{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 29.868722148620982,
  "eval_steps": 500,
  "global_step": 124000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24087679152113695,
      "grad_norm": 0.5082331299781799,
      "learning_rate": 0.000991969806472336,
      "loss": 1.4852,
      "step": 1000
    },
    {
      "epoch": 0.4817535830422739,
      "grad_norm": 0.4949457347393036,
      "learning_rate": 0.0009839396129446719,
      "loss": 1.369,
      "step": 2000
    },
    {
      "epoch": 0.7226303745634108,
      "grad_norm": 0.5630651116371155,
      "learning_rate": 0.0009759094194170079,
      "loss": 1.3189,
      "step": 3000
    },
    {
      "epoch": 0.9635071660845478,
      "grad_norm": 0.5108479261398315,
      "learning_rate": 0.000967879225889344,
      "loss": 1.2817,
      "step": 4000
    },
    {
      "epoch": 1.2043839576056847,
      "grad_norm": 0.47163671255111694,
      "learning_rate": 0.00095984903236168,
      "loss": 1.2511,
      "step": 5000
    },
    {
      "epoch": 1.4452607491268217,
      "grad_norm": 0.531821072101593,
      "learning_rate": 0.0009518188388340159,
      "loss": 1.2309,
      "step": 6000
    },
    {
      "epoch": 1.6861375406479586,
      "grad_norm": 0.4891831874847412,
      "learning_rate": 0.0009437886453063518,
      "loss": 1.2088,
      "step": 7000
    },
    {
      "epoch": 1.9270143321690956,
      "grad_norm": 0.4778994619846344,
      "learning_rate": 0.0009357584517786879,
      "loss": 1.1936,
      "step": 8000
    },
    {
      "epoch": 2.1678911236902323,
      "grad_norm": 0.5436965823173523,
      "learning_rate": 0.0009277282582510239,
      "loss": 1.1792,
      "step": 9000
    },
    {
      "epoch": 2.4087679152113695,
      "grad_norm": 0.45789214968681335,
      "learning_rate": 0.0009196980647233599,
      "loss": 1.1609,
      "step": 10000
    },
    {
      "epoch": 2.649644706732506,
      "grad_norm": 0.49292871356010437,
      "learning_rate": 0.0009116678711956958,
      "loss": 1.1465,
      "step": 11000
    },
    {
      "epoch": 2.8905214982536434,
      "grad_norm": 0.4877796769142151,
      "learning_rate": 0.0009036376776680318,
      "loss": 1.1339,
      "step": 12000
    },
    {
      "epoch": 3.13139828977478,
      "grad_norm": 0.45624956488609314,
      "learning_rate": 0.0008956074841403679,
      "loss": 1.1235,
      "step": 13000
    },
    {
      "epoch": 3.3722750812959172,
      "grad_norm": 0.45705732703208923,
      "learning_rate": 0.0008875772906127038,
      "loss": 1.114,
      "step": 14000
    },
    {
      "epoch": 3.613151872817054,
      "grad_norm": 0.4534723460674286,
      "learning_rate": 0.0008795470970850398,
      "loss": 1.1022,
      "step": 15000
    },
    {
      "epoch": 3.854028664338191,
      "grad_norm": 0.5117238163948059,
      "learning_rate": 0.0008715169035573758,
      "loss": 1.0936,
      "step": 16000
    },
    {
      "epoch": 4.094905455859328,
      "grad_norm": 0.4832773804664612,
      "learning_rate": 0.0008634867100297117,
      "loss": 1.0895,
      "step": 17000
    },
    {
      "epoch": 4.335782247380465,
      "grad_norm": 0.5012445449829102,
      "learning_rate": 0.0008554565165020477,
      "loss": 1.0793,
      "step": 18000
    },
    {
      "epoch": 4.576659038901602,
      "grad_norm": 0.5131984353065491,
      "learning_rate": 0.0008474263229743838,
      "loss": 1.0737,
      "step": 19000
    },
    {
      "epoch": 4.817535830422739,
      "grad_norm": 0.5085521340370178,
      "learning_rate": 0.0008393961294467197,
      "loss": 1.068,
      "step": 20000
    },
    {
      "epoch": 5.058412621943876,
      "grad_norm": 0.4861578345298767,
      "learning_rate": 0.0008313659359190556,
      "loss": 1.0596,
      "step": 21000
    },
    {
      "epoch": 5.299289413465012,
      "grad_norm": 0.4493337869644165,
      "learning_rate": 0.0008233357423913917,
      "loss": 1.0549,
      "step": 22000
    },
    {
      "epoch": 5.54016620498615,
      "grad_norm": 0.5158481001853943,
      "learning_rate": 0.0008153055488637277,
      "loss": 1.0501,
      "step": 23000
    },
    {
      "epoch": 5.781042996507287,
      "grad_norm": 0.5318390130996704,
      "learning_rate": 0.0008072753553360636,
      "loss": 1.0423,
      "step": 24000
    },
    {
      "epoch": 6.021919788028423,
      "grad_norm": 0.4411888122558594,
      "learning_rate": 0.0007992451618083995,
      "loss": 1.0329,
      "step": 25000
    },
    {
      "epoch": 6.26279657954956,
      "grad_norm": 0.5529501438140869,
      "learning_rate": 0.0007912149682807356,
      "loss": 1.0304,
      "step": 26000
    },
    {
      "epoch": 6.503673371070697,
      "grad_norm": 0.4464714229106903,
      "learning_rate": 0.0007831847747530716,
      "loss": 1.0246,
      "step": 27000
    },
    {
      "epoch": 6.7445501625918345,
      "grad_norm": 0.5307004451751709,
      "learning_rate": 0.0007751545812254074,
      "loss": 1.0229,
      "step": 28000
    },
    {
      "epoch": 6.985426954112971,
      "grad_norm": 0.5123757123947144,
      "learning_rate": 0.0007671243876977435,
      "loss": 1.0172,
      "step": 29000
    },
    {
      "epoch": 7.226303745634108,
      "grad_norm": 0.47260963916778564,
      "learning_rate": 0.0007590941941700795,
      "loss": 1.0122,
      "step": 30000
    },
    {
      "epoch": 7.4671805371552455,
      "grad_norm": 0.5172567963600159,
      "learning_rate": 0.0007510640006424156,
      "loss": 1.0041,
      "step": 31000
    },
    {
      "epoch": 7.708057328676382,
      "grad_norm": 0.5100764036178589,
      "learning_rate": 0.0007430338071147515,
      "loss": 0.9996,
      "step": 32000
    },
    {
      "epoch": 7.948934120197519,
      "grad_norm": 0.5113524198532104,
      "learning_rate": 0.0007350036135870874,
      "loss": 0.9962,
      "step": 33000
    },
    {
      "epoch": 8.189810911718656,
      "grad_norm": 0.5284003615379333,
      "learning_rate": 0.0007269734200594235,
      "loss": 0.9902,
      "step": 34000
    },
    {
      "epoch": 8.430687703239792,
      "grad_norm": 0.45138561725616455,
      "learning_rate": 0.0007189432265317595,
      "loss": 0.9853,
      "step": 35000
    },
    {
      "epoch": 8.67156449476093,
      "grad_norm": 0.5026872158050537,
      "learning_rate": 0.0007109130330040954,
      "loss": 0.9817,
      "step": 36000
    },
    {
      "epoch": 8.912441286282068,
      "grad_norm": 0.553321123123169,
      "learning_rate": 0.0007028828394764313,
      "loss": 0.9842,
      "step": 37000
    },
    {
      "epoch": 9.153318077803204,
      "grad_norm": 0.4765004515647888,
      "learning_rate": 0.0006948526459487674,
      "loss": 0.9748,
      "step": 38000
    },
    {
      "epoch": 9.394194869324341,
      "grad_norm": 0.4472289979457855,
      "learning_rate": 0.0006868224524211034,
      "loss": 0.9734,
      "step": 39000
    },
    {
      "epoch": 9.635071660845478,
      "grad_norm": 0.4811370372772217,
      "learning_rate": 0.0006787922588934393,
      "loss": 0.9671,
      "step": 40000
    },
    {
      "epoch": 9.875948452366615,
      "grad_norm": 0.5080583691596985,
      "learning_rate": 0.0006707620653657753,
      "loss": 0.9687,
      "step": 41000
    },
    {
      "epoch": 10.116825243887751,
      "grad_norm": 0.49223220348358154,
      "learning_rate": 0.0006627318718381113,
      "loss": 0.9592,
      "step": 42000
    },
    {
      "epoch": 10.357702035408888,
      "grad_norm": 0.5603600740432739,
      "learning_rate": 0.0006547016783104472,
      "loss": 0.9559,
      "step": 43000
    },
    {
      "epoch": 10.598578826930025,
      "grad_norm": 0.503847599029541,
      "learning_rate": 0.0006466714847827833,
      "loss": 0.9533,
      "step": 44000
    },
    {
      "epoch": 10.839455618451161,
      "grad_norm": 0.4978269934654236,
      "learning_rate": 0.0006386412912551193,
      "loss": 0.9486,
      "step": 45000
    },
    {
      "epoch": 11.0803324099723,
      "grad_norm": 0.5506151914596558,
      "learning_rate": 0.0006306110977274552,
      "loss": 0.951,
      "step": 46000
    },
    {
      "epoch": 11.321209201493437,
      "grad_norm": 0.5171232223510742,
      "learning_rate": 0.0006225809041997912,
      "loss": 0.9399,
      "step": 47000
    },
    {
      "epoch": 11.562085993014573,
      "grad_norm": 0.656745970249176,
      "learning_rate": 0.0006145507106721272,
      "loss": 0.937,
      "step": 48000
    },
    {
      "epoch": 11.80296278453571,
      "grad_norm": 0.5088077783584595,
      "learning_rate": 0.0006065205171444633,
      "loss": 0.9376,
      "step": 49000
    },
    {
      "epoch": 12.043839576056847,
      "grad_norm": 0.4850046932697296,
      "learning_rate": 0.0005984903236167992,
      "loss": 0.9302,
      "step": 50000
    },
    {
      "epoch": 12.284716367577984,
      "grad_norm": 0.5553488731384277,
      "learning_rate": 0.0005904601300891351,
      "loss": 0.9302,
      "step": 51000
    },
    {
      "epoch": 12.52559315909912,
      "grad_norm": 0.47318387031555176,
      "learning_rate": 0.0005824299365614711,
      "loss": 0.9298,
      "step": 52000
    },
    {
      "epoch": 12.766469950620257,
      "grad_norm": 0.6019132733345032,
      "learning_rate": 0.0005743997430338072,
      "loss": 0.9241,
      "step": 53000
    },
    {
      "epoch": 13.007346742141396,
      "grad_norm": 0.49550944566726685,
      "learning_rate": 0.000566369549506143,
      "loss": 0.9236,
      "step": 54000
    },
    {
      "epoch": 13.248223533662532,
      "grad_norm": 0.5007643103599548,
      "learning_rate": 0.000558339355978479,
      "loss": 0.9196,
      "step": 55000
    },
    {
      "epoch": 13.489100325183669,
      "grad_norm": 0.5525193810462952,
      "learning_rate": 0.0005503091624508151,
      "loss": 0.9113,
      "step": 56000
    },
    {
      "epoch": 13.729977116704806,
      "grad_norm": 0.5109050273895264,
      "learning_rate": 0.0005422789689231511,
      "loss": 0.9077,
      "step": 57000
    },
    {
      "epoch": 13.970853908225942,
      "grad_norm": 0.5197868347167969,
      "learning_rate": 0.000534248775395487,
      "loss": 0.9076,
      "step": 58000
    },
    {
      "epoch": 14.21173069974708,
      "grad_norm": 0.4690844416618347,
      "learning_rate": 0.000526218581867823,
      "loss": 0.9097,
      "step": 59000
    },
    {
      "epoch": 14.452607491268216,
      "grad_norm": 0.5010888576507568,
      "learning_rate": 0.000518188388340159,
      "loss": 0.9022,
      "step": 60000
    },
    {
      "epoch": 14.693484282789353,
      "grad_norm": 0.5394883751869202,
      "learning_rate": 0.000510158194812495,
      "loss": 0.8982,
      "step": 61000
    },
    {
      "epoch": 14.934361074310491,
      "grad_norm": 0.5398752689361572,
      "learning_rate": 0.000502128001284831,
      "loss": 0.8982,
      "step": 62000
    },
    {
      "epoch": 15.175237865831628,
      "grad_norm": 0.48452773690223694,
      "learning_rate": 0.0004940978077571669,
      "loss": 0.8937,
      "step": 63000
    },
    {
      "epoch": 15.416114657352765,
      "grad_norm": 0.5147862434387207,
      "learning_rate": 0.00048606761422950295,
      "loss": 0.894,
      "step": 64000
    },
    {
      "epoch": 15.656991448873901,
      "grad_norm": 0.5301661491394043,
      "learning_rate": 0.00047803742070183893,
      "loss": 0.8865,
      "step": 65000
    },
    {
      "epoch": 15.897868240395038,
      "grad_norm": 0.49967125058174133,
      "learning_rate": 0.0004700072271741749,
      "loss": 0.8825,
      "step": 66000
    },
    {
      "epoch": 16.138745031916176,
      "grad_norm": 0.4977249801158905,
      "learning_rate": 0.0004619770336465109,
      "loss": 0.884,
      "step": 67000
    },
    {
      "epoch": 16.37962182343731,
      "grad_norm": 0.5272189378738403,
      "learning_rate": 0.0004539468401188468,
      "loss": 0.8799,
      "step": 68000
    },
    {
      "epoch": 16.62049861495845,
      "grad_norm": 0.5125630497932434,
      "learning_rate": 0.00044591664659118286,
      "loss": 0.8809,
      "step": 69000
    },
    {
      "epoch": 16.861375406479585,
      "grad_norm": 0.4780360460281372,
      "learning_rate": 0.00043788645306351885,
      "loss": 0.8744,
      "step": 70000
    },
    {
      "epoch": 17.102252198000723,
      "grad_norm": 0.541357159614563,
      "learning_rate": 0.00042985625953585483,
      "loss": 0.8729,
      "step": 71000
    },
    {
      "epoch": 17.34312898952186,
      "grad_norm": 0.5186867713928223,
      "learning_rate": 0.0004218260660081908,
      "loss": 0.8673,
      "step": 72000
    },
    {
      "epoch": 17.584005781042997,
      "grad_norm": 0.5490289330482483,
      "learning_rate": 0.0004137958724805268,
      "loss": 0.8644,
      "step": 73000
    },
    {
      "epoch": 17.824882572564132,
      "grad_norm": 0.5589401125907898,
      "learning_rate": 0.0004057656789528628,
      "loss": 0.8676,
      "step": 74000
    },
    {
      "epoch": 18.06575936408527,
      "grad_norm": 0.5271314382553101,
      "learning_rate": 0.00039773548542519876,
      "loss": 0.861,
      "step": 75000
    },
    {
      "epoch": 18.30663615560641,
      "grad_norm": 0.586135983467102,
      "learning_rate": 0.00038970529189753474,
      "loss": 0.8556,
      "step": 76000
    },
    {
      "epoch": 18.547512947127544,
      "grad_norm": 0.5827994346618652,
      "learning_rate": 0.00038167509836987073,
      "loss": 0.8565,
      "step": 77000
    },
    {
      "epoch": 18.788389738648682,
      "grad_norm": 0.5451443195343018,
      "learning_rate": 0.0003736449048422067,
      "loss": 0.8554,
      "step": 78000
    },
    {
      "epoch": 19.029266530169817,
      "grad_norm": 0.6020991206169128,
      "learning_rate": 0.0003656147113145427,
      "loss": 0.8506,
      "step": 79000
    },
    {
      "epoch": 19.270143321690956,
      "grad_norm": 0.48624420166015625,
      "learning_rate": 0.0003575845177868787,
      "loss": 0.8449,
      "step": 80000
    },
    {
      "epoch": 19.51102011321209,
      "grad_norm": 0.6073954105377197,
      "learning_rate": 0.0003495543242592146,
      "loss": 0.8436,
      "step": 81000
    },
    {
      "epoch": 19.75189690473323,
      "grad_norm": 0.5890400409698486,
      "learning_rate": 0.00034152413073155064,
      "loss": 0.8445,
      "step": 82000
    },
    {
      "epoch": 19.992773696254368,
      "grad_norm": 0.5391818881034851,
      "learning_rate": 0.0003334939372038866,
      "loss": 0.8405,
      "step": 83000
    },
    {
      "epoch": 20.233650487775503,
      "grad_norm": 0.5576732158660889,
      "learning_rate": 0.0003254637436762226,
      "loss": 0.8315,
      "step": 84000
    },
    {
      "epoch": 20.47452727929664,
      "grad_norm": 0.5405558347702026,
      "learning_rate": 0.0003174335501485586,
      "loss": 0.8348,
      "step": 85000
    },
    {
      "epoch": 20.715404070817776,
      "grad_norm": 0.5441027879714966,
      "learning_rate": 0.0003094033566208946,
      "loss": 0.8326,
      "step": 86000
    },
    {
      "epoch": 20.956280862338915,
      "grad_norm": 0.5216940641403198,
      "learning_rate": 0.00030137316309323056,
      "loss": 0.8251,
      "step": 87000
    },
    {
      "epoch": 21.19715765386005,
      "grad_norm": 0.6281733512878418,
      "learning_rate": 0.00029334296956556654,
      "loss": 0.8219,
      "step": 88000
    },
    {
      "epoch": 21.438034445381188,
      "grad_norm": 0.6415626406669617,
      "learning_rate": 0.0002853127760379025,
      "loss": 0.8225,
      "step": 89000
    },
    {
      "epoch": 21.678911236902323,
      "grad_norm": 0.5944454073905945,
      "learning_rate": 0.0002772825825102385,
      "loss": 0.8223,
      "step": 90000
    },
    {
      "epoch": 21.91978802842346,
      "grad_norm": 0.5434209704399109,
      "learning_rate": 0.0002692523889825745,
      "loss": 0.8161,
      "step": 91000
    },
    {
      "epoch": 22.1606648199446,
      "grad_norm": 0.5393619537353516,
      "learning_rate": 0.0002612221954549105,
      "loss": 0.8126,
      "step": 92000
    },
    {
      "epoch": 22.401541611465735,
      "grad_norm": 0.6141464710235596,
      "learning_rate": 0.00025319200192724646,
      "loss": 0.8119,
      "step": 93000
    },
    {
      "epoch": 22.642418402986873,
      "grad_norm": 0.6085337400436401,
      "learning_rate": 0.00024516180839958244,
      "loss": 0.8082,
      "step": 94000
    },
    {
      "epoch": 22.88329519450801,
      "grad_norm": 0.6050975322723389,
      "learning_rate": 0.00023713161487191843,
      "loss": 0.8065,
      "step": 95000
    },
    {
      "epoch": 23.124171986029147,
      "grad_norm": 0.5710690021514893,
      "learning_rate": 0.0002291014213442544,
      "loss": 0.7971,
      "step": 96000
    },
    {
      "epoch": 23.36504877755028,
      "grad_norm": 0.5681021213531494,
      "learning_rate": 0.0002210712278165904,
      "loss": 0.7996,
      "step": 97000
    },
    {
      "epoch": 23.60592556907142,
      "grad_norm": 0.5795422792434692,
      "learning_rate": 0.00021304103428892638,
      "loss": 0.8006,
      "step": 98000
    },
    {
      "epoch": 23.846802360592555,
      "grad_norm": 0.6810296773910522,
      "learning_rate": 0.00020501084076126236,
      "loss": 0.7931,
      "step": 99000
    },
    {
      "epoch": 24.087679152113694,
      "grad_norm": 0.5023326277732849,
      "learning_rate": 0.00019698064723359831,
      "loss": 0.7895,
      "step": 100000
    },
    {
      "epoch": 24.328555943634832,
      "grad_norm": 0.6325027346611023,
      "learning_rate": 0.0001889504537059343,
      "loss": 0.7902,
      "step": 101000
    },
    {
      "epoch": 24.569432735155967,
      "grad_norm": 0.5804798007011414,
      "learning_rate": 0.00018092026017827028,
      "loss": 0.7912,
      "step": 102000
    },
    {
      "epoch": 24.810309526677106,
      "grad_norm": 0.5688096284866333,
      "learning_rate": 0.00017289006665060626,
      "loss": 0.7886,
      "step": 103000
    },
    {
      "epoch": 25.05118631819824,
      "grad_norm": 0.5234955549240112,
      "learning_rate": 0.00016485987312294225,
      "loss": 0.7828,
      "step": 104000
    },
    {
      "epoch": 25.29206310971938,
      "grad_norm": 0.5501936078071594,
      "learning_rate": 0.00015682967959527826,
      "loss": 0.7769,
      "step": 105000
    },
    {
      "epoch": 25.532939901240514,
      "grad_norm": 0.6095595359802246,
      "learning_rate": 0.00014879948606761424,
      "loss": 0.7788,
      "step": 106000
    },
    {
      "epoch": 25.773816692761653,
      "grad_norm": 0.6600815057754517,
      "learning_rate": 0.00014076929253995022,
      "loss": 0.778,
      "step": 107000
    },
    {
      "epoch": 26.01469348428279,
      "grad_norm": 0.6249046921730042,
      "learning_rate": 0.0001327390990122862,
      "loss": 0.7701,
      "step": 108000
    },
    {
      "epoch": 26.255570275803926,
      "grad_norm": 0.7678042054176331,
      "learning_rate": 0.0001247089054846222,
      "loss": 0.7661,
      "step": 109000
    },
    {
      "epoch": 26.496447067325064,
      "grad_norm": 0.5331607460975647,
      "learning_rate": 0.00011667871195695816,
      "loss": 0.7689,
      "step": 110000
    },
    {
      "epoch": 26.7373238588462,
      "grad_norm": 0.6330080628395081,
      "learning_rate": 0.00010864851842929414,
      "loss": 0.7655,
      "step": 111000
    },
    {
      "epoch": 26.978200650367338,
      "grad_norm": 0.6966120004653931,
      "learning_rate": 0.00010061832490163013,
      "loss": 0.7593,
      "step": 112000
    },
    {
      "epoch": 27.219077441888473,
      "grad_norm": 0.6162911653518677,
      "learning_rate": 9.258813137396611e-05,
      "loss": 0.7619,
      "step": 113000
    },
    {
      "epoch": 27.45995423340961,
      "grad_norm": 0.6430843472480774,
      "learning_rate": 8.45579378463021e-05,
      "loss": 0.7598,
      "step": 114000
    },
    {
      "epoch": 27.700831024930746,
      "grad_norm": 0.6248263120651245,
      "learning_rate": 7.652774431863809e-05,
      "loss": 0.7584,
      "step": 115000
    },
    {
      "epoch": 27.941707816451885,
      "grad_norm": 0.6525952219963074,
      "learning_rate": 6.849755079097407e-05,
      "loss": 0.7536,
      "step": 116000
    },
    {
      "epoch": 28.182584607973023,
      "grad_norm": 0.64836186170578,
      "learning_rate": 6.046735726331005e-05,
      "loss": 0.7535,
      "step": 117000
    },
    {
      "epoch": 28.42346139949416,
      "grad_norm": 0.5937727689743042,
      "learning_rate": 5.243716373564603e-05,
      "loss": 0.7453,
      "step": 118000
    },
    {
      "epoch": 28.664338191015297,
      "grad_norm": 0.5951708555221558,
      "learning_rate": 4.440697020798201e-05,
      "loss": 0.7462,
      "step": 119000
    },
    {
      "epoch": 28.90521498253643,
      "grad_norm": 0.5529988408088684,
      "learning_rate": 3.6376776680318e-05,
      "loss": 0.7478,
      "step": 120000
    },
    {
      "epoch": 29.14609177405757,
      "grad_norm": 0.5422804355621338,
      "learning_rate": 2.834658315265398e-05,
      "loss": 0.7454,
      "step": 121000
    },
    {
      "epoch": 29.386968565578705,
      "grad_norm": 0.5853854417800903,
      "learning_rate": 2.0316389624989963e-05,
      "loss": 0.7424,
      "step": 122000
    },
    {
      "epoch": 29.627845357099844,
      "grad_norm": 0.6154918074607849,
      "learning_rate": 1.2286196097325946e-05,
      "loss": 0.7431,
      "step": 123000
    },
    {
      "epoch": 29.868722148620982,
      "grad_norm": 0.596747875213623,
      "learning_rate": 4.256002569661929e-06,
      "loss": 0.7426,
      "step": 124000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 124530,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2404512265548595e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}