{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007979253939756632,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.979253939756632e-05,
      "grad_norm": 49.58061599731445,
      "learning_rate": 1e-05,
      "loss": 12.6025,
      "step": 1
    },
    {
      "epoch": 7.979253939756632e-05,
      "eval_loss": 12.32382869720459,
      "eval_runtime": 1172.7302,
      "eval_samples_per_second": 9.0,
      "eval_steps_per_second": 1.126,
      "step": 1
    },
    {
      "epoch": 0.00015958507879513265,
      "grad_norm": 49.661338806152344,
      "learning_rate": 2e-05,
      "loss": 12.5151,
      "step": 2
    },
    {
      "epoch": 0.00023937761819269897,
      "grad_norm": 50.13138961791992,
      "learning_rate": 3e-05,
      "loss": 12.2248,
      "step": 3
    },
    {
      "epoch": 0.0003191701575902653,
      "grad_norm": 49.847042083740234,
      "learning_rate": 4e-05,
      "loss": 11.2231,
      "step": 4
    },
    {
      "epoch": 0.00039896269698783165,
      "grad_norm": 50.987586975097656,
      "learning_rate": 5e-05,
      "loss": 9.7104,
      "step": 5
    },
    {
      "epoch": 0.00047875523638539794,
      "grad_norm": 41.77866744995117,
      "learning_rate": 6e-05,
      "loss": 7.4558,
      "step": 6
    },
    {
      "epoch": 0.0005585477757829643,
      "grad_norm": 55.25391387939453,
      "learning_rate": 7e-05,
      "loss": 4.8936,
      "step": 7
    },
    {
      "epoch": 0.0006383403151805306,
      "grad_norm": 16.7445068359375,
      "learning_rate": 8e-05,
      "loss": 1.5216,
      "step": 8
    },
    {
      "epoch": 0.000718132854578097,
      "grad_norm": 3.6262011528015137,
      "learning_rate": 9e-05,
      "loss": 0.2591,
      "step": 9
    },
    {
      "epoch": 0.000718132854578097,
      "eval_loss": 0.46281757950782776,
      "eval_runtime": 1174.3636,
      "eval_samples_per_second": 8.987,
      "eval_steps_per_second": 1.124,
      "step": 9
    },
    {
      "epoch": 0.0007979253939756633,
      "grad_norm": 4.694632053375244,
      "learning_rate": 0.0001,
      "loss": 0.2082,
      "step": 10
    },
    {
      "epoch": 0.0008777179333732296,
      "grad_norm": 1.9988242387771606,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.0607,
      "step": 11
    },
    {
      "epoch": 0.0009575104727707959,
      "grad_norm": 8.024397850036621,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4178,
      "step": 12
    },
    {
      "epoch": 0.0010373030121683623,
      "grad_norm": 6.280609130859375,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.165,
      "step": 13
    },
    {
      "epoch": 0.0011170955515659286,
      "grad_norm": 4.712234973907471,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.2918,
      "step": 14
    },
    {
      "epoch": 0.0011968880909634949,
      "grad_norm": 2.203125,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0287,
      "step": 15
    },
    {
      "epoch": 0.0012766806303610612,
      "grad_norm": 0.5412839651107788,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0081,
      "step": 16
    },
    {
      "epoch": 0.0013564731697586275,
      "grad_norm": 5.122644424438477,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.2632,
      "step": 17
    },
    {
      "epoch": 0.001436265709156194,
      "grad_norm": 4.5444536209106445,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1299,
      "step": 18
    },
    {
      "epoch": 0.001436265709156194,
      "eval_loss": 0.0943012535572052,
      "eval_runtime": 1173.87,
      "eval_samples_per_second": 8.991,
      "eval_steps_per_second": 1.124,
      "step": 18
    },
    {
      "epoch": 0.0015160582485537603,
      "grad_norm": 4.412929058074951,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1196,
      "step": 19
    },
    {
      "epoch": 0.0015958507879513266,
      "grad_norm": 2.766735553741455,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.089,
      "step": 20
    },
    {
      "epoch": 0.0016756433273488929,
      "grad_norm": 5.6620612144470215,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1141,
      "step": 21
    },
    {
      "epoch": 0.0017554358667464592,
      "grad_norm": 6.14534330368042,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1721,
      "step": 22
    },
    {
      "epoch": 0.0018352284061440255,
      "grad_norm": 3.442941665649414,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.132,
      "step": 23
    },
    {
      "epoch": 0.0019150209455415918,
      "grad_norm": 2.6705148220062256,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0579,
      "step": 24
    },
    {
      "epoch": 0.001994813484939158,
      "grad_norm": 1.9801841974258423,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0466,
      "step": 25
    },
    {
      "epoch": 0.0020746060243367246,
      "grad_norm": 0.9174854159355164,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0168,
      "step": 26
    },
    {
      "epoch": 0.0021543985637342907,
      "grad_norm": 2.2525856494903564,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0473,
      "step": 27
    },
    {
      "epoch": 0.0021543985637342907,
      "eval_loss": 0.04498429223895073,
      "eval_runtime": 1173.9036,
      "eval_samples_per_second": 8.991,
      "eval_steps_per_second": 1.124,
      "step": 27
    },
    {
      "epoch": 0.002234191103131857,
      "grad_norm": 0.8390412330627441,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0102,
      "step": 28
    },
    {
      "epoch": 0.0023139836425294237,
      "grad_norm": 2.946712017059326,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0567,
      "step": 29
    },
    {
      "epoch": 0.0023937761819269898,
      "grad_norm": 0.6669507622718811,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0098,
      "step": 30
    },
    {
      "epoch": 0.0024735687213245563,
      "grad_norm": 0.16865402460098267,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0027,
      "step": 31
    },
    {
      "epoch": 0.0025533612607221224,
      "grad_norm": 0.015903962776064873,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0002,
      "step": 32
    },
    {
      "epoch": 0.002633153800119689,
      "grad_norm": 4.723154067993164,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.1846,
      "step": 33
    },
    {
      "epoch": 0.002712946339517255,
      "grad_norm": 6.566627502441406,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.1417,
      "step": 34
    },
    {
      "epoch": 0.0027927388789148215,
      "grad_norm": 2.141747236251831,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0161,
      "step": 35
    },
    {
      "epoch": 0.002872531418312388,
      "grad_norm": 0.03964311629533768,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0006,
      "step": 36
    },
    {
      "epoch": 0.002872531418312388,
      "eval_loss": 0.03792188689112663,
      "eval_runtime": 1173.7246,
      "eval_samples_per_second": 8.992,
      "eval_steps_per_second": 1.125,
      "step": 36
    },
    {
      "epoch": 0.002952323957709954,
      "grad_norm": 4.035125732421875,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0534,
      "step": 37
    },
    {
      "epoch": 0.0030321164971075206,
      "grad_norm": 0.05110321193933487,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0006,
      "step": 38
    },
    {
      "epoch": 0.0031119090365050867,
      "grad_norm": 8.2391996383667,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2745,
      "step": 39
    },
    {
      "epoch": 0.003191701575902653,
      "grad_norm": 0.9015544056892395,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0121,
      "step": 40
    },
    {
      "epoch": 0.0032714941153002192,
      "grad_norm": 0.042826250195503235,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0006,
      "step": 41
    },
    {
      "epoch": 0.0033512866546977858,
      "grad_norm": 0.03836386650800705,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0006,
      "step": 42
    },
    {
      "epoch": 0.0034310791940953523,
      "grad_norm": 0.009723003022372723,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0002,
      "step": 43
    },
    {
      "epoch": 0.0035108717334929184,
      "grad_norm": 0.021289482712745667,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0002,
      "step": 44
    },
    {
      "epoch": 0.003590664272890485,
      "grad_norm": 0.303159236907959,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0027,
      "step": 45
    },
    {
      "epoch": 0.003590664272890485,
      "eval_loss": 0.03881511464715004,
      "eval_runtime": 1173.5436,
      "eval_samples_per_second": 8.993,
      "eval_steps_per_second": 1.125,
      "step": 45
    },
    {
      "epoch": 0.003670456812288051,
      "grad_norm": 7.318003177642822,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2397,
      "step": 46
    },
    {
      "epoch": 0.0037502493516856175,
      "grad_norm": 0.019719544798135757,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0003,
      "step": 47
    },
    {
      "epoch": 0.0038300418910831835,
      "grad_norm": 0.07693640887737274,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0009,
      "step": 48
    },
    {
      "epoch": 0.00390983443048075,
      "grad_norm": 0.008079406805336475,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0002,
      "step": 49
    },
    {
      "epoch": 0.003989626969878316,
      "grad_norm": 4.140525817871094,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.2047,
      "step": 50
    },
    {
      "epoch": 0.004069419509275883,
      "grad_norm": 0.11653276532888412,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0022,
      "step": 51
    },
    {
      "epoch": 0.004149212048673449,
      "grad_norm": 0.16084034740924835,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0014,
      "step": 52
    },
    {
      "epoch": 0.004229004588071015,
      "grad_norm": 0.20590780675411224,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0025,
      "step": 53
    },
    {
      "epoch": 0.004308797127468581,
      "grad_norm": 1.4190741777420044,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0184,
      "step": 54
    },
    {
      "epoch": 0.004308797127468581,
      "eval_loss": 0.02837800793349743,
      "eval_runtime": 1173.8058,
      "eval_samples_per_second": 8.991,
      "eval_steps_per_second": 1.125,
      "step": 54
    },
    {
      "epoch": 0.004388589666866148,
      "grad_norm": 1.102265477180481,
      "learning_rate": 5e-05,
      "loss": 0.0127,
      "step": 55
    },
    {
      "epoch": 0.004468382206263714,
      "grad_norm": 1.8974970579147339,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0293,
      "step": 56
    },
    {
      "epoch": 0.00454817474566128,
      "grad_norm": 0.21190974116325378,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0026,
      "step": 57
    },
    {
      "epoch": 0.004627967285058847,
      "grad_norm": 0.4437422752380371,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0035,
      "step": 58
    },
    {
      "epoch": 0.0047077598244564135,
      "grad_norm": 0.28629863262176514,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0026,
      "step": 59
    },
    {
      "epoch": 0.0047875523638539795,
      "grad_norm": 3.096703290939331,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0311,
      "step": 60
    },
    {
      "epoch": 0.004867344903251546,
      "grad_norm": 0.03261572867631912,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0006,
      "step": 61
    },
    {
      "epoch": 0.0049471374426491126,
      "grad_norm": 0.06204415112733841,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0005,
      "step": 62
    },
    {
      "epoch": 0.005026929982046679,
      "grad_norm": 0.5233569145202637,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0042,
      "step": 63
    },
    {
      "epoch": 0.005026929982046679,
      "eval_loss": 0.025455670431256294,
      "eval_runtime": 1174.0011,
      "eval_samples_per_second": 8.99,
      "eval_steps_per_second": 1.124,
      "step": 63
    },
    {
      "epoch": 0.005106722521444245,
      "grad_norm": 4.643551349639893,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0454,
      "step": 64
    },
    {
      "epoch": 0.005186515060841812,
      "grad_norm": 0.028440676629543304,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0004,
      "step": 65
    },
    {
      "epoch": 0.005266307600239378,
      "grad_norm": 0.04242803528904915,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0005,
      "step": 66
    },
    {
      "epoch": 0.005346100139636944,
      "grad_norm": 0.27321672439575195,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.004,
      "step": 67
    },
    {
      "epoch": 0.00542589267903451,
      "grad_norm": 6.701133728027344,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0502,
      "step": 68
    },
    {
      "epoch": 0.005505685218432077,
      "grad_norm": 5.985700607299805,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1721,
      "step": 69
    },
    {
      "epoch": 0.005585477757829643,
      "grad_norm": 0.29113706946372986,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0026,
      "step": 70
    },
    {
      "epoch": 0.005665270297227209,
      "grad_norm": 0.01628880761563778,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0002,
      "step": 71
    },
    {
      "epoch": 0.005745062836624776,
      "grad_norm": 4.214999198913574,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0808,
      "step": 72
    },
    {
      "epoch": 0.005745062836624776,
      "eval_loss": 0.02509034425020218,
      "eval_runtime": 1173.8944,
      "eval_samples_per_second": 8.991,
      "eval_steps_per_second": 1.124,
      "step": 72
    },
    {
      "epoch": 0.005824855376022342,
      "grad_norm": 3.7103044986724854,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0401,
      "step": 73
    },
    {
      "epoch": 0.005904647915419908,
      "grad_norm": 0.00788003671914339,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0002,
      "step": 74
    },
    {
      "epoch": 0.005984440454817474,
      "grad_norm": 0.42486655712127686,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.002,
      "step": 75
    },
    {
      "epoch": 0.006064232994215041,
      "grad_norm": 7.127850532531738,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.1193,
      "step": 76
    },
    {
      "epoch": 0.006144025533612607,
      "grad_norm": 0.14497733116149902,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0009,
      "step": 77
    },
    {
      "epoch": 0.006223818073010173,
      "grad_norm": 0.9754450917243958,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.009,
      "step": 78
    },
    {
      "epoch": 0.00630361061240774,
      "grad_norm": 4.28366756439209,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.1988,
      "step": 79
    },
    {
      "epoch": 0.006383403151805306,
      "grad_norm": 3.1929945945739746,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.4929,
      "step": 80
    },
    {
      "epoch": 0.006463195691202872,
      "grad_norm": 0.1286645233631134,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0013,
      "step": 81
    },
    {
      "epoch": 0.006463195691202872,
      "eval_loss": 0.025878826156258583,
      "eval_runtime": 1174.081,
      "eval_samples_per_second": 8.989,
      "eval_steps_per_second": 1.124,
      "step": 81
    },
    {
      "epoch": 0.0065429882306004385,
      "grad_norm": 1.1662371158599854,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0132,
      "step": 82
    },
    {
      "epoch": 0.0066227807699980054,
      "grad_norm": 0.022257689386606216,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0003,
      "step": 83
    },
    {
      "epoch": 0.0067025733093955715,
      "grad_norm": 2.7045812606811523,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0221,
      "step": 84
    },
    {
      "epoch": 0.006782365848793138,
      "grad_norm": 0.13790157437324524,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0008,
      "step": 85
    },
    {
      "epoch": 0.0068621583881907046,
      "grad_norm": 0.2832893431186676,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0018,
      "step": 86
    },
    {
      "epoch": 0.006941950927588271,
      "grad_norm": 0.11073965579271317,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0015,
      "step": 87
    },
    {
      "epoch": 0.007021743466985837,
      "grad_norm": 0.02817540243268013,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0003,
      "step": 88
    },
    {
      "epoch": 0.007101536006383403,
      "grad_norm": 0.1966514140367508,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0026,
      "step": 89
    },
    {
      "epoch": 0.00718132854578097,
      "grad_norm": 1.2392982244491577,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.006,
      "step": 90
    },
    {
      "epoch": 0.00718132854578097,
      "eval_loss": 0.02482367493212223,
      "eval_runtime": 1174.0418,
      "eval_samples_per_second": 8.989,
      "eval_steps_per_second": 1.124,
      "step": 90
    },
    {
      "epoch": 0.007261121085178536,
      "grad_norm": 1.3133395910263062,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0251,
      "step": 91
    },
    {
      "epoch": 0.007340913624576102,
      "grad_norm": 0.3340592384338379,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0024,
      "step": 92
    },
    {
      "epoch": 0.007420706163973669,
      "grad_norm": 3.8292672634124756,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.1161,
      "step": 93
    },
    {
      "epoch": 0.007500498703371235,
      "grad_norm": 0.7972753047943115,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0042,
      "step": 94
    },
    {
      "epoch": 0.007580291242768801,
      "grad_norm": 7.937070369720459,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.1994,
      "step": 95
    },
    {
      "epoch": 0.007660083782166367,
      "grad_norm": 0.028258243575692177,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0004,
      "step": 96
    },
    {
      "epoch": 0.007739876321563934,
      "grad_norm": 0.40683069825172424,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0033,
      "step": 97
    },
    {
      "epoch": 0.0078196688609615,
      "grad_norm": 0.29506799578666687,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0024,
      "step": 98
    },
    {
      "epoch": 0.007899461400359067,
      "grad_norm": 0.03002856858074665,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0003,
      "step": 99
    },
    {
      "epoch": 0.007899461400359067,
      "eval_loss": 0.02486652322113514,
      "eval_runtime": 1173.8985,
      "eval_samples_per_second": 8.991,
      "eval_steps_per_second": 1.124,
      "step": 99
    },
    {
      "epoch": 0.007979253939756632,
      "grad_norm": 0.1410716474056244,
      "learning_rate": 0.0,
      "loss": 0.0016,
      "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": 7.455967199782502e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}