{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6578947368421053,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006578947368421052,
      "grad_norm": 1.3723570108413696,
      "learning_rate": 1e-05,
      "loss": 3.0553,
      "step": 1
    },
    {
      "epoch": 0.006578947368421052,
      "eval_loss": 1.5740034580230713,
      "eval_runtime": 11.8121,
      "eval_samples_per_second": 10.921,
      "eval_steps_per_second": 1.439,
      "step": 1
    },
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 1.1681878566741943,
      "learning_rate": 2e-05,
      "loss": 3.2758,
      "step": 2
    },
    {
      "epoch": 0.019736842105263157,
      "grad_norm": 1.0519293546676636,
      "learning_rate": 3e-05,
      "loss": 3.1613,
      "step": 3
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 1.101668357849121,
      "learning_rate": 4e-05,
      "loss": 3.4138,
      "step": 4
    },
    {
      "epoch": 0.03289473684210526,
      "grad_norm": 1.1148228645324707,
      "learning_rate": 5e-05,
      "loss": 2.9756,
      "step": 5
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 1.173661470413208,
      "learning_rate": 6e-05,
      "loss": 3.1312,
      "step": 6
    },
    {
      "epoch": 0.046052631578947366,
      "grad_norm": 1.14241623878479,
      "learning_rate": 7e-05,
      "loss": 3.3283,
      "step": 7
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 1.1389048099517822,
      "learning_rate": 8e-05,
      "loss": 2.9638,
      "step": 8
    },
    {
      "epoch": 0.05921052631578947,
      "grad_norm": 1.3418545722961426,
      "learning_rate": 9e-05,
      "loss": 3.2313,
      "step": 9
    },
    {
      "epoch": 0.05921052631578947,
      "eval_loss": 1.5062702894210815,
      "eval_runtime": 11.8114,
      "eval_samples_per_second": 10.922,
      "eval_steps_per_second": 1.439,
      "step": 9
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 1.3892360925674438,
      "learning_rate": 0.0001,
      "loss": 3.018,
      "step": 10
    },
    {
      "epoch": 0.07236842105263158,
      "grad_norm": 1.392829179763794,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.9436,
      "step": 11
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 1.3135286569595337,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.777,
      "step": 12
    },
    {
      "epoch": 0.08552631578947369,
      "grad_norm": 1.4119974374771118,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.8531,
      "step": 13
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 1.4262498617172241,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.9748,
      "step": 14
    },
    {
      "epoch": 0.09868421052631579,
      "grad_norm": 1.5271186828613281,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.9193,
      "step": 15
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.459143042564392,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.0888,
      "step": 16
    },
    {
      "epoch": 0.1118421052631579,
      "grad_norm": 1.589043378829956,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.6161,
      "step": 17
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 1.6413291692733765,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6796,
      "step": 18
    },
    {
      "epoch": 0.11842105263157894,
      "eval_loss": 1.397473931312561,
      "eval_runtime": 11.8253,
      "eval_samples_per_second": 10.909,
      "eval_steps_per_second": 1.438,
      "step": 18
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.7178572416305542,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1593,
      "step": 19
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 1.754470944404602,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5053,
      "step": 20
    },
    {
      "epoch": 0.13815789473684212,
      "grad_norm": 1.851193904876709,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.593,
      "step": 21
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 1.6767325401306152,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.6815,
      "step": 22
    },
    {
      "epoch": 0.1513157894736842,
      "grad_norm": 1.5205342769622803,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.9393,
      "step": 23
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.2843806743621826,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.7322,
      "step": 24
    },
    {
      "epoch": 0.16447368421052633,
      "grad_norm": 1.3868401050567627,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.2179,
      "step": 25
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 1.266970157623291,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.8427,
      "step": 26
    },
    {
      "epoch": 0.17763157894736842,
      "grad_norm": 1.2429920434951782,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.1787,
      "step": 27
    },
    {
      "epoch": 0.17763157894736842,
      "eval_loss": 1.3803091049194336,
      "eval_runtime": 11.8674,
      "eval_samples_per_second": 10.87,
      "eval_steps_per_second": 1.432,
      "step": 27
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 1.2589099407196045,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.7419,
      "step": 28
    },
    {
      "epoch": 0.19078947368421054,
      "grad_norm": 1.3871017694473267,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.8042,
      "step": 29
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 1.4038580656051636,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1988,
      "step": 30
    },
    {
      "epoch": 0.20394736842105263,
      "grad_norm": 1.4135472774505615,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.9387,
      "step": 31
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.3331189155578613,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.6233,
      "step": 32
    },
    {
      "epoch": 0.21710526315789475,
      "grad_norm": 1.1323872804641724,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.7354,
      "step": 33
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 1.418157935142517,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.3975,
      "step": 34
    },
    {
      "epoch": 0.23026315789473684,
      "grad_norm": 1.3568916320800781,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.0784,
      "step": 35
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 1.3986948728561401,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.5897,
      "step": 36
    },
    {
      "epoch": 0.23684210526315788,
      "eval_loss": 1.370699167251587,
      "eval_runtime": 11.8268,
      "eval_samples_per_second": 10.907,
      "eval_steps_per_second": 1.437,
      "step": 36
    },
    {
      "epoch": 0.24342105263157895,
      "grad_norm": 1.5328569412231445,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.4975,
      "step": 37
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.337712287902832,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.9457,
      "step": 38
    },
    {
      "epoch": 0.2565789473684211,
      "grad_norm": 1.5058380365371704,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.1068,
      "step": 39
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.2327181100845337,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.9551,
      "step": 40
    },
    {
      "epoch": 0.26973684210526316,
      "grad_norm": 1.3438504934310913,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.6813,
      "step": 41
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 1.286442518234253,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.7649,
      "step": 42
    },
    {
      "epoch": 0.28289473684210525,
      "grad_norm": 1.1970598697662354,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.7959,
      "step": 43
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 1.364403486251831,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.7091,
      "step": 44
    },
    {
      "epoch": 0.29605263157894735,
      "grad_norm": 1.4657368659973145,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.1348,
      "step": 45
    },
    {
      "epoch": 0.29605263157894735,
      "eval_loss": 1.3640621900558472,
      "eval_runtime": 11.8242,
      "eval_samples_per_second": 10.91,
      "eval_steps_per_second": 1.438,
      "step": 45
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 1.2050580978393555,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.9441,
      "step": 46
    },
    {
      "epoch": 0.3092105263157895,
      "grad_norm": 1.3498376607894897,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.3152,
      "step": 47
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.2633366584777832,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.8021,
      "step": 48
    },
    {
      "epoch": 0.3223684210526316,
      "grad_norm": 1.2623326778411865,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.7536,
      "step": 49
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 1.339303970336914,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.6516,
      "step": 50
    },
    {
      "epoch": 0.3355263157894737,
      "grad_norm": 1.2920477390289307,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.7238,
      "step": 51
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 1.2608016729354858,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.0049,
      "step": 52
    },
    {
      "epoch": 0.34868421052631576,
      "grad_norm": 1.2182189226150513,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.3852,
      "step": 53
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 1.3804212808609009,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.1034,
      "step": 54
    },
    {
      "epoch": 0.35526315789473684,
      "eval_loss": 1.3594610691070557,
      "eval_runtime": 11.8459,
      "eval_samples_per_second": 10.89,
      "eval_steps_per_second": 1.435,
      "step": 54
    },
    {
      "epoch": 0.3618421052631579,
      "grad_norm": 1.2306569814682007,
      "learning_rate": 5e-05,
      "loss": 2.7315,
      "step": 55
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 1.3036292791366577,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.7876,
      "step": 56
    },
    {
      "epoch": 0.375,
      "grad_norm": 1.4032416343688965,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.3895,
      "step": 57
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 1.294589638710022,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.7449,
      "step": 58
    },
    {
      "epoch": 0.3881578947368421,
      "grad_norm": 1.363023042678833,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.85,
      "step": 59
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 1.122846007347107,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.03,
      "step": 60
    },
    {
      "epoch": 0.40131578947368424,
      "grad_norm": 1.334709882736206,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.4658,
      "step": 61
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 1.2854145765304565,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.5487,
      "step": 62
    },
    {
      "epoch": 0.4144736842105263,
      "grad_norm": 1.2864726781845093,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.958,
      "step": 63
    },
    {
      "epoch": 0.4144736842105263,
      "eval_loss": 1.357467770576477,
      "eval_runtime": 11.8191,
      "eval_samples_per_second": 10.915,
      "eval_steps_per_second": 1.438,
      "step": 63
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.4652857780456543,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.7546,
      "step": 64
    },
    {
      "epoch": 0.4276315789473684,
      "grad_norm": 1.1192301511764526,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.5874,
      "step": 65
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 1.2290575504302979,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.612,
      "step": 66
    },
    {
      "epoch": 0.4407894736842105,
      "grad_norm": 1.116075038909912,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.2593,
      "step": 67
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 1.1417109966278076,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.7438,
      "step": 68
    },
    {
      "epoch": 0.45394736842105265,
      "grad_norm": 1.0783743858337402,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.5557,
      "step": 69
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 1.123271107673645,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.4786,
      "step": 70
    },
    {
      "epoch": 0.46710526315789475,
      "grad_norm": 1.5043975114822388,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.8537,
      "step": 71
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 1.3817392587661743,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.5979,
      "step": 72
    },
    {
      "epoch": 0.47368421052631576,
      "eval_loss": 1.3560445308685303,
      "eval_runtime": 11.8334,
      "eval_samples_per_second": 10.901,
      "eval_steps_per_second": 1.437,
      "step": 72
    },
    {
      "epoch": 0.48026315789473684,
      "grad_norm": 1.221788763999939,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.7083,
      "step": 73
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 1.255094051361084,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.736,
      "step": 74
    },
    {
      "epoch": 0.4934210526315789,
      "grad_norm": 1.0735032558441162,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.1575,
      "step": 75
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.1724132299423218,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.919,
      "step": 76
    },
    {
      "epoch": 0.506578947368421,
      "grad_norm": 1.2114452123641968,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.6806,
      "step": 77
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 1.2915575504302979,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.6593,
      "step": 78
    },
    {
      "epoch": 0.5197368421052632,
      "grad_norm": 1.0405056476593018,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.988,
      "step": 79
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.0308349132537842,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.5931,
      "step": 80
    },
    {
      "epoch": 0.5328947368421053,
      "grad_norm": 1.2563862800598145,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.2365,
      "step": 81
    },
    {
      "epoch": 0.5328947368421053,
      "eval_loss": 1.3557542562484741,
      "eval_runtime": 11.8127,
      "eval_samples_per_second": 10.92,
      "eval_steps_per_second": 1.439,
      "step": 81
    },
    {
      "epoch": 0.5394736842105263,
      "grad_norm": 1.1508125066757202,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.4557,
      "step": 82
    },
    {
      "epoch": 0.5460526315789473,
      "grad_norm": 1.2678468227386475,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.6471,
      "step": 83
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 1.2328356504440308,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.8384,
      "step": 84
    },
    {
      "epoch": 0.5592105263157895,
      "grad_norm": 1.3108208179473877,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.5576,
      "step": 85
    },
    {
      "epoch": 0.5657894736842105,
      "grad_norm": 1.195551872253418,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.7296,
      "step": 86
    },
    {
      "epoch": 0.5723684210526315,
      "grad_norm": 1.2313472032546997,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.6876,
      "step": 87
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 1.1951091289520264,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.7786,
      "step": 88
    },
    {
      "epoch": 0.5855263157894737,
      "grad_norm": 1.2675416469573975,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.7165,
      "step": 89
    },
    {
      "epoch": 0.5921052631578947,
      "grad_norm": 1.135334849357605,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.7501,
      "step": 90
    },
    {
      "epoch": 0.5921052631578947,
      "eval_loss": 1.355621337890625,
      "eval_runtime": 11.818,
      "eval_samples_per_second": 10.916,
      "eval_steps_per_second": 1.438,
      "step": 90
    },
    {
      "epoch": 0.5986842105263158,
      "grad_norm": 1.2185972929000854,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.348,
      "step": 91
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 1.2187449932098389,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.9864,
      "step": 92
    },
    {
      "epoch": 0.6118421052631579,
      "grad_norm": 1.176838755607605,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.9543,
      "step": 93
    },
    {
      "epoch": 0.618421052631579,
      "grad_norm": 1.1729670763015747,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.7812,
      "step": 94
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.0939475297927856,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.7562,
      "step": 95
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 1.284177541732788,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.7301,
      "step": 96
    },
    {
      "epoch": 0.6381578947368421,
      "grad_norm": 1.2222950458526611,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.3219,
      "step": 97
    },
    {
      "epoch": 0.6447368421052632,
      "grad_norm": 1.2235487699508667,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.538,
      "step": 98
    },
    {
      "epoch": 0.6513157894736842,
      "grad_norm": 1.1274579763412476,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.5219,
      "step": 99
    },
    {
      "epoch": 0.6513157894736842,
      "eval_loss": 1.3554550409317017,
      "eval_runtime": 11.828,
      "eval_samples_per_second": 10.906,
      "eval_steps_per_second": 1.437,
      "step": 99
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 1.147770643234253,
      "learning_rate": 0.0,
      "loss": 2.2666,
      "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
}