{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006095145216834791,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.095145216834791e-05,
      "grad_norm": 19.30591583251953,
      "learning_rate": 1e-05,
      "loss": 7.8233,
      "step": 1
    },
    {
      "epoch": 6.095145216834791e-05,
      "eval_loss": 7.634002685546875,
      "eval_runtime": 2098.1042,
      "eval_samples_per_second": 6.585,
      "eval_steps_per_second": 0.823,
      "step": 1
    },
    {
      "epoch": 0.00012190290433669582,
      "grad_norm": 18.737558364868164,
      "learning_rate": 2e-05,
      "loss": 7.3666,
      "step": 2
    },
    {
      "epoch": 0.00018285435650504373,
      "grad_norm": 19.3597469329834,
      "learning_rate": 3e-05,
      "loss": 8.0233,
      "step": 3
    },
    {
      "epoch": 0.00024380580867339164,
      "grad_norm": 19.723112106323242,
      "learning_rate": 4e-05,
      "loss": 8.2161,
      "step": 4
    },
    {
      "epoch": 0.00030475726084173955,
      "grad_norm": 22.727209091186523,
      "learning_rate": 5e-05,
      "loss": 6.5671,
      "step": 5
    },
    {
      "epoch": 0.00036570871301008746,
      "grad_norm": 18.060890197753906,
      "learning_rate": 6e-05,
      "loss": 5.3978,
      "step": 6
    },
    {
      "epoch": 0.00042666016517843537,
      "grad_norm": 19.09143829345703,
      "learning_rate": 7e-05,
      "loss": 4.7898,
      "step": 7
    },
    {
      "epoch": 0.0004876116173467833,
      "grad_norm": 19.793140411376953,
      "learning_rate": 8e-05,
      "loss": 3.0144,
      "step": 8
    },
    {
      "epoch": 0.0005485630695151312,
      "grad_norm": 12.354540824890137,
      "learning_rate": 9e-05,
      "loss": 0.6829,
      "step": 9
    },
    {
      "epoch": 0.0005485630695151312,
      "eval_loss": 0.7424596548080444,
      "eval_runtime": 2103.0887,
      "eval_samples_per_second": 6.569,
      "eval_steps_per_second": 0.821,
      "step": 9
    },
    {
      "epoch": 0.0006095145216834791,
      "grad_norm": 8.043534278869629,
      "learning_rate": 0.0001,
      "loss": 1.264,
      "step": 10
    },
    {
      "epoch": 0.0006704659738518271,
      "grad_norm": 2.2055182456970215,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.0682,
      "step": 11
    },
    {
      "epoch": 0.0007314174260201749,
      "grad_norm": 0.3776053190231323,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0059,
      "step": 12
    },
    {
      "epoch": 0.0007923688781885229,
      "grad_norm": 4.13097620010376,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.4817,
      "step": 13
    },
    {
      "epoch": 0.0008533203303568707,
      "grad_norm": 2.3062400817871094,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1627,
      "step": 14
    },
    {
      "epoch": 0.0009142717825252187,
      "grad_norm": 4.56626558303833,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0748,
      "step": 15
    },
    {
      "epoch": 0.0009752232346935666,
      "grad_norm": 3.2404799461364746,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2836,
      "step": 16
    },
    {
      "epoch": 0.0010361746868619145,
      "grad_norm": 1.4391580820083618,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0194,
      "step": 17
    },
    {
      "epoch": 0.0010971261390302625,
      "grad_norm": 0.050521451979875565,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0003,
      "step": 18
    },
    {
      "epoch": 0.0010971261390302625,
      "eval_loss": 0.031156441196799278,
      "eval_runtime": 2102.7836,
      "eval_samples_per_second": 6.57,
      "eval_steps_per_second": 0.821,
      "step": 18
    },
    {
      "epoch": 0.0011580775911986102,
      "grad_norm": 0.015599433332681656,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0001,
      "step": 19
    },
    {
      "epoch": 0.0012190290433669582,
      "grad_norm": 0.005438444670289755,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0012799804955353062,
      "grad_norm": 0.07070866972208023,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0004,
      "step": 21
    },
    {
      "epoch": 0.0013409319477036541,
      "grad_norm": 0.10057298094034195,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0005,
      "step": 22
    },
    {
      "epoch": 0.0014018833998720019,
      "grad_norm": 7.556246280670166,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.4752,
      "step": 23
    },
    {
      "epoch": 0.0014628348520403498,
      "grad_norm": 0.003154378617182374,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0015237863042086978,
      "grad_norm": 0.002021010732278228,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0015847377563770458,
      "grad_norm": 0.004336357582360506,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.0016456892085453935,
      "grad_norm": 0.0034702522680163383,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0016456892085453935,
      "eval_loss": 0.00582321360707283,
      "eval_runtime": 2102.5287,
      "eval_samples_per_second": 6.571,
      "eval_steps_per_second": 0.821,
      "step": 27
    },
    {
      "epoch": 0.0017066406607137415,
      "grad_norm": 0.005274789407849312,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.0017675921128820894,
      "grad_norm": 0.0021689534187316895,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.0018285435650504374,
      "grad_norm": 0.007156506180763245,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0018894950172187851,
      "grad_norm": 0.0025761344004422426,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.001950446469387133,
      "grad_norm": 0.0019654526840895414,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.002011397921555481,
      "grad_norm": 0.0015995341818779707,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.002072349373723829,
      "grad_norm": 0.008186628110706806,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.002133300825892177,
      "grad_norm": 0.004007392097264528,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.002194252278060525,
      "grad_norm": 0.0012297423090785742,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.002194252278060525,
      "eval_loss": 0.0025516680907458067,
      "eval_runtime": 2101.3758,
      "eval_samples_per_second": 6.575,
      "eval_steps_per_second": 0.822,
      "step": 36
    },
    {
      "epoch": 0.0022552037302288725,
      "grad_norm": 0.002535809064283967,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0023161551823972205,
      "grad_norm": 0.0014279191382229328,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.0023771066345655684,
      "grad_norm": 0.0011304673971608281,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.0024380580867339164,
      "grad_norm": 0.05122983083128929,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0002,
      "step": 40
    },
    {
      "epoch": 0.0024990095389022643,
      "grad_norm": 0.0008824480464681983,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.0025599609910706123,
      "grad_norm": 5.697413444519043,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0421,
      "step": 42
    },
    {
      "epoch": 0.0026209124432389603,
      "grad_norm": 0.000364432082278654,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0026818638954073082,
      "grad_norm": 0.0002612911630421877,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.002742815347575656,
      "grad_norm": 0.0002420325472485274,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.002742815347575656,
      "eval_loss": 0.002355450764298439,
      "eval_runtime": 2103.3931,
      "eval_samples_per_second": 6.568,
      "eval_steps_per_second": 0.821,
      "step": 45
    },
    {
      "epoch": 0.0028037667997440037,
      "grad_norm": 0.001806682557798922,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.0028647182519123517,
      "grad_norm": 3.982408046722412,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0256,
      "step": 47
    },
    {
      "epoch": 0.0029256697040806997,
      "grad_norm": 0.00027734501054510474,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0029866211562490476,
      "grad_norm": 0.0004443471261765808,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0030475726084173956,
      "grad_norm": 0.0003288051811978221,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0031085240605857435,
      "grad_norm": 0.00022381207963917404,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.0031694755127540915,
      "grad_norm": 0.0013293400406837463,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.0032304269649224395,
      "grad_norm": 0.00028961049974896014,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.003291378417090787,
      "grad_norm": 0.00037395075196400285,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.003291378417090787,
      "eval_loss": 0.0012881968868896365,
      "eval_runtime": 2103.4377,
      "eval_samples_per_second": 6.568,
      "eval_steps_per_second": 0.821,
      "step": 54
    },
    {
      "epoch": 0.003352329869259135,
      "grad_norm": 0.000291243166429922,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.003413281321427483,
      "grad_norm": 0.00040752225322648883,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.003474232773595831,
      "grad_norm": 0.0002688828099053353,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.003535184225764179,
      "grad_norm": 0.0007541452068835497,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.003596135677932527,
      "grad_norm": 0.0003042304306291044,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.003657087130100875,
      "grad_norm": 0.0003237078490201384,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.0037180385822692228,
      "grad_norm": 0.0005371847655624151,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.0037789900344375703,
      "grad_norm": 0.000351637921994552,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.0038399414866059182,
      "grad_norm": 0.00044268937199376523,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.0038399414866059182,
      "eval_loss": 0.0018626422388479114,
      "eval_runtime": 2102.9059,
      "eval_samples_per_second": 6.57,
      "eval_steps_per_second": 0.821,
      "step": 63
    },
    {
      "epoch": 0.003900892938774266,
      "grad_norm": 0.0018635762389749289,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.003961844390942614,
      "grad_norm": 0.000782185175921768,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.004022795843110962,
      "grad_norm": 0.001013163710013032,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.00408374729527931,
      "grad_norm": 0.0011713090352714062,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.004144698747447658,
      "grad_norm": 0.0005544234882108867,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.004205650199616006,
      "grad_norm": 0.0009957266738638282,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.004266601651784354,
      "grad_norm": 0.0022838555742055178,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.004327553103952702,
      "grad_norm": 0.0009302516118623316,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.00438850455612105,
      "grad_norm": 0.0004281099245417863,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.00438850455612105,
      "eval_loss": 0.002097652992233634,
      "eval_runtime": 2107.927,
      "eval_samples_per_second": 6.554,
      "eval_steps_per_second": 0.819,
      "step": 72
    },
    {
      "epoch": 0.004449456008289398,
      "grad_norm": 0.012079447507858276,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.004510407460457745,
      "grad_norm": 0.0004687201580964029,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.004571358912626093,
      "grad_norm": 0.0004222751595079899,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.004632310364794441,
      "grad_norm": 0.004577755928039551,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.004693261816962789,
      "grad_norm": 0.00045730435522273183,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.004754213269131137,
      "grad_norm": 0.00031118057086132467,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.004815164721299485,
      "grad_norm": 0.0005092663923278451,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.004876116173467833,
      "grad_norm": 0.00029153015930205584,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.004937067625636181,
      "grad_norm": 0.00032549205934628844,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.004937067625636181,
      "eval_loss": 0.0021451739594340324,
      "eval_runtime": 2103.3459,
      "eval_samples_per_second": 6.569,
      "eval_steps_per_second": 0.821,
      "step": 81
    },
    {
      "epoch": 0.004998019077804529,
      "grad_norm": 0.0006757644005119801,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.005058970529972877,
      "grad_norm": 0.0008024928974919021,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.005119921982141225,
      "grad_norm": 0.00041792544652707875,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.005180873434309573,
      "grad_norm": 0.0006066655623726547,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.0052418248864779205,
      "grad_norm": 0.00035250242217443883,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.0053027763386462685,
      "grad_norm": 0.00059564906405285,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.0053637277908146165,
      "grad_norm": 0.0004675053933169693,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.0054246792429829644,
      "grad_norm": 0.00046611728612333536,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.005485630695151312,
      "grad_norm": 0.00036150909727439284,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.005485630695151312,
      "eval_loss": 0.0021452573128044605,
      "eval_runtime": 2102.0113,
      "eval_samples_per_second": 6.573,
      "eval_steps_per_second": 0.822,
      "step": 90
    },
    {
      "epoch": 0.0055465821473196595,
      "grad_norm": 0.0003072117397096008,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.0056075335994880075,
      "grad_norm": 0.04003473371267319,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0001,
      "step": 92
    },
    {
      "epoch": 0.005668485051656355,
      "grad_norm": 0.00045625370694324374,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.005729436503824703,
      "grad_norm": 0.0004790804523508996,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.005790387955993051,
      "grad_norm": 0.000417745322920382,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.005851339408161399,
      "grad_norm": 0.000524096074514091,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.005912290860329747,
      "grad_norm": 0.0004284666501916945,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.005973242312498095,
      "grad_norm": 0.00031758853583596647,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.006034193764666443,
      "grad_norm": 0.0005975643871352077,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.006034193764666443,
      "eval_loss": 0.0021247444674372673,
      "eval_runtime": 2103.361,
      "eval_samples_per_second": 6.569,
      "eval_steps_per_second": 0.821,
      "step": 99
    },
    {
      "epoch": 0.006095145216834791,
      "grad_norm": 0.0004037336620967835,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1.0163855784778138e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}