{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020751193193608634,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020751193193608634,
      "grad_norm": 1.4039883613586426,
      "learning_rate": 1e-05,
      "loss": 2.1244,
      "step": 1
    },
    {
      "epoch": 0.00020751193193608634,
      "eval_loss": 2.2763936519622803,
      "eval_runtime": 237.6501,
      "eval_samples_per_second": 17.076,
      "eval_steps_per_second": 2.138,
      "step": 1
    },
    {
      "epoch": 0.0004150238638721727,
      "grad_norm": 1.3511576652526855,
      "learning_rate": 2e-05,
      "loss": 2.3025,
      "step": 2
    },
    {
      "epoch": 0.0006225357958082589,
      "grad_norm": 1.3691860437393188,
      "learning_rate": 3e-05,
      "loss": 2.0968,
      "step": 3
    },
    {
      "epoch": 0.0008300477277443454,
      "grad_norm": 1.2978947162628174,
      "learning_rate": 4e-05,
      "loss": 1.891,
      "step": 4
    },
    {
      "epoch": 0.0010375596596804316,
      "grad_norm": 1.3064836263656616,
      "learning_rate": 5e-05,
      "loss": 2.0951,
      "step": 5
    },
    {
      "epoch": 0.0012450715916165179,
      "grad_norm": 1.510711431503296,
      "learning_rate": 6e-05,
      "loss": 2.1635,
      "step": 6
    },
    {
      "epoch": 0.0014525835235526042,
      "grad_norm": 1.724186897277832,
      "learning_rate": 7e-05,
      "loss": 2.3924,
      "step": 7
    },
    {
      "epoch": 0.0016600954554886907,
      "grad_norm": 1.3614786863327026,
      "learning_rate": 8e-05,
      "loss": 2.1578,
      "step": 8
    },
    {
      "epoch": 0.001867607387424777,
      "grad_norm": 1.291449785232544,
      "learning_rate": 9e-05,
      "loss": 2.0637,
      "step": 9
    },
    {
      "epoch": 0.001867607387424777,
      "eval_loss": 1.9984328746795654,
      "eval_runtime": 236.7978,
      "eval_samples_per_second": 17.137,
      "eval_steps_per_second": 2.145,
      "step": 9
    },
    {
      "epoch": 0.002075119319360863,
      "grad_norm": 1.0605844259262085,
      "learning_rate": 0.0001,
      "loss": 1.895,
      "step": 10
    },
    {
      "epoch": 0.0022826312512969496,
      "grad_norm": 1.6267553567886353,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.0418,
      "step": 11
    },
    {
      "epoch": 0.0024901431832330357,
      "grad_norm": 1.5893021821975708,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.9267,
      "step": 12
    },
    {
      "epoch": 0.0026976551151691223,
      "grad_norm": 1.1723555326461792,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8826,
      "step": 13
    },
    {
      "epoch": 0.0029051670471052084,
      "grad_norm": 1.140472173690796,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.9261,
      "step": 14
    },
    {
      "epoch": 0.003112678979041295,
      "grad_norm": 1.1380834579467773,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.8419,
      "step": 15
    },
    {
      "epoch": 0.0033201909109773814,
      "grad_norm": 1.0181565284729004,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7555,
      "step": 16
    },
    {
      "epoch": 0.0035277028429134675,
      "grad_norm": 0.8560456037521362,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7858,
      "step": 17
    },
    {
      "epoch": 0.003735214774849554,
      "grad_norm": 1.1353284120559692,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7424,
      "step": 18
    },
    {
      "epoch": 0.003735214774849554,
      "eval_loss": 1.7517411708831787,
      "eval_runtime": 236.5855,
      "eval_samples_per_second": 17.152,
      "eval_steps_per_second": 2.147,
      "step": 18
    },
    {
      "epoch": 0.00394272670678564,
      "grad_norm": 1.1942611932754517,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6209,
      "step": 19
    },
    {
      "epoch": 0.004150238638721726,
      "grad_norm": 1.261995792388916,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.6995,
      "step": 20
    },
    {
      "epoch": 0.004357750570657813,
      "grad_norm": 1.0118539333343506,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.698,
      "step": 21
    },
    {
      "epoch": 0.004565262502593899,
      "grad_norm": 0.9871833920478821,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7638,
      "step": 22
    },
    {
      "epoch": 0.004772774434529985,
      "grad_norm": 1.1649303436279297,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.707,
      "step": 23
    },
    {
      "epoch": 0.0049802863664660715,
      "grad_norm": 1.3631136417388916,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9811,
      "step": 24
    },
    {
      "epoch": 0.005187798298402158,
      "grad_norm": 1.030550479888916,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.7537,
      "step": 25
    },
    {
      "epoch": 0.0053953102303382445,
      "grad_norm": 0.9769826531410217,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.6765,
      "step": 26
    },
    {
      "epoch": 0.005602822162274331,
      "grad_norm": 0.9318863749504089,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.7317,
      "step": 27
    },
    {
      "epoch": 0.005602822162274331,
      "eval_loss": 1.6895153522491455,
      "eval_runtime": 236.6294,
      "eval_samples_per_second": 17.149,
      "eval_steps_per_second": 2.147,
      "step": 27
    },
    {
      "epoch": 0.005810334094210417,
      "grad_norm": 0.8478034734725952,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6692,
      "step": 28
    },
    {
      "epoch": 0.006017846026146504,
      "grad_norm": 0.8709442019462585,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.7439,
      "step": 29
    },
    {
      "epoch": 0.00622535795808259,
      "grad_norm": 1.0114762783050537,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.8279,
      "step": 30
    },
    {
      "epoch": 0.006432869890018676,
      "grad_norm": 0.9320862293243408,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.6338,
      "step": 31
    },
    {
      "epoch": 0.006640381821954763,
      "grad_norm": 1.1853289604187012,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.7087,
      "step": 32
    },
    {
      "epoch": 0.006847893753890849,
      "grad_norm": 1.043468713760376,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.7378,
      "step": 33
    },
    {
      "epoch": 0.007055405685826935,
      "grad_norm": 1.0408753156661987,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.667,
      "step": 34
    },
    {
      "epoch": 0.007262917617763021,
      "grad_norm": 1.1300815343856812,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.7674,
      "step": 35
    },
    {
      "epoch": 0.007470429549699108,
      "grad_norm": 0.8315098285675049,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.4602,
      "step": 36
    },
    {
      "epoch": 0.007470429549699108,
      "eval_loss": 1.6478559970855713,
      "eval_runtime": 236.6275,
      "eval_samples_per_second": 17.149,
      "eval_steps_per_second": 2.147,
      "step": 36
    },
    {
      "epoch": 0.007677941481635194,
      "grad_norm": 0.8866711854934692,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5759,
      "step": 37
    },
    {
      "epoch": 0.00788545341357128,
      "grad_norm": 0.9419971108436584,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.7353,
      "step": 38
    },
    {
      "epoch": 0.008092965345507366,
      "grad_norm": 0.9975749254226685,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.6594,
      "step": 39
    },
    {
      "epoch": 0.008300477277443452,
      "grad_norm": 1.215224266052246,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.7351,
      "step": 40
    },
    {
      "epoch": 0.008507989209379539,
      "grad_norm": 0.988749623298645,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.6431,
      "step": 41
    },
    {
      "epoch": 0.008715501141315626,
      "grad_norm": 1.409287929534912,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9033,
      "step": 42
    },
    {
      "epoch": 0.008923013073251712,
      "grad_norm": 1.0360569953918457,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.5189,
      "step": 43
    },
    {
      "epoch": 0.009130525005187799,
      "grad_norm": 1.1524792909622192,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.5597,
      "step": 44
    },
    {
      "epoch": 0.009338036937123885,
      "grad_norm": 0.8985092639923096,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5392,
      "step": 45
    },
    {
      "epoch": 0.009338036937123885,
      "eval_loss": 1.6274610757827759,
      "eval_runtime": 236.6209,
      "eval_samples_per_second": 17.15,
      "eval_steps_per_second": 2.147,
      "step": 45
    },
    {
      "epoch": 0.00954554886905997,
      "grad_norm": 0.9461812376976013,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.801,
      "step": 46
    },
    {
      "epoch": 0.009753060800996057,
      "grad_norm": 1.0675175189971924,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.6215,
      "step": 47
    },
    {
      "epoch": 0.009960572732932143,
      "grad_norm": 0.9971215128898621,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.791,
      "step": 48
    },
    {
      "epoch": 0.01016808466486823,
      "grad_norm": 0.9369943141937256,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.5656,
      "step": 49
    },
    {
      "epoch": 0.010375596596804317,
      "grad_norm": 1.0417509078979492,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.7613,
      "step": 50
    },
    {
      "epoch": 0.010583108528740403,
      "grad_norm": 1.0997047424316406,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.5435,
      "step": 51
    },
    {
      "epoch": 0.010790620460676489,
      "grad_norm": 0.8529770374298096,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.7494,
      "step": 52
    },
    {
      "epoch": 0.010998132392612575,
      "grad_norm": 1.1557135581970215,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.6652,
      "step": 53
    },
    {
      "epoch": 0.011205644324548661,
      "grad_norm": 0.973082959651947,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.6062,
      "step": 54
    },
    {
      "epoch": 0.011205644324548661,
      "eval_loss": 1.616413950920105,
      "eval_runtime": 236.5946,
      "eval_samples_per_second": 17.152,
      "eval_steps_per_second": 2.147,
      "step": 54
    },
    {
      "epoch": 0.011413156256484747,
      "grad_norm": 0.811787486076355,
      "learning_rate": 5e-05,
      "loss": 1.5222,
      "step": 55
    },
    {
      "epoch": 0.011620668188420833,
      "grad_norm": 1.0629674196243286,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.6022,
      "step": 56
    },
    {
      "epoch": 0.011828180120356921,
      "grad_norm": 1.2176127433776855,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.6937,
      "step": 57
    },
    {
      "epoch": 0.012035692052293007,
      "grad_norm": 1.077357292175293,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.6371,
      "step": 58
    },
    {
      "epoch": 0.012243203984229093,
      "grad_norm": 1.0355650186538696,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.6118,
      "step": 59
    },
    {
      "epoch": 0.01245071591616518,
      "grad_norm": 1.0891892910003662,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6164,
      "step": 60
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": 0.7828339338302612,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5463,
      "step": 61
    },
    {
      "epoch": 0.012865739780037352,
      "grad_norm": 0.8645059466362,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.6327,
      "step": 62
    },
    {
      "epoch": 0.013073251711973438,
      "grad_norm": 1.0416123867034912,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.6092,
      "step": 63
    },
    {
      "epoch": 0.013073251711973438,
      "eval_loss": 1.6092809438705444,
      "eval_runtime": 236.5411,
      "eval_samples_per_second": 17.156,
      "eval_steps_per_second": 2.148,
      "step": 63
    },
    {
      "epoch": 0.013280763643909526,
      "grad_norm": 1.1945778131484985,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7276,
      "step": 64
    },
    {
      "epoch": 0.013488275575845612,
      "grad_norm": 0.8667076230049133,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6485,
      "step": 65
    },
    {
      "epoch": 0.013695787507781698,
      "grad_norm": 0.9858114719390869,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.5364,
      "step": 66
    },
    {
      "epoch": 0.013903299439717784,
      "grad_norm": 0.9003591537475586,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4869,
      "step": 67
    },
    {
      "epoch": 0.01411081137165387,
      "grad_norm": 0.9594292640686035,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.7525,
      "step": 68
    },
    {
      "epoch": 0.014318323303589956,
      "grad_norm": 0.7268180847167969,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.59,
      "step": 69
    },
    {
      "epoch": 0.014525835235526042,
      "grad_norm": 0.7998595833778381,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7044,
      "step": 70
    },
    {
      "epoch": 0.014733347167462128,
      "grad_norm": 0.9934815168380737,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.7302,
      "step": 71
    },
    {
      "epoch": 0.014940859099398216,
      "grad_norm": 0.9405103921890259,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.5256,
      "step": 72
    },
    {
      "epoch": 0.014940859099398216,
      "eval_loss": 1.6017986536026,
      "eval_runtime": 236.6572,
      "eval_samples_per_second": 17.147,
      "eval_steps_per_second": 2.147,
      "step": 72
    },
    {
      "epoch": 0.015148371031334302,
      "grad_norm": 0.6856156587600708,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.6503,
      "step": 73
    },
    {
      "epoch": 0.015355882963270388,
      "grad_norm": 0.773373007774353,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.2891,
      "step": 74
    },
    {
      "epoch": 0.015563394895206474,
      "grad_norm": 1.2244831323623657,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.7002,
      "step": 75
    },
    {
      "epoch": 0.01577090682714256,
      "grad_norm": 1.1597203016281128,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.5769,
      "step": 76
    },
    {
      "epoch": 0.01597841875907865,
      "grad_norm": 1.0011721849441528,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.6495,
      "step": 77
    },
    {
      "epoch": 0.016185930691014733,
      "grad_norm": 0.9478533864021301,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5925,
      "step": 78
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 0.9030246734619141,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.344,
      "step": 79
    },
    {
      "epoch": 0.016600954554886905,
      "grad_norm": 0.9802048802375793,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.565,
      "step": 80
    },
    {
      "epoch": 0.016808466486822993,
      "grad_norm": 0.9481618404388428,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.5097,
      "step": 81
    },
    {
      "epoch": 0.016808466486822993,
      "eval_loss": 1.5992255210876465,
      "eval_runtime": 236.6548,
      "eval_samples_per_second": 17.147,
      "eval_steps_per_second": 2.147,
      "step": 81
    },
    {
      "epoch": 0.017015978418759077,
      "grad_norm": 0.9746353626251221,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.6898,
      "step": 82
    },
    {
      "epoch": 0.017223490350695165,
      "grad_norm": 0.8424410223960876,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.635,
      "step": 83
    },
    {
      "epoch": 0.017431002282631253,
      "grad_norm": 0.9099277257919312,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.6312,
      "step": 84
    },
    {
      "epoch": 0.017638514214567337,
      "grad_norm": 1.0718952417373657,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.4818,
      "step": 85
    },
    {
      "epoch": 0.017846026146503425,
      "grad_norm": 0.802363932132721,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.0126,
      "step": 86
    },
    {
      "epoch": 0.01805353807843951,
      "grad_norm": 0.9490446448326111,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5363,
      "step": 87
    },
    {
      "epoch": 0.018261050010375597,
      "grad_norm": 1.1205114126205444,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6728,
      "step": 88
    },
    {
      "epoch": 0.01846856194231168,
      "grad_norm": 0.920365035533905,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.4411,
      "step": 89
    },
    {
      "epoch": 0.01867607387424777,
      "grad_norm": 1.0277124643325806,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.6717,
      "step": 90
    },
    {
      "epoch": 0.01867607387424777,
      "eval_loss": 1.5978589057922363,
      "eval_runtime": 236.7157,
      "eval_samples_per_second": 17.143,
      "eval_steps_per_second": 2.146,
      "step": 90
    },
    {
      "epoch": 0.018883585806183857,
      "grad_norm": 0.8812714219093323,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.5921,
      "step": 91
    },
    {
      "epoch": 0.01909109773811994,
      "grad_norm": 0.7979960441589355,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.548,
      "step": 92
    },
    {
      "epoch": 0.01929860967005603,
      "grad_norm": 0.9867696166038513,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.5016,
      "step": 93
    },
    {
      "epoch": 0.019506121601992114,
      "grad_norm": 1.1134464740753174,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.4178,
      "step": 94
    },
    {
      "epoch": 0.0197136335339282,
      "grad_norm": 0.9245745539665222,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.5979,
      "step": 95
    },
    {
      "epoch": 0.019921145465864286,
      "grad_norm": 0.90775066614151,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.4747,
      "step": 96
    },
    {
      "epoch": 0.020128657397800374,
      "grad_norm": 0.845889151096344,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.4275,
      "step": 97
    },
    {
      "epoch": 0.02033616932973646,
      "grad_norm": 1.0823585987091064,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.5404,
      "step": 98
    },
    {
      "epoch": 0.020543681261672546,
      "grad_norm": 0.9024697542190552,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.7078,
      "step": 99
    },
    {
      "epoch": 0.020543681261672546,
      "eval_loss": 1.5974575281143188,
      "eval_runtime": 236.5477,
      "eval_samples_per_second": 17.155,
      "eval_steps_per_second": 2.148,
      "step": 99
    },
    {
      "epoch": 0.020751193193608634,
      "grad_norm": 1.1790575981140137,
      "learning_rate": 0.0,
      "loss": 1.6402,
      "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": 8.19785448334295e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}