{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.182070606902023,
  "eval_steps": 500,
  "global_step": 459,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019833399444664813,
      "grad_norm": 13.009576797485352,
      "learning_rate": 6.640316205533597e-07,
      "loss": 1.5644,
      "mean_token_accuracy": 0.7042247533798218,
      "num_tokens": 326181.0,
      "step": 5
    },
    {
      "epoch": 0.003966679888932963,
      "grad_norm": 8.792983055114746,
      "learning_rate": 1.4940711462450595e-06,
      "loss": 1.5378,
      "mean_token_accuracy": 0.7056464672088623,
      "num_tokens": 651788.0,
      "step": 10
    },
    {
      "epoch": 0.005950019833399445,
      "grad_norm": 4.603586196899414,
      "learning_rate": 2.3241106719367593e-06,
      "loss": 1.3484,
      "mean_token_accuracy": 0.7221232891082764,
      "num_tokens": 977583.0,
      "step": 15
    },
    {
      "epoch": 0.007933359777865925,
      "grad_norm": 3.480231285095215,
      "learning_rate": 3.1541501976284585e-06,
      "loss": 1.1445,
      "mean_token_accuracy": 0.7440239787101746,
      "num_tokens": 1303146.0,
      "step": 20
    },
    {
      "epoch": 0.009916699722332408,
      "grad_norm": 3.0345399379730225,
      "learning_rate": 3.984189723320158e-06,
      "loss": 0.9339,
      "mean_token_accuracy": 0.7866192579269409,
      "num_tokens": 1628167.0,
      "step": 25
    },
    {
      "epoch": 0.01190003966679889,
      "grad_norm": 3.2852017879486084,
      "learning_rate": 4.814229249011859e-06,
      "loss": 0.6696,
      "mean_token_accuracy": 0.8428134202957154,
      "num_tokens": 1953993.0,
      "step": 30
    },
    {
      "epoch": 0.013883379611265371,
      "grad_norm": 2.816546678543091,
      "learning_rate": 5.644268774703558e-06,
      "loss": 0.3843,
      "mean_token_accuracy": 0.9053638696670532,
      "num_tokens": 2279856.0,
      "step": 35
    },
    {
      "epoch": 0.01586671955573185,
      "grad_norm": 1.1652649641036987,
      "learning_rate": 6.474308300395258e-06,
      "loss": 0.2105,
      "mean_token_accuracy": 0.9522119283676147,
      "num_tokens": 2605535.0,
      "step": 40
    },
    {
      "epoch": 0.017850059500198336,
      "grad_norm": 0.68040531873703,
      "learning_rate": 7.304347826086957e-06,
      "loss": 0.1326,
      "mean_token_accuracy": 0.9684872388839721,
      "num_tokens": 2930962.0,
      "step": 45
    },
    {
      "epoch": 0.019833399444664817,
      "grad_norm": 0.37328460812568665,
      "learning_rate": 8.134387351778657e-06,
      "loss": 0.0769,
      "mean_token_accuracy": 0.9798487663269043,
      "num_tokens": 3257123.0,
      "step": 50
    },
    {
      "epoch": 0.0218167393891313,
      "grad_norm": 0.23437659442424774,
      "learning_rate": 8.964426877470356e-06,
      "loss": 0.0574,
      "mean_token_accuracy": 0.9833760738372803,
      "num_tokens": 3583864.0,
      "step": 55
    },
    {
      "epoch": 0.02380007933359778,
      "grad_norm": 0.2768382430076599,
      "learning_rate": 9.794466403162056e-06,
      "loss": 0.0475,
      "mean_token_accuracy": 0.9852861881256103,
      "num_tokens": 3910191.0,
      "step": 60
    },
    {
      "epoch": 0.02578341927806426,
      "grad_norm": 0.19247464835643768,
      "learning_rate": 1.0624505928853755e-05,
      "loss": 0.0506,
      "mean_token_accuracy": 0.9847354054450989,
      "num_tokens": 4235347.0,
      "step": 65
    },
    {
      "epoch": 0.027766759222530742,
      "grad_norm": 0.1612633913755417,
      "learning_rate": 1.1454545454545455e-05,
      "loss": 0.0392,
      "mean_token_accuracy": 0.9871959805488586,
      "num_tokens": 4560646.0,
      "step": 70
    },
    {
      "epoch": 0.029750099166997224,
      "grad_norm": 0.19791056215763092,
      "learning_rate": 1.2284584980237154e-05,
      "loss": 0.0415,
      "mean_token_accuracy": 0.9865655899047852,
      "num_tokens": 4886686.0,
      "step": 75
    },
    {
      "epoch": 0.0317334391114637,
      "grad_norm": 0.1378227025270462,
      "learning_rate": 1.3114624505928855e-05,
      "loss": 0.0376,
      "mean_token_accuracy": 0.9875198721885681,
      "num_tokens": 5212272.0,
      "step": 80
    },
    {
      "epoch": 0.033716779055930186,
      "grad_norm": 0.1562591791152954,
      "learning_rate": 1.3944664031620555e-05,
      "loss": 0.0387,
      "mean_token_accuracy": 0.9868713259696961,
      "num_tokens": 5537919.0,
      "step": 85
    },
    {
      "epoch": 0.03570011900039667,
      "grad_norm": 0.12814277410507202,
      "learning_rate": 1.4774703557312256e-05,
      "loss": 0.0367,
      "mean_token_accuracy": 0.9875417709350586,
      "num_tokens": 5863503.0,
      "step": 90
    },
    {
      "epoch": 0.03768345894486315,
      "grad_norm": 0.09386385232210159,
      "learning_rate": 1.5604743083003954e-05,
      "loss": 0.0364,
      "mean_token_accuracy": 0.9876734137535095,
      "num_tokens": 6189546.0,
      "step": 95
    },
    {
      "epoch": 0.039666798889329634,
      "grad_norm": 0.10281820595264435,
      "learning_rate": 1.6434782608695655e-05,
      "loss": 0.0345,
      "mean_token_accuracy": 0.9879400491714477,
      "num_tokens": 6515601.0,
      "step": 100
    },
    {
      "epoch": 0.04165013883379611,
      "grad_norm": 0.11958280950784683,
      "learning_rate": 1.7264822134387355e-05,
      "loss": 0.0354,
      "mean_token_accuracy": 0.9879724621772766,
      "num_tokens": 6841273.0,
      "step": 105
    },
    {
      "epoch": 0.0436334787782626,
      "grad_norm": 0.13139063119888306,
      "learning_rate": 1.8094861660079052e-05,
      "loss": 0.0359,
      "mean_token_accuracy": 0.9878909111022949,
      "num_tokens": 7166389.0,
      "step": 110
    },
    {
      "epoch": 0.045616818722729074,
      "grad_norm": 0.15603236854076385,
      "learning_rate": 1.8924901185770753e-05,
      "loss": 0.033,
      "mean_token_accuracy": 0.9884216666221619,
      "num_tokens": 7492834.0,
      "step": 115
    },
    {
      "epoch": 0.04760015866719556,
      "grad_norm": 0.10683172196149826,
      "learning_rate": 1.9754940711462453e-05,
      "loss": 0.035,
      "mean_token_accuracy": 0.9880732536315918,
      "num_tokens": 7819098.0,
      "step": 120
    },
    {
      "epoch": 0.04958349861166204,
      "grad_norm": 0.0788409411907196,
      "learning_rate": 2.0584980237154154e-05,
      "loss": 0.0354,
      "mean_token_accuracy": 0.9875108003616333,
      "num_tokens": 8145038.0,
      "step": 125
    },
    {
      "epoch": 0.05156683855612852,
      "grad_norm": 0.0988345742225647,
      "learning_rate": 2.1415019762845854e-05,
      "loss": 0.0355,
      "mean_token_accuracy": 0.9879102587699891,
      "num_tokens": 8470127.0,
      "step": 130
    },
    {
      "epoch": 0.053550178500595,
      "grad_norm": 0.1098787784576416,
      "learning_rate": 2.2245059288537555e-05,
      "loss": 0.036,
      "mean_token_accuracy": 0.9879190802574158,
      "num_tokens": 8796316.0,
      "step": 135
    },
    {
      "epoch": 0.055533518445061485,
      "grad_norm": 0.08738281577825546,
      "learning_rate": 2.3075098814229255e-05,
      "loss": 0.0363,
      "mean_token_accuracy": 0.9878134846687316,
      "num_tokens": 9121704.0,
      "step": 140
    },
    {
      "epoch": 0.05751685838952796,
      "grad_norm": 0.13733771443367004,
      "learning_rate": 2.3905138339920952e-05,
      "loss": 0.0328,
      "mean_token_accuracy": 0.9886667847633361,
      "num_tokens": 9446221.0,
      "step": 145
    },
    {
      "epoch": 0.05950019833399445,
      "grad_norm": 0.09321099519729614,
      "learning_rate": 2.4735177865612653e-05,
      "loss": 0.0343,
      "mean_token_accuracy": 0.9882395029067993,
      "num_tokens": 9772303.0,
      "step": 150
    },
    {
      "epoch": 0.061483538278460925,
      "grad_norm": 0.08978913724422455,
      "learning_rate": 2.5565217391304353e-05,
      "loss": 0.0328,
      "mean_token_accuracy": 0.9885679364204407,
      "num_tokens": 10097679.0,
      "step": 155
    },
    {
      "epoch": 0.0634668782229274,
      "grad_norm": 0.09274271875619888,
      "learning_rate": 2.639525691699605e-05,
      "loss": 0.0345,
      "mean_token_accuracy": 0.9881798505783081,
      "num_tokens": 10423129.0,
      "step": 160
    },
    {
      "epoch": 0.0654502181673939,
      "grad_norm": 0.08157507330179214,
      "learning_rate": 2.722529644268775e-05,
      "loss": 0.033,
      "mean_token_accuracy": 0.9884914517402649,
      "num_tokens": 10749527.0,
      "step": 165
    },
    {
      "epoch": 0.06743355811186037,
      "grad_norm": 0.0861135944724083,
      "learning_rate": 2.805533596837945e-05,
      "loss": 0.036,
      "mean_token_accuracy": 0.9876286745071411,
      "num_tokens": 11074763.0,
      "step": 170
    },
    {
      "epoch": 0.06941689805632685,
      "grad_norm": 0.08185163140296936,
      "learning_rate": 2.888537549407115e-05,
      "loss": 0.0325,
      "mean_token_accuracy": 0.98879075050354,
      "num_tokens": 11401024.0,
      "step": 175
    },
    {
      "epoch": 0.07140023800079334,
      "grad_norm": 0.0789119228720665,
      "learning_rate": 2.971541501976285e-05,
      "loss": 0.0318,
      "mean_token_accuracy": 0.9887811303138733,
      "num_tokens": 11726981.0,
      "step": 180
    },
    {
      "epoch": 0.07338357794525982,
      "grad_norm": 0.07192517071962357,
      "learning_rate": 3.054545454545455e-05,
      "loss": 0.0329,
      "mean_token_accuracy": 0.9886021494865418,
      "num_tokens": 12053334.0,
      "step": 185
    },
    {
      "epoch": 0.0753669178897263,
      "grad_norm": 0.0838698223233223,
      "learning_rate": 3.137549407114625e-05,
      "loss": 0.0336,
      "mean_token_accuracy": 0.9885774612426758,
      "num_tokens": 12378539.0,
      "step": 190
    },
    {
      "epoch": 0.07735025783419278,
      "grad_norm": 0.08229051530361176,
      "learning_rate": 3.2205533596837947e-05,
      "loss": 0.0348,
      "mean_token_accuracy": 0.9879387736320495,
      "num_tokens": 12703899.0,
      "step": 195
    },
    {
      "epoch": 0.07933359777865927,
      "grad_norm": 0.10113668441772461,
      "learning_rate": 3.303557312252965e-05,
      "loss": 0.0349,
      "mean_token_accuracy": 0.9880047559738159,
      "num_tokens": 13029456.0,
      "step": 200
    },
    {
      "epoch": 0.08131693772312575,
      "grad_norm": 0.12065479159355164,
      "learning_rate": 3.386561264822135e-05,
      "loss": 0.0306,
      "mean_token_accuracy": 0.9890530228614807,
      "num_tokens": 13355094.0,
      "step": 205
    },
    {
      "epoch": 0.08330027766759222,
      "grad_norm": 0.07454061508178711,
      "learning_rate": 3.4695652173913045e-05,
      "loss": 0.0327,
      "mean_token_accuracy": 0.9885002017021179,
      "num_tokens": 13681086.0,
      "step": 210
    },
    {
      "epoch": 0.0852836176120587,
      "grad_norm": 0.07741031050682068,
      "learning_rate": 3.552569169960475e-05,
      "loss": 0.0325,
      "mean_token_accuracy": 0.9884979844093322,
      "num_tokens": 14007056.0,
      "step": 215
    },
    {
      "epoch": 0.0872669575565252,
      "grad_norm": 0.06388735771179199,
      "learning_rate": 3.6355731225296445e-05,
      "loss": 0.0311,
      "mean_token_accuracy": 0.9889849901199341,
      "num_tokens": 14333192.0,
      "step": 220
    },
    {
      "epoch": 0.08925029750099167,
      "grad_norm": 0.06051572412252426,
      "learning_rate": 3.718577075098815e-05,
      "loss": 0.0333,
      "mean_token_accuracy": 0.9883559465408325,
      "num_tokens": 14659140.0,
      "step": 225
    },
    {
      "epoch": 0.09123363744545815,
      "grad_norm": 0.06976372748613358,
      "learning_rate": 3.8015810276679846e-05,
      "loss": 0.0329,
      "mean_token_accuracy": 0.9886322021484375,
      "num_tokens": 14983567.0,
      "step": 230
    },
    {
      "epoch": 0.09321697738992463,
      "grad_norm": 0.08022960275411606,
      "learning_rate": 3.8845849802371543e-05,
      "loss": 0.0319,
      "mean_token_accuracy": 0.9886075139045716,
      "num_tokens": 15309754.0,
      "step": 235
    },
    {
      "epoch": 0.09520031733439112,
      "grad_norm": 0.05907947197556496,
      "learning_rate": 3.967588932806325e-05,
      "loss": 0.0326,
      "mean_token_accuracy": 0.9883954286575317,
      "num_tokens": 15635883.0,
      "step": 240
    },
    {
      "epoch": 0.0971836572788576,
      "grad_norm": 0.06979040801525116,
      "learning_rate": 4.0505928853754944e-05,
      "loss": 0.0328,
      "mean_token_accuracy": 0.9884350895881653,
      "num_tokens": 15960716.0,
      "step": 245
    },
    {
      "epoch": 0.09916699722332407,
      "grad_norm": 0.05938795208930969,
      "learning_rate": 4.133596837944664e-05,
      "loss": 0.0312,
      "mean_token_accuracy": 0.9890452265739441,
      "num_tokens": 16285394.0,
      "step": 250
    },
    {
      "epoch": 0.10115033716779057,
      "grad_norm": 0.06661718338727951,
      "learning_rate": 4.1999996611085455e-05,
      "loss": 0.0327,
      "mean_token_accuracy": 0.9886176466941834,
      "num_tokens": 16610519.0,
      "step": 255
    },
    {
      "epoch": 0.10313367711225704,
      "grad_norm": 0.06063701957464218,
      "learning_rate": 4.1999877999229394e-05,
      "loss": 0.0348,
      "mean_token_accuracy": 0.9881076216697693,
      "num_tokens": 16936144.0,
      "step": 260
    },
    {
      "epoch": 0.10511701705672352,
      "grad_norm": 0.10526250302791595,
      "learning_rate": 4.199958994310432e-05,
      "loss": 0.0317,
      "mean_token_accuracy": 0.9887692332267761,
      "num_tokens": 17262285.0,
      "step": 265
    },
    {
      "epoch": 0.10710035700119,
      "grad_norm": 0.060554388910532,
      "learning_rate": 4.199913244580924e-05,
      "loss": 0.0327,
      "mean_token_accuracy": 0.9885782480239869,
      "num_tokens": 17588115.0,
      "step": 270
    },
    {
      "epoch": 0.10908369694565649,
      "grad_norm": 0.055011894553899765,
      "learning_rate": 4.1998505512266134e-05,
      "loss": 0.0316,
      "mean_token_accuracy": 0.9888274312019348,
      "num_tokens": 17913879.0,
      "step": 275
    },
    {
      "epoch": 0.11106703689012297,
      "grad_norm": 0.054953426122665405,
      "learning_rate": 4.1997709149219827e-05,
      "loss": 0.0313,
      "mean_token_accuracy": 0.9887822508811951,
      "num_tokens": 18239107.0,
      "step": 280
    },
    {
      "epoch": 0.11305037683458945,
      "grad_norm": 0.05183308944106102,
      "learning_rate": 4.199674336523796e-05,
      "loss": 0.032,
      "mean_token_accuracy": 0.9885534286499024,
      "num_tokens": 18565560.0,
      "step": 285
    },
    {
      "epoch": 0.11503371677905593,
      "grad_norm": 0.05493587255477905,
      "learning_rate": 4.199560817071086e-05,
      "loss": 0.0327,
      "mean_token_accuracy": 0.9884983539581299,
      "num_tokens": 18891288.0,
      "step": 290
    },
    {
      "epoch": 0.11701705672352242,
      "grad_norm": 0.06698191165924072,
      "learning_rate": 4.199430357785147e-05,
      "loss": 0.0311,
      "mean_token_accuracy": 0.9888833522796631,
      "num_tokens": 19216661.0,
      "step": 295
    },
    {
      "epoch": 0.1190003966679889,
      "grad_norm": 0.06470832228660583,
      "learning_rate": 4.199282960069518e-05,
      "loss": 0.0314,
      "mean_token_accuracy": 0.988831079006195,
      "num_tokens": 19542139.0,
      "step": 300
    },
    {
      "epoch": 0.12098373661245537,
      "grad_norm": 0.06125377118587494,
      "learning_rate": 4.19911862550997e-05,
      "loss": 0.0291,
      "mean_token_accuracy": 0.9896031737327575,
      "num_tokens": 19868344.0,
      "step": 305
    },
    {
      "epoch": 0.12296707655692185,
      "grad_norm": 0.053872209042310715,
      "learning_rate": 4.1989373558744885e-05,
      "loss": 0.0314,
      "mean_token_accuracy": 0.9890127062797547,
      "num_tokens": 20194176.0,
      "step": 310
    },
    {
      "epoch": 0.12495041650138834,
      "grad_norm": 0.06589643657207489,
      "learning_rate": 4.198739153113253e-05,
      "loss": 0.0296,
      "mean_token_accuracy": 0.9894452691078186,
      "num_tokens": 20519970.0,
      "step": 315
    },
    {
      "epoch": 0.1269337564458548,
      "grad_norm": 0.05561014637351036,
      "learning_rate": 4.1985240193586184e-05,
      "loss": 0.0293,
      "mean_token_accuracy": 0.9895825982093811,
      "num_tokens": 20846178.0,
      "step": 320
    },
    {
      "epoch": 0.1289170963903213,
      "grad_norm": 0.04598958417773247,
      "learning_rate": 4.1982919569250904e-05,
      "loss": 0.032,
      "mean_token_accuracy": 0.9887881994247436,
      "num_tokens": 21171408.0,
      "step": 325
    },
    {
      "epoch": 0.1309004363347878,
      "grad_norm": 0.05960153415799141,
      "learning_rate": 4.198042968309301e-05,
      "loss": 0.0331,
      "mean_token_accuracy": 0.9884612679481506,
      "num_tokens": 21497263.0,
      "step": 330
    },
    {
      "epoch": 0.13288377627925427,
      "grad_norm": 0.058145031332969666,
      "learning_rate": 4.197777056189982e-05,
      "loss": 0.0336,
      "mean_token_accuracy": 0.9885963320732116,
      "num_tokens": 21822688.0,
      "step": 335
    },
    {
      "epoch": 0.13486711622372075,
      "grad_norm": 0.04651043564081192,
      "learning_rate": 4.197494223427935e-05,
      "loss": 0.0305,
      "mean_token_accuracy": 0.9890809059143066,
      "num_tokens": 22149076.0,
      "step": 340
    },
    {
      "epoch": 0.13685045616818722,
      "grad_norm": 0.04251869022846222,
      "learning_rate": 4.1971944730660016e-05,
      "loss": 0.0325,
      "mean_token_accuracy": 0.9886854648590088,
      "num_tokens": 22475268.0,
      "step": 345
    },
    {
      "epoch": 0.1388337961126537,
      "grad_norm": 0.05756017565727234,
      "learning_rate": 4.196877808329032e-05,
      "loss": 0.0302,
      "mean_token_accuracy": 0.989712917804718,
      "num_tokens": 22800000.0,
      "step": 350
    },
    {
      "epoch": 0.14081713605712018,
      "grad_norm": 0.05053173378109932,
      "learning_rate": 4.1965442326238465e-05,
      "loss": 0.0301,
      "mean_token_accuracy": 0.9892629265785218,
      "num_tokens": 23125703.0,
      "step": 355
    },
    {
      "epoch": 0.14280047600158668,
      "grad_norm": 0.04995382949709892,
      "learning_rate": 4.196193749539204e-05,
      "loss": 0.0333,
      "mean_token_accuracy": 0.9883558869361877,
      "num_tokens": 23451585.0,
      "step": 360
    },
    {
      "epoch": 0.14478381594605316,
      "grad_norm": 0.05309329926967621,
      "learning_rate": 4.195826362845759e-05,
      "loss": 0.0317,
      "mean_token_accuracy": 0.9889032125473023,
      "num_tokens": 23776911.0,
      "step": 365
    },
    {
      "epoch": 0.14676715589051964,
      "grad_norm": 0.05378350615501404,
      "learning_rate": 4.195442076496022e-05,
      "loss": 0.0302,
      "mean_token_accuracy": 0.9892802953720092,
      "num_tokens": 24102892.0,
      "step": 370
    },
    {
      "epoch": 0.14875049583498612,
      "grad_norm": 0.04636659100651741,
      "learning_rate": 4.195040894624318e-05,
      "loss": 0.0305,
      "mean_token_accuracy": 0.989180064201355,
      "num_tokens": 24428694.0,
      "step": 375
    },
    {
      "epoch": 0.1507338357794526,
      "grad_norm": 0.05095836892724037,
      "learning_rate": 4.1946228215467426e-05,
      "loss": 0.0303,
      "mean_token_accuracy": 0.9891937017440796,
      "num_tokens": 24754979.0,
      "step": 380
    },
    {
      "epoch": 0.15271717572391907,
      "grad_norm": 0.04929406940937042,
      "learning_rate": 4.194187861761114e-05,
      "loss": 0.0293,
      "mean_token_accuracy": 0.9895755290985108,
      "num_tokens": 25080678.0,
      "step": 385
    },
    {
      "epoch": 0.15470051566838555,
      "grad_norm": 0.04400492459535599,
      "learning_rate": 4.193736019946925e-05,
      "loss": 0.0289,
      "mean_token_accuracy": 0.9895238280296326,
      "num_tokens": 25406344.0,
      "step": 390
    },
    {
      "epoch": 0.15668385561285203,
      "grad_norm": 0.05919414386153221,
      "learning_rate": 4.193267300965293e-05,
      "loss": 0.0298,
      "mean_token_accuracy": 0.9893435359001159,
      "num_tokens": 25732360.0,
      "step": 395
    },
    {
      "epoch": 0.15866719555731854,
      "grad_norm": 0.045788154006004333,
      "learning_rate": 4.192781709858908e-05,
      "loss": 0.0306,
      "mean_token_accuracy": 0.9892921686172486,
      "num_tokens": 26058535.0,
      "step": 400
    },
    {
      "epoch": 0.160650535501785,
      "grad_norm": 0.05360753834247589,
      "learning_rate": 4.1922792518519766e-05,
      "loss": 0.0317,
      "mean_token_accuracy": 0.9891477823257446,
      "num_tokens": 26384237.0,
      "step": 405
    },
    {
      "epoch": 0.1626338754462515,
      "grad_norm": 0.0435139536857605,
      "learning_rate": 4.191759932350168e-05,
      "loss": 0.0313,
      "mean_token_accuracy": 0.9887478470802307,
      "num_tokens": 26710030.0,
      "step": 410
    },
    {
      "epoch": 0.16461721539071797,
      "grad_norm": 0.054890286177396774,
      "learning_rate": 4.1912237569405555e-05,
      "loss": 0.0331,
      "mean_token_accuracy": 0.9885681867599487,
      "num_tokens": 27035967.0,
      "step": 415
    },
    {
      "epoch": 0.16660055533518445,
      "grad_norm": 0.05243918299674988,
      "learning_rate": 4.1906707313915556e-05,
      "loss": 0.0316,
      "mean_token_accuracy": 0.9888489246368408,
      "num_tokens": 27361157.0,
      "step": 420
    },
    {
      "epoch": 0.16858389527965092,
      "grad_norm": 0.04567275568842888,
      "learning_rate": 4.1901008616528644e-05,
      "loss": 0.0317,
      "mean_token_accuracy": 0.9888611793518066,
      "num_tokens": 27687246.0,
      "step": 425
    },
    {
      "epoch": 0.1705672352241174,
      "grad_norm": 0.047864675521850586,
      "learning_rate": 4.1895141538553973e-05,
      "loss": 0.0303,
      "mean_token_accuracy": 0.9891236424446106,
      "num_tokens": 28013220.0,
      "step": 430
    },
    {
      "epoch": 0.1725505751685839,
      "grad_norm": 0.04355285316705704,
      "learning_rate": 4.1889106143112215e-05,
      "loss": 0.0313,
      "mean_token_accuracy": 0.9888152480125427,
      "num_tokens": 28339278.0,
      "step": 435
    },
    {
      "epoch": 0.1745339151130504,
      "grad_norm": 0.044995393604040146,
      "learning_rate": 4.1882902495134855e-05,
      "loss": 0.0292,
      "mean_token_accuracy": 0.9894786477088928,
      "num_tokens": 28665261.0,
      "step": 440
    },
    {
      "epoch": 0.17651725505751686,
      "grad_norm": 0.0460113063454628,
      "learning_rate": 4.187653066136354e-05,
      "loss": 0.0308,
      "mean_token_accuracy": 0.9891098380088806,
      "num_tokens": 28991458.0,
      "step": 445
    },
    {
      "epoch": 0.17850059500198334,
      "grad_norm": 0.04992527514696121,
      "learning_rate": 4.186999071034931e-05,
      "loss": 0.0292,
      "mean_token_accuracy": 0.9894602060317993,
      "num_tokens": 29317728.0,
      "step": 450
    },
    {
      "epoch": 0.18048393494644982,
      "grad_norm": 0.040118150413036346,
      "learning_rate": 4.1863282712451914e-05,
      "loss": 0.0292,
      "mean_token_accuracy": 0.9895520448684693,
      "num_tokens": 29643855.0,
      "step": 455
    }
  ],
  "logging_steps": 5,
  "max_steps": 5042,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3266346738240717e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}