{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022462067184042945,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.246206718404295e-05,
      "grad_norm": 3.0712389945983887,
      "learning_rate": 1e-05,
      "loss": 4.5815,
      "step": 1
    },
    {
      "epoch": 2.246206718404295e-05,
      "eval_loss": 2.2074947357177734,
      "eval_runtime": 3664.8507,
      "eval_samples_per_second": 10.23,
      "eval_steps_per_second": 1.279,
      "step": 1
    },
    {
      "epoch": 4.49241343680859e-05,
      "grad_norm": 2.025412082672119,
      "learning_rate": 2e-05,
      "loss": 3.7769,
      "step": 2
    },
    {
      "epoch": 6.738620155212884e-05,
      "grad_norm": 2.5275726318359375,
      "learning_rate": 3e-05,
      "loss": 4.2228,
      "step": 3
    },
    {
      "epoch": 8.98482687361718e-05,
      "grad_norm": 2.5390024185180664,
      "learning_rate": 4e-05,
      "loss": 4.9002,
      "step": 4
    },
    {
      "epoch": 0.00011231033592021474,
      "grad_norm": 2.9198367595672607,
      "learning_rate": 5e-05,
      "loss": 4.7604,
      "step": 5
    },
    {
      "epoch": 0.00013477240310425767,
      "grad_norm": 3.3159918785095215,
      "learning_rate": 6e-05,
      "loss": 4.1514,
      "step": 6
    },
    {
      "epoch": 0.00015723447028830065,
      "grad_norm": 3.7733492851257324,
      "learning_rate": 7e-05,
      "loss": 4.502,
      "step": 7
    },
    {
      "epoch": 0.0001796965374723436,
      "grad_norm": 3.3140640258789062,
      "learning_rate": 8e-05,
      "loss": 3.4606,
      "step": 8
    },
    {
      "epoch": 0.00020215860465638654,
      "grad_norm": 5.731607437133789,
      "learning_rate": 9e-05,
      "loss": 4.2619,
      "step": 9
    },
    {
      "epoch": 0.00020215860465638654,
      "eval_loss": 2.0114121437072754,
      "eval_runtime": 3693.2986,
      "eval_samples_per_second": 10.151,
      "eval_steps_per_second": 1.269,
      "step": 9
    },
    {
      "epoch": 0.00022462067184042948,
      "grad_norm": 4.831848621368408,
      "learning_rate": 0.0001,
      "loss": 4.6822,
      "step": 10
    },
    {
      "epoch": 0.0002470827390244724,
      "grad_norm": 2.6047534942626953,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.2618,
      "step": 11
    },
    {
      "epoch": 0.00026954480620851535,
      "grad_norm": 2.650613784790039,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.7387,
      "step": 12
    },
    {
      "epoch": 0.0002920068733925583,
      "grad_norm": 2.0770010948181152,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.8619,
      "step": 13
    },
    {
      "epoch": 0.0003144689405766013,
      "grad_norm": 4.928474426269531,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.99,
      "step": 14
    },
    {
      "epoch": 0.00033693100776064424,
      "grad_norm": 3.021501064300537,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.1065,
      "step": 15
    },
    {
      "epoch": 0.0003593930749446872,
      "grad_norm": 2.1191632747650146,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.3574,
      "step": 16
    },
    {
      "epoch": 0.0003818551421287301,
      "grad_norm": 2.9330360889434814,
      "learning_rate": 9.851478631379982e-05,
      "loss": 4.126,
      "step": 17
    },
    {
      "epoch": 0.00040431720931277307,
      "grad_norm": 3.0402603149414062,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.7699,
      "step": 18
    },
    {
      "epoch": 0.00040431720931277307,
      "eval_loss": 1.824965000152588,
      "eval_runtime": 3686.782,
      "eval_samples_per_second": 10.169,
      "eval_steps_per_second": 1.271,
      "step": 18
    },
    {
      "epoch": 0.000426779276496816,
      "grad_norm": 2.7607719898223877,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1566,
      "step": 19
    },
    {
      "epoch": 0.00044924134368085896,
      "grad_norm": 2.5294137001037598,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.1573,
      "step": 20
    },
    {
      "epoch": 0.0004717034108649019,
      "grad_norm": 3.3328206539154053,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.941,
      "step": 21
    },
    {
      "epoch": 0.0004941654780489448,
      "grad_norm": 3.416025161743164,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.0187,
      "step": 22
    },
    {
      "epoch": 0.0005166275452329877,
      "grad_norm": 2.709918975830078,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.157,
      "step": 23
    },
    {
      "epoch": 0.0005390896124170307,
      "grad_norm": 1.9112098217010498,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.7691,
      "step": 24
    },
    {
      "epoch": 0.0005615516796010736,
      "grad_norm": 4.849649906158447,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.0183,
      "step": 25
    },
    {
      "epoch": 0.0005840137467851166,
      "grad_norm": 2.103466749191284,
      "learning_rate": 9.24024048078213e-05,
      "loss": 3.4025,
      "step": 26
    },
    {
      "epoch": 0.0006064758139691596,
      "grad_norm": 3.230963706970215,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.5154,
      "step": 27
    },
    {
      "epoch": 0.0006064758139691596,
      "eval_loss": 1.7792279720306396,
      "eval_runtime": 3681.2941,
      "eval_samples_per_second": 10.184,
      "eval_steps_per_second": 1.273,
      "step": 27
    },
    {
      "epoch": 0.0006289378811532026,
      "grad_norm": 2.934743642807007,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.8063,
      "step": 28
    },
    {
      "epoch": 0.0006513999483372455,
      "grad_norm": 2.2931652069091797,
      "learning_rate": 8.940053768033609e-05,
      "loss": 3.2289,
      "step": 29
    },
    {
      "epoch": 0.0006738620155212885,
      "grad_norm": 2.0550167560577393,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.5572,
      "step": 30
    },
    {
      "epoch": 0.0006963240827053314,
      "grad_norm": 2.689479112625122,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.8316,
      "step": 31
    },
    {
      "epoch": 0.0007187861498893744,
      "grad_norm": 2.3837599754333496,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.6778,
      "step": 32
    },
    {
      "epoch": 0.0007412482170734173,
      "grad_norm": 1.7243388891220093,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.8325,
      "step": 33
    },
    {
      "epoch": 0.0007637102842574603,
      "grad_norm": 1.5656968355178833,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.4658,
      "step": 34
    },
    {
      "epoch": 0.0007861723514415032,
      "grad_norm": 2.050574541091919,
      "learning_rate": 8.213938048432697e-05,
      "loss": 3.0947,
      "step": 35
    },
    {
      "epoch": 0.0008086344186255461,
      "grad_norm": 2.5437257289886475,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.542,
      "step": 36
    },
    {
      "epoch": 0.0008086344186255461,
      "eval_loss": 1.754611611366272,
      "eval_runtime": 3681.2645,
      "eval_samples_per_second": 10.184,
      "eval_steps_per_second": 1.273,
      "step": 36
    },
    {
      "epoch": 0.0008310964858095891,
      "grad_norm": 1.6302906274795532,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.4016,
      "step": 37
    },
    {
      "epoch": 0.000853558552993632,
      "grad_norm": 1.7559148073196411,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.5425,
      "step": 38
    },
    {
      "epoch": 0.000876020620177675,
      "grad_norm": 1.4714686870574951,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.3241,
      "step": 39
    },
    {
      "epoch": 0.0008984826873617179,
      "grad_norm": 1.4767100811004639,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.8463,
      "step": 40
    },
    {
      "epoch": 0.0009209447545457609,
      "grad_norm": 1.9836409091949463,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.7879,
      "step": 41
    },
    {
      "epoch": 0.0009434068217298038,
      "grad_norm": 1.814116358757019,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.1036,
      "step": 42
    },
    {
      "epoch": 0.0009658688889138468,
      "grad_norm": 2.1047916412353516,
      "learning_rate": 7.033683215379002e-05,
      "loss": 3.3429,
      "step": 43
    },
    {
      "epoch": 0.0009883309560978896,
      "grad_norm": 1.9513884782791138,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.781,
      "step": 44
    },
    {
      "epoch": 0.0010107930232819327,
      "grad_norm": 1.578654408454895,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.1111,
      "step": 45
    },
    {
      "epoch": 0.0010107930232819327,
      "eval_loss": 1.7505167722702026,
      "eval_runtime": 3680.9902,
      "eval_samples_per_second": 10.185,
      "eval_steps_per_second": 1.273,
      "step": 45
    },
    {
      "epoch": 0.0010332550904659755,
      "grad_norm": 1.6159331798553467,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.4682,
      "step": 46
    },
    {
      "epoch": 0.0010557171576500185,
      "grad_norm": 1.515406847000122,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.3227,
      "step": 47
    },
    {
      "epoch": 0.0010781792248340614,
      "grad_norm": 1.6186057329177856,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.6773,
      "step": 48
    },
    {
      "epoch": 0.0011006412920181044,
      "grad_norm": 1.5859049558639526,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.9975,
      "step": 49
    },
    {
      "epoch": 0.0011231033592021473,
      "grad_norm": 1.5546660423278809,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.194,
      "step": 50
    },
    {
      "epoch": 0.0011455654263861903,
      "grad_norm": 1.9549919366836548,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.9626,
      "step": 51
    },
    {
      "epoch": 0.0011680274935702332,
      "grad_norm": 1.655892252922058,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.8807,
      "step": 52
    },
    {
      "epoch": 0.0011904895607542762,
      "grad_norm": 1.8876769542694092,
      "learning_rate": 5.348782368720626e-05,
      "loss": 3.6625,
      "step": 53
    },
    {
      "epoch": 0.0012129516279383193,
      "grad_norm": 1.4899976253509521,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.6721,
      "step": 54
    },
    {
      "epoch": 0.0012129516279383193,
      "eval_loss": 1.7459241151809692,
      "eval_runtime": 3680.3071,
      "eval_samples_per_second": 10.187,
      "eval_steps_per_second": 1.274,
      "step": 54
    },
    {
      "epoch": 0.001235413695122362,
      "grad_norm": 2.0449488162994385,
      "learning_rate": 5e-05,
      "loss": 3.4899,
      "step": 55
    },
    {
      "epoch": 0.0012578757623064052,
      "grad_norm": 2.274089813232422,
      "learning_rate": 4.825502516487497e-05,
      "loss": 3.551,
      "step": 56
    },
    {
      "epoch": 0.001280337829490448,
      "grad_norm": 2.418734550476074,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.9936,
      "step": 57
    },
    {
      "epoch": 0.001302799896674491,
      "grad_norm": 1.5241280794143677,
      "learning_rate": 4.477357683661734e-05,
      "loss": 4.1763,
      "step": 58
    },
    {
      "epoch": 0.0013252619638585339,
      "grad_norm": 1.6124359369277954,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.8093,
      "step": 59
    },
    {
      "epoch": 0.001347724031042577,
      "grad_norm": 1.7779384851455688,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.73,
      "step": 60
    },
    {
      "epoch": 0.0013701860982266198,
      "grad_norm": 1.860193133354187,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.7427,
      "step": 61
    },
    {
      "epoch": 0.0013926481654106628,
      "grad_norm": 1.6981223821640015,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.6855,
      "step": 62
    },
    {
      "epoch": 0.0014151102325947057,
      "grad_norm": 1.6831542253494263,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.7359,
      "step": 63
    },
    {
      "epoch": 0.0014151102325947057,
      "eval_loss": 1.7401080131530762,
      "eval_runtime": 3683.6574,
      "eval_samples_per_second": 10.177,
      "eval_steps_per_second": 1.272,
      "step": 63
    },
    {
      "epoch": 0.0014375722997787487,
      "grad_norm": 1.6022491455078125,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.0342,
      "step": 64
    },
    {
      "epoch": 0.0014600343669627916,
      "grad_norm": 1.8418630361557007,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.6607,
      "step": 65
    },
    {
      "epoch": 0.0014824964341468346,
      "grad_norm": 1.5198544263839722,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.8486,
      "step": 66
    },
    {
      "epoch": 0.0015049585013308775,
      "grad_norm": 1.892826795578003,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.1487,
      "step": 67
    },
    {
      "epoch": 0.0015274205685149205,
      "grad_norm": 1.6396154165267944,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 3.4122,
      "step": 68
    },
    {
      "epoch": 0.0015498826356989633,
      "grad_norm": 1.505338191986084,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.1957,
      "step": 69
    },
    {
      "epoch": 0.0015723447028830064,
      "grad_norm": 1.8308162689208984,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.4024,
      "step": 70
    },
    {
      "epoch": 0.0015948067700670492,
      "grad_norm": 1.852408766746521,
      "learning_rate": 2.350403678833976e-05,
      "loss": 3.4826,
      "step": 71
    },
    {
      "epoch": 0.0016172688372510923,
      "grad_norm": 1.7535667419433594,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.8102,
      "step": 72
    },
    {
      "epoch": 0.0016172688372510923,
      "eval_loss": 1.7378809452056885,
      "eval_runtime": 3683.9491,
      "eval_samples_per_second": 10.177,
      "eval_steps_per_second": 1.272,
      "step": 72
    },
    {
      "epoch": 0.0016397309044351351,
      "grad_norm": 1.760179877281189,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.7427,
      "step": 73
    },
    {
      "epoch": 0.0016621929716191782,
      "grad_norm": 1.4445101022720337,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 3.7283,
      "step": 74
    },
    {
      "epoch": 0.001684655038803221,
      "grad_norm": 1.5233592987060547,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.3569,
      "step": 75
    },
    {
      "epoch": 0.001707117105987264,
      "grad_norm": 1.6450163125991821,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 4.1236,
      "step": 76
    },
    {
      "epoch": 0.001729579173171307,
      "grad_norm": 1.7483961582183838,
      "learning_rate": 1.526708147705013e-05,
      "loss": 3.4614,
      "step": 77
    },
    {
      "epoch": 0.00175204124035535,
      "grad_norm": 1.6474915742874146,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.6418,
      "step": 78
    },
    {
      "epoch": 0.0017745033075393928,
      "grad_norm": 1.821834921836853,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 3.7526,
      "step": 79
    },
    {
      "epoch": 0.0017969653747234359,
      "grad_norm": 1.957961082458496,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 3.4547,
      "step": 80
    },
    {
      "epoch": 0.0018194274419074787,
      "grad_norm": 1.7345044612884521,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.4015,
      "step": 81
    },
    {
      "epoch": 0.0018194274419074787,
      "eval_loss": 1.7359950542449951,
      "eval_runtime": 3689.1959,
      "eval_samples_per_second": 10.162,
      "eval_steps_per_second": 1.27,
      "step": 81
    },
    {
      "epoch": 0.0018418895090915217,
      "grad_norm": 1.4380539655685425,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.8638,
      "step": 82
    },
    {
      "epoch": 0.0018643515762755646,
      "grad_norm": 1.7943803071975708,
      "learning_rate": 8.548121372247918e-06,
      "loss": 3.9001,
      "step": 83
    },
    {
      "epoch": 0.0018868136434596076,
      "grad_norm": 1.9069151878356934,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.5066,
      "step": 84
    },
    {
      "epoch": 0.0019092757106436505,
      "grad_norm": 1.470371961593628,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.9766,
      "step": 85
    },
    {
      "epoch": 0.0019317377778276935,
      "grad_norm": 1.998091697692871,
      "learning_rate": 5.852620357053651e-06,
      "loss": 3.3901,
      "step": 86
    },
    {
      "epoch": 0.0019541998450117366,
      "grad_norm": 1.914188027381897,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.6886,
      "step": 87
    },
    {
      "epoch": 0.001976661912195779,
      "grad_norm": 1.7242233753204346,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.8862,
      "step": 88
    },
    {
      "epoch": 0.0019991239793798223,
      "grad_norm": 2.258370876312256,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 3.637,
      "step": 89
    },
    {
      "epoch": 0.0020215860465638653,
      "grad_norm": 1.4420782327651978,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.3784,
      "step": 90
    },
    {
      "epoch": 0.0020215860465638653,
      "eval_loss": 1.7353334426879883,
      "eval_runtime": 3683.2503,
      "eval_samples_per_second": 10.179,
      "eval_steps_per_second": 1.273,
      "step": 90
    },
    {
      "epoch": 0.0020440481137479084,
      "grad_norm": 1.5986779928207397,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.7943,
      "step": 91
    },
    {
      "epoch": 0.002066510180931951,
      "grad_norm": 1.8626093864440918,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 3.2405,
      "step": 92
    },
    {
      "epoch": 0.002088972248115994,
      "grad_norm": 1.8892990350723267,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.6672,
      "step": 93
    },
    {
      "epoch": 0.002111434315300037,
      "grad_norm": 1.4795621633529663,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 3.5423,
      "step": 94
    },
    {
      "epoch": 0.00213389638248408,
      "grad_norm": 1.5005255937576294,
      "learning_rate": 7.596123493895991e-07,
      "loss": 3.5053,
      "step": 95
    },
    {
      "epoch": 0.0021563584496681228,
      "grad_norm": 1.7678977251052856,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.5019,
      "step": 96
    },
    {
      "epoch": 0.002178820516852166,
      "grad_norm": 2.1480631828308105,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 3.2112,
      "step": 97
    },
    {
      "epoch": 0.002201282584036209,
      "grad_norm": 1.2812981605529785,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 3.7643,
      "step": 98
    },
    {
      "epoch": 0.002223744651220252,
      "grad_norm": 1.8966565132141113,
      "learning_rate": 3.04586490452119e-08,
      "loss": 3.2049,
      "step": 99
    },
    {
      "epoch": 0.002223744651220252,
      "eval_loss": 1.7351884841918945,
      "eval_runtime": 3690.552,
      "eval_samples_per_second": 10.158,
      "eval_steps_per_second": 1.27,
      "step": 99
    },
    {
      "epoch": 0.0022462067184042945,
      "grad_norm": 1.917539119720459,
      "learning_rate": 0.0,
      "loss": 3.8109,
      "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": 6.53458201903104e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}