{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.984182776801406,
  "eval_steps": 500,
  "global_step": 424,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0046865846514352666,
      "grad_norm": 0.051384374499320984,
      "learning_rate": 0.0,
      "loss": 0.9135436415672302,
      "num_tokens": 27577.0,
      "step": 1
    },
    {
      "epoch": 0.009373169302870533,
      "grad_norm": 0.05661161243915558,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.0476775169372559,
      "num_tokens": 53769.0,
      "step": 2
    },
    {
      "epoch": 0.014059753954305799,
      "grad_norm": 0.06055368855595589,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.018783688545227,
      "num_tokens": 83710.0,
      "step": 3
    },
    {
      "epoch": 0.018746338605741066,
      "grad_norm": 0.05393720418214798,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.016797661781311,
      "num_tokens": 110526.0,
      "step": 4
    },
    {
      "epoch": 0.023432923257176334,
      "grad_norm": 0.040069058537483215,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.8858492374420166,
      "num_tokens": 141157.0,
      "step": 5
    },
    {
      "epoch": 0.028119507908611598,
      "grad_norm": 0.027801791206002235,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.8189319372177124,
      "num_tokens": 167869.0,
      "step": 6
    },
    {
      "epoch": 0.032806092560046865,
      "grad_norm": 0.03238449990749359,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.8969806432723999,
      "num_tokens": 195198.0,
      "step": 7
    },
    {
      "epoch": 0.03749267721148213,
      "grad_norm": 0.04445185512304306,
      "learning_rate": 6.363636363636364e-05,
      "loss": 0.840364933013916,
      "num_tokens": 222221.0,
      "step": 8
    },
    {
      "epoch": 0.0421792618629174,
      "grad_norm": 0.03980391472578049,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.7074636816978455,
      "num_tokens": 253886.0,
      "step": 9
    },
    {
      "epoch": 0.04686584651435267,
      "grad_norm": 0.037389349192380905,
      "learning_rate": 8.181818181818183e-05,
      "loss": 0.7766112089157104,
      "num_tokens": 282084.0,
      "step": 10
    },
    {
      "epoch": 0.051552431165787935,
      "grad_norm": 0.03370026499032974,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.9224791526794434,
      "num_tokens": 306274.0,
      "step": 11
    },
    {
      "epoch": 0.056239015817223195,
      "grad_norm": 0.030875062569975853,
      "learning_rate": 0.0001,
      "loss": 0.8241673707962036,
      "num_tokens": 333896.0,
      "step": 12
    },
    {
      "epoch": 0.06092560046865846,
      "grad_norm": 0.027592068538069725,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.7796958684921265,
      "num_tokens": 358218.0,
      "step": 13
    },
    {
      "epoch": 0.06561218512009373,
      "grad_norm": 0.021626442670822144,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.8019801378250122,
      "num_tokens": 386330.0,
      "step": 14
    },
    {
      "epoch": 0.070298769771529,
      "grad_norm": 0.027092255651950836,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.7218313217163086,
      "num_tokens": 418249.0,
      "step": 15
    },
    {
      "epoch": 0.07498535442296426,
      "grad_norm": 0.023632660508155823,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.8899157047271729,
      "num_tokens": 445646.0,
      "step": 16
    },
    {
      "epoch": 0.07967193907439953,
      "grad_norm": 0.03362816572189331,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8559063673019409,
      "num_tokens": 470930.0,
      "step": 17
    },
    {
      "epoch": 0.0843585237258348,
      "grad_norm": 0.020501242950558662,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.7042301297187805,
      "num_tokens": 498059.0,
      "step": 18
    },
    {
      "epoch": 0.08904510837727006,
      "grad_norm": 0.018128708004951477,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.7310709953308105,
      "num_tokens": 530592.0,
      "step": 19
    },
    {
      "epoch": 0.09373169302870533,
      "grad_norm": 0.018460258841514587,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.6924107074737549,
      "num_tokens": 562330.0,
      "step": 20
    },
    {
      "epoch": 0.0984182776801406,
      "grad_norm": 0.02003256231546402,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7911130785942078,
      "num_tokens": 589956.0,
      "step": 21
    },
    {
      "epoch": 0.10310486233157587,
      "grad_norm": 0.018715323880314827,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.7266192436218262,
      "num_tokens": 616859.0,
      "step": 22
    },
    {
      "epoch": 0.10779144698301113,
      "grad_norm": 0.01817537099123001,
      "learning_rate": 0.0002,
      "loss": 0.6269426941871643,
      "num_tokens": 642701.0,
      "step": 23
    },
    {
      "epoch": 0.11247803163444639,
      "grad_norm": 0.018678782507777214,
      "learning_rate": 0.00019999700625010443,
      "loss": 0.7403688430786133,
      "num_tokens": 676504.0,
      "step": 24
    },
    {
      "epoch": 0.11716461628588166,
      "grad_norm": 0.020272132009267807,
      "learning_rate": 0.0001999880251796685,
      "loss": 0.7321911454200745,
      "num_tokens": 705912.0,
      "step": 25
    },
    {
      "epoch": 0.12185120093731693,
      "grad_norm": 0.01957310177385807,
      "learning_rate": 0.00019997305732643374,
      "loss": 0.7002245187759399,
      "num_tokens": 732194.0,
      "step": 26
    },
    {
      "epoch": 0.1265377855887522,
      "grad_norm": 0.01948855258524418,
      "learning_rate": 0.00019995210358660038,
      "loss": 0.7347348928451538,
      "num_tokens": 759652.0,
      "step": 27
    },
    {
      "epoch": 0.13122437024018746,
      "grad_norm": 0.023063676431775093,
      "learning_rate": 0.00019992516521477352,
      "loss": 0.6699464917182922,
      "num_tokens": 785242.0,
      "step": 28
    },
    {
      "epoch": 0.13591095489162272,
      "grad_norm": 0.021980423480272293,
      "learning_rate": 0.00019989224382388813,
      "loss": 0.6514506340026855,
      "num_tokens": 810494.0,
      "step": 29
    },
    {
      "epoch": 0.140597539543058,
      "grad_norm": 0.02254093810915947,
      "learning_rate": 0.00019985334138511237,
      "loss": 0.8430403470993042,
      "num_tokens": 833820.0,
      "step": 30
    },
    {
      "epoch": 0.14528412419449327,
      "grad_norm": 0.020795788615942,
      "learning_rate": 0.00019980846022772978,
      "loss": 0.8233045339584351,
      "num_tokens": 855801.0,
      "step": 31
    },
    {
      "epoch": 0.14997070884592853,
      "grad_norm": 0.02146788127720356,
      "learning_rate": 0.00019975760303899952,
      "loss": 0.8730515241622925,
      "num_tokens": 883156.0,
      "step": 32
    },
    {
      "epoch": 0.1546572934973638,
      "grad_norm": 0.020464448258280754,
      "learning_rate": 0.0001997007728639956,
      "loss": 0.6831374168395996,
      "num_tokens": 910253.0,
      "step": 33
    },
    {
      "epoch": 0.15934387814879905,
      "grad_norm": 0.02013879455626011,
      "learning_rate": 0.0001996379731054247,
      "loss": 0.701470673084259,
      "num_tokens": 939939.0,
      "step": 34
    },
    {
      "epoch": 0.16403046280023434,
      "grad_norm": 0.02222023718059063,
      "learning_rate": 0.00019956920752342225,
      "loss": 0.803076446056366,
      "num_tokens": 964809.0,
      "step": 35
    },
    {
      "epoch": 0.1687170474516696,
      "grad_norm": 0.019367733970284462,
      "learning_rate": 0.00019949448023532726,
      "loss": 0.775732696056366,
      "num_tokens": 990661.0,
      "step": 36
    },
    {
      "epoch": 0.17340363210310486,
      "grad_norm": 0.016949206590652466,
      "learning_rate": 0.00019941379571543596,
      "loss": 0.6347322463989258,
      "num_tokens": 1016336.0,
      "step": 37
    },
    {
      "epoch": 0.17809021675454012,
      "grad_norm": 0.01832510717213154,
      "learning_rate": 0.00019932715879473386,
      "loss": 0.703629732131958,
      "num_tokens": 1043264.0,
      "step": 38
    },
    {
      "epoch": 0.1827768014059754,
      "grad_norm": 0.01435445062816143,
      "learning_rate": 0.00019923457466060636,
      "loss": 0.7372844219207764,
      "num_tokens": 1080968.0,
      "step": 39
    },
    {
      "epoch": 0.18746338605741067,
      "grad_norm": 0.017573175951838493,
      "learning_rate": 0.00019913604885652832,
      "loss": 0.6736240386962891,
      "num_tokens": 1107301.0,
      "step": 40
    },
    {
      "epoch": 0.19214997070884593,
      "grad_norm": 0.018299151211977005,
      "learning_rate": 0.00019903158728173205,
      "loss": 0.6043229103088379,
      "num_tokens": 1135940.0,
      "step": 41
    },
    {
      "epoch": 0.1968365553602812,
      "grad_norm": 0.017435841262340546,
      "learning_rate": 0.00019892119619085413,
      "loss": 0.8914448618888855,
      "num_tokens": 1168551.0,
      "step": 42
    },
    {
      "epoch": 0.20152314001171645,
      "grad_norm": 0.017910778522491455,
      "learning_rate": 0.00019880488219356087,
      "loss": 0.6544086337089539,
      "num_tokens": 1192822.0,
      "step": 43
    },
    {
      "epoch": 0.20620972466315174,
      "grad_norm": 0.014131936244666576,
      "learning_rate": 0.00019868265225415265,
      "loss": 0.5981888175010681,
      "num_tokens": 1224533.0,
      "step": 44
    },
    {
      "epoch": 0.210896309314587,
      "grad_norm": 0.013926932588219643,
      "learning_rate": 0.00019855451369114676,
      "loss": 0.5678025484085083,
      "num_tokens": 1258277.0,
      "step": 45
    },
    {
      "epoch": 0.21558289396602226,
      "grad_norm": 0.019710620865225792,
      "learning_rate": 0.0001984204741768395,
      "loss": 0.741448163986206,
      "num_tokens": 1283306.0,
      "step": 46
    },
    {
      "epoch": 0.22026947861745752,
      "grad_norm": 0.014478852972388268,
      "learning_rate": 0.00019828054173684644,
      "loss": 0.6968680024147034,
      "num_tokens": 1314849.0,
      "step": 47
    },
    {
      "epoch": 0.22495606326889278,
      "grad_norm": 0.0185406357049942,
      "learning_rate": 0.00019813472474962217,
      "loss": 0.70443195104599,
      "num_tokens": 1341950.0,
      "step": 48
    },
    {
      "epoch": 0.22964264792032807,
      "grad_norm": 0.01472421269863844,
      "learning_rate": 0.00019798303194595846,
      "loss": 0.7086731195449829,
      "num_tokens": 1374717.0,
      "step": 49
    },
    {
      "epoch": 0.23432923257176333,
      "grad_norm": 0.01715102605521679,
      "learning_rate": 0.00019782547240846166,
      "loss": 0.7801943421363831,
      "num_tokens": 1405423.0,
      "step": 50
    },
    {
      "epoch": 0.2390158172231986,
      "grad_norm": 0.01534986775368452,
      "learning_rate": 0.00019766205557100868,
      "loss": 0.7315295934677124,
      "num_tokens": 1435797.0,
      "step": 51
    },
    {
      "epoch": 0.24370240187463385,
      "grad_norm": 0.01790514402091503,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.6989485025405884,
      "num_tokens": 1460603.0,
      "step": 52
    },
    {
      "epoch": 0.24838898652606914,
      "grad_norm": 0.019122600555419922,
      "learning_rate": 0.00019731768948468549,
      "loss": 0.8172528743743896,
      "num_tokens": 1485860.0,
      "step": 53
    },
    {
      "epoch": 0.2530755711775044,
      "grad_norm": 0.015816036611795425,
      "learning_rate": 0.00019713676085473397,
      "loss": 0.6920545101165771,
      "num_tokens": 1516763.0,
      "step": 54
    },
    {
      "epoch": 0.2577621558289397,
      "grad_norm": 0.0181569941341877,
      "learning_rate": 0.00019695001616142915,
      "loss": 0.6596686840057373,
      "num_tokens": 1541863.0,
      "step": 55
    },
    {
      "epoch": 0.2624487404803749,
      "grad_norm": 0.017863502725958824,
      "learning_rate": 0.00019675746658610917,
      "loss": 0.8410529494285583,
      "num_tokens": 1571150.0,
      "step": 56
    },
    {
      "epoch": 0.2671353251318102,
      "grad_norm": 0.017747659236192703,
      "learning_rate": 0.0001965591236576794,
      "loss": 0.6777825355529785,
      "num_tokens": 1596156.0,
      "step": 57
    },
    {
      "epoch": 0.27182190978324544,
      "grad_norm": 0.018964149057865143,
      "learning_rate": 0.0001963549992519223,
      "loss": 0.7582053542137146,
      "num_tokens": 1620023.0,
      "step": 58
    },
    {
      "epoch": 0.27650849443468073,
      "grad_norm": 0.01840493083000183,
      "learning_rate": 0.00019614510559078625,
      "loss": 0.7568569183349609,
      "num_tokens": 1645111.0,
      "step": 59
    },
    {
      "epoch": 0.281195079086116,
      "grad_norm": 0.014947458170354366,
      "learning_rate": 0.00019592945524165374,
      "loss": 0.7009609341621399,
      "num_tokens": 1676825.0,
      "step": 60
    },
    {
      "epoch": 0.28588166373755125,
      "grad_norm": 0.018854359164834023,
      "learning_rate": 0.00019570806111658898,
      "loss": 0.7680045366287231,
      "num_tokens": 1704692.0,
      "step": 61
    },
    {
      "epoch": 0.29056824838898654,
      "grad_norm": 0.018227359279990196,
      "learning_rate": 0.0001954809364715648,
      "loss": 0.7715598940849304,
      "num_tokens": 1731109.0,
      "step": 62
    },
    {
      "epoch": 0.29525483304042177,
      "grad_norm": 0.030492570251226425,
      "learning_rate": 0.00019524809490566877,
      "loss": 0.7712352275848389,
      "num_tokens": 1759415.0,
      "step": 63
    },
    {
      "epoch": 0.29994141769185706,
      "grad_norm": 0.017521576955914497,
      "learning_rate": 0.00019500955036028922,
      "loss": 0.760728120803833,
      "num_tokens": 1785521.0,
      "step": 64
    },
    {
      "epoch": 0.30462800234329235,
      "grad_norm": 0.015448614954948425,
      "learning_rate": 0.00019476531711828027,
      "loss": 0.7066532969474792,
      "num_tokens": 1817775.0,
      "step": 65
    },
    {
      "epoch": 0.3093145869947276,
      "grad_norm": 0.017962772399187088,
      "learning_rate": 0.00019451540980310676,
      "loss": 0.7092620730400085,
      "num_tokens": 1842665.0,
      "step": 66
    },
    {
      "epoch": 0.31400117164616287,
      "grad_norm": 0.017784444615244865,
      "learning_rate": 0.0001942598433779687,
      "loss": 0.7012664079666138,
      "num_tokens": 1869577.0,
      "step": 67
    },
    {
      "epoch": 0.3186877562975981,
      "grad_norm": 0.017005180940032005,
      "learning_rate": 0.00019399863314490526,
      "loss": 0.6345712542533875,
      "num_tokens": 1897675.0,
      "step": 68
    },
    {
      "epoch": 0.3233743409490334,
      "grad_norm": 0.01969163678586483,
      "learning_rate": 0.00019373179474387858,
      "loss": 0.883948802947998,
      "num_tokens": 1925451.0,
      "step": 69
    },
    {
      "epoch": 0.3280609256004687,
      "grad_norm": 0.015260924585163593,
      "learning_rate": 0.0001934593441518374,
      "loss": 0.5999019742012024,
      "num_tokens": 1955944.0,
      "step": 70
    },
    {
      "epoch": 0.3327475102519039,
      "grad_norm": 0.015242267400026321,
      "learning_rate": 0.00019318129768176032,
      "loss": 0.7795001268386841,
      "num_tokens": 1992104.0,
      "step": 71
    },
    {
      "epoch": 0.3374340949033392,
      "grad_norm": 0.015679946169257164,
      "learning_rate": 0.00019289767198167916,
      "loss": 0.6518503427505493,
      "num_tokens": 2024006.0,
      "step": 72
    },
    {
      "epoch": 0.34212067955477443,
      "grad_norm": 0.016625264659523964,
      "learning_rate": 0.0001926084840336821,
      "loss": 0.655728280544281,
      "num_tokens": 2048339.0,
      "step": 73
    },
    {
      "epoch": 0.3468072642062097,
      "grad_norm": 0.016117312014102936,
      "learning_rate": 0.00019231375115289696,
      "loss": 0.6389369964599609,
      "num_tokens": 2079167.0,
      "step": 74
    },
    {
      "epoch": 0.351493848857645,
      "grad_norm": 0.015863342210650444,
      "learning_rate": 0.00019201349098645434,
      "loss": 0.6088578104972839,
      "num_tokens": 2110608.0,
      "step": 75
    },
    {
      "epoch": 0.35618043350908024,
      "grad_norm": 0.0166738610714674,
      "learning_rate": 0.00019170772151243107,
      "loss": 0.6107393503189087,
      "num_tokens": 2142233.0,
      "step": 76
    },
    {
      "epoch": 0.36086701816051553,
      "grad_norm": 0.01740742288529873,
      "learning_rate": 0.0001913964610387738,
      "loss": 0.7315651774406433,
      "num_tokens": 2169376.0,
      "step": 77
    },
    {
      "epoch": 0.3655536028119508,
      "grad_norm": 0.021772760897874832,
      "learning_rate": 0.00019107972820220267,
      "loss": 0.8029112815856934,
      "num_tokens": 2189864.0,
      "step": 78
    },
    {
      "epoch": 0.37024018746338605,
      "grad_norm": 0.021346885710954666,
      "learning_rate": 0.00019075754196709572,
      "loss": 0.7283374667167664,
      "num_tokens": 2212915.0,
      "step": 79
    },
    {
      "epoch": 0.37492677211482134,
      "grad_norm": 0.015978064388036728,
      "learning_rate": 0.00019042992162435302,
      "loss": 0.6502755880355835,
      "num_tokens": 2243293.0,
      "step": 80
    },
    {
      "epoch": 0.37961335676625657,
      "grad_norm": 0.018250679597258568,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.6920264363288879,
      "num_tokens": 2271476.0,
      "step": 81
    },
    {
      "epoch": 0.38429994141769186,
      "grad_norm": 0.018970279023051262,
      "learning_rate": 0.00018975845740522244,
      "loss": 0.8388804197311401,
      "num_tokens": 2301194.0,
      "step": 82
    },
    {
      "epoch": 0.38898652606912715,
      "grad_norm": 0.01729811541736126,
      "learning_rate": 0.0001894146537327533,
      "loss": 0.7298757433891296,
      "num_tokens": 2331066.0,
      "step": 83
    },
    {
      "epoch": 0.3936731107205624,
      "grad_norm": 0.016176382079720497,
      "learning_rate": 0.00018906549635807861,
      "loss": 0.6759993433952332,
      "num_tokens": 2364333.0,
      "step": 84
    },
    {
      "epoch": 0.39835969537199767,
      "grad_norm": 0.02077021636068821,
      "learning_rate": 0.00018871100618699554,
      "loss": 0.6763718128204346,
      "num_tokens": 2391743.0,
      "step": 85
    },
    {
      "epoch": 0.4030462800234329,
      "grad_norm": 0.018082395195961,
      "learning_rate": 0.0001883512044446023,
      "loss": 0.5660803318023682,
      "num_tokens": 2414298.0,
      "step": 86
    },
    {
      "epoch": 0.4077328646748682,
      "grad_norm": 0.014369606971740723,
      "learning_rate": 0.00018798611267402746,
      "loss": 0.6493896245956421,
      "num_tokens": 2448533.0,
      "step": 87
    },
    {
      "epoch": 0.4124194493263035,
      "grad_norm": 0.01696608029305935,
      "learning_rate": 0.00018761575273514003,
      "loss": 0.7302640676498413,
      "num_tokens": 2475822.0,
      "step": 88
    },
    {
      "epoch": 0.4171060339777387,
      "grad_norm": 0.014188491739332676,
      "learning_rate": 0.00018724014680324057,
      "loss": 0.6129812002182007,
      "num_tokens": 2507447.0,
      "step": 89
    },
    {
      "epoch": 0.421792618629174,
      "grad_norm": 0.020873507484793663,
      "learning_rate": 0.0001868593173677335,
      "loss": 0.7562912106513977,
      "num_tokens": 2533325.0,
      "step": 90
    },
    {
      "epoch": 0.42647920328060923,
      "grad_norm": 0.02266933023929596,
      "learning_rate": 0.00018647328723078038,
      "loss": 0.7829717993736267,
      "num_tokens": 2557554.0,
      "step": 91
    },
    {
      "epoch": 0.4311657879320445,
      "grad_norm": 0.01618797518312931,
      "learning_rate": 0.000186082079505935,
      "loss": 0.6683343648910522,
      "num_tokens": 2584256.0,
      "step": 92
    },
    {
      "epoch": 0.4358523725834798,
      "grad_norm": 0.01636049523949623,
      "learning_rate": 0.00018568571761675893,
      "loss": 0.6867488622665405,
      "num_tokens": 2611538.0,
      "step": 93
    },
    {
      "epoch": 0.44053895723491504,
      "grad_norm": 0.019674455747008324,
      "learning_rate": 0.00018528422529541952,
      "loss": 0.7042540311813354,
      "num_tokens": 2634546.0,
      "step": 94
    },
    {
      "epoch": 0.44522554188635033,
      "grad_norm": 0.01726832054555416,
      "learning_rate": 0.0001848776265812687,
      "loss": 0.7717908024787903,
      "num_tokens": 2663498.0,
      "step": 95
    },
    {
      "epoch": 0.44991212653778556,
      "grad_norm": 0.019708722829818726,
      "learning_rate": 0.0001844659458194036,
      "loss": 0.7058840394020081,
      "num_tokens": 2690495.0,
      "step": 96
    },
    {
      "epoch": 0.45459871118922085,
      "grad_norm": 0.015666253864765167,
      "learning_rate": 0.00018404920765920896,
      "loss": 0.6890168190002441,
      "num_tokens": 2721805.0,
      "step": 97
    },
    {
      "epoch": 0.45928529584065614,
      "grad_norm": 0.017277831211686134,
      "learning_rate": 0.00018362743705288125,
      "loss": 0.7441021800041199,
      "num_tokens": 2750865.0,
      "step": 98
    },
    {
      "epoch": 0.46397188049209137,
      "grad_norm": 0.019693659618496895,
      "learning_rate": 0.00018320065925393468,
      "loss": 0.7525553107261658,
      "num_tokens": 2774941.0,
      "step": 99
    },
    {
      "epoch": 0.46865846514352666,
      "grad_norm": 0.018467402085661888,
      "learning_rate": 0.00018276889981568906,
      "loss": 0.7478335499763489,
      "num_tokens": 2798754.0,
      "step": 100
    },
    {
      "epoch": 0.47334504979496195,
      "grad_norm": 0.016140319406986237,
      "learning_rate": 0.00018233218458973984,
      "loss": 0.6552085876464844,
      "num_tokens": 2830956.0,
      "step": 101
    },
    {
      "epoch": 0.4780316344463972,
      "grad_norm": 0.01590798981487751,
      "learning_rate": 0.00018189053972441025,
      "loss": 0.7423396110534668,
      "num_tokens": 2862140.0,
      "step": 102
    },
    {
      "epoch": 0.48271821909783247,
      "grad_norm": 0.01869652047753334,
      "learning_rate": 0.00018144399166318572,
      "loss": 0.7427437901496887,
      "num_tokens": 2886612.0,
      "step": 103
    },
    {
      "epoch": 0.4874048037492677,
      "grad_norm": 0.01759265922009945,
      "learning_rate": 0.0001809925671431304,
      "loss": 0.7087360620498657,
      "num_tokens": 2912450.0,
      "step": 104
    },
    {
      "epoch": 0.492091388400703,
      "grad_norm": 0.02047079987823963,
      "learning_rate": 0.00018053629319328662,
      "loss": 0.7138317227363586,
      "num_tokens": 2937623.0,
      "step": 105
    },
    {
      "epoch": 0.4967779730521383,
      "grad_norm": 0.017713995650410652,
      "learning_rate": 0.00018007519713305605,
      "loss": 0.8792675733566284,
      "num_tokens": 2966948.0,
      "step": 106
    },
    {
      "epoch": 0.5014645577035736,
      "grad_norm": 0.017888452857732773,
      "learning_rate": 0.00017960930657056438,
      "loss": 0.7580028176307678,
      "num_tokens": 2995391.0,
      "step": 107
    },
    {
      "epoch": 0.5061511423550088,
      "grad_norm": 0.01546698808670044,
      "learning_rate": 0.00017913864940100808,
      "loss": 0.6153715252876282,
      "num_tokens": 3027800.0,
      "step": 108
    },
    {
      "epoch": 0.510837727006444,
      "grad_norm": 0.016936223953962326,
      "learning_rate": 0.00017866325380498416,
      "loss": 0.7080944180488586,
      "num_tokens": 3059479.0,
      "step": 109
    },
    {
      "epoch": 0.5155243116578794,
      "grad_norm": 0.014087708666920662,
      "learning_rate": 0.000178183148246803,
      "loss": 0.6673498749732971,
      "num_tokens": 3090276.0,
      "step": 110
    },
    {
      "epoch": 0.5202108963093146,
      "grad_norm": 0.01673322543501854,
      "learning_rate": 0.0001776983614727838,
      "loss": 0.7345165014266968,
      "num_tokens": 3117983.0,
      "step": 111
    },
    {
      "epoch": 0.5248974809607498,
      "grad_norm": 0.020172668620944023,
      "learning_rate": 0.00017720892250953373,
      "loss": 0.7241357564926147,
      "num_tokens": 3142487.0,
      "step": 112
    },
    {
      "epoch": 0.5295840656121851,
      "grad_norm": 0.017690038308501244,
      "learning_rate": 0.00017671486066220965,
      "loss": 0.7055312395095825,
      "num_tokens": 3168339.0,
      "step": 113
    },
    {
      "epoch": 0.5342706502636204,
      "grad_norm": 0.02020364999771118,
      "learning_rate": 0.00017621620551276366,
      "loss": 0.8319218158721924,
      "num_tokens": 3188724.0,
      "step": 114
    },
    {
      "epoch": 0.5389572349150556,
      "grad_norm": 0.01781732589006424,
      "learning_rate": 0.00017571298691817177,
      "loss": 0.6731840372085571,
      "num_tokens": 3212012.0,
      "step": 115
    },
    {
      "epoch": 0.5436438195664909,
      "grad_norm": 0.01930844970047474,
      "learning_rate": 0.00017520523500864625,
      "loss": 0.7961735725402832,
      "num_tokens": 3234866.0,
      "step": 116
    },
    {
      "epoch": 0.5483304042179262,
      "grad_norm": 0.01762983947992325,
      "learning_rate": 0.0001746929801858317,
      "loss": 0.7620041966438293,
      "num_tokens": 3263912.0,
      "step": 117
    },
    {
      "epoch": 0.5530169888693615,
      "grad_norm": 0.01918371021747589,
      "learning_rate": 0.00017417625312098452,
      "loss": 0.7817209362983704,
      "num_tokens": 3291531.0,
      "step": 118
    },
    {
      "epoch": 0.5577035735207967,
      "grad_norm": 0.015562949702143669,
      "learning_rate": 0.0001736550847531366,
      "loss": 0.5484626889228821,
      "num_tokens": 3319717.0,
      "step": 119
    },
    {
      "epoch": 0.562390158172232,
      "grad_norm": 0.014110572636127472,
      "learning_rate": 0.00017312950628724295,
      "loss": 0.6404852867126465,
      "num_tokens": 3353800.0,
      "step": 120
    },
    {
      "epoch": 0.5670767428236673,
      "grad_norm": 0.01469608023762703,
      "learning_rate": 0.0001725995491923131,
      "loss": 0.5291256904602051,
      "num_tokens": 3383165.0,
      "step": 121
    },
    {
      "epoch": 0.5717633274751025,
      "grad_norm": 0.012918651103973389,
      "learning_rate": 0.00017206524519952697,
      "loss": 0.6107466220855713,
      "num_tokens": 3422397.0,
      "step": 122
    },
    {
      "epoch": 0.5764499121265377,
      "grad_norm": 0.020249634981155396,
      "learning_rate": 0.00017152662630033505,
      "loss": 0.8056011199951172,
      "num_tokens": 3446864.0,
      "step": 123
    },
    {
      "epoch": 0.5811364967779731,
      "grad_norm": 0.01469720620661974,
      "learning_rate": 0.00017098372474454277,
      "loss": 0.5424352884292603,
      "num_tokens": 3480661.0,
      "step": 124
    },
    {
      "epoch": 0.5858230814294083,
      "grad_norm": 0.018604544922709465,
      "learning_rate": 0.00017043657303837963,
      "loss": 0.7502825260162354,
      "num_tokens": 3506115.0,
      "step": 125
    },
    {
      "epoch": 0.5905096660808435,
      "grad_norm": 0.018334681168198586,
      "learning_rate": 0.000169885203942553,
      "loss": 0.8402462005615234,
      "num_tokens": 3538294.0,
      "step": 126
    },
    {
      "epoch": 0.5951962507322789,
      "grad_norm": 0.016648396849632263,
      "learning_rate": 0.0001693296504702862,
      "loss": 0.6800752878189087,
      "num_tokens": 3566829.0,
      "step": 127
    },
    {
      "epoch": 0.5998828353837141,
      "grad_norm": 0.01815720461308956,
      "learning_rate": 0.00016876994588534234,
      "loss": 0.6151847839355469,
      "num_tokens": 3593345.0,
      "step": 128
    },
    {
      "epoch": 0.6045694200351494,
      "grad_norm": 0.01732209511101246,
      "learning_rate": 0.00016820612370003221,
      "loss": 0.6896803975105286,
      "num_tokens": 3616682.0,
      "step": 129
    },
    {
      "epoch": 0.6092560046865847,
      "grad_norm": 0.016574790701270103,
      "learning_rate": 0.000167638217673208,
      "loss": 0.6374701261520386,
      "num_tokens": 3643326.0,
      "step": 130
    },
    {
      "epoch": 0.6139425893380199,
      "grad_norm": 0.01585974544286728,
      "learning_rate": 0.00016706626180824186,
      "loss": 0.6000485420227051,
      "num_tokens": 3674755.0,
      "step": 131
    },
    {
      "epoch": 0.6186291739894552,
      "grad_norm": 0.02168286219239235,
      "learning_rate": 0.00016649029035099,
      "loss": 0.6615947484970093,
      "num_tokens": 3702146.0,
      "step": 132
    },
    {
      "epoch": 0.6233157586408905,
      "grad_norm": 0.01953584887087345,
      "learning_rate": 0.0001659103377877423,
      "loss": 0.631389856338501,
      "num_tokens": 3724254.0,
      "step": 133
    },
    {
      "epoch": 0.6280023432923257,
      "grad_norm": 0.01740172505378723,
      "learning_rate": 0.0001653264388431572,
      "loss": 0.782500684261322,
      "num_tokens": 3754889.0,
      "step": 134
    },
    {
      "epoch": 0.632688927943761,
      "grad_norm": 0.01756126992404461,
      "learning_rate": 0.00016473862847818277,
      "loss": 0.6240105628967285,
      "num_tokens": 3780049.0,
      "step": 135
    },
    {
      "epoch": 0.6373755125951962,
      "grad_norm": 0.018631862476468086,
      "learning_rate": 0.00016414694188796345,
      "loss": 0.6254751682281494,
      "num_tokens": 3805994.0,
      "step": 136
    },
    {
      "epoch": 0.6420620972466315,
      "grad_norm": 0.01772165298461914,
      "learning_rate": 0.00016355141449973256,
      "loss": 0.7138672471046448,
      "num_tokens": 3838692.0,
      "step": 137
    },
    {
      "epoch": 0.6467486818980668,
      "grad_norm": 0.02134813368320465,
      "learning_rate": 0.0001629520819706912,
      "loss": 0.6843606233596802,
      "num_tokens": 3861136.0,
      "step": 138
    },
    {
      "epoch": 0.651435266549502,
      "grad_norm": 0.019024241715669632,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.7739150524139404,
      "num_tokens": 3884299.0,
      "step": 139
    },
    {
      "epoch": 0.6561218512009374,
      "grad_norm": 0.017018890008330345,
      "learning_rate": 0.0001617421452559971,
      "loss": 0.7982111573219299,
      "num_tokens": 3911990.0,
      "step": 140
    },
    {
      "epoch": 0.6608084358523726,
      "grad_norm": 0.017716465517878532,
      "learning_rate": 0.0001611316135153026,
      "loss": 0.6516788005828857,
      "num_tokens": 3937590.0,
      "step": 141
    },
    {
      "epoch": 0.6654950205038078,
      "grad_norm": 0.018196681514382362,
      "learning_rate": 0.00016051742151937655,
      "loss": 0.6962698101997375,
      "num_tokens": 3968492.0,
      "step": 142
    },
    {
      "epoch": 0.6701816051552432,
      "grad_norm": 0.019828489050269127,
      "learning_rate": 0.0001598996060429634,
      "loss": 0.7837550640106201,
      "num_tokens": 3992077.0,
      "step": 143
    },
    {
      "epoch": 0.6748681898066784,
      "grad_norm": 0.019504865631461143,
      "learning_rate": 0.00015927820407776353,
      "loss": 0.8257341384887695,
      "num_tokens": 4017854.0,
      "step": 144
    },
    {
      "epoch": 0.6795547744581136,
      "grad_norm": 0.024247588589787483,
      "learning_rate": 0.0001586532528302183,
      "loss": 0.7519227266311646,
      "num_tokens": 4040498.0,
      "step": 145
    },
    {
      "epoch": 0.6842413591095489,
      "grad_norm": 0.017198674380779266,
      "learning_rate": 0.00015802478971928242,
      "loss": 0.6746048331260681,
      "num_tokens": 4064754.0,
      "step": 146
    },
    {
      "epoch": 0.6889279437609842,
      "grad_norm": 0.018579604104161263,
      "learning_rate": 0.0001573928523741832,
      "loss": 0.8102442622184753,
      "num_tokens": 4088447.0,
      "step": 147
    },
    {
      "epoch": 0.6936145284124194,
      "grad_norm": 0.017206164076924324,
      "learning_rate": 0.00015675747863216801,
      "loss": 0.6687013506889343,
      "num_tokens": 4118049.0,
      "step": 148
    },
    {
      "epoch": 0.6983011130638547,
      "grad_norm": 0.018775764852762222,
      "learning_rate": 0.00015611870653623825,
      "loss": 0.7222660183906555,
      "num_tokens": 4141820.0,
      "step": 149
    },
    {
      "epoch": 0.70298769771529,
      "grad_norm": 0.01597282849252224,
      "learning_rate": 0.00015547657433287183,
      "loss": 0.7305333018302917,
      "num_tokens": 4171467.0,
      "step": 150
    },
    {
      "epoch": 0.7076742823667252,
      "grad_norm": 0.014281094074249268,
      "learning_rate": 0.0001548311204697331,
      "loss": 0.6703628301620483,
      "num_tokens": 4210286.0,
      "step": 151
    },
    {
      "epoch": 0.7123608670181605,
      "grad_norm": 0.021154943853616714,
      "learning_rate": 0.00015418238359337077,
      "loss": 0.6685652732849121,
      "num_tokens": 4234631.0,
      "step": 152
    },
    {
      "epoch": 0.7170474516695958,
      "grad_norm": 0.018537605181336403,
      "learning_rate": 0.00015353040254690393,
      "loss": 0.6078515648841858,
      "num_tokens": 4260789.0,
      "step": 153
    },
    {
      "epoch": 0.7217340363210311,
      "grad_norm": 0.01671479269862175,
      "learning_rate": 0.0001528752163676964,
      "loss": 0.7512734532356262,
      "num_tokens": 4291494.0,
      "step": 154
    },
    {
      "epoch": 0.7264206209724663,
      "grad_norm": 0.015522940084338188,
      "learning_rate": 0.00015221686428501928,
      "loss": 0.6290964484214783,
      "num_tokens": 4321851.0,
      "step": 155
    },
    {
      "epoch": 0.7311072056239016,
      "grad_norm": 0.018737254664301872,
      "learning_rate": 0.00015155538571770218,
      "loss": 0.6476538777351379,
      "num_tokens": 4345682.0,
      "step": 156
    },
    {
      "epoch": 0.7357937902753369,
      "grad_norm": 0.016887914389371872,
      "learning_rate": 0.0001508908202717729,
      "loss": 0.7374083995819092,
      "num_tokens": 4377398.0,
      "step": 157
    },
    {
      "epoch": 0.7404803749267721,
      "grad_norm": 0.019042199477553368,
      "learning_rate": 0.00015022320773808612,
      "loss": 0.727727472782135,
      "num_tokens": 4407190.0,
      "step": 158
    },
    {
      "epoch": 0.7451669595782073,
      "grad_norm": 0.015718845650553703,
      "learning_rate": 0.00014955258808994096,
      "loss": 0.7678956389427185,
      "num_tokens": 4443267.0,
      "step": 159
    },
    {
      "epoch": 0.7498535442296427,
      "grad_norm": 0.01766720600426197,
      "learning_rate": 0.00014887900148068735,
      "loss": 0.6393877267837524,
      "num_tokens": 4471233.0,
      "step": 160
    },
    {
      "epoch": 0.7545401288810779,
      "grad_norm": 0.01771809719502926,
      "learning_rate": 0.0001482024882413222,
      "loss": 0.7477349042892456,
      "num_tokens": 4498609.0,
      "step": 161
    },
    {
      "epoch": 0.7592267135325131,
      "grad_norm": 0.01701246201992035,
      "learning_rate": 0.00014752308887807427,
      "loss": 0.6386726498603821,
      "num_tokens": 4523329.0,
      "step": 162
    },
    {
      "epoch": 0.7639132981839485,
      "grad_norm": 0.02258412167429924,
      "learning_rate": 0.00014684084406997903,
      "loss": 0.751873254776001,
      "num_tokens": 4546858.0,
      "step": 163
    },
    {
      "epoch": 0.7685998828353837,
      "grad_norm": 0.018019448965787888,
      "learning_rate": 0.00014615579466644292,
      "loss": 0.6369242072105408,
      "num_tokens": 4573004.0,
      "step": 164
    },
    {
      "epoch": 0.773286467486819,
      "grad_norm": 0.015171061269938946,
      "learning_rate": 0.00014546798168479756,
      "loss": 0.6253129243850708,
      "num_tokens": 4600141.0,
      "step": 165
    },
    {
      "epoch": 0.7779730521382543,
      "grad_norm": 0.01836264133453369,
      "learning_rate": 0.00014477744630784378,
      "loss": 0.6729415655136108,
      "num_tokens": 4622472.0,
      "step": 166
    },
    {
      "epoch": 0.7826596367896895,
      "grad_norm": 0.016997816041111946,
      "learning_rate": 0.00014408422988138584,
      "loss": 0.7881853580474854,
      "num_tokens": 4654084.0,
      "step": 167
    },
    {
      "epoch": 0.7873462214411248,
      "grad_norm": 0.017668506130576134,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.6245524287223816,
      "num_tokens": 4678962.0,
      "step": 168
    },
    {
      "epoch": 0.79203280609256,
      "grad_norm": 0.01410279143601656,
      "learning_rate": 0.00014268992006332846,
      "loss": 0.6286853551864624,
      "num_tokens": 4714998.0,
      "step": 169
    },
    {
      "epoch": 0.7967193907439953,
      "grad_norm": 0.016260406002402306,
      "learning_rate": 0.00014198891015602646,
      "loss": 0.5806441307067871,
      "num_tokens": 4744061.0,
      "step": 170
    },
    {
      "epoch": 0.8014059753954306,
      "grad_norm": 0.016793547198176384,
      "learning_rate": 0.0001412853861628166,
      "loss": 0.6900240778923035,
      "num_tokens": 4771394.0,
      "step": 171
    },
    {
      "epoch": 0.8060925600468658,
      "grad_norm": 0.01554949302226305,
      "learning_rate": 0.0001405793902071964,
      "loss": 0.5430771708488464,
      "num_tokens": 4797695.0,
      "step": 172
    },
    {
      "epoch": 0.8107791446983011,
      "grad_norm": 0.021834636107087135,
      "learning_rate": 0.00013987096456067236,
      "loss": 0.7372509837150574,
      "num_tokens": 4818473.0,
      "step": 173
    },
    {
      "epoch": 0.8154657293497364,
      "grad_norm": 0.017153380438685417,
      "learning_rate": 0.00013916015164022852,
      "loss": 0.7403316497802734,
      "num_tokens": 4850247.0,
      "step": 174
    },
    {
      "epoch": 0.8201523140011716,
      "grad_norm": 0.017557591199874878,
      "learning_rate": 0.00013844699400578696,
      "loss": 0.5496473908424377,
      "num_tokens": 4875104.0,
      "step": 175
    },
    {
      "epoch": 0.824838898652607,
      "grad_norm": 0.018106888979673386,
      "learning_rate": 0.00013773153435765964,
      "loss": 0.656714677810669,
      "num_tokens": 4902439.0,
      "step": 176
    },
    {
      "epoch": 0.8295254833040422,
      "grad_norm": 0.014749976806342602,
      "learning_rate": 0.00013701381553399145,
      "loss": 0.514419674873352,
      "num_tokens": 4934804.0,
      "step": 177
    },
    {
      "epoch": 0.8342120679554774,
      "grad_norm": 0.015780452638864517,
      "learning_rate": 0.00013629388050819547,
      "loss": 0.6916260719299316,
      "num_tokens": 4964820.0,
      "step": 178
    },
    {
      "epoch": 0.8388986526069128,
      "grad_norm": 0.02181050553917885,
      "learning_rate": 0.00013557177238637986,
      "loss": 0.789571225643158,
      "num_tokens": 4987774.0,
      "step": 179
    },
    {
      "epoch": 0.843585237258348,
      "grad_norm": 0.019028659909963608,
      "learning_rate": 0.00013484753440476692,
      "loss": 0.7827271819114685,
      "num_tokens": 5012356.0,
      "step": 180
    },
    {
      "epoch": 0.8482718219097832,
      "grad_norm": 0.018884286284446716,
      "learning_rate": 0.00013412120992710425,
      "loss": 0.7337446808815002,
      "num_tokens": 5039247.0,
      "step": 181
    },
    {
      "epoch": 0.8529584065612185,
      "grad_norm": 0.015975872054696083,
      "learning_rate": 0.00013339284244206847,
      "loss": 0.6652353405952454,
      "num_tokens": 5069912.0,
      "step": 182
    },
    {
      "epoch": 0.8576449912126538,
      "grad_norm": 0.019088014960289,
      "learning_rate": 0.00013266247556066122,
      "loss": 0.6951537132263184,
      "num_tokens": 5098146.0,
      "step": 183
    },
    {
      "epoch": 0.862331575864089,
      "grad_norm": 0.014904006384313107,
      "learning_rate": 0.000131930153013598,
      "loss": 0.5959742069244385,
      "num_tokens": 5128454.0,
      "step": 184
    },
    {
      "epoch": 0.8670181605155243,
      "grad_norm": 0.01810140162706375,
      "learning_rate": 0.0001311959186486898,
      "loss": 0.7200735807418823,
      "num_tokens": 5154213.0,
      "step": 185
    },
    {
      "epoch": 0.8717047451669596,
      "grad_norm": 0.019789377227425575,
      "learning_rate": 0.0001304598164282176,
      "loss": 0.6804766654968262,
      "num_tokens": 5175623.0,
      "step": 186
    },
    {
      "epoch": 0.8763913298183948,
      "grad_norm": 0.017321709543466568,
      "learning_rate": 0.00012972189042630044,
      "loss": 0.7105655670166016,
      "num_tokens": 5201293.0,
      "step": 187
    },
    {
      "epoch": 0.8810779144698301,
      "grad_norm": 0.022706087678670883,
      "learning_rate": 0.00012898218482625606,
      "loss": 0.7062239646911621,
      "num_tokens": 5227922.0,
      "step": 188
    },
    {
      "epoch": 0.8857644991212654,
      "grad_norm": 0.014490657486021519,
      "learning_rate": 0.0001282407439179557,
      "loss": 0.6353857517242432,
      "num_tokens": 5260546.0,
      "step": 189
    },
    {
      "epoch": 0.8904510837727007,
      "grad_norm": 0.01803654059767723,
      "learning_rate": 0.0001274976120951723,
      "loss": 0.6230901479721069,
      "num_tokens": 5288394.0,
      "step": 190
    },
    {
      "epoch": 0.8951376684241359,
      "grad_norm": 0.023029128089547157,
      "learning_rate": 0.00012675283385292212,
      "loss": 0.6824889183044434,
      "num_tokens": 5313596.0,
      "step": 191
    },
    {
      "epoch": 0.8998242530755711,
      "grad_norm": 0.02031250298023224,
      "learning_rate": 0.00012600645378480082,
      "loss": 0.7509975433349609,
      "num_tokens": 5340851.0,
      "step": 192
    },
    {
      "epoch": 0.9045108377270065,
      "grad_norm": 0.01629417948424816,
      "learning_rate": 0.00012525851658031352,
      "loss": 0.6494298577308655,
      "num_tokens": 5372120.0,
      "step": 193
    },
    {
      "epoch": 0.9091974223784417,
      "grad_norm": 0.01852346956729889,
      "learning_rate": 0.0001245090670221987,
      "loss": 0.615811288356781,
      "num_tokens": 5400573.0,
      "step": 194
    },
    {
      "epoch": 0.9138840070298769,
      "grad_norm": 0.0194899570196867,
      "learning_rate": 0.00012375814998374712,
      "loss": 0.8159194588661194,
      "num_tokens": 5424108.0,
      "step": 195
    },
    {
      "epoch": 0.9185705916813123,
      "grad_norm": 0.017043786123394966,
      "learning_rate": 0.00012300581042611492,
      "loss": 0.6191376447677612,
      "num_tokens": 5448551.0,
      "step": 196
    },
    {
      "epoch": 0.9232571763327475,
      "grad_norm": 0.01926240883767605,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.7384488582611084,
      "num_tokens": 5475526.0,
      "step": 197
    },
    {
      "epoch": 0.9279437609841827,
      "grad_norm": 0.020789049565792084,
      "learning_rate": 0.00012149704402110243,
      "loss": 0.7020618915557861,
      "num_tokens": 5502611.0,
      "step": 198
    },
    {
      "epoch": 0.9326303456356181,
      "grad_norm": 0.01582273840904236,
      "learning_rate": 0.00012074070751110751,
      "loss": 0.6311229467391968,
      "num_tokens": 5529480.0,
      "step": 199
    },
    {
      "epoch": 0.9373169302870533,
      "grad_norm": 0.02086408995091915,
      "learning_rate": 0.00011998312915129371,
      "loss": 0.7435621619224548,
      "num_tokens": 5553458.0,
      "step": 200
    },
    {
      "epoch": 0.9420035149384886,
      "grad_norm": 0.01609129272401333,
      "learning_rate": 0.0001192243543016637,
      "loss": 0.6395267844200134,
      "num_tokens": 5584758.0,
      "step": 201
    },
    {
      "epoch": 0.9466900995899239,
      "grad_norm": 0.01869116723537445,
      "learning_rate": 0.00011846442839386003,
      "loss": 0.6983841061592102,
      "num_tokens": 5615997.0,
      "step": 202
    },
    {
      "epoch": 0.9513766842413591,
      "grad_norm": 0.03048761747777462,
      "learning_rate": 0.00011770339692844483,
      "loss": 0.6789813041687012,
      "num_tokens": 5640891.0,
      "step": 203
    },
    {
      "epoch": 0.9560632688927944,
      "grad_norm": 0.01786402240395546,
      "learning_rate": 0.00011694130547217554,
      "loss": 0.75504469871521,
      "num_tokens": 5670686.0,
      "step": 204
    },
    {
      "epoch": 0.9607498535442296,
      "grad_norm": 0.01641128584742546,
      "learning_rate": 0.0001161781996552765,
      "loss": 0.5403404235839844,
      "num_tokens": 5699611.0,
      "step": 205
    },
    {
      "epoch": 0.9654364381956649,
      "grad_norm": 0.01727338694036007,
      "learning_rate": 0.00011541412516870684,
      "loss": 0.6894916296005249,
      "num_tokens": 5729248.0,
      "step": 206
    },
    {
      "epoch": 0.9701230228471002,
      "grad_norm": 0.01573982834815979,
      "learning_rate": 0.00011464912776142494,
      "loss": 0.5996260046958923,
      "num_tokens": 5757744.0,
      "step": 207
    },
    {
      "epoch": 0.9748096074985354,
      "grad_norm": 0.017988774925470352,
      "learning_rate": 0.00011388325323764888,
      "loss": 0.6654211282730103,
      "num_tokens": 5788566.0,
      "step": 208
    },
    {
      "epoch": 0.9794961921499707,
      "grad_norm": 0.014979843981564045,
      "learning_rate": 0.00011311654745411425,
      "loss": 0.6495011448860168,
      "num_tokens": 5824022.0,
      "step": 209
    },
    {
      "epoch": 0.984182776801406,
      "grad_norm": 0.01659063622355461,
      "learning_rate": 0.00011234905631732819,
      "loss": 0.6396357417106628,
      "num_tokens": 5853973.0,
      "step": 210
    },
    {
      "epoch": 0.9888693614528412,
      "grad_norm": 0.016888733953237534,
      "learning_rate": 0.00011158082578082089,
      "loss": 0.6784655451774597,
      "num_tokens": 5883848.0,
      "step": 211
    },
    {
      "epoch": 0.9935559461042766,
      "grad_norm": 0.01959056593477726,
      "learning_rate": 0.00011081190184239419,
      "loss": 0.6131283044815063,
      "num_tokens": 5907061.0,
      "step": 212
    },
    {
      "epoch": 0.9982425307557118,
      "grad_norm": 0.016141943633556366,
      "learning_rate": 0.00011004233054136725,
      "loss": 0.5719535946846008,
      "num_tokens": 5937101.0,
      "step": 213
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.025195077061653137,
      "learning_rate": 0.00010927215795582012,
      "loss": 0.5020159482955933,
      "num_tokens": 5947501.0,
      "step": 214
    },
    {
      "epoch": 1.0046865846514352,
      "grad_norm": 0.01583407074213028,
      "learning_rate": 0.00010850143019983474,
      "loss": 0.4937314987182617,
      "num_tokens": 5970493.0,
      "step": 215
    },
    {
      "epoch": 1.0093731693028705,
      "grad_norm": 0.017454253509640694,
      "learning_rate": 0.0001077301934207339,
      "loss": 0.6226227879524231,
      "num_tokens": 6003077.0,
      "step": 216
    },
    {
      "epoch": 1.0140597539543057,
      "grad_norm": 0.014966587536036968,
      "learning_rate": 0.00010695849379631813,
      "loss": 0.5236163139343262,
      "num_tokens": 6033093.0,
      "step": 217
    },
    {
      "epoch": 1.0187463386057412,
      "grad_norm": 0.015618878416717052,
      "learning_rate": 0.00010618637753210085,
      "loss": 0.5199332237243652,
      "num_tokens": 6060819.0,
      "step": 218
    },
    {
      "epoch": 1.0234329232571764,
      "grad_norm": 0.01610647886991501,
      "learning_rate": 0.00010541389085854176,
      "loss": 0.5474415421485901,
      "num_tokens": 6091049.0,
      "step": 219
    },
    {
      "epoch": 1.0281195079086116,
      "grad_norm": 0.015623976476490498,
      "learning_rate": 0.00010464108002827882,
      "loss": 0.48489633202552795,
      "num_tokens": 6122790.0,
      "step": 220
    },
    {
      "epoch": 1.0328060925600469,
      "grad_norm": 0.015523376874625683,
      "learning_rate": 0.00010386799131335889,
      "loss": 0.5330443382263184,
      "num_tokens": 6157043.0,
      "step": 221
    },
    {
      "epoch": 1.037492677211482,
      "grad_norm": 0.017354318872094154,
      "learning_rate": 0.00010309467100246713,
      "loss": 0.49863070249557495,
      "num_tokens": 6182364.0,
      "step": 222
    },
    {
      "epoch": 1.0421792618629173,
      "grad_norm": 0.014648743905127048,
      "learning_rate": 0.00010232116539815558,
      "loss": 0.5403507947921753,
      "num_tokens": 6217015.0,
      "step": 223
    },
    {
      "epoch": 1.0468658465143528,
      "grad_norm": 0.017757907509803772,
      "learning_rate": 0.00010154752081407066,
      "loss": 0.5948547720909119,
      "num_tokens": 6246427.0,
      "step": 224
    },
    {
      "epoch": 1.051552431165788,
      "grad_norm": 0.03653530776500702,
      "learning_rate": 0.00010077378357218021,
      "loss": 0.5761139392852783,
      "num_tokens": 6275025.0,
      "step": 225
    },
    {
      "epoch": 1.0562390158172232,
      "grad_norm": 0.016985690221190453,
      "learning_rate": 0.0001,
      "loss": 0.539291501045227,
      "num_tokens": 6304885.0,
      "step": 226
    },
    {
      "epoch": 1.0609256004686585,
      "grad_norm": 0.017139555886387825,
      "learning_rate": 9.92262164278198e-05,
      "loss": 0.48060083389282227,
      "num_tokens": 6331616.0,
      "step": 227
    },
    {
      "epoch": 1.0656121851200937,
      "grad_norm": 0.015508485957980156,
      "learning_rate": 9.845247918592937e-05,
      "loss": 0.4607234299182892,
      "num_tokens": 6361325.0,
      "step": 228
    },
    {
      "epoch": 1.070298769771529,
      "grad_norm": 0.01898042857646942,
      "learning_rate": 9.767883460184443e-05,
      "loss": 0.5976904034614563,
      "num_tokens": 6387046.0,
      "step": 229
    },
    {
      "epoch": 1.0749853544229642,
      "grad_norm": 0.01673644594848156,
      "learning_rate": 9.69053289975329e-05,
      "loss": 0.49898090958595276,
      "num_tokens": 6417864.0,
      "step": 230
    },
    {
      "epoch": 1.0796719390743996,
      "grad_norm": 0.020018402487039566,
      "learning_rate": 9.613200868664112e-05,
      "loss": 0.5435779094696045,
      "num_tokens": 6444931.0,
      "step": 231
    },
    {
      "epoch": 1.0843585237258349,
      "grad_norm": 0.021194079890847206,
      "learning_rate": 9.53589199717212e-05,
      "loss": 0.6362026929855347,
      "num_tokens": 6475713.0,
      "step": 232
    },
    {
      "epoch": 1.08904510837727,
      "grad_norm": 0.017888659611344337,
      "learning_rate": 9.458610914145826e-05,
      "loss": 0.5617181658744812,
      "num_tokens": 6504178.0,
      "step": 233
    },
    {
      "epoch": 1.0937316930287053,
      "grad_norm": 0.020780451595783234,
      "learning_rate": 9.381362246789917e-05,
      "loss": 0.49862992763519287,
      "num_tokens": 6529543.0,
      "step": 234
    },
    {
      "epoch": 1.0984182776801406,
      "grad_norm": 0.01968269981443882,
      "learning_rate": 9.304150620368188e-05,
      "loss": 0.6710590124130249,
      "num_tokens": 6557912.0,
      "step": 235
    },
    {
      "epoch": 1.1031048623315758,
      "grad_norm": 0.01871589943766594,
      "learning_rate": 9.226980657926614e-05,
      "loss": 0.44637927412986755,
      "num_tokens": 6582586.0,
      "step": 236
    },
    {
      "epoch": 1.1077914469830112,
      "grad_norm": 0.021373949944972992,
      "learning_rate": 9.149856980016529e-05,
      "loss": 0.5362990498542786,
      "num_tokens": 6605854.0,
      "step": 237
    },
    {
      "epoch": 1.1124780316344465,
      "grad_norm": 0.018750222399830818,
      "learning_rate": 9.072784204417995e-05,
      "loss": 0.543184757232666,
      "num_tokens": 6633003.0,
      "step": 238
    },
    {
      "epoch": 1.1171646162858817,
      "grad_norm": 0.01677524298429489,
      "learning_rate": 8.995766945863277e-05,
      "loss": 0.5202764868736267,
      "num_tokens": 6665844.0,
      "step": 239
    },
    {
      "epoch": 1.121851200937317,
      "grad_norm": 0.01806574873626232,
      "learning_rate": 8.918809815760585e-05,
      "loss": 0.5611273646354675,
      "num_tokens": 6698052.0,
      "step": 240
    },
    {
      "epoch": 1.1265377855887522,
      "grad_norm": 0.022728972136974335,
      "learning_rate": 8.841917421917912e-05,
      "loss": 0.5777214765548706,
      "num_tokens": 6719727.0,
      "step": 241
    },
    {
      "epoch": 1.1312243702401874,
      "grad_norm": 0.018225179985165596,
      "learning_rate": 8.765094368267186e-05,
      "loss": 0.4442354440689087,
      "num_tokens": 6745434.0,
      "step": 242
    },
    {
      "epoch": 1.1359109548916226,
      "grad_norm": 0.020616615191102028,
      "learning_rate": 8.688345254588578e-05,
      "loss": 0.5914826989173889,
      "num_tokens": 6773920.0,
      "step": 243
    },
    {
      "epoch": 1.140597539543058,
      "grad_norm": 0.018396707251667976,
      "learning_rate": 8.611674676235115e-05,
      "loss": 0.4618031084537506,
      "num_tokens": 6800391.0,
      "step": 244
    },
    {
      "epoch": 1.1452841241944933,
      "grad_norm": 0.016975924372673035,
      "learning_rate": 8.535087223857508e-05,
      "loss": 0.5435763001441956,
      "num_tokens": 6832207.0,
      "step": 245
    },
    {
      "epoch": 1.1499707088459286,
      "grad_norm": 0.015872633084654808,
      "learning_rate": 8.458587483129316e-05,
      "loss": 0.471432626247406,
      "num_tokens": 6864377.0,
      "step": 246
    },
    {
      "epoch": 1.1546572934973638,
      "grad_norm": 0.020818166434764862,
      "learning_rate": 8.382180034472353e-05,
      "loss": 0.5589307546615601,
      "num_tokens": 6890689.0,
      "step": 247
    },
    {
      "epoch": 1.159343878148799,
      "grad_norm": 0.020436430349946022,
      "learning_rate": 8.305869452782446e-05,
      "loss": 0.5633253455162048,
      "num_tokens": 6916605.0,
      "step": 248
    },
    {
      "epoch": 1.1640304628002343,
      "grad_norm": 0.021504931151866913,
      "learning_rate": 8.229660307155518e-05,
      "loss": 0.5318947434425354,
      "num_tokens": 6941217.0,
      "step": 249
    },
    {
      "epoch": 1.1687170474516697,
      "grad_norm": 0.015647897496819496,
      "learning_rate": 8.153557160613998e-05,
      "loss": 0.41660377383232117,
      "num_tokens": 6971845.0,
      "step": 250
    },
    {
      "epoch": 1.173403632103105,
      "grad_norm": 0.01813015528023243,
      "learning_rate": 8.077564569833632e-05,
      "loss": 0.4969935417175293,
      "num_tokens": 7000145.0,
      "step": 251
    },
    {
      "epoch": 1.1780902167545402,
      "grad_norm": 0.02095090039074421,
      "learning_rate": 8.00168708487063e-05,
      "loss": 0.5970808267593384,
      "num_tokens": 7028674.0,
      "step": 252
    },
    {
      "epoch": 1.1827768014059754,
      "grad_norm": 0.01675095222890377,
      "learning_rate": 7.92592924888925e-05,
      "loss": 0.5089432001113892,
      "num_tokens": 7057684.0,
      "step": 253
    },
    {
      "epoch": 1.1874633860574106,
      "grad_norm": 0.018853550776839256,
      "learning_rate": 7.85029559788976e-05,
      "loss": 0.6490843892097473,
      "num_tokens": 7088398.0,
      "step": 254
    },
    {
      "epoch": 1.1921499707088459,
      "grad_norm": 0.01821407489478588,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.5658373236656189,
      "num_tokens": 7119190.0,
      "step": 255
    },
    {
      "epoch": 1.196836555360281,
      "grad_norm": 0.017882108688354492,
      "learning_rate": 7.699418957388512e-05,
      "loss": 0.5955532789230347,
      "num_tokens": 7153203.0,
      "step": 256
    },
    {
      "epoch": 1.2015231400117163,
      "grad_norm": 0.017674054950475693,
      "learning_rate": 7.624185001625292e-05,
      "loss": 0.5457881689071655,
      "num_tokens": 7184609.0,
      "step": 257
    },
    {
      "epoch": 1.2062097246631518,
      "grad_norm": 0.01938200183212757,
      "learning_rate": 7.549093297780132e-05,
      "loss": 0.5812852382659912,
      "num_tokens": 7212942.0,
      "step": 258
    },
    {
      "epoch": 1.210896309314587,
      "grad_norm": 0.021312085911631584,
      "learning_rate": 7.474148341968652e-05,
      "loss": 0.5053731203079224,
      "num_tokens": 7235722.0,
      "step": 259
    },
    {
      "epoch": 1.2155828939660223,
      "grad_norm": 0.015914585441350937,
      "learning_rate": 7.39935462151992e-05,
      "loss": 0.4808054566383362,
      "num_tokens": 7268853.0,
      "step": 260
    },
    {
      "epoch": 1.2202694786174575,
      "grad_norm": 0.016284095123410225,
      "learning_rate": 7.324716614707793e-05,
      "loss": 0.5059459209442139,
      "num_tokens": 7301735.0,
      "step": 261
    },
    {
      "epoch": 1.2249560632688927,
      "grad_norm": 0.02114776149392128,
      "learning_rate": 7.250238790482773e-05,
      "loss": 0.5616275072097778,
      "num_tokens": 7326126.0,
      "step": 262
    },
    {
      "epoch": 1.2296426479203282,
      "grad_norm": 0.018290745094418526,
      "learning_rate": 7.175925608204428e-05,
      "loss": 0.4677993357181549,
      "num_tokens": 7353023.0,
      "step": 263
    },
    {
      "epoch": 1.2343292325717634,
      "grad_norm": 0.018801284953951836,
      "learning_rate": 7.101781517374398e-05,
      "loss": 0.495519757270813,
      "num_tokens": 7378830.0,
      "step": 264
    },
    {
      "epoch": 1.2390158172231986,
      "grad_norm": 0.01867852732539177,
      "learning_rate": 7.027810957369957e-05,
      "loss": 0.6183238625526428,
      "num_tokens": 7409846.0,
      "step": 265
    },
    {
      "epoch": 1.2437024018746339,
      "grad_norm": 0.021188955754041672,
      "learning_rate": 6.954018357178241e-05,
      "loss": 0.5982891917228699,
      "num_tokens": 7435647.0,
      "step": 266
    },
    {
      "epoch": 1.248388986526069,
      "grad_norm": 0.016743872314691544,
      "learning_rate": 6.880408135131022e-05,
      "loss": 0.4980001151561737,
      "num_tokens": 7466694.0,
      "step": 267
    },
    {
      "epoch": 1.2530755711775043,
      "grad_norm": 0.019149333238601685,
      "learning_rate": 6.806984698640202e-05,
      "loss": 0.6516995429992676,
      "num_tokens": 7496653.0,
      "step": 268
    },
    {
      "epoch": 1.2577621558289396,
      "grad_norm": 0.019356200471520424,
      "learning_rate": 6.733752443933878e-05,
      "loss": 0.5884249210357666,
      "num_tokens": 7523023.0,
      "step": 269
    },
    {
      "epoch": 1.2624487404803748,
      "grad_norm": 0.02171611227095127,
      "learning_rate": 6.660715755793154e-05,
      "loss": 0.49592259526252747,
      "num_tokens": 7542791.0,
      "step": 270
    },
    {
      "epoch": 1.2671353251318103,
      "grad_norm": 0.017002740874886513,
      "learning_rate": 6.587879007289576e-05,
      "loss": 0.5243790149688721,
      "num_tokens": 7577560.0,
      "step": 271
    },
    {
      "epoch": 1.2718219097832455,
      "grad_norm": 0.020400408655405045,
      "learning_rate": 6.515246559523312e-05,
      "loss": 0.5987250804901123,
      "num_tokens": 7603100.0,
      "step": 272
    },
    {
      "epoch": 1.2765084944346807,
      "grad_norm": 0.019193653017282486,
      "learning_rate": 6.442822761362015e-05,
      "loss": 0.6312786936759949,
      "num_tokens": 7630292.0,
      "step": 273
    },
    {
      "epoch": 1.281195079086116,
      "grad_norm": 0.01957247033715248,
      "learning_rate": 6.370611949180457e-05,
      "loss": 0.5242177844047546,
      "num_tokens": 7655668.0,
      "step": 274
    },
    {
      "epoch": 1.2858816637375512,
      "grad_norm": 0.017094500362873077,
      "learning_rate": 6.298618446600856e-05,
      "loss": 0.4949776828289032,
      "num_tokens": 7684925.0,
      "step": 275
    },
    {
      "epoch": 1.2905682483889866,
      "grad_norm": 0.02443353645503521,
      "learning_rate": 6.22684656423404e-05,
      "loss": 0.5696538090705872,
      "num_tokens": 7719008.0,
      "step": 276
    },
    {
      "epoch": 1.2952548330404219,
      "grad_norm": 0.057685527950525284,
      "learning_rate": 6.155300599421306e-05,
      "loss": 0.5062693953514099,
      "num_tokens": 7751344.0,
      "step": 277
    },
    {
      "epoch": 1.2999414176918571,
      "grad_norm": 0.02328214980661869,
      "learning_rate": 6.0839848359771536e-05,
      "loss": 0.5536410212516785,
      "num_tokens": 7777488.0,
      "step": 278
    },
    {
      "epoch": 1.3046280023432923,
      "grad_norm": 0.02110743522644043,
      "learning_rate": 6.012903543932766e-05,
      "loss": 0.6596872806549072,
      "num_tokens": 7805208.0,
      "step": 279
    },
    {
      "epoch": 1.3093145869947276,
      "grad_norm": 0.019983140751719475,
      "learning_rate": 5.9420609792803604e-05,
      "loss": 0.5163890719413757,
      "num_tokens": 7831286.0,
      "step": 280
    },
    {
      "epoch": 1.3140011716461628,
      "grad_norm": 0.019265560433268547,
      "learning_rate": 5.871461383718344e-05,
      "loss": 0.5131065845489502,
      "num_tokens": 7859261.0,
      "step": 281
    },
    {
      "epoch": 1.318687756297598,
      "grad_norm": 0.022508597001433372,
      "learning_rate": 5.801108984397354e-05,
      "loss": 0.6271864175796509,
      "num_tokens": 7885431.0,
      "step": 282
    },
    {
      "epoch": 1.3233743409490333,
      "grad_norm": 0.017685849219560623,
      "learning_rate": 5.7310079936671545e-05,
      "loss": 0.4501059353351593,
      "num_tokens": 7913746.0,
      "step": 283
    },
    {
      "epoch": 1.3280609256004687,
      "grad_norm": 0.016956064850091934,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.47412410378456116,
      "num_tokens": 7942905.0,
      "step": 284
    },
    {
      "epoch": 1.332747510251904,
      "grad_norm": 0.01661519892513752,
      "learning_rate": 5.59157701186142e-05,
      "loss": 0.47091153264045715,
      "num_tokens": 7974222.0,
      "step": 285
    },
    {
      "epoch": 1.3374340949033392,
      "grad_norm": 0.02206377312541008,
      "learning_rate": 5.522255369215622e-05,
      "loss": 0.45931947231292725,
      "num_tokens": 8001662.0,
      "step": 286
    },
    {
      "epoch": 1.3421206795547744,
      "grad_norm": 0.021219369024038315,
      "learning_rate": 5.453201831520245e-05,
      "loss": 0.6900108456611633,
      "num_tokens": 8027798.0,
      "step": 287
    },
    {
      "epoch": 1.3468072642062097,
      "grad_norm": 0.018379267305135727,
      "learning_rate": 5.38442053335571e-05,
      "loss": 0.5277714729309082,
      "num_tokens": 8060964.0,
      "step": 288
    },
    {
      "epoch": 1.3514938488576451,
      "grad_norm": 0.016046447679400444,
      "learning_rate": 5.3159155930021e-05,
      "loss": 0.5390745401382446,
      "num_tokens": 8097006.0,
      "step": 289
    },
    {
      "epoch": 1.3561804335090804,
      "grad_norm": 0.021015141159296036,
      "learning_rate": 5.247691112192577e-05,
      "loss": 0.5474106073379517,
      "num_tokens": 8127461.0,
      "step": 290
    },
    {
      "epoch": 1.3608670181605156,
      "grad_norm": 0.019383052363991737,
      "learning_rate": 5.179751175867784e-05,
      "loss": 0.5751417875289917,
      "num_tokens": 8156154.0,
      "step": 291
    },
    {
      "epoch": 1.3655536028119508,
      "grad_norm": 0.018249724060297012,
      "learning_rate": 5.112099851931265e-05,
      "loss": 0.4899910092353821,
      "num_tokens": 8181611.0,
      "step": 292
    },
    {
      "epoch": 1.370240187463386,
      "grad_norm": 0.021499330177903175,
      "learning_rate": 5.044741191005908e-05,
      "loss": 0.6149919629096985,
      "num_tokens": 8208053.0,
      "step": 293
    },
    {
      "epoch": 1.3749267721148213,
      "grad_norm": 0.018448660150170326,
      "learning_rate": 4.9776792261913896e-05,
      "loss": 0.5378507375717163,
      "num_tokens": 8236427.0,
      "step": 294
    },
    {
      "epoch": 1.3796133567662565,
      "grad_norm": 0.020480727776885033,
      "learning_rate": 4.910917972822713e-05,
      "loss": 0.5937903523445129,
      "num_tokens": 8261482.0,
      "step": 295
    },
    {
      "epoch": 1.3842999414176917,
      "grad_norm": 0.021023282781243324,
      "learning_rate": 4.844461428229782e-05,
      "loss": 0.475787878036499,
      "num_tokens": 8283675.0,
      "step": 296
    },
    {
      "epoch": 1.3889865260691272,
      "grad_norm": 0.022145070135593414,
      "learning_rate": 4.7783135714980744e-05,
      "loss": 0.6385347843170166,
      "num_tokens": 8308823.0,
      "step": 297
    },
    {
      "epoch": 1.3936731107205624,
      "grad_norm": 0.019477400928735733,
      "learning_rate": 4.712478363230362e-05,
      "loss": 0.6258922815322876,
      "num_tokens": 8336711.0,
      "step": 298
    },
    {
      "epoch": 1.3983596953719977,
      "grad_norm": 0.022344205528497696,
      "learning_rate": 4.646959745309609e-05,
      "loss": 0.49651363492012024,
      "num_tokens": 8355982.0,
      "step": 299
    },
    {
      "epoch": 1.403046280023433,
      "grad_norm": 0.018516717478632927,
      "learning_rate": 4.581761640662927e-05,
      "loss": 0.5565701723098755,
      "num_tokens": 8392293.0,
      "step": 300
    },
    {
      "epoch": 1.4077328646748681,
      "grad_norm": 0.02049725316464901,
      "learning_rate": 4.516887953026691e-05,
      "loss": 0.5584365725517273,
      "num_tokens": 8418190.0,
      "step": 301
    },
    {
      "epoch": 1.4124194493263036,
      "grad_norm": 0.018973683938384056,
      "learning_rate": 4.452342566712818e-05,
      "loss": 0.5133151412010193,
      "num_tokens": 8446616.0,
      "step": 302
    },
    {
      "epoch": 1.4171060339777388,
      "grad_norm": 0.02378571778535843,
      "learning_rate": 4.388129346376178e-05,
      "loss": 0.48315972089767456,
      "num_tokens": 8470185.0,
      "step": 303
    },
    {
      "epoch": 1.421792618629174,
      "grad_norm": 0.023281428962945938,
      "learning_rate": 4.3242521367832015e-05,
      "loss": 0.5316978096961975,
      "num_tokens": 8494772.0,
      "step": 304
    },
    {
      "epoch": 1.4264792032806093,
      "grad_norm": 0.020904844626784325,
      "learning_rate": 4.260714762581677e-05,
      "loss": 0.5123225450515747,
      "num_tokens": 8519300.0,
      "step": 305
    },
    {
      "epoch": 1.4311657879320445,
      "grad_norm": 0.022328970953822136,
      "learning_rate": 4.197521028071765e-05,
      "loss": 0.46863052248954773,
      "num_tokens": 8544147.0,
      "step": 306
    },
    {
      "epoch": 1.4358523725834798,
      "grad_norm": 0.02324979566037655,
      "learning_rate": 4.13467471697817e-05,
      "loss": 0.6753160953521729,
      "num_tokens": 8568351.0,
      "step": 307
    },
    {
      "epoch": 1.440538957234915,
      "grad_norm": 0.01805717498064041,
      "learning_rate": 4.0721795922236496e-05,
      "loss": 0.5179596543312073,
      "num_tokens": 8598849.0,
      "step": 308
    },
    {
      "epoch": 1.4452255418863502,
      "grad_norm": 0.016879988834261894,
      "learning_rate": 4.010039395703664e-05,
      "loss": 0.5598073601722717,
      "num_tokens": 8635197.0,
      "step": 309
    },
    {
      "epoch": 1.4499121265377855,
      "grad_norm": 0.019025171175599098,
      "learning_rate": 3.948257848062351e-05,
      "loss": 0.5200734734535217,
      "num_tokens": 8668440.0,
      "step": 310
    },
    {
      "epoch": 1.454598711189221,
      "grad_norm": 0.020963799208402634,
      "learning_rate": 3.8868386484697417e-05,
      "loss": 0.5326945185661316,
      "num_tokens": 8689757.0,
      "step": 311
    },
    {
      "epoch": 1.4592852958406561,
      "grad_norm": 0.02187330089509487,
      "learning_rate": 3.825785474400291e-05,
      "loss": 0.48833855986595154,
      "num_tokens": 8716599.0,
      "step": 312
    },
    {
      "epoch": 1.4639718804920914,
      "grad_norm": 0.01959657296538353,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.5740939974784851,
      "num_tokens": 8747984.0,
      "step": 313
    },
    {
      "epoch": 1.4686584651435266,
      "grad_norm": 0.022587157785892487,
      "learning_rate": 3.7047918029308815e-05,
      "loss": 0.5537501573562622,
      "num_tokens": 8768742.0,
      "step": 314
    },
    {
      "epoch": 1.473345049794962,
      "grad_norm": 0.01806885376572609,
      "learning_rate": 3.6448585500267485e-05,
      "loss": 0.5617669224739075,
      "num_tokens": 8799757.0,
      "step": 315
    },
    {
      "epoch": 1.4780316344463973,
      "grad_norm": 0.017536548897624016,
      "learning_rate": 3.5853058112036596e-05,
      "loss": 0.5035026669502258,
      "num_tokens": 8832220.0,
      "step": 316
    },
    {
      "epoch": 1.4827182190978325,
      "grad_norm": 0.018568003550171852,
      "learning_rate": 3.5261371521817244e-05,
      "loss": 0.5434101819992065,
      "num_tokens": 8862171.0,
      "step": 317
    },
    {
      "epoch": 1.4874048037492678,
      "grad_norm": 0.01621602475643158,
      "learning_rate": 3.467356115684284e-05,
      "loss": 0.5029686093330383,
      "num_tokens": 8896875.0,
      "step": 318
    },
    {
      "epoch": 1.492091388400703,
      "grad_norm": 0.023901382461190224,
      "learning_rate": 3.408966221225773e-05,
      "loss": 0.528933584690094,
      "num_tokens": 8921290.0,
      "step": 319
    },
    {
      "epoch": 1.4967779730521382,
      "grad_norm": 0.020985329523682594,
      "learning_rate": 3.350970964900998e-05,
      "loss": 0.532300591468811,
      "num_tokens": 8943823.0,
      "step": 320
    },
    {
      "epoch": 1.5014645577035735,
      "grad_norm": 0.016975343227386475,
      "learning_rate": 3.293373819175816e-05,
      "loss": 0.4847569465637207,
      "num_tokens": 8974156.0,
      "step": 321
    },
    {
      "epoch": 1.5061511423550087,
      "grad_norm": 0.021665778011083603,
      "learning_rate": 3.236178232679202e-05,
      "loss": 0.49303680658340454,
      "num_tokens": 8998207.0,
      "step": 322
    },
    {
      "epoch": 1.510837727006444,
      "grad_norm": 0.020978335291147232,
      "learning_rate": 3.1793876299967816e-05,
      "loss": 0.49797046184539795,
      "num_tokens": 9025073.0,
      "step": 323
    },
    {
      "epoch": 1.5155243116578794,
      "grad_norm": 0.02384047396481037,
      "learning_rate": 3.123005411465766e-05,
      "loss": 0.48021501302719116,
      "num_tokens": 9048431.0,
      "step": 324
    },
    {
      "epoch": 1.5202108963093146,
      "grad_norm": 0.02224925346672535,
      "learning_rate": 3.0670349529713816e-05,
      "loss": 0.5561593174934387,
      "num_tokens": 9074520.0,
      "step": 325
    },
    {
      "epoch": 1.5248974809607498,
      "grad_norm": 0.02000618539750576,
      "learning_rate": 3.0114796057447026e-05,
      "loss": 0.5325280427932739,
      "num_tokens": 9100009.0,
      "step": 326
    },
    {
      "epoch": 1.529584065612185,
      "grad_norm": 0.019758600741624832,
      "learning_rate": 2.9563426961620367e-05,
      "loss": 0.6052445769309998,
      "num_tokens": 9126580.0,
      "step": 327
    },
    {
      "epoch": 1.5342706502636205,
      "grad_norm": 0.018562018871307373,
      "learning_rate": 2.901627525545726e-05,
      "loss": 0.5577982664108276,
      "num_tokens": 9155723.0,
      "step": 328
    },
    {
      "epoch": 1.5389572349150558,
      "grad_norm": 0.020161550492048264,
      "learning_rate": 2.8473373699664997e-05,
      "loss": 0.48411282896995544,
      "num_tokens": 9180730.0,
      "step": 329
    },
    {
      "epoch": 1.543643819566491,
      "grad_norm": 0.01843865029513836,
      "learning_rate": 2.793475480047303e-05,
      "loss": 0.6604800224304199,
      "num_tokens": 9214318.0,
      "step": 330
    },
    {
      "epoch": 1.5483304042179262,
      "grad_norm": 0.020535748451948166,
      "learning_rate": 2.7400450807686938e-05,
      "loss": 0.5858520865440369,
      "num_tokens": 9240822.0,
      "step": 331
    },
    {
      "epoch": 1.5530169888693615,
      "grad_norm": 0.022782601416110992,
      "learning_rate": 2.687049371275705e-05,
      "loss": 0.46998876333236694,
      "num_tokens": 9264481.0,
      "step": 332
    },
    {
      "epoch": 1.5577035735207967,
      "grad_norm": 0.0198629479855299,
      "learning_rate": 2.6344915246863412e-05,
      "loss": 0.534439742565155,
      "num_tokens": 9289213.0,
      "step": 333
    },
    {
      "epoch": 1.562390158172232,
      "grad_norm": 0.02262199856340885,
      "learning_rate": 2.582374687901553e-05,
      "loss": 0.5112385153770447,
      "num_tokens": 9316345.0,
      "step": 334
    },
    {
      "epoch": 1.5670767428236672,
      "grad_norm": 0.019158268347382545,
      "learning_rate": 2.5307019814168342e-05,
      "loss": 0.5436915159225464,
      "num_tokens": 9343539.0,
      "step": 335
    },
    {
      "epoch": 1.5717633274751024,
      "grad_norm": 0.01680525206029415,
      "learning_rate": 2.4794764991353748e-05,
      "loss": 0.5591372847557068,
      "num_tokens": 9377789.0,
      "step": 336
    },
    {
      "epoch": 1.5764499121265376,
      "grad_norm": 0.020835794508457184,
      "learning_rate": 2.4287013081828257e-05,
      "loss": 0.47972720861434937,
      "num_tokens": 9399684.0,
      "step": 337
    },
    {
      "epoch": 1.581136496777973,
      "grad_norm": 0.02286120317876339,
      "learning_rate": 2.3783794487236365e-05,
      "loss": 0.47875186800956726,
      "num_tokens": 9425859.0,
      "step": 338
    },
    {
      "epoch": 1.5858230814294083,
      "grad_norm": 0.020349981263279915,
      "learning_rate": 2.328513933779034e-05,
      "loss": 0.4517807960510254,
      "num_tokens": 9454284.0,
      "step": 339
    },
    {
      "epoch": 1.5905096660808435,
      "grad_norm": 0.018499430269002914,
      "learning_rate": 2.2791077490466262e-05,
      "loss": 0.46991515159606934,
      "num_tokens": 9480127.0,
      "step": 340
    },
    {
      "epoch": 1.595196250732279,
      "grad_norm": 0.01904108189046383,
      "learning_rate": 2.2301638527216194e-05,
      "loss": 0.5170081853866577,
      "num_tokens": 9503810.0,
      "step": 341
    },
    {
      "epoch": 1.5998828353837142,
      "grad_norm": 0.026131968945264816,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.5478099584579468,
      "num_tokens": 9524862.0,
      "step": 342
    },
    {
      "epoch": 1.6045694200351495,
      "grad_norm": 0.021739963442087173,
      "learning_rate": 2.1336746195015846e-05,
      "loss": 0.5281755328178406,
      "num_tokens": 9550537.0,
      "step": 343
    },
    {
      "epoch": 1.6092560046865847,
      "grad_norm": 0.023870104923844337,
      "learning_rate": 2.0861350598991945e-05,
      "loss": 0.5209230184555054,
      "num_tokens": 9573327.0,
      "step": 344
    },
    {
      "epoch": 1.61394258933802,
      "grad_norm": 0.017477530986070633,
      "learning_rate": 2.0390693429435627e-05,
      "loss": 0.49637410044670105,
      "num_tokens": 9604830.0,
      "step": 345
    },
    {
      "epoch": 1.6186291739894552,
      "grad_norm": 0.01921052113175392,
      "learning_rate": 1.992480286694397e-05,
      "loss": 0.5098212361335754,
      "num_tokens": 9629372.0,
      "step": 346
    },
    {
      "epoch": 1.6233157586408904,
      "grad_norm": 0.019054904580116272,
      "learning_rate": 1.946370680671341e-05,
      "loss": 0.5386035442352295,
      "num_tokens": 9660579.0,
      "step": 347
    },
    {
      "epoch": 1.6280023432923256,
      "grad_norm": 0.01880921795964241,
      "learning_rate": 1.90074328568696e-05,
      "loss": 0.5067959427833557,
      "num_tokens": 9689577.0,
      "step": 348
    },
    {
      "epoch": 1.6326889279437609,
      "grad_norm": 0.021123239770531654,
      "learning_rate": 1.85560083368143e-05,
      "loss": 0.5928493738174438,
      "num_tokens": 9718988.0,
      "step": 349
    },
    {
      "epoch": 1.637375512595196,
      "grad_norm": 0.018862782046198845,
      "learning_rate": 1.8109460275589773e-05,
      "loss": 0.5666136145591736,
      "num_tokens": 9749603.0,
      "step": 350
    },
    {
      "epoch": 1.6420620972466315,
      "grad_norm": 0.017942598089575768,
      "learning_rate": 1.766781541026018e-05,
      "loss": 0.4736426770687103,
      "num_tokens": 9776858.0,
      "step": 351
    },
    {
      "epoch": 1.6467486818980668,
      "grad_norm": 0.019833028316497803,
      "learning_rate": 1.7231100184310956e-05,
      "loss": 0.44382166862487793,
      "num_tokens": 9799949.0,
      "step": 352
    },
    {
      "epoch": 1.651435266549502,
      "grad_norm": 0.021584438160061836,
      "learning_rate": 1.679934074606533e-05,
      "loss": 0.6359472274780273,
      "num_tokens": 9828297.0,
      "step": 353
    },
    {
      "epoch": 1.6561218512009375,
      "grad_norm": 0.02021203748881817,
      "learning_rate": 1.6372562947118763e-05,
      "loss": 0.4740830063819885,
      "num_tokens": 9851858.0,
      "step": 354
    },
    {
      "epoch": 1.6608084358523727,
      "grad_norm": 0.01691586710512638,
      "learning_rate": 1.5950792340791043e-05,
      "loss": 0.5469228625297546,
      "num_tokens": 9884175.0,
      "step": 355
    },
    {
      "epoch": 1.665495020503808,
      "grad_norm": 0.021979546174407005,
      "learning_rate": 1.5534054180596415e-05,
      "loss": 0.5678442716598511,
      "num_tokens": 9905644.0,
      "step": 356
    },
    {
      "epoch": 1.6701816051552432,
      "grad_norm": 0.016724595800042152,
      "learning_rate": 1.5122373418731306e-05,
      "loss": 0.5001986622810364,
      "num_tokens": 9941030.0,
      "step": 357
    },
    {
      "epoch": 1.6748681898066784,
      "grad_norm": 0.02123427577316761,
      "learning_rate": 1.4715774704580453e-05,
      "loss": 0.4547899067401886,
      "num_tokens": 9964745.0,
      "step": 358
    },
    {
      "epoch": 1.6795547744581136,
      "grad_norm": 0.01946537382900715,
      "learning_rate": 1.4314282383241096e-05,
      "loss": 0.5664156079292297,
      "num_tokens": 9993848.0,
      "step": 359
    },
    {
      "epoch": 1.6842413591095489,
      "grad_norm": 0.02165166288614273,
      "learning_rate": 1.3917920494065029e-05,
      "loss": 0.5498170852661133,
      "num_tokens": 10019419.0,
      "step": 360
    },
    {
      "epoch": 1.688927943760984,
      "grad_norm": 0.027894677594304085,
      "learning_rate": 1.3526712769219618e-05,
      "loss": 0.5285916924476624,
      "num_tokens": 10040091.0,
      "step": 361
    },
    {
      "epoch": 1.6936145284124193,
      "grad_norm": 0.02080203965306282,
      "learning_rate": 1.3140682632266543e-05,
      "loss": 0.5912659168243408,
      "num_tokens": 10065923.0,
      "step": 362
    },
    {
      "epoch": 1.6983011130638546,
      "grad_norm": 0.019554127007722855,
      "learning_rate": 1.2759853196759453e-05,
      "loss": 0.441616028547287,
      "num_tokens": 10093915.0,
      "step": 363
    },
    {
      "epoch": 1.70298769771529,
      "grad_norm": 0.02050815336406231,
      "learning_rate": 1.2384247264859972e-05,
      "loss": 0.49888181686401367,
      "num_tokens": 10118212.0,
      "step": 364
    },
    {
      "epoch": 1.7076742823667252,
      "grad_norm": 0.020279014483094215,
      "learning_rate": 1.201388732597255e-05,
      "loss": 0.4945400357246399,
      "num_tokens": 10143351.0,
      "step": 365
    },
    {
      "epoch": 1.7123608670181605,
      "grad_norm": 0.019057748839259148,
      "learning_rate": 1.1648795555397719e-05,
      "loss": 0.5163283348083496,
      "num_tokens": 10174779.0,
      "step": 366
    },
    {
      "epoch": 1.717047451669596,
      "grad_norm": 0.01879844442009926,
      "learning_rate": 1.1288993813004467e-05,
      "loss": 0.5313307642936707,
      "num_tokens": 10202383.0,
      "step": 367
    },
    {
      "epoch": 1.7217340363210312,
      "grad_norm": 0.018921202048659325,
      "learning_rate": 1.0934503641921402e-05,
      "loss": 0.48551756143569946,
      "num_tokens": 10235803.0,
      "step": 368
    },
    {
      "epoch": 1.7264206209724664,
      "grad_norm": 0.01716609112918377,
      "learning_rate": 1.0585346267246743e-05,
      "loss": 0.5063148736953735,
      "num_tokens": 10268966.0,
      "step": 369
    },
    {
      "epoch": 1.7311072056239016,
      "grad_norm": 0.01891188696026802,
      "learning_rate": 1.0241542594777576e-05,
      "loss": 0.5777374505996704,
      "num_tokens": 10297902.0,
      "step": 370
    },
    {
      "epoch": 1.7357937902753369,
      "grad_norm": 0.02161267399787903,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.630595326423645,
      "num_tokens": 10326670.0,
      "step": 371
    },
    {
      "epoch": 1.740480374926772,
      "grad_norm": 0.023411279544234276,
      "learning_rate": 9.570078375647006e-06,
      "loss": 0.6194709539413452,
      "num_tokens": 10349607.0,
      "step": 372
    },
    {
      "epoch": 1.7451669595782073,
      "grad_norm": 0.019727453589439392,
      "learning_rate": 9.242458032904311e-06,
      "loss": 0.5031743049621582,
      "num_tokens": 10373422.0,
      "step": 373
    },
    {
      "epoch": 1.7498535442296426,
      "grad_norm": 0.019163846969604492,
      "learning_rate": 8.92027179779732e-06,
      "loss": 0.4999467730522156,
      "num_tokens": 10402421.0,
      "step": 374
    },
    {
      "epoch": 1.7545401288810778,
      "grad_norm": 0.021549245342612267,
      "learning_rate": 8.603538961226232e-06,
      "loss": 0.5685415267944336,
      "num_tokens": 10426989.0,
      "step": 375
    },
    {
      "epoch": 1.759226713532513,
      "grad_norm": 0.02077486179769039,
      "learning_rate": 8.29227848756895e-06,
      "loss": 0.514248788356781,
      "num_tokens": 10452635.0,
      "step": 376
    },
    {
      "epoch": 1.7639132981839485,
      "grad_norm": 0.018285604193806648,
      "learning_rate": 7.986509013545673e-06,
      "loss": 0.4518004357814789,
      "num_tokens": 10480273.0,
      "step": 377
    },
    {
      "epoch": 1.7685998828353837,
      "grad_norm": 0.021749719977378845,
      "learning_rate": 7.686248847103072e-06,
      "loss": 0.5042576193809509,
      "num_tokens": 10507011.0,
      "step": 378
    },
    {
      "epoch": 1.773286467486819,
      "grad_norm": 0.021965045481920242,
      "learning_rate": 7.3915159663179075e-06,
      "loss": 0.45958468317985535,
      "num_tokens": 10534246.0,
      "step": 379
    },
    {
      "epoch": 1.7779730521382544,
      "grad_norm": 0.021479103714227676,
      "learning_rate": 7.102328018320858e-06,
      "loss": 0.5604655146598816,
      "num_tokens": 10558840.0,
      "step": 380
    },
    {
      "epoch": 1.7826596367896896,
      "grad_norm": 0.01994527317583561,
      "learning_rate": 6.818702318239689e-06,
      "loss": 0.4710320234298706,
      "num_tokens": 10590794.0,
      "step": 381
    },
    {
      "epoch": 1.7873462214411249,
      "grad_norm": 0.01706208661198616,
      "learning_rate": 6.540655848162602e-06,
      "loss": 0.4675799012184143,
      "num_tokens": 10622140.0,
      "step": 382
    },
    {
      "epoch": 1.79203280609256,
      "grad_norm": 0.01773303933441639,
      "learning_rate": 6.268205256121396e-06,
      "loss": 0.4936879575252533,
      "num_tokens": 10654133.0,
      "step": 383
    },
    {
      "epoch": 1.7967193907439953,
      "grad_norm": 0.017565935850143433,
      "learning_rate": 6.001366855094748e-06,
      "loss": 0.5558208227157593,
      "num_tokens": 10686465.0,
      "step": 384
    },
    {
      "epoch": 1.8014059753954306,
      "grad_norm": 0.01927906833589077,
      "learning_rate": 5.7401566220313005e-06,
      "loss": 0.5841928720474243,
      "num_tokens": 10714635.0,
      "step": 385
    },
    {
      "epoch": 1.8060925600468658,
      "grad_norm": 0.019323930144309998,
      "learning_rate": 5.484590196893247e-06,
      "loss": 0.4622519016265869,
      "num_tokens": 10742740.0,
      "step": 386
    },
    {
      "epoch": 1.810779144698301,
      "grad_norm": 0.015881702303886414,
      "learning_rate": 5.2346828817197655e-06,
      "loss": 0.45405709743499756,
      "num_tokens": 10777991.0,
      "step": 387
    },
    {
      "epoch": 1.8154657293497363,
      "grad_norm": 0.018986620008945465,
      "learning_rate": 4.990449639710815e-06,
      "loss": 0.564063310623169,
      "num_tokens": 10806693.0,
      "step": 388
    },
    {
      "epoch": 1.8201523140011715,
      "grad_norm": 0.021286584436893463,
      "learning_rate": 4.7519050943312325e-06,
      "loss": 0.543327808380127,
      "num_tokens": 10828841.0,
      "step": 389
    },
    {
      "epoch": 1.824838898652607,
      "grad_norm": 0.019425073638558388,
      "learning_rate": 4.5190635284352075e-06,
      "loss": 0.48441281914711,
      "num_tokens": 10854566.0,
      "step": 390
    },
    {
      "epoch": 1.8295254833040422,
      "grad_norm": 0.019170712679624557,
      "learning_rate": 4.291938883411007e-06,
      "loss": 0.5729823708534241,
      "num_tokens": 10884951.0,
      "step": 391
    },
    {
      "epoch": 1.8342120679554774,
      "grad_norm": 0.017468182370066643,
      "learning_rate": 4.070544758346273e-06,
      "loss": 0.4848058819770813,
      "num_tokens": 10913730.0,
      "step": 392
    },
    {
      "epoch": 1.8388986526069129,
      "grad_norm": 0.015333449468016624,
      "learning_rate": 3.85489440921376e-06,
      "loss": 0.43799474835395813,
      "num_tokens": 10948137.0,
      "step": 393
    },
    {
      "epoch": 1.843585237258348,
      "grad_norm": 0.02028125524520874,
      "learning_rate": 3.6450007480777093e-06,
      "loss": 0.5041326284408569,
      "num_tokens": 10979119.0,
      "step": 394
    },
    {
      "epoch": 1.8482718219097833,
      "grad_norm": 0.019283445551991463,
      "learning_rate": 3.440876342320609e-06,
      "loss": 0.5077893137931824,
      "num_tokens": 11007970.0,
      "step": 395
    },
    {
      "epoch": 1.8529584065612186,
      "grad_norm": 0.020001094788312912,
      "learning_rate": 3.2425334138908583e-06,
      "loss": 0.46497297286987305,
      "num_tokens": 11035006.0,
      "step": 396
    },
    {
      "epoch": 1.8576449912126538,
      "grad_norm": 0.01882210001349449,
      "learning_rate": 3.049983838570858e-06,
      "loss": 0.5870270133018494,
      "num_tokens": 11067650.0,
      "step": 397
    },
    {
      "epoch": 1.862331575864089,
      "grad_norm": 0.018075548112392426,
      "learning_rate": 2.863239145266028e-06,
      "loss": 0.5191249847412109,
      "num_tokens": 11099231.0,
      "step": 398
    },
    {
      "epoch": 1.8670181605155243,
      "grad_norm": 0.018168693408370018,
      "learning_rate": 2.682310515314512e-06,
      "loss": 0.5420185327529907,
      "num_tokens": 11127026.0,
      "step": 399
    },
    {
      "epoch": 1.8717047451669595,
      "grad_norm": 0.023422107100486755,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.547164261341095,
      "num_tokens": 11148798.0,
      "step": 400
    },
    {
      "epoch": 1.8763913298183947,
      "grad_norm": 0.021397290751338005,
      "learning_rate": 2.3379444289913342e-06,
      "loss": 0.5418939590454102,
      "num_tokens": 11172786.0,
      "step": 401
    },
    {
      "epoch": 1.88107791446983,
      "grad_norm": 0.02199622616171837,
      "learning_rate": 2.174527591538367e-06,
      "loss": 0.6194959878921509,
      "num_tokens": 11201185.0,
      "step": 402
    },
    {
      "epoch": 1.8857644991212654,
      "grad_norm": 0.02652847021818161,
      "learning_rate": 2.016968054041546e-06,
      "loss": 0.5110518932342529,
      "num_tokens": 11228646.0,
      "step": 403
    },
    {
      "epoch": 1.8904510837727007,
      "grad_norm": 0.019725376740098,
      "learning_rate": 1.8652752503778404e-06,
      "loss": 0.4974381625652313,
      "num_tokens": 11261129.0,
      "step": 404
    },
    {
      "epoch": 1.895137668424136,
      "grad_norm": 0.01984337344765663,
      "learning_rate": 1.7194582631535617e-06,
      "loss": 0.42750030755996704,
      "num_tokens": 11280803.0,
      "step": 405
    },
    {
      "epoch": 1.8998242530755711,
      "grad_norm": 0.023329835385084152,
      "learning_rate": 1.5795258231605103e-06,
      "loss": 0.6441700458526611,
      "num_tokens": 11308211.0,
      "step": 406
    },
    {
      "epoch": 1.9045108377270066,
      "grad_norm": 0.01877567172050476,
      "learning_rate": 1.4454863088532388e-06,
      "loss": 0.5390148162841797,
      "num_tokens": 11337040.0,
      "step": 407
    },
    {
      "epoch": 1.9091974223784418,
      "grad_norm": 0.01908472180366516,
      "learning_rate": 1.317347745847386e-06,
      "loss": 0.48877766728401184,
      "num_tokens": 11364700.0,
      "step": 408
    },
    {
      "epoch": 1.913884007029877,
      "grad_norm": 0.01864306814968586,
      "learning_rate": 1.19511780643915e-06,
      "loss": 0.4961361885070801,
      "num_tokens": 11395825.0,
      "step": 409
    },
    {
      "epoch": 1.9185705916813123,
      "grad_norm": 0.019876793026924133,
      "learning_rate": 1.0788038091458897e-06,
      "loss": 0.4837869107723236,
      "num_tokens": 11422663.0,
      "step": 410
    },
    {
      "epoch": 1.9232571763327475,
      "grad_norm": 0.023133547976613045,
      "learning_rate": 9.684127182679526e-07,
      "loss": 0.7084198594093323,
      "num_tokens": 11449224.0,
      "step": 411
    },
    {
      "epoch": 1.9279437609841827,
      "grad_norm": 0.019681880250573158,
      "learning_rate": 8.639511434716863e-07,
      "loss": 0.5047839879989624,
      "num_tokens": 11473306.0,
      "step": 412
    },
    {
      "epoch": 1.932630345635618,
      "grad_norm": 0.020686620846390724,
      "learning_rate": 7.654253393936439e-07,
      "loss": 0.5622538924217224,
      "num_tokens": 11500514.0,
      "step": 413
    },
    {
      "epoch": 1.9373169302870532,
      "grad_norm": 0.019955623894929886,
      "learning_rate": 6.728412052661504e-07,
      "loss": 0.5109364986419678,
      "num_tokens": 11527844.0,
      "step": 414
    },
    {
      "epoch": 1.9420035149384884,
      "grad_norm": 0.017660239711403847,
      "learning_rate": 5.862042845640403e-07,
      "loss": 0.4417906403541565,
      "num_tokens": 11557249.0,
      "step": 415
    },
    {
      "epoch": 1.946690099589924,
      "grad_norm": 0.020532328635454178,
      "learning_rate": 5.055197646727572e-07,
      "loss": 0.4714352488517761,
      "num_tokens": 11578525.0,
      "step": 416
    },
    {
      "epoch": 1.9513766842413591,
      "grad_norm": 0.019848326221108437,
      "learning_rate": 4.307924765777682e-07,
      "loss": 0.5248512029647827,
      "num_tokens": 11608618.0,
      "step": 417
    },
    {
      "epoch": 1.9560632688927944,
      "grad_norm": 0.020434431731700897,
      "learning_rate": 3.620268945752847e-07,
      "loss": 0.5544653534889221,
      "num_tokens": 11638839.0,
      "step": 418
    },
    {
      "epoch": 1.9607498535442296,
      "grad_norm": 0.022809825837612152,
      "learning_rate": 2.9922713600439854e-07,
      "loss": 0.5914061069488525,
      "num_tokens": 11664072.0,
      "step": 419
    },
    {
      "epoch": 1.965436438195665,
      "grad_norm": 0.02258451282978058,
      "learning_rate": 2.423969610005017e-07,
      "loss": 0.513454258441925,
      "num_tokens": 11687079.0,
      "step": 420
    },
    {
      "epoch": 1.9701230228471003,
      "grad_norm": 0.019712379202246666,
      "learning_rate": 1.915397722702217e-07,
      "loss": 0.5471534132957458,
      "num_tokens": 11716523.0,
      "step": 421
    },
    {
      "epoch": 1.9748096074985355,
      "grad_norm": 0.02510920725762844,
      "learning_rate": 1.4665861488761813e-07,
      "loss": 0.5896034836769104,
      "num_tokens": 11743511.0,
      "step": 422
    },
    {
      "epoch": 1.9794961921499707,
      "grad_norm": 0.020893312990665436,
      "learning_rate": 1.0775617611189503e-07,
      "loss": 0.5265234708786011,
      "num_tokens": 11769416.0,
      "step": 423
    },
    {
      "epoch": 1.984182776801406,
      "grad_norm": 0.021829666569828987,
      "learning_rate": 7.483478522649634e-08,
      "loss": 0.5084213018417358,
      "num_tokens": 11795821.0,
      "step": 424
    }
  ],
  "logging_steps": 1,
  "max_steps": 428,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 106,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.111260115849377e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}