval_runtime": 8.8908,
      "eval_samples_per_second": 10.123,
      "eval_steps_per_second": 1.35,
      "step": 90
    },
    {
      "epoch": 0.8504672897196262,
      "grad_norm": 0.8548187613487244,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2475,
      "step": 91
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": 0.7053015828132629,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2288,
      "step": 92
    },
    {
      "epoch": 0.8691588785046729,
      "grad_norm": 1.0452989339828491,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2491,
      "step": 93
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": 0.5804879069328308,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.2201,
      "step": 94
    },
    {
      "epoch": 0.8878504672897196,
      "grad_norm": 0.7856619954109192,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2481,
      "step": 95
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 0.8506635427474976,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.239,
      "step": 96
    },
    {
      "epoch": 0.9065420560747663,
      "grad_norm": 0.7877066731452942,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.2645,
      "step": 97
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": 0.5927013158798218,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.2305,
      "step": 98
    },
    {
      "epoch": 0.9252336448598131,
      "grad_norm": 0.5697266459465027,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2202,
      "step": 99
    },
    {
      "epoch": 0.9252336448598131,
      "eval_loss": 0.12411493808031082,
      "eval_runtime": 8.8981,
      "eval_samples_per_second": 10.114,
      "eval_steps_per_second": 1.349,
      "step": 99
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.7628682255744934,
      "learning_rate": 0.0,
      "loss": 0.2392,
      "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": 6.53458201903104e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}