{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.043449923962633065,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00043449923962633063,
      "grad_norm": 0.7322242259979248,
      "learning_rate": 1e-05,
      "loss": 4.6281,
      "step": 1
    },
    {
      "epoch": 0.00043449923962633063,
      "eval_loss": 2.2681100368499756,
      "eval_runtime": 936.1826,
      "eval_samples_per_second": 2.071,
      "eval_steps_per_second": 0.26,
      "step": 1
    },
    {
      "epoch": 0.0008689984792526613,
      "grad_norm": 0.7169781923294067,
      "learning_rate": 2e-05,
      "loss": 4.5781,
      "step": 2
    },
    {
      "epoch": 0.001303497718878992,
      "grad_norm": 0.6220166683197021,
      "learning_rate": 3e-05,
      "loss": 4.5088,
      "step": 3
    },
    {
      "epoch": 0.0017379969585053225,
      "grad_norm": 0.6577661037445068,
      "learning_rate": 4e-05,
      "loss": 4.5698,
      "step": 4
    },
    {
      "epoch": 0.0021724961981316533,
      "grad_norm": 0.6816755533218384,
      "learning_rate": 5e-05,
      "loss": 4.5211,
      "step": 5
    },
    {
      "epoch": 0.002606995437757984,
      "grad_norm": 0.7988889217376709,
      "learning_rate": 6e-05,
      "loss": 4.4963,
      "step": 6
    },
    {
      "epoch": 0.0030414946773843145,
      "grad_norm": 0.9024376273155212,
      "learning_rate": 7e-05,
      "loss": 4.5237,
      "step": 7
    },
    {
      "epoch": 0.003475993917010645,
      "grad_norm": 1.0115993022918701,
      "learning_rate": 8e-05,
      "loss": 4.321,
      "step": 8
    },
    {
      "epoch": 0.003910493156636976,
      "grad_norm": 1.0931627750396729,
      "learning_rate": 9e-05,
      "loss": 4.1351,
      "step": 9
    },
    {
      "epoch": 0.003910493156636976,
      "eval_loss": 1.9916020631790161,
      "eval_runtime": 939.5626,
      "eval_samples_per_second": 2.064,
      "eval_steps_per_second": 0.259,
      "step": 9
    },
    {
      "epoch": 0.004344992396263307,
      "grad_norm": 1.3642878532409668,
      "learning_rate": 0.0001,
      "loss": 3.9607,
      "step": 10
    },
    {
      "epoch": 0.004779491635889637,
      "grad_norm": 1.5105156898498535,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.7648,
      "step": 11
    },
    {
      "epoch": 0.005213990875515968,
      "grad_norm": 1.1561989784240723,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.3213,
      "step": 12
    },
    {
      "epoch": 0.005648490115142298,
      "grad_norm": 1.2711970806121826,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.1605,
      "step": 13
    },
    {
      "epoch": 0.006082989354768629,
      "grad_norm": 1.2520768642425537,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.7325,
      "step": 14
    },
    {
      "epoch": 0.00651748859439496,
      "grad_norm": 1.3953733444213867,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4149,
      "step": 15
    },
    {
      "epoch": 0.00695198783402129,
      "grad_norm": 1.2582489252090454,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3447,
      "step": 16
    },
    {
      "epoch": 0.007386487073647621,
      "grad_norm": 1.0818967819213867,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.0851,
      "step": 17
    },
    {
      "epoch": 0.007820986313273952,
      "grad_norm": 1.0467973947525024,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.9362,
      "step": 18
    },
    {
      "epoch": 0.007820986313273952,
      "eval_loss": 0.9285404086112976,
      "eval_runtime": 938.7411,
      "eval_samples_per_second": 2.066,
      "eval_steps_per_second": 0.259,
      "step": 18
    },
    {
      "epoch": 0.008255485552900283,
      "grad_norm": 1.0093339681625366,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9558,
      "step": 19
    },
    {
      "epoch": 0.008689984792526613,
      "grad_norm": 0.9407274723052979,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.7688,
      "step": 20
    },
    {
      "epoch": 0.009124484032152944,
      "grad_norm": 0.89859539270401,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6283,
      "step": 21
    },
    {
      "epoch": 0.009558983271779274,
      "grad_norm": 1.0678013563156128,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.2764,
      "step": 22
    },
    {
      "epoch": 0.009993482511405605,
      "grad_norm": 0.9045027494430542,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.4258,
      "step": 23
    },
    {
      "epoch": 0.010427981751031936,
      "grad_norm": 0.9049425721168518,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.3559,
      "step": 24
    },
    {
      "epoch": 0.010862480990658266,
      "grad_norm": 0.9243524074554443,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1685,
      "step": 25
    },
    {
      "epoch": 0.011296980230284597,
      "grad_norm": 0.8838552832603455,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.3244,
      "step": 26
    },
    {
      "epoch": 0.011731479469910927,
      "grad_norm": 1.061066746711731,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.21,
      "step": 27
    },
    {
      "epoch": 0.011731479469910927,
      "eval_loss": 0.6456077694892883,
      "eval_runtime": 938.9828,
      "eval_samples_per_second": 2.065,
      "eval_steps_per_second": 0.259,
      "step": 27
    },
    {
      "epoch": 0.012165978709537258,
      "grad_norm": 1.0086060762405396,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2234,
      "step": 28
    },
    {
      "epoch": 0.012600477949163589,
      "grad_norm": 1.3487379550933838,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1388,
      "step": 29
    },
    {
      "epoch": 0.01303497718878992,
      "grad_norm": 0.9925966858863831,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1835,
      "step": 30
    },
    {
      "epoch": 0.01346947642841625,
      "grad_norm": 0.9810362458229065,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1286,
      "step": 31
    },
    {
      "epoch": 0.01390397566804258,
      "grad_norm": 0.8999232649803162,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.0797,
      "step": 32
    },
    {
      "epoch": 0.014338474907668911,
      "grad_norm": 0.8485479354858398,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.1772,
      "step": 33
    },
    {
      "epoch": 0.014772974147295241,
      "grad_norm": 0.721775472164154,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.1839,
      "step": 34
    },
    {
      "epoch": 0.015207473386921572,
      "grad_norm": 0.7297196984291077,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.9739,
      "step": 35
    },
    {
      "epoch": 0.015641972626547904,
      "grad_norm": 0.7651397585868835,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.9736,
      "step": 36
    },
    {
      "epoch": 0.015641972626547904,
      "eval_loss": 0.5466849207878113,
      "eval_runtime": 937.7836,
      "eval_samples_per_second": 2.068,
      "eval_steps_per_second": 0.259,
      "step": 36
    },
    {
      "epoch": 0.016076471866174235,
      "grad_norm": 0.6458867788314819,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0337,
      "step": 37
    },
    {
      "epoch": 0.016510971105800566,
      "grad_norm": 0.7283520698547363,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.8557,
      "step": 38
    },
    {
      "epoch": 0.016945470345426896,
      "grad_norm": 0.8763824701309204,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.2412,
      "step": 39
    },
    {
      "epoch": 0.017379969585053227,
      "grad_norm": 0.7463090419769287,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0294,
      "step": 40
    },
    {
      "epoch": 0.017814468824679557,
      "grad_norm": 0.7758802771568298,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.1152,
      "step": 41
    },
    {
      "epoch": 0.018248968064305888,
      "grad_norm": 0.8491073846817017,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.0326,
      "step": 42
    },
    {
      "epoch": 0.01868346730393222,
      "grad_norm": 0.8055416345596313,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.0835,
      "step": 43
    },
    {
      "epoch": 0.01911796654355855,
      "grad_norm": 0.7747017741203308,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.0585,
      "step": 44
    },
    {
      "epoch": 0.01955246578318488,
      "grad_norm": 0.8274694085121155,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.9503,
      "step": 45
    },
    {
      "epoch": 0.01955246578318488,
      "eval_loss": 0.4956837594509125,
      "eval_runtime": 937.9087,
      "eval_samples_per_second": 2.067,
      "eval_steps_per_second": 0.259,
      "step": 45
    },
    {
      "epoch": 0.01998696502281121,
      "grad_norm": 0.7109098434448242,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9899,
      "step": 46
    },
    {
      "epoch": 0.02042146426243754,
      "grad_norm": 0.6250343918800354,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.9105,
      "step": 47
    },
    {
      "epoch": 0.02085596350206387,
      "grad_norm": 0.6676877737045288,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.124,
      "step": 48
    },
    {
      "epoch": 0.021290462741690202,
      "grad_norm": 0.6898258328437805,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.0348,
      "step": 49
    },
    {
      "epoch": 0.021724961981316532,
      "grad_norm": 0.7583088278770447,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8024,
      "step": 50
    },
    {
      "epoch": 0.022159461220942863,
      "grad_norm": 0.7032544016838074,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.9822,
      "step": 51
    },
    {
      "epoch": 0.022593960460569194,
      "grad_norm": 0.8667249083518982,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7966,
      "step": 52
    },
    {
      "epoch": 0.023028459700195524,
      "grad_norm": 0.7494419813156128,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.9368,
      "step": 53
    },
    {
      "epoch": 0.023462958939821855,
      "grad_norm": 0.6607624888420105,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.8481,
      "step": 54
    },
    {
      "epoch": 0.023462958939821855,
      "eval_loss": 0.4661303162574768,
      "eval_runtime": 937.0866,
      "eval_samples_per_second": 2.069,
      "eval_steps_per_second": 0.259,
      "step": 54
    },
    {
      "epoch": 0.023897458179448185,
      "grad_norm": 1.3510135412216187,
      "learning_rate": 5e-05,
      "loss": 0.955,
      "step": 55
    },
    {
      "epoch": 0.024331957419074516,
      "grad_norm": 0.7510749101638794,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.8116,
      "step": 56
    },
    {
      "epoch": 0.024766456658700847,
      "grad_norm": 0.7377657294273376,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.8809,
      "step": 57
    },
    {
      "epoch": 0.025200955898327177,
      "grad_norm": 0.6575254201889038,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.9222,
      "step": 58
    },
    {
      "epoch": 0.025635455137953508,
      "grad_norm": 0.7421597242355347,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.009,
      "step": 59
    },
    {
      "epoch": 0.02606995437757984,
      "grad_norm": 0.6919296383857727,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.8832,
      "step": 60
    },
    {
      "epoch": 0.02650445361720617,
      "grad_norm": 0.7524620294570923,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0048,
      "step": 61
    },
    {
      "epoch": 0.0269389528568325,
      "grad_norm": 0.7775732278823853,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.9253,
      "step": 62
    },
    {
      "epoch": 0.02737345209645883,
      "grad_norm": 0.7206799387931824,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.9962,
      "step": 63
    },
    {
      "epoch": 0.02737345209645883,
      "eval_loss": 0.4474518597126007,
      "eval_runtime": 938.4115,
      "eval_samples_per_second": 2.066,
      "eval_steps_per_second": 0.259,
      "step": 63
    },
    {
      "epoch": 0.02780795133608516,
      "grad_norm": 0.7352960705757141,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8807,
      "step": 64
    },
    {
      "epoch": 0.02824245057571149,
      "grad_norm": 0.6605808138847351,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.7756,
      "step": 65
    },
    {
      "epoch": 0.028676949815337822,
      "grad_norm": 0.76267409324646,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.8257,
      "step": 66
    },
    {
      "epoch": 0.029111449054964152,
      "grad_norm": 0.739069938659668,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.9447,
      "step": 67
    },
    {
      "epoch": 0.029545948294590483,
      "grad_norm": 0.8183147311210632,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8142,
      "step": 68
    },
    {
      "epoch": 0.029980447534216813,
      "grad_norm": 0.8828584551811218,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.8426,
      "step": 69
    },
    {
      "epoch": 0.030414946773843144,
      "grad_norm": 0.8308943510055542,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0606,
      "step": 70
    },
    {
      "epoch": 0.030849446013469478,
      "grad_norm": 0.7810403108596802,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7237,
      "step": 71
    },
    {
      "epoch": 0.03128394525309581,
      "grad_norm": 0.8019788861274719,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0645,
      "step": 72
    },
    {
      "epoch": 0.03128394525309581,
      "eval_loss": 0.43661898374557495,
      "eval_runtime": 937.5407,
      "eval_samples_per_second": 2.068,
      "eval_steps_per_second": 0.259,
      "step": 72
    },
    {
      "epoch": 0.03171844449272214,
      "grad_norm": 0.7618681192398071,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.859,
      "step": 73
    },
    {
      "epoch": 0.03215294373234847,
      "grad_norm": 0.8050389885902405,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.9631,
      "step": 74
    },
    {
      "epoch": 0.0325874429719748,
      "grad_norm": 0.8176538944244385,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.9906,
      "step": 75
    },
    {
      "epoch": 0.03302194221160113,
      "grad_norm": 0.7703763842582703,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.9075,
      "step": 76
    },
    {
      "epoch": 0.03345644145122746,
      "grad_norm": 0.7331583499908447,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.9032,
      "step": 77
    },
    {
      "epoch": 0.03389094069085379,
      "grad_norm": 0.8618801832199097,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.9932,
      "step": 78
    },
    {
      "epoch": 0.03432543993048012,
      "grad_norm": 0.7720716595649719,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7723,
      "step": 79
    },
    {
      "epoch": 0.03475993917010645,
      "grad_norm": 0.7049722075462341,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.004,
      "step": 80
    },
    {
      "epoch": 0.035194438409732784,
      "grad_norm": 0.7694608569145203,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.001,
      "step": 81
    },
    {
      "epoch": 0.035194438409732784,
      "eval_loss": 0.42849254608154297,
      "eval_runtime": 937.4186,
      "eval_samples_per_second": 2.068,
      "eval_steps_per_second": 0.259,
      "step": 81
    },
    {
      "epoch": 0.035628937649359115,
      "grad_norm": 0.7914429903030396,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8019,
      "step": 82
    },
    {
      "epoch": 0.036063436888985445,
      "grad_norm": 0.7216392159461975,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.7337,
      "step": 83
    },
    {
      "epoch": 0.036497936128611776,
      "grad_norm": 0.7539612054824829,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.7445,
      "step": 84
    },
    {
      "epoch": 0.036932435368238106,
      "grad_norm": 0.7819778323173523,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.759,
      "step": 85
    },
    {
      "epoch": 0.03736693460786444,
      "grad_norm": 0.8650638461112976,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.903,
      "step": 86
    },
    {
      "epoch": 0.03780143384749077,
      "grad_norm": 0.7645513415336609,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.8763,
      "step": 87
    },
    {
      "epoch": 0.0382359330871171,
      "grad_norm": 0.7570232152938843,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.9802,
      "step": 88
    },
    {
      "epoch": 0.03867043232674343,
      "grad_norm": 0.6940462589263916,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.8409,
      "step": 89
    },
    {
      "epoch": 0.03910493156636976,
      "grad_norm": 0.7175998687744141,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.8271,
      "step": 90
    },
    {
      "epoch": 0.03910493156636976,
      "eval_loss": 0.42518991231918335,
      "eval_runtime": 937.2878,
      "eval_samples_per_second": 2.069,
      "eval_steps_per_second": 0.259,
      "step": 90
    },
    {
      "epoch": 0.03953943080599609,
      "grad_norm": 0.7848137021064758,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7753,
      "step": 91
    },
    {
      "epoch": 0.03997393004562242,
      "grad_norm": 0.8303205370903015,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.9935,
      "step": 92
    },
    {
      "epoch": 0.04040842928524875,
      "grad_norm": 0.7627360820770264,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.8909,
      "step": 93
    },
    {
      "epoch": 0.04084292852487508,
      "grad_norm": 0.7823213934898376,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7864,
      "step": 94
    },
    {
      "epoch": 0.04127742776450141,
      "grad_norm": 0.7386431694030762,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.8293,
      "step": 95
    },
    {
      "epoch": 0.04171192700412774,
      "grad_norm": 0.7980239987373352,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.8131,
      "step": 96
    },
    {
      "epoch": 0.04214642624375407,
      "grad_norm": 0.6765995621681213,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.7674,
      "step": 97
    },
    {
      "epoch": 0.042580925483380404,
      "grad_norm": 0.8706260919570923,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.8537,
      "step": 98
    },
    {
      "epoch": 0.043015424723006734,
      "grad_norm": 0.7013819217681885,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8367,
      "step": 99
    },
    {
      "epoch": 0.043015424723006734,
      "eval_loss": 0.4246019124984741,
      "eval_runtime": 937.3227,
      "eval_samples_per_second": 2.069,
      "eval_steps_per_second": 0.259,
      "step": 99
    },
    {
      "epoch": 0.043449923962633065,
      "grad_norm": 0.7123420834541321,
      "learning_rate": 0.0,
      "loss": 0.9134,
      "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": 2.443914535501824e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}