{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9216589861751152,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009216589861751152,
      "grad_norm": 0.6020486950874329,
      "learning_rate": 1e-05,
      "loss": 1.2617,
      "step": 1
    },
    {
      "epoch": 0.009216589861751152,
      "eval_loss": 1.3991881608963013,
      "eval_runtime": 12.5287,
      "eval_samples_per_second": 7.343,
      "eval_steps_per_second": 0.958,
      "step": 1
    },
    {
      "epoch": 0.018433179723502304,
      "grad_norm": 0.7095889449119568,
      "learning_rate": 2e-05,
      "loss": 1.4084,
      "step": 2
    },
    {
      "epoch": 0.027649769585253458,
      "grad_norm": 0.6638815999031067,
      "learning_rate": 3e-05,
      "loss": 1.4946,
      "step": 3
    },
    {
      "epoch": 0.03686635944700461,
      "grad_norm": 0.5155582427978516,
      "learning_rate": 4e-05,
      "loss": 1.4326,
      "step": 4
    },
    {
      "epoch": 0.04608294930875576,
      "grad_norm": 0.6354131102561951,
      "learning_rate": 5e-05,
      "loss": 1.4885,
      "step": 5
    },
    {
      "epoch": 0.055299539170506916,
      "grad_norm": 1.0160484313964844,
      "learning_rate": 6e-05,
      "loss": 1.6363,
      "step": 6
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 1.0248684883117676,
      "learning_rate": 7e-05,
      "loss": 1.5755,
      "step": 7
    },
    {
      "epoch": 0.07373271889400922,
      "grad_norm": 0.6762824058532715,
      "learning_rate": 8e-05,
      "loss": 1.2228,
      "step": 8
    },
    {
      "epoch": 0.08294930875576037,
      "grad_norm": 0.6877623796463013,
      "learning_rate": 9e-05,
      "loss": 1.3707,
      "step": 9
    },
    {
      "epoch": 0.08294930875576037,
      "eval_loss": 1.2450069189071655,
      "eval_runtime": 11.0469,
      "eval_samples_per_second": 8.328,
      "eval_steps_per_second": 1.086,
      "step": 9
    },
    {
      "epoch": 0.09216589861751152,
      "grad_norm": 0.5674454569816589,
      "learning_rate": 0.0001,
      "loss": 1.2391,
      "step": 10
    },
    {
      "epoch": 0.10138248847926268,
      "grad_norm": 1.004395842552185,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.2827,
      "step": 11
    },
    {
      "epoch": 0.11059907834101383,
      "grad_norm": 0.9745106101036072,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.309,
      "step": 12
    },
    {
      "epoch": 0.11981566820276497,
      "grad_norm": 0.7911168336868286,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.2503,
      "step": 13
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.8025805950164795,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.0757,
      "step": 14
    },
    {
      "epoch": 0.1382488479262673,
      "grad_norm": 0.6433544754981995,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0867,
      "step": 15
    },
    {
      "epoch": 0.14746543778801843,
      "grad_norm": 1.022860050201416,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2298,
      "step": 16
    },
    {
      "epoch": 0.15668202764976957,
      "grad_norm": 0.7965829372406006,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.0882,
      "step": 17
    },
    {
      "epoch": 0.16589861751152074,
      "grad_norm": 0.5904141664505005,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.0843,
      "step": 18
    },
    {
      "epoch": 0.16589861751152074,
      "eval_loss": 1.1211318969726562,
      "eval_runtime": 11.0662,
      "eval_samples_per_second": 8.314,
      "eval_steps_per_second": 1.084,
      "step": 18
    },
    {
      "epoch": 0.17511520737327188,
      "grad_norm": 0.8747940063476562,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1302,
      "step": 19
    },
    {
      "epoch": 0.18433179723502305,
      "grad_norm": 0.914085865020752,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.243,
      "step": 20
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 0.7389581203460693,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.006,
      "step": 21
    },
    {
      "epoch": 0.20276497695852536,
      "grad_norm": 0.7628523707389832,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0089,
      "step": 22
    },
    {
      "epoch": 0.2119815668202765,
      "grad_norm": 0.9323219656944275,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.1665,
      "step": 23
    },
    {
      "epoch": 0.22119815668202766,
      "grad_norm": 0.9112899303436279,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.1546,
      "step": 24
    },
    {
      "epoch": 0.2304147465437788,
      "grad_norm": 0.8170014023780823,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.248,
      "step": 25
    },
    {
      "epoch": 0.23963133640552994,
      "grad_norm": 0.8940214514732361,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.1786,
      "step": 26
    },
    {
      "epoch": 0.2488479262672811,
      "grad_norm": 0.7923563122749329,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.092,
      "step": 27
    },
    {
      "epoch": 0.2488479262672811,
      "eval_loss": 1.0744620561599731,
      "eval_runtime": 11.0513,
      "eval_samples_per_second": 8.325,
      "eval_steps_per_second": 1.086,
      "step": 27
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.7313264012336731,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1987,
      "step": 28
    },
    {
      "epoch": 0.2672811059907834,
      "grad_norm": 0.7360963225364685,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.0541,
      "step": 29
    },
    {
      "epoch": 0.2764976958525346,
      "grad_norm": 0.8408584594726562,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.0301,
      "step": 30
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.7449260354042053,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.1199,
      "step": 31
    },
    {
      "epoch": 0.29493087557603687,
      "grad_norm": 0.7829388976097107,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.1198,
      "step": 32
    },
    {
      "epoch": 0.30414746543778803,
      "grad_norm": 0.6732165217399597,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9592,
      "step": 33
    },
    {
      "epoch": 0.31336405529953915,
      "grad_norm": 0.8087509870529175,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.2257,
      "step": 34
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.7753763794898987,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.1163,
      "step": 35
    },
    {
      "epoch": 0.3317972350230415,
      "grad_norm": 0.896714448928833,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.1567,
      "step": 36
    },
    {
      "epoch": 0.3317972350230415,
      "eval_loss": 1.049620270729065,
      "eval_runtime": 11.0483,
      "eval_samples_per_second": 8.327,
      "eval_steps_per_second": 1.086,
      "step": 36
    },
    {
      "epoch": 0.34101382488479265,
      "grad_norm": 0.9242726564407349,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2014,
      "step": 37
    },
    {
      "epoch": 0.35023041474654376,
      "grad_norm": 0.7677705883979797,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.9391,
      "step": 38
    },
    {
      "epoch": 0.35944700460829493,
      "grad_norm": 1.0923584699630737,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.0083,
      "step": 39
    },
    {
      "epoch": 0.3686635944700461,
      "grad_norm": 0.5865107178688049,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0555,
      "step": 40
    },
    {
      "epoch": 0.3778801843317972,
      "grad_norm": 0.8392916321754456,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.1126,
      "step": 41
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 0.7484853863716125,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.1251,
      "step": 42
    },
    {
      "epoch": 0.39631336405529954,
      "grad_norm": 0.9701381921768188,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.268,
      "step": 43
    },
    {
      "epoch": 0.4055299539170507,
      "grad_norm": 0.901788055896759,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.1903,
      "step": 44
    },
    {
      "epoch": 0.4147465437788018,
      "grad_norm": 0.516913890838623,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.9569,
      "step": 45
    },
    {
      "epoch": 0.4147465437788018,
      "eval_loss": 1.0289723873138428,
      "eval_runtime": 11.0778,
      "eval_samples_per_second": 8.305,
      "eval_steps_per_second": 1.083,
      "step": 45
    },
    {
      "epoch": 0.423963133640553,
      "grad_norm": 0.6888841390609741,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1008,
      "step": 46
    },
    {
      "epoch": 0.43317972350230416,
      "grad_norm": 0.8466167449951172,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.1525,
      "step": 47
    },
    {
      "epoch": 0.4423963133640553,
      "grad_norm": 0.7238967418670654,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.9355,
      "step": 48
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 0.6457561254501343,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.0782,
      "step": 49
    },
    {
      "epoch": 0.4608294930875576,
      "grad_norm": 0.6437515616416931,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.8966,
      "step": 50
    },
    {
      "epoch": 0.4700460829493088,
      "grad_norm": 0.7265362739562988,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.0726,
      "step": 51
    },
    {
      "epoch": 0.4792626728110599,
      "grad_norm": 0.6666373610496521,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.9776,
      "step": 52
    },
    {
      "epoch": 0.48847926267281105,
      "grad_norm": 1.1823261976242065,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.0739,
      "step": 53
    },
    {
      "epoch": 0.4976958525345622,
      "grad_norm": 0.7592246532440186,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.9637,
      "step": 54
    },
    {
      "epoch": 0.4976958525345622,
      "eval_loss": 1.0075299739837646,
      "eval_runtime": 11.0761,
      "eval_samples_per_second": 8.306,
      "eval_steps_per_second": 1.083,
      "step": 54
    },
    {
      "epoch": 0.5069124423963134,
      "grad_norm": 0.9630380868911743,
      "learning_rate": 5e-05,
      "loss": 1.1823,
      "step": 55
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.8581224679946899,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.9804,
      "step": 56
    },
    {
      "epoch": 0.5253456221198156,
      "grad_norm": 0.72942715883255,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.0405,
      "step": 57
    },
    {
      "epoch": 0.5345622119815668,
      "grad_norm": 0.7310763001441956,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.9986,
      "step": 58
    },
    {
      "epoch": 0.543778801843318,
      "grad_norm": 0.8449254035949707,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.9641,
      "step": 59
    },
    {
      "epoch": 0.5529953917050692,
      "grad_norm": 0.8063848614692688,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.9988,
      "step": 60
    },
    {
      "epoch": 0.5622119815668203,
      "grad_norm": 0.9789047837257385,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.0653,
      "step": 61
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.8241631388664246,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.0918,
      "step": 62
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 1.76102876663208,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.1036,
      "step": 63
    },
    {
      "epoch": 0.5806451612903226,
      "eval_loss": 0.9918219447135925,
      "eval_runtime": 11.0869,
      "eval_samples_per_second": 8.298,
      "eval_steps_per_second": 1.082,
      "step": 63
    },
    {
      "epoch": 0.5898617511520737,
      "grad_norm": 0.57708740234375,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9456,
      "step": 64
    },
    {
      "epoch": 0.5990783410138248,
      "grad_norm": 0.8000180721282959,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8919,
      "step": 65
    },
    {
      "epoch": 0.6082949308755761,
      "grad_norm": 0.759195864200592,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.921,
      "step": 66
    },
    {
      "epoch": 0.6175115207373272,
      "grad_norm": 0.7203258872032166,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.987,
      "step": 67
    },
    {
      "epoch": 0.6267281105990783,
      "grad_norm": 1.042421817779541,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.1359,
      "step": 68
    },
    {
      "epoch": 0.6359447004608295,
      "grad_norm": 0.7227110266685486,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.9977,
      "step": 69
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.8088738322257996,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.127,
      "step": 70
    },
    {
      "epoch": 0.6543778801843319,
      "grad_norm": 0.7786197662353516,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.0038,
      "step": 71
    },
    {
      "epoch": 0.663594470046083,
      "grad_norm": 0.8227571845054626,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0009,
      "step": 72
    },
    {
      "epoch": 0.663594470046083,
      "eval_loss": 0.9819597005844116,
      "eval_runtime": 11.0775,
      "eval_samples_per_second": 8.305,
      "eval_steps_per_second": 1.083,
      "step": 72
    },
    {
      "epoch": 0.6728110599078341,
      "grad_norm": 1.0306525230407715,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.0768,
      "step": 73
    },
    {
      "epoch": 0.6820276497695853,
      "grad_norm": 0.6918361186981201,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8636,
      "step": 74
    },
    {
      "epoch": 0.6912442396313364,
      "grad_norm": 0.8258764147758484,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.9472,
      "step": 75
    },
    {
      "epoch": 0.7004608294930875,
      "grad_norm": 0.8010578751564026,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7877,
      "step": 76
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 0.7281570434570312,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.8955,
      "step": 77
    },
    {
      "epoch": 0.7188940092165899,
      "grad_norm": 0.9054828882217407,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.0624,
      "step": 78
    },
    {
      "epoch": 0.728110599078341,
      "grad_norm": 0.8313905000686646,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.1328,
      "step": 79
    },
    {
      "epoch": 0.7373271889400922,
      "grad_norm": 0.7095636129379272,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.9775,
      "step": 80
    },
    {
      "epoch": 0.7465437788018433,
      "grad_norm": 0.7196549773216248,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.8421,
      "step": 81
    },
    {
      "epoch": 0.7465437788018433,
      "eval_loss": 0.9770323038101196,
      "eval_runtime": 11.0706,
      "eval_samples_per_second": 8.31,
      "eval_steps_per_second": 1.084,
      "step": 81
    },
    {
      "epoch": 0.7557603686635944,
      "grad_norm": 1.0790183544158936,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1106,
      "step": 82
    },
    {
      "epoch": 0.7649769585253456,
      "grad_norm": 0.5855507850646973,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.8817,
      "step": 83
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.7169812917709351,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.9767,
      "step": 84
    },
    {
      "epoch": 0.783410138248848,
      "grad_norm": 0.963414192199707,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.0716,
      "step": 85
    },
    {
      "epoch": 0.7926267281105991,
      "grad_norm": 0.8065404295921326,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.9223,
      "step": 86
    },
    {
      "epoch": 0.8018433179723502,
      "grad_norm": 0.9426746368408203,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.0459,
      "step": 87
    },
    {
      "epoch": 0.8110599078341014,
      "grad_norm": 0.8868968486785889,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.0269,
      "step": 88
    },
    {
      "epoch": 0.8202764976958525,
      "grad_norm": 0.7493672966957092,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.0344,
      "step": 89
    },
    {
      "epoch": 0.8294930875576036,
      "grad_norm": 0.9347946643829346,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.0281,
      "step": 90
    },
    {
      "epoch": 0.8294930875576036,
      "eval_loss": 0.9749319553375244,
      "eval_runtime": 11.1139,
      "eval_samples_per_second": 8.278,
      "eval_steps_per_second": 1.08,
      "step": 90
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 0.8222431540489197,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.943,
      "step": 91
    },
    {
      "epoch": 0.847926267281106,
      "grad_norm": 0.8993135094642639,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.9071,
      "step": 92
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.6946989893913269,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.8811,
      "step": 93
    },
    {
      "epoch": 0.8663594470046083,
      "grad_norm": 0.8377668857574463,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.8923,
      "step": 94
    },
    {
      "epoch": 0.8755760368663594,
      "grad_norm": 0.951482355594635,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.0178,
      "step": 95
    },
    {
      "epoch": 0.8847926267281107,
      "grad_norm": 0.9337249994277954,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.1243,
      "step": 96
    },
    {
      "epoch": 0.8940092165898618,
      "grad_norm": 0.8228960037231445,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.0891,
      "step": 97
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 1.0015751123428345,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.1583,
      "step": 98
    },
    {
      "epoch": 0.9124423963133641,
      "grad_norm": 1.1057360172271729,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.0895,
      "step": 99
    },
    {
      "epoch": 0.9124423963133641,
      "eval_loss": 0.9739326238632202,
      "eval_runtime": 11.0518,
      "eval_samples_per_second": 8.324,
      "eval_steps_per_second": 1.086,
      "step": 99
    },
    {
      "epoch": 0.9216589861751152,
      "grad_norm": 0.7851902842521667,
      "learning_rate": 0.0,
      "loss": 1.0242,
      "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": 7.938193934096794e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}