{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3412969283276451,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034129692832764505,
      "grad_norm": 2.079373598098755,
      "learning_rate": 1e-05,
      "loss": 2.5868,
      "step": 1
    },
    {
      "epoch": 0.0034129692832764505,
      "eval_loss": 2.7036800384521484,
      "eval_runtime": 27.3169,
      "eval_samples_per_second": 9.042,
      "eval_steps_per_second": 1.135,
      "step": 1
    },
    {
      "epoch": 0.006825938566552901,
      "grad_norm": 2.0402865409851074,
      "learning_rate": 2e-05,
      "loss": 2.4651,
      "step": 2
    },
    {
      "epoch": 0.010238907849829351,
      "grad_norm": 2.076801061630249,
      "learning_rate": 3e-05,
      "loss": 2.8165,
      "step": 3
    },
    {
      "epoch": 0.013651877133105802,
      "grad_norm": 1.6631640195846558,
      "learning_rate": 4e-05,
      "loss": 2.2195,
      "step": 4
    },
    {
      "epoch": 0.017064846416382253,
      "grad_norm": 2.028144598007202,
      "learning_rate": 5e-05,
      "loss": 2.6315,
      "step": 5
    },
    {
      "epoch": 0.020477815699658702,
      "grad_norm": 1.8099565505981445,
      "learning_rate": 6e-05,
      "loss": 2.4778,
      "step": 6
    },
    {
      "epoch": 0.023890784982935155,
      "grad_norm": 1.6257520914077759,
      "learning_rate": 7e-05,
      "loss": 2.3758,
      "step": 7
    },
    {
      "epoch": 0.027303754266211604,
      "grad_norm": 1.7331541776657104,
      "learning_rate": 8e-05,
      "loss": 2.559,
      "step": 8
    },
    {
      "epoch": 0.030716723549488054,
      "grad_norm": 1.7911136150360107,
      "learning_rate": 9e-05,
      "loss": 2.608,
      "step": 9
    },
    {
      "epoch": 0.030716723549488054,
      "eval_loss": 2.539431571960449,
      "eval_runtime": 26.8662,
      "eval_samples_per_second": 9.194,
      "eval_steps_per_second": 1.154,
      "step": 9
    },
    {
      "epoch": 0.034129692832764506,
      "grad_norm": 2.2013070583343506,
      "learning_rate": 0.0001,
      "loss": 2.531,
      "step": 10
    },
    {
      "epoch": 0.03754266211604096,
      "grad_norm": 1.7735546827316284,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.4787,
      "step": 11
    },
    {
      "epoch": 0.040955631399317405,
      "grad_norm": 1.930301308631897,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.3883,
      "step": 12
    },
    {
      "epoch": 0.04436860068259386,
      "grad_norm": 1.7519022226333618,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.4389,
      "step": 13
    },
    {
      "epoch": 0.04778156996587031,
      "grad_norm": 1.6566658020019531,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.3203,
      "step": 14
    },
    {
      "epoch": 0.051194539249146756,
      "grad_norm": 1.966662049293518,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.5567,
      "step": 15
    },
    {
      "epoch": 0.05460750853242321,
      "grad_norm": 1.885459303855896,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.4018,
      "step": 16
    },
    {
      "epoch": 0.05802047781569966,
      "grad_norm": 1.802748203277588,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.482,
      "step": 17
    },
    {
      "epoch": 0.06143344709897611,
      "grad_norm": 1.6314976215362549,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.3482,
      "step": 18
    },
    {
      "epoch": 0.06143344709897611,
      "eval_loss": 2.3051397800445557,
      "eval_runtime": 26.9205,
      "eval_samples_per_second": 9.175,
      "eval_steps_per_second": 1.152,
      "step": 18
    },
    {
      "epoch": 0.06484641638225255,
      "grad_norm": 1.987666130065918,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0318,
      "step": 19
    },
    {
      "epoch": 0.06825938566552901,
      "grad_norm": 1.8698854446411133,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.4697,
      "step": 20
    },
    {
      "epoch": 0.07167235494880546,
      "grad_norm": 1.8349987268447876,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2409,
      "step": 21
    },
    {
      "epoch": 0.07508532423208192,
      "grad_norm": 1.4180082082748413,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.1531,
      "step": 22
    },
    {
      "epoch": 0.07849829351535836,
      "grad_norm": 1.8734818696975708,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.226,
      "step": 23
    },
    {
      "epoch": 0.08191126279863481,
      "grad_norm": 1.8889721632003784,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.2444,
      "step": 24
    },
    {
      "epoch": 0.08532423208191127,
      "grad_norm": 2.4509947299957275,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.5033,
      "step": 25
    },
    {
      "epoch": 0.08873720136518772,
      "grad_norm": 2.0969078540802,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.135,
      "step": 26
    },
    {
      "epoch": 0.09215017064846416,
      "grad_norm": 2.146559000015259,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.3215,
      "step": 27
    },
    {
      "epoch": 0.09215017064846416,
      "eval_loss": 2.1996543407440186,
      "eval_runtime": 26.9102,
      "eval_samples_per_second": 9.179,
      "eval_steps_per_second": 1.152,
      "step": 27
    },
    {
      "epoch": 0.09556313993174062,
      "grad_norm": 2.174332857131958,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.081,
      "step": 28
    },
    {
      "epoch": 0.09897610921501707,
      "grad_norm": 2.005492687225342,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.2362,
      "step": 29
    },
    {
      "epoch": 0.10238907849829351,
      "grad_norm": 2.333951234817505,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.0891,
      "step": 30
    },
    {
      "epoch": 0.10580204778156997,
      "grad_norm": 1.9656646251678467,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.2006,
      "step": 31
    },
    {
      "epoch": 0.10921501706484642,
      "grad_norm": 1.2520757913589478,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.1468,
      "step": 32
    },
    {
      "epoch": 0.11262798634812286,
      "grad_norm": 1.8385062217712402,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.2589,
      "step": 33
    },
    {
      "epoch": 0.11604095563139932,
      "grad_norm": 1.7657023668289185,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.16,
      "step": 34
    },
    {
      "epoch": 0.11945392491467577,
      "grad_norm": 1.7102572917938232,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3067,
      "step": 35
    },
    {
      "epoch": 0.12286689419795221,
      "grad_norm": 1.650964379310608,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.3077,
      "step": 36
    },
    {
      "epoch": 0.12286689419795221,
      "eval_loss": 2.137897491455078,
      "eval_runtime": 26.9438,
      "eval_samples_per_second": 9.167,
      "eval_steps_per_second": 1.151,
      "step": 36
    },
    {
      "epoch": 0.12627986348122866,
      "grad_norm": 1.6150387525558472,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8981,
      "step": 37
    },
    {
      "epoch": 0.1296928327645051,
      "grad_norm": 1.7720524072647095,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.2199,
      "step": 38
    },
    {
      "epoch": 0.13310580204778158,
      "grad_norm": 1.5529892444610596,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.9775,
      "step": 39
    },
    {
      "epoch": 0.13651877133105803,
      "grad_norm": 1.651555061340332,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2185,
      "step": 40
    },
    {
      "epoch": 0.13993174061433447,
      "grad_norm": 1.7184780836105347,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.2563,
      "step": 41
    },
    {
      "epoch": 0.14334470989761092,
      "grad_norm": 1.4973491430282593,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.2334,
      "step": 42
    },
    {
      "epoch": 0.14675767918088736,
      "grad_norm": 1.6694294214248657,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.0514,
      "step": 43
    },
    {
      "epoch": 0.15017064846416384,
      "grad_norm": 1.5407490730285645,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.0227,
      "step": 44
    },
    {
      "epoch": 0.15358361774744028,
      "grad_norm": 1.580428957939148,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0356,
      "step": 45
    },
    {
      "epoch": 0.15358361774744028,
      "eval_loss": 2.1069095134735107,
      "eval_runtime": 26.7956,
      "eval_samples_per_second": 9.218,
      "eval_steps_per_second": 1.157,
      "step": 45
    },
    {
      "epoch": 0.15699658703071673,
      "grad_norm": 1.7561475038528442,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9107,
      "step": 46
    },
    {
      "epoch": 0.16040955631399317,
      "grad_norm": 1.1351089477539062,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.9218,
      "step": 47
    },
    {
      "epoch": 0.16382252559726962,
      "grad_norm": 1.3753199577331543,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.0367,
      "step": 48
    },
    {
      "epoch": 0.16723549488054607,
      "grad_norm": 1.5735177993774414,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.1999,
      "step": 49
    },
    {
      "epoch": 0.17064846416382254,
      "grad_norm": 1.6417649984359741,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.8783,
      "step": 50
    },
    {
      "epoch": 0.17406143344709898,
      "grad_norm": 1.2222497463226318,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.9914,
      "step": 51
    },
    {
      "epoch": 0.17747440273037543,
      "grad_norm": 1.1959785223007202,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.9126,
      "step": 52
    },
    {
      "epoch": 0.18088737201365188,
      "grad_norm": 1.8517333269119263,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.3288,
      "step": 53
    },
    {
      "epoch": 0.18430034129692832,
      "grad_norm": 1.3594970703125,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.9605,
      "step": 54
    },
    {
      "epoch": 0.18430034129692832,
      "eval_loss": 2.094463586807251,
      "eval_runtime": 26.9493,
      "eval_samples_per_second": 9.165,
      "eval_steps_per_second": 1.15,
      "step": 54
    },
    {
      "epoch": 0.18771331058020477,
      "grad_norm": 1.6013035774230957,
      "learning_rate": 5e-05,
      "loss": 2.165,
      "step": 55
    },
    {
      "epoch": 0.19112627986348124,
      "grad_norm": 1.512694239616394,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.0015,
      "step": 56
    },
    {
      "epoch": 0.1945392491467577,
      "grad_norm": 1.7241512537002563,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.1202,
      "step": 57
    },
    {
      "epoch": 0.19795221843003413,
      "grad_norm": 1.6105077266693115,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.9934,
      "step": 58
    },
    {
      "epoch": 0.20136518771331058,
      "grad_norm": 1.646561861038208,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2339,
      "step": 59
    },
    {
      "epoch": 0.20477815699658702,
      "grad_norm": 2.0392093658447266,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.0267,
      "step": 60
    },
    {
      "epoch": 0.20819112627986347,
      "grad_norm": 1.7951915264129639,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.8352,
      "step": 61
    },
    {
      "epoch": 0.21160409556313994,
      "grad_norm": 1.5555702447891235,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.9366,
      "step": 62
    },
    {
      "epoch": 0.2150170648464164,
      "grad_norm": 1.3045828342437744,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8585,
      "step": 63
    },
    {
      "epoch": 0.2150170648464164,
      "eval_loss": 2.084052085876465,
      "eval_runtime": 26.9697,
      "eval_samples_per_second": 9.158,
      "eval_steps_per_second": 1.149,
      "step": 63
    },
    {
      "epoch": 0.21843003412969283,
      "grad_norm": 1.4040144681930542,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.0018,
      "step": 64
    },
    {
      "epoch": 0.22184300341296928,
      "grad_norm": 1.5868518352508545,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.2824,
      "step": 65
    },
    {
      "epoch": 0.22525597269624573,
      "grad_norm": 1.5335170030593872,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.0454,
      "step": 66
    },
    {
      "epoch": 0.22866894197952217,
      "grad_norm": 1.497534990310669,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.0806,
      "step": 67
    },
    {
      "epoch": 0.23208191126279865,
      "grad_norm": 1.6238112449645996,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1491,
      "step": 68
    },
    {
      "epoch": 0.2354948805460751,
      "grad_norm": 1.7866332530975342,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8769,
      "step": 69
    },
    {
      "epoch": 0.23890784982935154,
      "grad_norm": 1.6166279315948486,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1569,
      "step": 70
    },
    {
      "epoch": 0.24232081911262798,
      "grad_norm": 1.6272120475769043,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.1745,
      "step": 71
    },
    {
      "epoch": 0.24573378839590443,
      "grad_norm": 1.530362844467163,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.2734,
      "step": 72
    },
    {
      "epoch": 0.24573378839590443,
      "eval_loss": 2.0737767219543457,
      "eval_runtime": 26.9193,
      "eval_samples_per_second": 9.176,
      "eval_steps_per_second": 1.152,
      "step": 72
    },
    {
      "epoch": 0.24914675767918087,
      "grad_norm": 1.415154218673706,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0388,
      "step": 73
    },
    {
      "epoch": 0.2525597269624573,
      "grad_norm": 1.8105053901672363,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.9757,
      "step": 74
    },
    {
      "epoch": 0.25597269624573377,
      "grad_norm": 1.4281625747680664,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.9339,
      "step": 75
    },
    {
      "epoch": 0.2593856655290102,
      "grad_norm": 1.4440678358078003,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.1059,
      "step": 76
    },
    {
      "epoch": 0.2627986348122867,
      "grad_norm": 1.389583706855774,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.8714,
      "step": 77
    },
    {
      "epoch": 0.26621160409556316,
      "grad_norm": 1.7297189235687256,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.2086,
      "step": 78
    },
    {
      "epoch": 0.2696245733788396,
      "grad_norm": 1.7446703910827637,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.127,
      "step": 79
    },
    {
      "epoch": 0.27303754266211605,
      "grad_norm": 1.3824653625488281,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.0338,
      "step": 80
    },
    {
      "epoch": 0.2764505119453925,
      "grad_norm": 1.4320341348648071,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.0411,
      "step": 81
    },
    {
      "epoch": 0.2764505119453925,
      "eval_loss": 2.069126605987549,
      "eval_runtime": 26.9081,
      "eval_samples_per_second": 9.179,
      "eval_steps_per_second": 1.152,
      "step": 81
    },
    {
      "epoch": 0.27986348122866894,
      "grad_norm": 1.480116844177246,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.0643,
      "step": 82
    },
    {
      "epoch": 0.2832764505119454,
      "grad_norm": 1.8999114036560059,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.157,
      "step": 83
    },
    {
      "epoch": 0.28668941979522183,
      "grad_norm": 1.308530330657959,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7852,
      "step": 84
    },
    {
      "epoch": 0.2901023890784983,
      "grad_norm": 1.470007300376892,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.0305,
      "step": 85
    },
    {
      "epoch": 0.2935153583617747,
      "grad_norm": 1.597455620765686,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.943,
      "step": 86
    },
    {
      "epoch": 0.29692832764505117,
      "grad_norm": 1.6729841232299805,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.1409,
      "step": 87
    },
    {
      "epoch": 0.3003412969283277,
      "grad_norm": 1.3991917371749878,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.7859,
      "step": 88
    },
    {
      "epoch": 0.3037542662116041,
      "grad_norm": 2.0168936252593994,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.8601,
      "step": 89
    },
    {
      "epoch": 0.30716723549488056,
      "grad_norm": 1.3044103384017944,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.905,
      "step": 90
    },
    {
      "epoch": 0.30716723549488056,
      "eval_loss": 2.0664398670196533,
      "eval_runtime": 26.9322,
      "eval_samples_per_second": 9.171,
      "eval_steps_per_second": 1.151,
      "step": 90
    },
    {
      "epoch": 0.310580204778157,
      "grad_norm": 1.8602319955825806,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0407,
      "step": 91
    },
    {
      "epoch": 0.31399317406143346,
      "grad_norm": 1.766486406326294,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1698,
      "step": 92
    },
    {
      "epoch": 0.3174061433447099,
      "grad_norm": 1.5754814147949219,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.9333,
      "step": 93
    },
    {
      "epoch": 0.32081911262798635,
      "grad_norm": 1.565163493156433,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.0126,
      "step": 94
    },
    {
      "epoch": 0.3242320819112628,
      "grad_norm": 1.5636179447174072,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.9294,
      "step": 95
    },
    {
      "epoch": 0.32764505119453924,
      "grad_norm": 1.5645039081573486,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.9164,
      "step": 96
    },
    {
      "epoch": 0.3310580204778157,
      "grad_norm": 1.7887978553771973,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.1109,
      "step": 97
    },
    {
      "epoch": 0.33447098976109213,
      "grad_norm": 1.5961296558380127,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.1222,
      "step": 98
    },
    {
      "epoch": 0.3378839590443686,
      "grad_norm": 1.6942273378372192,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.1367,
      "step": 99
    },
    {
      "epoch": 0.3378839590443686,
      "eval_loss": 2.0657413005828857,
      "eval_runtime": 26.9482,
      "eval_samples_per_second": 9.166,
      "eval_steps_per_second": 1.15,
      "step": 99
    },
    {
      "epoch": 0.3412969283276451,
      "grad_norm": 1.4741626977920532,
      "learning_rate": 0.0,
      "loss": 2.0636,
      "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": 7.56725029231657e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}