{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.723716381418093,
  "eval_steps": 500,
  "global_step": 765,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.097799511002445,
      "grad_norm": 2.395451784133911,
      "learning_rate": 1.9997891995035914e-05,
      "loss": 0.8739,
      "num_input_tokens_seen": 163840,
      "step": 5
    },
    {
      "epoch": 0.19559902200489,
      "grad_norm": 1.3395614624023438,
      "learning_rate": 1.999156886888064e-05,
      "loss": 0.7957,
      "num_input_tokens_seen": 327680,
      "step": 10
    },
    {
      "epoch": 0.293398533007335,
      "grad_norm": 1.125549554824829,
      "learning_rate": 1.9981033287370443e-05,
      "loss": 0.7822,
      "num_input_tokens_seen": 491520,
      "step": 15
    },
    {
      "epoch": 0.39119804400978,
      "grad_norm": 1.1936776638031006,
      "learning_rate": 1.9966289692316944e-05,
      "loss": 0.7815,
      "num_input_tokens_seen": 655360,
      "step": 20
    },
    {
      "epoch": 0.4889975550122249,
      "grad_norm": 1.230684757232666,
      "learning_rate": 1.9947344299634464e-05,
      "loss": 0.7432,
      "num_input_tokens_seen": 819200,
      "step": 25
    },
    {
      "epoch": 0.58679706601467,
      "grad_norm": 1.0630358457565308,
      "learning_rate": 1.992420509671936e-05,
      "loss": 0.7389,
      "num_input_tokens_seen": 982368,
      "step": 30
    },
    {
      "epoch": 0.684596577017115,
      "grad_norm": 1.1900779008865356,
      "learning_rate": 1.9896881839082554e-05,
      "loss": 0.7654,
      "num_input_tokens_seen": 1146208,
      "step": 35
    },
    {
      "epoch": 0.78239608801956,
      "grad_norm": 1.0942089557647705,
      "learning_rate": 1.9865386046236597e-05,
      "loss": 0.7753,
      "num_input_tokens_seen": 1310048,
      "step": 40
    },
    {
      "epoch": 0.8801955990220048,
      "grad_norm": 1.0910882949829102,
      "learning_rate": 1.982973099683902e-05,
      "loss": 0.7256,
      "num_input_tokens_seen": 1473888,
      "step": 45
    },
    {
      "epoch": 0.9779951100244498,
      "grad_norm": 1.0902478694915771,
      "learning_rate": 1.9789931723094046e-05,
      "loss": 0.727,
      "num_input_tokens_seen": 1637728,
      "step": 50
    },
    {
      "epoch": 1.058679706601467,
      "grad_norm": 1.3777414560317993,
      "learning_rate": 1.9746005004415004e-05,
      "loss": 0.582,
      "num_input_tokens_seen": 1770848,
      "step": 55
    },
    {
      "epoch": 1.156479217603912,
      "grad_norm": 1.3062232732772827,
      "learning_rate": 1.9697969360350098e-05,
      "loss": 0.5628,
      "num_input_tokens_seen": 1934688,
      "step": 60
    },
    {
      "epoch": 1.254278728606357,
      "grad_norm": 1.239915132522583,
      "learning_rate": 1.9645845042774555e-05,
      "loss": 0.5561,
      "num_input_tokens_seen": 2098528,
      "step": 65
    },
    {
      "epoch": 1.352078239608802,
      "grad_norm": 1.1612083911895752,
      "learning_rate": 1.9589654027352412e-05,
      "loss": 0.5778,
      "num_input_tokens_seen": 2262368,
      "step": 70
    },
    {
      "epoch": 1.449877750611247,
      "grad_norm": 1.2168060541152954,
      "learning_rate": 1.9529420004271568e-05,
      "loss": 0.5207,
      "num_input_tokens_seen": 2426128,
      "step": 75
    },
    {
      "epoch": 1.5476772616136918,
      "grad_norm": 1.2806190252304077,
      "learning_rate": 1.9465168368255946e-05,
      "loss": 0.5452,
      "num_input_tokens_seen": 2589968,
      "step": 80
    },
    {
      "epoch": 1.6454767726161368,
      "grad_norm": 1.17153000831604,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.5379,
      "num_input_tokens_seen": 2753808,
      "step": 85
    },
    {
      "epoch": 1.7432762836185818,
      "grad_norm": 1.1548662185668945,
      "learning_rate": 1.932472229404356e-05,
      "loss": 0.5116,
      "num_input_tokens_seen": 2917648,
      "step": 90
    },
    {
      "epoch": 1.8410757946210268,
      "grad_norm": 1.3172167539596558,
      "learning_rate": 1.924858706805112e-05,
      "loss": 0.5532,
      "num_input_tokens_seen": 3081488,
      "step": 95
    },
    {
      "epoch": 1.9388753056234718,
      "grad_norm": 1.1930724382400513,
      "learning_rate": 1.9168552628568632e-05,
      "loss": 0.5659,
      "num_input_tokens_seen": 3245328,
      "step": 100
    },
    {
      "epoch": 2.019559902200489,
      "grad_norm": 1.7079554796218872,
      "learning_rate": 1.9084652718195237e-05,
      "loss": 0.6028,
      "num_input_tokens_seen": 3378448,
      "step": 105
    },
    {
      "epoch": 2.117359413202934,
      "grad_norm": 1.7393510341644287,
      "learning_rate": 1.8996922709216456e-05,
      "loss": 0.4228,
      "num_input_tokens_seen": 3542288,
      "step": 110
    },
    {
      "epoch": 2.215158924205379,
      "grad_norm": 1.2822431325912476,
      "learning_rate": 1.8905399588691165e-05,
      "loss": 0.3648,
      "num_input_tokens_seen": 3706128,
      "step": 115
    },
    {
      "epoch": 2.312958435207824,
      "grad_norm": 1.3198189735412598,
      "learning_rate": 1.8810121942857848e-05,
      "loss": 0.3822,
      "num_input_tokens_seen": 3869968,
      "step": 120
    },
    {
      "epoch": 2.410757946210269,
      "grad_norm": 1.2831072807312012,
      "learning_rate": 1.8711129940866577e-05,
      "loss": 0.3907,
      "num_input_tokens_seen": 4033808,
      "step": 125
    },
    {
      "epoch": 2.508557457212714,
      "grad_norm": 1.4272454977035522,
      "learning_rate": 1.860846531784368e-05,
      "loss": 0.3936,
      "num_input_tokens_seen": 4197648,
      "step": 130
    },
    {
      "epoch": 2.606356968215159,
      "grad_norm": 1.3846728801727295,
      "learning_rate": 1.8502171357296144e-05,
      "loss": 0.376,
      "num_input_tokens_seen": 4361488,
      "step": 135
    },
    {
      "epoch": 2.704156479217604,
      "grad_norm": 1.1824907064437866,
      "learning_rate": 1.839229287286327e-05,
      "loss": 0.3735,
      "num_input_tokens_seen": 4525328,
      "step": 140
    },
    {
      "epoch": 2.801955990220049,
      "grad_norm": 1.2617613077163696,
      "learning_rate": 1.827887618942318e-05,
      "loss": 0.4114,
      "num_input_tokens_seen": 4689168,
      "step": 145
    },
    {
      "epoch": 2.899755501222494,
      "grad_norm": 1.1593624353408813,
      "learning_rate": 1.816196912356222e-05,
      "loss": 0.3696,
      "num_input_tokens_seen": 4853008,
      "step": 150
    },
    {
      "epoch": 2.997555012224939,
      "grad_norm": 1.1450086832046509,
      "learning_rate": 1.8041620963415418e-05,
      "loss": 0.3888,
      "num_input_tokens_seen": 5016848,
      "step": 155
    },
    {
      "epoch": 3.078239608801956,
      "grad_norm": 1.4760794639587402,
      "learning_rate": 1.7917882447886585e-05,
      "loss": 0.2605,
      "num_input_tokens_seen": 5149968,
      "step": 160
    },
    {
      "epoch": 3.176039119804401,
      "grad_norm": 1.520880103111267,
      "learning_rate": 1.7790805745256703e-05,
      "loss": 0.2475,
      "num_input_tokens_seen": 5313808,
      "step": 165
    },
    {
      "epoch": 3.273838630806846,
      "grad_norm": 1.4768394231796265,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.2344,
      "num_input_tokens_seen": 5477648,
      "step": 170
    },
    {
      "epoch": 3.371638141809291,
      "grad_norm": 1.4958367347717285,
      "learning_rate": 1.7526853466145248e-05,
      "loss": 0.2665,
      "num_input_tokens_seen": 5641488,
      "step": 175
    },
    {
      "epoch": 3.469437652811736,
      "grad_norm": 1.4445388317108154,
      "learning_rate": 1.7390089172206594e-05,
      "loss": 0.2477,
      "num_input_tokens_seen": 5805328,
      "step": 180
    },
    {
      "epoch": 3.567237163814181,
      "grad_norm": 1.4173372983932495,
      "learning_rate": 1.725020920933593e-05,
      "loss": 0.2679,
      "num_input_tokens_seen": 5969168,
      "step": 185
    },
    {
      "epoch": 3.665036674816626,
      "grad_norm": 1.6111114025115967,
      "learning_rate": 1.710727255106447e-05,
      "loss": 0.234,
      "num_input_tokens_seen": 6133008,
      "step": 190
    },
    {
      "epoch": 3.762836185819071,
      "grad_norm": 1.4121896028518677,
      "learning_rate": 1.696133945962927e-05,
      "loss": 0.2587,
      "num_input_tokens_seen": 6296848,
      "step": 195
    },
    {
      "epoch": 3.860635696821516,
      "grad_norm": 1.3143867254257202,
      "learning_rate": 1.681247146056654e-05,
      "loss": 0.2606,
      "num_input_tokens_seen": 6460688,
      "step": 200
    },
    {
      "epoch": 3.958435207823961,
      "grad_norm": 1.2710639238357544,
      "learning_rate": 1.6660731316772503e-05,
      "loss": 0.2543,
      "num_input_tokens_seen": 6624528,
      "step": 205
    },
    {
      "epoch": 4.039119804400978,
      "grad_norm": 1.284611463546753,
      "learning_rate": 1.650618300204242e-05,
      "loss": 0.1856,
      "num_input_tokens_seen": 6757128,
      "step": 210
    },
    {
      "epoch": 4.136919315403423,
      "grad_norm": 1.6113184690475464,
      "learning_rate": 1.634889167409923e-05,
      "loss": 0.1462,
      "num_input_tokens_seen": 6920968,
      "step": 215
    },
    {
      "epoch": 4.234718826405868,
      "grad_norm": 1.230480432510376,
      "learning_rate": 1.6188923647122946e-05,
      "loss": 0.17,
      "num_input_tokens_seen": 7084808,
      "step": 220
    },
    {
      "epoch": 4.332518337408313,
      "grad_norm": 1.388247013092041,
      "learning_rate": 1.6026346363792565e-05,
      "loss": 0.1427,
      "num_input_tokens_seen": 7248648,
      "step": 225
    },
    {
      "epoch": 4.430317848410758,
      "grad_norm": 1.3794785737991333,
      "learning_rate": 1.5861228366852148e-05,
      "loss": 0.15,
      "num_input_tokens_seen": 7412488,
      "step": 230
    },
    {
      "epoch": 4.528117359413203,
      "grad_norm": 1.5547810792922974,
      "learning_rate": 1.5693639270213138e-05,
      "loss": 0.1603,
      "num_input_tokens_seen": 7576264,
      "step": 235
    },
    {
      "epoch": 4.625916870415648,
      "grad_norm": 1.49036705493927,
      "learning_rate": 1.552364972960506e-05,
      "loss": 0.1536,
      "num_input_tokens_seen": 7740104,
      "step": 240
    },
    {
      "epoch": 4.723716381418093,
      "grad_norm": 1.2922449111938477,
      "learning_rate": 1.5351331412787004e-05,
      "loss": 0.1415,
      "num_input_tokens_seen": 7903944,
      "step": 245
    },
    {
      "epoch": 4.821515892420538,
      "grad_norm": 1.5458725690841675,
      "learning_rate": 1.5176756969332428e-05,
      "loss": 0.159,
      "num_input_tokens_seen": 8067784,
      "step": 250
    },
    {
      "epoch": 4.919315403422983,
      "grad_norm": 1.3060288429260254,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.1699,
      "num_input_tokens_seen": 8231624,
      "step": 255
    },
    {
      "epoch": 5.0,
      "grad_norm": 4.3814568519592285,
      "learning_rate": 1.4821135025703491e-05,
      "loss": 0.1295,
      "num_input_tokens_seen": 8364744,
      "step": 260
    },
    {
      "epoch": 5.097799511002445,
      "grad_norm": 1.496863842010498,
      "learning_rate": 1.4640237456093636e-05,
      "loss": 0.1019,
      "num_input_tokens_seen": 8528584,
      "step": 265
    },
    {
      "epoch": 5.19559902200489,
      "grad_norm": 1.3016966581344604,
      "learning_rate": 1.4457383557765385e-05,
      "loss": 0.0916,
      "num_input_tokens_seen": 8692424,
      "step": 270
    },
    {
      "epoch": 5.293398533007335,
      "grad_norm": 1.3272321224212646,
      "learning_rate": 1.427265042210381e-05,
      "loss": 0.0935,
      "num_input_tokens_seen": 8856264,
      "step": 275
    },
    {
      "epoch": 5.39119804400978,
      "grad_norm": 1.2260195016860962,
      "learning_rate": 1.4086115932782316e-05,
      "loss": 0.0679,
      "num_input_tokens_seen": 9020104,
      "step": 280
    },
    {
      "epoch": 5.488997555012225,
      "grad_norm": 1.1941609382629395,
      "learning_rate": 1.3897858732926794e-05,
      "loss": 0.101,
      "num_input_tokens_seen": 9183944,
      "step": 285
    },
    {
      "epoch": 5.58679706601467,
      "grad_norm": 1.3348464965820312,
      "learning_rate": 1.3707958191959609e-05,
      "loss": 0.0802,
      "num_input_tokens_seen": 9347784,
      "step": 290
    },
    {
      "epoch": 5.684596577017115,
      "grad_norm": 1.3610597848892212,
      "learning_rate": 1.3516494372137368e-05,
      "loss": 0.0812,
      "num_input_tokens_seen": 9511624,
      "step": 295
    },
    {
      "epoch": 5.78239608801956,
      "grad_norm": 1.1276705265045166,
      "learning_rate": 1.3323547994796597e-05,
      "loss": 0.0812,
      "num_input_tokens_seen": 9675464,
      "step": 300
    },
    {
      "epoch": 5.880195599022005,
      "grad_norm": 1.4052499532699585,
      "learning_rate": 1.3129200406321545e-05,
      "loss": 0.0884,
      "num_input_tokens_seen": 9839304,
      "step": 305
    },
    {
      "epoch": 5.97799511002445,
      "grad_norm": 1.2434982061386108,
      "learning_rate": 1.2933533543848462e-05,
      "loss": 0.0906,
      "num_input_tokens_seen": 10003144,
      "step": 310
    },
    {
      "epoch": 6.058679706601467,
      "grad_norm": 1.19767427444458,
      "learning_rate": 1.2736629900720832e-05,
      "loss": 0.0616,
      "num_input_tokens_seen": 10136264,
      "step": 315
    },
    {
      "epoch": 6.156479217603912,
      "grad_norm": 1.2783230543136597,
      "learning_rate": 1.2538572491710079e-05,
      "loss": 0.0447,
      "num_input_tokens_seen": 10300104,
      "step": 320
    },
    {
      "epoch": 6.254278728606357,
      "grad_norm": 1.1590359210968018,
      "learning_rate": 1.2339444818016488e-05,
      "loss": 0.0528,
      "num_input_tokens_seen": 10463944,
      "step": 325
    },
    {
      "epoch": 6.352078239608802,
      "grad_norm": 1.2891935110092163,
      "learning_rate": 1.2139330832064975e-05,
      "loss": 0.0429,
      "num_input_tokens_seen": 10627784,
      "step": 330
    },
    {
      "epoch": 6.449877750611247,
      "grad_norm": 1.0882583856582642,
      "learning_rate": 1.1938314902110701e-05,
      "loss": 0.0442,
      "num_input_tokens_seen": 10791624,
      "step": 335
    },
    {
      "epoch": 6.547677261613692,
      "grad_norm": 1.1069742441177368,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.047,
      "num_input_tokens_seen": 10955464,
      "step": 340
    },
    {
      "epoch": 6.645476772616137,
      "grad_norm": 1.0986578464508057,
      "learning_rate": 1.1533916548786856e-05,
      "loss": 0.0437,
      "num_input_tokens_seen": 11119304,
      "step": 345
    },
    {
      "epoch": 6.743276283618582,
      "grad_norm": 1.1824274063110352,
      "learning_rate": 1.133070462016454e-05,
      "loss": 0.0466,
      "num_input_tokens_seen": 11282568,
      "step": 350
    },
    {
      "epoch": 6.841075794621027,
      "grad_norm": 1.197988510131836,
      "learning_rate": 1.1126931665153213e-05,
      "loss": 0.0498,
      "num_input_tokens_seen": 11446408,
      "step": 355
    },
    {
      "epoch": 6.938875305623472,
      "grad_norm": 1.1721147298812866,
      "learning_rate": 1.092268359463302e-05,
      "loss": 0.0409,
      "num_input_tokens_seen": 11610248,
      "step": 360
    },
    {
      "epoch": 7.019559902200489,
      "grad_norm": 0.9280807971954346,
      "learning_rate": 1.0718046519793276e-05,
      "loss": 0.0444,
      "num_input_tokens_seen": 11743368,
      "step": 365
    },
    {
      "epoch": 7.117359413202934,
      "grad_norm": 0.8121551871299744,
      "learning_rate": 1.0513106715827897e-05,
      "loss": 0.0212,
      "num_input_tokens_seen": 11906632,
      "step": 370
    },
    {
      "epoch": 7.215158924205379,
      "grad_norm": 0.974238932132721,
      "learning_rate": 1.0307950585561705e-05,
      "loss": 0.0275,
      "num_input_tokens_seen": 12070472,
      "step": 375
    },
    {
      "epoch": 7.312958435207824,
      "grad_norm": 0.8143863081932068,
      "learning_rate": 1.01026646230229e-05,
      "loss": 0.0234,
      "num_input_tokens_seen": 12234312,
      "step": 380
    },
    {
      "epoch": 7.410757946210269,
      "grad_norm": 0.9007371664047241,
      "learning_rate": 9.897335376977104e-06,
      "loss": 0.0227,
      "num_input_tokens_seen": 12398152,
      "step": 385
    },
    {
      "epoch": 7.508557457212714,
      "grad_norm": 0.8347233533859253,
      "learning_rate": 9.692049414438298e-06,
      "loss": 0.0264,
      "num_input_tokens_seen": 12561992,
      "step": 390
    },
    {
      "epoch": 7.606356968215159,
      "grad_norm": 1.0170607566833496,
      "learning_rate": 9.486893284172103e-06,
      "loss": 0.0251,
      "num_input_tokens_seen": 12725832,
      "step": 395
    },
    {
      "epoch": 7.704156479217604,
      "grad_norm": 0.8994267582893372,
      "learning_rate": 9.281953480206725e-06,
      "loss": 0.0237,
      "num_input_tokens_seen": 12889672,
      "step": 400
    },
    {
      "epoch": 7.801955990220049,
      "grad_norm": 1.0272514820098877,
      "learning_rate": 9.07731640536698e-06,
      "loss": 0.0228,
      "num_input_tokens_seen": 13053512,
      "step": 405
    },
    {
      "epoch": 7.899755501222494,
      "grad_norm": 0.8432409167289734,
      "learning_rate": 8.87306833484679e-06,
      "loss": 0.0238,
      "num_input_tokens_seen": 13217352,
      "step": 410
    },
    {
      "epoch": 7.997555012224939,
      "grad_norm": 0.9295158386230469,
      "learning_rate": 8.669295379835467e-06,
      "loss": 0.0222,
      "num_input_tokens_seen": 13381192,
      "step": 415
    },
    {
      "epoch": 8.078239608801956,
      "grad_norm": 0.6758769750595093,
      "learning_rate": 8.466083451213145e-06,
      "loss": 0.0109,
      "num_input_tokens_seen": 13514312,
      "step": 420
    },
    {
      "epoch": 8.1760391198044,
      "grad_norm": 0.5933005213737488,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.0118,
      "num_input_tokens_seen": 13677448,
      "step": 425
    },
    {
      "epoch": 8.273838630806846,
      "grad_norm": 0.7031515836715698,
      "learning_rate": 8.0616850978893e-06,
      "loss": 0.01,
      "num_input_tokens_seen": 13841288,
      "step": 430
    },
    {
      "epoch": 8.37163814180929,
      "grad_norm": 0.8007884621620178,
      "learning_rate": 7.860669167935028e-06,
      "loss": 0.0112,
      "num_input_tokens_seen": 14005128,
      "step": 435
    },
    {
      "epoch": 8.469437652811736,
      "grad_norm": 0.6427900195121765,
      "learning_rate": 7.660555181983517e-06,
      "loss": 0.0133,
      "num_input_tokens_seen": 14168968,
      "step": 440
    },
    {
      "epoch": 8.56723716381418,
      "grad_norm": 0.6638085246086121,
      "learning_rate": 7.461427508289922e-06,
      "loss": 0.0113,
      "num_input_tokens_seen": 14332808,
      "step": 445
    },
    {
      "epoch": 8.665036674816626,
      "grad_norm": 0.6730697751045227,
      "learning_rate": 7.263370099279173e-06,
      "loss": 0.0102,
      "num_input_tokens_seen": 14496648,
      "step": 450
    },
    {
      "epoch": 8.76283618581907,
      "grad_norm": 0.7171938419342041,
      "learning_rate": 7.066466456151541e-06,
      "loss": 0.01,
      "num_input_tokens_seen": 14660488,
      "step": 455
    },
    {
      "epoch": 8.860635696821516,
      "grad_norm": 0.7203698754310608,
      "learning_rate": 6.870799593678459e-06,
      "loss": 0.0116,
      "num_input_tokens_seen": 14824328,
      "step": 460
    },
    {
      "epoch": 8.95843520782396,
      "grad_norm": 0.7533681392669678,
      "learning_rate": 6.6764520052034054e-06,
      "loss": 0.0111,
      "num_input_tokens_seen": 14988168,
      "step": 465
    },
    {
      "epoch": 9.039119804400977,
      "grad_norm": 0.22926057875156403,
      "learning_rate": 6.483505627862632e-06,
      "loss": 0.0071,
      "num_input_tokens_seen": 15121288,
      "step": 470
    },
    {
      "epoch": 9.136919315403423,
      "grad_norm": 0.4467085301876068,
      "learning_rate": 6.292041808040393e-06,
      "loss": 0.0054,
      "num_input_tokens_seen": 15285128,
      "step": 475
    },
    {
      "epoch": 9.234718826405867,
      "grad_norm": 0.5730965733528137,
      "learning_rate": 6.102141267073207e-06,
      "loss": 0.0059,
      "num_input_tokens_seen": 15448968,
      "step": 480
    },
    {
      "epoch": 9.332518337408313,
      "grad_norm": 0.3801887333393097,
      "learning_rate": 5.913884067217686e-06,
      "loss": 0.0045,
      "num_input_tokens_seen": 15612552,
      "step": 485
    },
    {
      "epoch": 9.430317848410757,
      "grad_norm": 0.4900866448879242,
      "learning_rate": 5.727349577896194e-06,
      "loss": 0.004,
      "num_input_tokens_seen": 15776392,
      "step": 490
    },
    {
      "epoch": 9.528117359413203,
      "grad_norm": 0.3590303957462311,
      "learning_rate": 5.542616442234618e-06,
      "loss": 0.0042,
      "num_input_tokens_seen": 15940232,
      "step": 495
    },
    {
      "epoch": 9.625916870415647,
      "grad_norm": 0.36999812722206116,
      "learning_rate": 5.3597625439063685e-06,
      "loss": 0.0049,
      "num_input_tokens_seen": 16104072,
      "step": 500
    },
    {
      "epoch": 9.723716381418093,
      "grad_norm": 0.3589613735675812,
      "learning_rate": 5.178864974296511e-06,
      "loss": 0.0045,
      "num_input_tokens_seen": 16267912,
      "step": 505
    },
    {
      "epoch": 9.821515892420537,
      "grad_norm": 0.30231136083602905,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.004,
      "num_input_tokens_seen": 16431752,
      "step": 510
    },
    {
      "epoch": 9.919315403422983,
      "grad_norm": 0.34575000405311584,
      "learning_rate": 4.823243030667576e-06,
      "loss": 0.0042,
      "num_input_tokens_seen": 16595592,
      "step": 515
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6714850068092346,
      "learning_rate": 4.648668587212998e-06,
      "loss": 0.0037,
      "num_input_tokens_seen": 16728712,
      "step": 520
    },
    {
      "epoch": 10.097799511002446,
      "grad_norm": 0.19611337780952454,
      "learning_rate": 4.476350270394942e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 16892552,
      "step": 525
    },
    {
      "epoch": 10.19559902200489,
      "grad_norm": 0.13641950488090515,
      "learning_rate": 4.306360729786867e-06,
      "loss": 0.002,
      "num_input_tokens_seen": 17056392,
      "step": 530
    },
    {
      "epoch": 10.293398533007334,
      "grad_norm": 0.16702738404273987,
      "learning_rate": 4.138771633147856e-06,
      "loss": 0.0023,
      "num_input_tokens_seen": 17220232,
      "step": 535
    },
    {
      "epoch": 10.39119804400978,
      "grad_norm": 0.2278226763010025,
      "learning_rate": 3.973653636207437e-06,
      "loss": 0.002,
      "num_input_tokens_seen": 17384072,
      "step": 540
    },
    {
      "epoch": 10.488997555012224,
      "grad_norm": 0.1814439296722412,
      "learning_rate": 3.8110763528770543e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 17547912,
      "step": 545
    },
    {
      "epoch": 10.58679706601467,
      "grad_norm": 0.2528248429298401,
      "learning_rate": 3.651108325900773e-06,
      "loss": 0.0025,
      "num_input_tokens_seen": 17711752,
      "step": 550
    },
    {
      "epoch": 10.684596577017114,
      "grad_norm": 0.165152445435524,
      "learning_rate": 3.493816997957582e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 17875592,
      "step": 555
    },
    {
      "epoch": 10.78239608801956,
      "grad_norm": 0.08041153103113174,
      "learning_rate": 3.339268683227499e-06,
      "loss": 0.0017,
      "num_input_tokens_seen": 18039432,
      "step": 560
    },
    {
      "epoch": 10.880195599022004,
      "grad_norm": 0.24567244946956635,
      "learning_rate": 3.1875285394334575e-06,
      "loss": 0.0018,
      "num_input_tokens_seen": 18203272,
      "step": 565
    },
    {
      "epoch": 10.97799511002445,
      "grad_norm": 0.21529506146907806,
      "learning_rate": 3.0386605403707347e-06,
      "loss": 0.0018,
      "num_input_tokens_seen": 18367112,
      "step": 570
    },
    {
      "epoch": 11.058679706601467,
      "grad_norm": 0.05531800910830498,
      "learning_rate": 2.8927274489355296e-06,
      "loss": 0.0014,
      "num_input_tokens_seen": 18500232,
      "step": 575
    },
    {
      "epoch": 11.156479217603913,
      "grad_norm": 0.04145563766360283,
      "learning_rate": 2.749790790664074e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 18662984,
      "step": 580
    },
    {
      "epoch": 11.254278728606357,
      "grad_norm": 0.07673907279968262,
      "learning_rate": 2.6099108277934105e-06,
      "loss": 0.0014,
      "num_input_tokens_seen": 18826824,
      "step": 585
    },
    {
      "epoch": 11.352078239608803,
      "grad_norm": 0.054488956928253174,
      "learning_rate": 2.4731465338547556e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 18990664,
      "step": 590
    },
    {
      "epoch": 11.449877750611247,
      "grad_norm": 0.11207219213247299,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 19154504,
      "step": 595
    },
    {
      "epoch": 11.547677261613693,
      "grad_norm": 0.062526635825634,
      "learning_rate": 2.209194254743295e-06,
      "loss": 0.0012,
      "num_input_tokens_seen": 19318344,
      "step": 600
    },
    {
      "epoch": 11.645476772616137,
      "grad_norm": 0.05114143341779709,
      "learning_rate": 2.0821175521134208e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 19482184,
      "step": 605
    },
    {
      "epoch": 11.743276283618583,
      "grad_norm": 0.05199455842375755,
      "learning_rate": 1.9583790365845823e-06,
      "loss": 0.0013,
      "num_input_tokens_seen": 19646024,
      "step": 610
    },
    {
      "epoch": 11.841075794621027,
      "grad_norm": 0.057281751185655594,
      "learning_rate": 1.8380308764377841e-06,
      "loss": 0.0014,
      "num_input_tokens_seen": 19809864,
      "step": 615
    },
    {
      "epoch": 11.938875305623473,
      "grad_norm": 0.04751597344875336,
      "learning_rate": 1.7211238105768213e-06,
      "loss": 0.0012,
      "num_input_tokens_seen": 19973704,
      "step": 620
    },
    {
      "epoch": 12.01955990220049,
      "grad_norm": 0.04285968840122223,
      "learning_rate": 1.607707127136734e-06,
      "loss": 0.0014,
      "num_input_tokens_seen": 20106824,
      "step": 625
    },
    {
      "epoch": 12.117359413202934,
      "grad_norm": 0.044368330389261246,
      "learning_rate": 1.4978286427038602e-06,
      "loss": 0.0011,
      "num_input_tokens_seen": 20270664,
      "step": 630
    },
    {
      "epoch": 12.21515892420538,
      "grad_norm": 0.04820827767252922,
      "learning_rate": 1.3915346821563235e-06,
      "loss": 0.0012,
      "num_input_tokens_seen": 20434504,
      "step": 635
    },
    {
      "epoch": 12.312958435207824,
      "grad_norm": 0.034025732427835464,
      "learning_rate": 1.2888700591334225e-06,
      "loss": 0.0011,
      "num_input_tokens_seen": 20598280,
      "step": 640
    },
    {
      "epoch": 12.41075794621027,
      "grad_norm": 0.03853330388665199,
      "learning_rate": 1.1898780571421554e-06,
      "loss": 0.0011,
      "num_input_tokens_seen": 20762120,
      "step": 645
    },
    {
      "epoch": 12.508557457212714,
      "grad_norm": 0.039888255298137665,
      "learning_rate": 1.0946004113088381e-06,
      "loss": 0.0012,
      "num_input_tokens_seen": 20925960,
      "step": 650
    },
    {
      "epoch": 12.60635696821516,
      "grad_norm": 0.04366978630423546,
      "learning_rate": 1.0030772907835484e-06,
      "loss": 0.001,
      "num_input_tokens_seen": 21089800,
      "step": 655
    },
    {
      "epoch": 12.704156479217604,
      "grad_norm": 0.03416445106267929,
      "learning_rate": 9.153472818047627e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 21253640,
      "step": 660
    },
    {
      "epoch": 12.80195599022005,
      "grad_norm": 0.04817335307598114,
      "learning_rate": 8.31447371431372e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 21417480,
      "step": 665
    },
    {
      "epoch": 12.899755501222494,
      "grad_norm": 0.03280309960246086,
      "learning_rate": 7.514129319488839e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 21581320,
      "step": 670
    },
    {
      "epoch": 12.99755501222494,
      "grad_norm": 0.04426475614309311,
      "learning_rate": 6.752777059564431e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 21745160,
      "step": 675
    },
    {
      "epoch": 13.078239608801956,
      "grad_norm": 0.03248964622616768,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 21877864,
      "step": 680
    },
    {
      "epoch": 13.1760391198044,
      "grad_norm": 0.0347786545753479,
      "learning_rate": 5.348316317440549e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 22041704,
      "step": 685
    },
    {
      "epoch": 13.273838630806846,
      "grad_norm": 0.04258348420262337,
      "learning_rate": 4.7057999572843516e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 22205544,
      "step": 690
    },
    {
      "epoch": 13.37163814180929,
      "grad_norm": 0.0364152230322361,
      "learning_rate": 4.103459726475889e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 22369384,
      "step": 695
    },
    {
      "epoch": 13.469437652811736,
      "grad_norm": 0.039297617971897125,
      "learning_rate": 3.541549572254488e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 22533224,
      "step": 700
    },
    {
      "epoch": 13.56723716381418,
      "grad_norm": 0.037363260984420776,
      "learning_rate": 3.020306396499062e-07,
      "loss": 0.0009,
      "num_input_tokens_seen": 22697064,
      "step": 705
    },
    {
      "epoch": 13.665036674816626,
      "grad_norm": 0.032989222556352615,
      "learning_rate": 2.539949955849985e-07,
      "loss": 0.0011,
      "num_input_tokens_seen": 22860904,
      "step": 710
    },
    {
      "epoch": 13.76283618581907,
      "grad_norm": 0.03354249894618988,
      "learning_rate": 2.1006827690595478e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 23024744,
      "step": 715
    },
    {
      "epoch": 13.860635696821516,
      "grad_norm": 0.03322712704539299,
      "learning_rate": 1.7026900316098217e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 23188584,
      "step": 720
    },
    {
      "epoch": 13.95843520782396,
      "grad_norm": 0.03775469958782196,
      "learning_rate": 1.3461395376340502e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 23352424,
      "step": 725
    },
    {
      "epoch": 14.039119804400977,
      "grad_norm": 0.039018385112285614,
      "learning_rate": 1.0311816091744698e-07,
      "loss": 0.001,
      "num_input_tokens_seen": 23485296,
      "step": 730
    },
    {
      "epoch": 14.136919315403423,
      "grad_norm": 0.03440910577774048,
      "learning_rate": 7.579490328064265e-08,
      "loss": 0.001,
      "num_input_tokens_seen": 23649136,
      "step": 735
    },
    {
      "epoch": 14.234718826405867,
      "grad_norm": 0.03226885199546814,
      "learning_rate": 5.265570036553813e-08,
      "loss": 0.001,
      "num_input_tokens_seen": 23812976,
      "step": 740
    },
    {
      "epoch": 14.332518337408313,
      "grad_norm": 0.03353099152445793,
      "learning_rate": 3.371030768305583e-08,
      "loss": 0.0009,
      "num_input_tokens_seen": 23976816,
      "step": 745
    },
    {
      "epoch": 14.430317848410757,
      "grad_norm": 0.04043235257267952,
      "learning_rate": 1.896671262955896e-08,
      "loss": 0.001,
      "num_input_tokens_seen": 24140656,
      "step": 750
    },
    {
      "epoch": 14.528117359413203,
      "grad_norm": 0.0331251285970211,
      "learning_rate": 8.431131119361891e-09,
      "loss": 0.001,
      "num_input_tokens_seen": 24304496,
      "step": 755
    },
    {
      "epoch": 14.625916870415647,
      "grad_norm": 0.03793644160032272,
      "learning_rate": 2.108004964086474e-09,
      "loss": 0.001,
      "num_input_tokens_seen": 24467760,
      "step": 760
    },
    {
      "epoch": 14.723716381418093,
      "grad_norm": 0.03213175758719444,
      "learning_rate": 0.0,
      "loss": 0.001,
      "num_input_tokens_seen": 24631600,
      "step": 765
    },
    {
      "epoch": 14.723716381418093,
      "num_input_tokens_seen": 24631600,
      "step": 765,
      "total_flos": 1.936547143200768e+17,
      "train_loss": 0.1555636612302776,
      "train_runtime": 3426.6896,
      "train_samples_per_second": 3.576,
      "train_steps_per_second": 0.223
    }
  ],
  "logging_steps": 5,
  "max_steps": 765,
  "num_input_tokens_seen": 24631600,
  "num_train_epochs": 15,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.936547143200768e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}