{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14903129657228018,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014903129657228018,
      "grad_norm": 2.0342986583709717,
      "learning_rate": 1e-05,
      "loss": 3.4859,
      "step": 1
    },
    {
      "epoch": 0.0014903129657228018,
      "eval_loss": 3.4842216968536377,
      "eval_runtime": 3.0911,
      "eval_samples_per_second": 182.782,
      "eval_steps_per_second": 22.969,
      "step": 1
    },
    {
      "epoch": 0.0029806259314456036,
      "grad_norm": 1.7465375661849976,
      "learning_rate": 2e-05,
      "loss": 3.4165,
      "step": 2
    },
    {
      "epoch": 0.004470938897168405,
      "grad_norm": 1.9989283084869385,
      "learning_rate": 3e-05,
      "loss": 3.4885,
      "step": 3
    },
    {
      "epoch": 0.005961251862891207,
      "grad_norm": 1.7901273965835571,
      "learning_rate": 4e-05,
      "loss": 3.388,
      "step": 4
    },
    {
      "epoch": 0.007451564828614009,
      "grad_norm": 1.8343313932418823,
      "learning_rate": 5e-05,
      "loss": 3.4413,
      "step": 5
    },
    {
      "epoch": 0.00894187779433681,
      "grad_norm": 1.9110901355743408,
      "learning_rate": 6e-05,
      "loss": 3.4883,
      "step": 6
    },
    {
      "epoch": 0.010432190760059613,
      "grad_norm": 1.8050709962844849,
      "learning_rate": 7e-05,
      "loss": 3.4939,
      "step": 7
    },
    {
      "epoch": 0.011922503725782414,
      "grad_norm": 1.8594285249710083,
      "learning_rate": 8e-05,
      "loss": 3.3683,
      "step": 8
    },
    {
      "epoch": 0.013412816691505217,
      "grad_norm": 2.0457093715667725,
      "learning_rate": 9e-05,
      "loss": 3.4379,
      "step": 9
    },
    {
      "epoch": 0.013412816691505217,
      "eval_loss": 3.1294145584106445,
      "eval_runtime": 2.6674,
      "eval_samples_per_second": 211.814,
      "eval_steps_per_second": 26.617,
      "step": 9
    },
    {
      "epoch": 0.014903129657228018,
      "grad_norm": 1.7745529413223267,
      "learning_rate": 0.0001,
      "loss": 3.1102,
      "step": 10
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 1.6581326723098755,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.9326,
      "step": 11
    },
    {
      "epoch": 0.01788375558867362,
      "grad_norm": 1.645290732383728,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.813,
      "step": 12
    },
    {
      "epoch": 0.019374068554396422,
      "grad_norm": 1.6816961765289307,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.6876,
      "step": 13
    },
    {
      "epoch": 0.020864381520119227,
      "grad_norm": 1.6662911176681519,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6106,
      "step": 14
    },
    {
      "epoch": 0.022354694485842028,
      "grad_norm": 1.542525053024292,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.5321,
      "step": 15
    },
    {
      "epoch": 0.02384500745156483,
      "grad_norm": 1.4631415605545044,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3101,
      "step": 16
    },
    {
      "epoch": 0.02533532041728763,
      "grad_norm": 1.5643318891525269,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2768,
      "step": 17
    },
    {
      "epoch": 0.026825633383010434,
      "grad_norm": 1.6115552186965942,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1149,
      "step": 18
    },
    {
      "epoch": 0.026825633383010434,
      "eval_loss": 2.07175612449646,
      "eval_runtime": 2.6646,
      "eval_samples_per_second": 212.036,
      "eval_steps_per_second": 26.645,
      "step": 18
    },
    {
      "epoch": 0.028315946348733235,
      "grad_norm": 1.5824073553085327,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0145,
      "step": 19
    },
    {
      "epoch": 0.029806259314456036,
      "grad_norm": 1.674318790435791,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.047,
      "step": 20
    },
    {
      "epoch": 0.03129657228017884,
      "grad_norm": 1.6824314594268799,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8464,
      "step": 21
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 1.9013198614120483,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7421,
      "step": 22
    },
    {
      "epoch": 0.03427719821162444,
      "grad_norm": 1.8643028736114502,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7526,
      "step": 23
    },
    {
      "epoch": 0.03576751117734724,
      "grad_norm": 1.9997265338897705,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6996,
      "step": 24
    },
    {
      "epoch": 0.037257824143070044,
      "grad_norm": 2.215336322784424,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6416,
      "step": 25
    },
    {
      "epoch": 0.038748137108792845,
      "grad_norm": 2.1552388668060303,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3777,
      "step": 26
    },
    {
      "epoch": 0.040238450074515646,
      "grad_norm": 2.4514808654785156,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.3392,
      "step": 27
    },
    {
      "epoch": 0.040238450074515646,
      "eval_loss": 1.2882710695266724,
      "eval_runtime": 2.7452,
      "eval_samples_per_second": 205.816,
      "eval_steps_per_second": 25.864,
      "step": 27
    },
    {
      "epoch": 0.041728763040238454,
      "grad_norm": 2.4231464862823486,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3952,
      "step": 28
    },
    {
      "epoch": 0.043219076005961254,
      "grad_norm": 2.0393948554992676,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1851,
      "step": 29
    },
    {
      "epoch": 0.044709388971684055,
      "grad_norm": 1.9575780630111694,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1068,
      "step": 30
    },
    {
      "epoch": 0.046199701937406856,
      "grad_norm": 1.8777871131896973,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.0618,
      "step": 31
    },
    {
      "epoch": 0.04769001490312966,
      "grad_norm": 2.131181001663208,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9559,
      "step": 32
    },
    {
      "epoch": 0.04918032786885246,
      "grad_norm": 2.0089690685272217,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.903,
      "step": 33
    },
    {
      "epoch": 0.05067064083457526,
      "grad_norm": 1.756807565689087,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8165,
      "step": 34
    },
    {
      "epoch": 0.05216095380029806,
      "grad_norm": 2.0079643726348877,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.8495,
      "step": 35
    },
    {
      "epoch": 0.05365126676602087,
      "grad_norm": 2.026780366897583,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.8717,
      "step": 36
    },
    {
      "epoch": 0.05365126676602087,
      "eval_loss": 0.7020303606987,
      "eval_runtime": 2.7139,
      "eval_samples_per_second": 208.188,
      "eval_steps_per_second": 26.162,
      "step": 36
    },
    {
      "epoch": 0.05514157973174367,
      "grad_norm": 2.029473304748535,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6712,
      "step": 37
    },
    {
      "epoch": 0.05663189269746647,
      "grad_norm": 1.649437427520752,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.6271,
      "step": 38
    },
    {
      "epoch": 0.05812220566318927,
      "grad_norm": 1.7296348810195923,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.714,
      "step": 39
    },
    {
      "epoch": 0.05961251862891207,
      "grad_norm": 1.313446044921875,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5392,
      "step": 40
    },
    {
      "epoch": 0.06110283159463487,
      "grad_norm": 1.2067147493362427,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.5773,
      "step": 41
    },
    {
      "epoch": 0.06259314456035768,
      "grad_norm": 1.3863986730575562,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5832,
      "step": 42
    },
    {
      "epoch": 0.06408345752608048,
      "grad_norm": 1.4204689264297485,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.4459,
      "step": 43
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 1.5218064785003662,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6278,
      "step": 44
    },
    {
      "epoch": 0.06706408345752608,
      "grad_norm": 1.6203991174697876,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4472,
      "step": 45
    },
    {
      "epoch": 0.06706408345752608,
      "eval_loss": 0.4401513338088989,
      "eval_runtime": 2.6576,
      "eval_samples_per_second": 212.596,
      "eval_steps_per_second": 26.716,
      "step": 45
    },
    {
      "epoch": 0.06855439642324888,
      "grad_norm": 1.0682734251022339,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3199,
      "step": 46
    },
    {
      "epoch": 0.07004470938897168,
      "grad_norm": 1.1575658321380615,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.3394,
      "step": 47
    },
    {
      "epoch": 0.07153502235469449,
      "grad_norm": 1.2181802988052368,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3898,
      "step": 48
    },
    {
      "epoch": 0.07302533532041729,
      "grad_norm": 1.1372705698013306,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.468,
      "step": 49
    },
    {
      "epoch": 0.07451564828614009,
      "grad_norm": 0.888025164604187,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.3541,
      "step": 50
    },
    {
      "epoch": 0.07600596125186289,
      "grad_norm": 0.8720141053199768,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.3429,
      "step": 51
    },
    {
      "epoch": 0.07749627421758569,
      "grad_norm": 1.314767599105835,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2712,
      "step": 52
    },
    {
      "epoch": 0.07898658718330849,
      "grad_norm": 1.2060467004776,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3906,
      "step": 53
    },
    {
      "epoch": 0.08047690014903129,
      "grad_norm": 1.077643871307373,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2892,
      "step": 54
    },
    {
      "epoch": 0.08047690014903129,
      "eval_loss": 0.35677972435951233,
      "eval_runtime": 2.708,
      "eval_samples_per_second": 208.641,
      "eval_steps_per_second": 26.219,
      "step": 54
    },
    {
      "epoch": 0.08196721311475409,
      "grad_norm": 1.2945141792297363,
      "learning_rate": 5e-05,
      "loss": 0.3159,
      "step": 55
    },
    {
      "epoch": 0.08345752608047691,
      "grad_norm": 1.3156005144119263,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3413,
      "step": 56
    },
    {
      "epoch": 0.08494783904619971,
      "grad_norm": 1.6275720596313477,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.3478,
      "step": 57
    },
    {
      "epoch": 0.08643815201192251,
      "grad_norm": 1.8152949810028076,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3269,
      "step": 58
    },
    {
      "epoch": 0.08792846497764531,
      "grad_norm": 1.127657413482666,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.339,
      "step": 59
    },
    {
      "epoch": 0.08941877794336811,
      "grad_norm": 1.2930176258087158,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.4244,
      "step": 60
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.3748923540115356,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2725,
      "step": 61
    },
    {
      "epoch": 0.09239940387481371,
      "grad_norm": 1.7203524112701416,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.3573,
      "step": 62
    },
    {
      "epoch": 0.09388971684053651,
      "grad_norm": 0.811051607131958,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2246,
      "step": 63
    },
    {
      "epoch": 0.09388971684053651,
      "eval_loss": 0.3099740743637085,
      "eval_runtime": 2.7369,
      "eval_samples_per_second": 206.441,
      "eval_steps_per_second": 25.942,
      "step": 63
    },
    {
      "epoch": 0.09538002980625931,
      "grad_norm": 1.456381916999817,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2353,
      "step": 64
    },
    {
      "epoch": 0.09687034277198212,
      "grad_norm": 0.758620023727417,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2168,
      "step": 65
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 1.1172595024108887,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2702,
      "step": 66
    },
    {
      "epoch": 0.09985096870342772,
      "grad_norm": 0.9833356738090515,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.3002,
      "step": 67
    },
    {
      "epoch": 0.10134128166915052,
      "grad_norm": 1.0243797302246094,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2407,
      "step": 68
    },
    {
      "epoch": 0.10283159463487332,
      "grad_norm": 0.6949136853218079,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2043,
      "step": 69
    },
    {
      "epoch": 0.10432190760059612,
      "grad_norm": 1.4197059869766235,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2862,
      "step": 70
    },
    {
      "epoch": 0.10581222056631892,
      "grad_norm": 0.7830525636672974,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2069,
      "step": 71
    },
    {
      "epoch": 0.10730253353204174,
      "grad_norm": 1.1061123609542847,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2021,
      "step": 72
    },
    {
      "epoch": 0.10730253353204174,
      "eval_loss": 0.2788161039352417,
      "eval_runtime": 2.6609,
      "eval_samples_per_second": 212.333,
      "eval_steps_per_second": 26.683,
      "step": 72
    },
    {
      "epoch": 0.10879284649776454,
      "grad_norm": 0.7569260001182556,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2181,
      "step": 73
    },
    {
      "epoch": 0.11028315946348734,
      "grad_norm": 0.9492326974868774,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.3657,
      "step": 74
    },
    {
      "epoch": 0.11177347242921014,
      "grad_norm": 0.8849908709526062,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2092,
      "step": 75
    },
    {
      "epoch": 0.11326378539493294,
      "grad_norm": 0.7134643197059631,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2253,
      "step": 76
    },
    {
      "epoch": 0.11475409836065574,
      "grad_norm": 1.2007724046707153,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2773,
      "step": 77
    },
    {
      "epoch": 0.11624441132637854,
      "grad_norm": 0.9633266925811768,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.3331,
      "step": 78
    },
    {
      "epoch": 0.11773472429210134,
      "grad_norm": 1.1672801971435547,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.3208,
      "step": 79
    },
    {
      "epoch": 0.11922503725782414,
      "grad_norm": 0.9459627270698547,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.2231,
      "step": 80
    },
    {
      "epoch": 0.12071535022354694,
      "grad_norm": 1.0871282815933228,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.366,
      "step": 81
    },
    {
      "epoch": 0.12071535022354694,
      "eval_loss": 0.2640610635280609,
      "eval_runtime": 2.7126,
      "eval_samples_per_second": 208.285,
      "eval_steps_per_second": 26.174,
      "step": 81
    },
    {
      "epoch": 0.12220566318926974,
      "grad_norm": 0.8887442350387573,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.172,
      "step": 82
    },
    {
      "epoch": 0.12369597615499255,
      "grad_norm": 0.8635609149932861,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.2841,
      "step": 83
    },
    {
      "epoch": 0.12518628912071536,
      "grad_norm": 0.701813817024231,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.159,
      "step": 84
    },
    {
      "epoch": 0.12667660208643816,
      "grad_norm": 1.2554618120193481,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.3869,
      "step": 85
    },
    {
      "epoch": 0.12816691505216096,
      "grad_norm": 0.7576965689659119,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2828,
      "step": 86
    },
    {
      "epoch": 0.12965722801788376,
      "grad_norm": 0.8593026995658875,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1677,
      "step": 87
    },
    {
      "epoch": 0.13114754098360656,
      "grad_norm": 0.8234618902206421,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2902,
      "step": 88
    },
    {
      "epoch": 0.13263785394932937,
      "grad_norm": 1.0881298780441284,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2905,
      "step": 89
    },
    {
      "epoch": 0.13412816691505217,
      "grad_norm": 0.7025581002235413,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2656,
      "step": 90
    },
    {
      "epoch": 0.13412816691505217,
      "eval_loss": 0.25454258918762207,
      "eval_runtime": 2.7005,
      "eval_samples_per_second": 209.222,
      "eval_steps_per_second": 26.292,
      "step": 90
    },
    {
      "epoch": 0.13561847988077497,
      "grad_norm": 0.595646321773529,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1637,
      "step": 91
    },
    {
      "epoch": 0.13710879284649777,
      "grad_norm": 0.8875901699066162,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.1471,
      "step": 92
    },
    {
      "epoch": 0.13859910581222057,
      "grad_norm": 0.6628938317298889,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2461,
      "step": 93
    },
    {
      "epoch": 0.14008941877794337,
      "grad_norm": 1.1476900577545166,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.2747,
      "step": 94
    },
    {
      "epoch": 0.14157973174366617,
      "grad_norm": 0.841936469078064,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1956,
      "step": 95
    },
    {
      "epoch": 0.14307004470938897,
      "grad_norm": 0.7711091637611389,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1328,
      "step": 96
    },
    {
      "epoch": 0.14456035767511177,
      "grad_norm": 1.0483628511428833,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.2153,
      "step": 97
    },
    {
      "epoch": 0.14605067064083457,
      "grad_norm": 0.7784842848777771,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.1979,
      "step": 98
    },
    {
      "epoch": 0.14754098360655737,
      "grad_norm": 0.7276144027709961,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2163,
      "step": 99
    },
    {
      "epoch": 0.14754098360655737,
      "eval_loss": 0.25341349840164185,
      "eval_runtime": 2.6609,
      "eval_samples_per_second": 212.333,
      "eval_steps_per_second": 26.683,
      "step": 99
    },
    {
      "epoch": 0.14903129657228018,
      "grad_norm": 1.0174576044082642,
      "learning_rate": 0.0,
      "loss": 0.2102,
      "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": 1388375860838400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}