{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.96,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.00016,
      "loss": 0.6554988384246826,
      "step": 5
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.126953125,
      "learning_rate": 0.00019870967741935483,
      "loss": 0.6316752910614014,
      "step": 10
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.05908203125,
      "learning_rate": 0.0001970967741935484,
      "loss": 0.6129528522491455,
      "step": 15
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.062255859375,
      "learning_rate": 0.00019548387096774195,
      "loss": 0.60089111328125,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0546875,
      "learning_rate": 0.00019387096774193548,
      "loss": 0.6051591873168946,
      "step": 25
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.00019225806451612904,
      "loss": 0.5910581588745117,
      "step": 30
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.04931640625,
      "learning_rate": 0.0001906451612903226,
      "loss": 0.5913372993469238,
      "step": 35
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.05078125,
      "learning_rate": 0.00018903225806451616,
      "loss": 0.5835432052612305,
      "step": 40
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.047119140625,
      "learning_rate": 0.0001874193548387097,
      "loss": 0.5777533054351807,
      "step": 45
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.04833984375,
      "learning_rate": 0.00018580645161290325,
      "loss": 0.5595584392547608,
      "step": 50
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.1103515625,
      "learning_rate": 0.0001841935483870968,
      "loss": 0.5782830715179443,
      "step": 55
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.052001953125,
      "learning_rate": 0.00018258064516129033,
      "loss": 0.561436939239502,
      "step": 60
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.0537109375,
      "learning_rate": 0.00018096774193548387,
      "loss": 0.5930795192718505,
      "step": 65
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.051513671875,
      "learning_rate": 0.00017935483870967742,
      "loss": 0.5740991592407226,
      "step": 70
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.053955078125,
      "learning_rate": 0.00017774193548387098,
      "loss": 0.5711933135986328,
      "step": 75
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.054443359375,
      "learning_rate": 0.0001761290322580645,
      "loss": 0.5878489494323731,
      "step": 80
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.083984375,
      "learning_rate": 0.00017451612903225807,
      "loss": 0.5775240421295166,
      "step": 85
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.06298828125,
      "learning_rate": 0.00017290322580645163,
      "loss": 0.5785224914550782,
      "step": 90
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.058837890625,
      "learning_rate": 0.00017129032258064516,
      "loss": 0.5774213314056397,
      "step": 95
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0556640625,
      "learning_rate": 0.00016967741935483872,
      "loss": 0.5569428443908692,
      "step": 100
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.057373046875,
      "learning_rate": 0.00016806451612903228,
      "loss": 0.5698188304901123,
      "step": 105
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.057861328125,
      "learning_rate": 0.0001664516129032258,
      "loss": 0.574033784866333,
      "step": 110
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.057373046875,
      "learning_rate": 0.00016483870967741937,
      "loss": 0.5798182010650634,
      "step": 115
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.06884765625,
      "learning_rate": 0.00016322580645161292,
      "loss": 0.5746054172515869,
      "step": 120
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.37109375,
      "learning_rate": 0.00016161290322580645,
      "loss": 0.5746851921081543,
      "step": 125
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.059326171875,
      "learning_rate": 0.00016,
      "loss": 0.5720233917236328,
      "step": 130
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.058349609375,
      "learning_rate": 0.00015838709677419357,
      "loss": 0.5694709777832031,
      "step": 135
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.06005859375,
      "learning_rate": 0.0001567741935483871,
      "loss": 0.56185941696167,
      "step": 140
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.06005859375,
      "learning_rate": 0.00015516129032258063,
      "loss": 0.5761864662170411,
      "step": 145
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.059814453125,
      "learning_rate": 0.0001535483870967742,
      "loss": 0.5672729969024658,
      "step": 150
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.05859375,
      "learning_rate": 0.00015193548387096775,
      "loss": 0.5709065437316895,
      "step": 155
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.06298828125,
      "learning_rate": 0.00015032258064516128,
      "loss": 0.5686789989471436,
      "step": 160
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.0595703125,
      "learning_rate": 0.00014870967741935484,
      "loss": 0.5607232570648193,
      "step": 165
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.06298828125,
      "learning_rate": 0.0001470967741935484,
      "loss": 0.5666838645935058,
      "step": 170
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.062255859375,
      "learning_rate": 0.00014548387096774196,
      "loss": 0.5663557052612305,
      "step": 175
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.06103515625,
      "learning_rate": 0.00014387096774193549,
      "loss": 0.5619307518005371,
      "step": 180
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.06494140625,
      "learning_rate": 0.00014225806451612904,
      "loss": 0.5675935268402099,
      "step": 185
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.09375,
      "learning_rate": 0.0001406451612903226,
      "loss": 0.558326530456543,
      "step": 190
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.068359375,
      "learning_rate": 0.00013903225806451613,
      "loss": 0.5571943759918213,
      "step": 195
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.06787109375,
      "learning_rate": 0.0001374193548387097,
      "loss": 0.5767090797424317,
      "step": 200
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.06542576849460602,
      "learning_rate": 0.00013580645161290325,
      "loss": 0.5813523292541504,
      "step": 205
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.06451020389795303,
      "learning_rate": 0.00013419354838709678,
      "loss": 0.5669836521148681,
      "step": 210
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.06229862943291664,
      "learning_rate": 0.00013258064516129034,
      "loss": 0.5780042171478271,
      "step": 215
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.09608947485685349,
      "learning_rate": 0.00013096774193548387,
      "loss": 0.5740575313568115,
      "step": 220
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.06359390914440155,
      "learning_rate": 0.00012935483870967743,
      "loss": 0.5707311630249023,
      "step": 225
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.06713160872459412,
      "learning_rate": 0.00012774193548387096,
      "loss": 0.5569428920745849,
      "step": 230
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.06508593261241913,
      "learning_rate": 0.00012612903225806452,
      "loss": 0.5606443881988525,
      "step": 235
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.06860020011663437,
      "learning_rate": 0.00012451612903225808,
      "loss": 0.5722582817077637,
      "step": 240
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.06724812090396881,
      "learning_rate": 0.0001229032258064516,
      "loss": 0.5671603202819824,
      "step": 245
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.06457360088825226,
      "learning_rate": 0.00012129032258064516,
      "loss": 0.5736354351043701,
      "step": 250
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.07162501662969589,
      "learning_rate": 0.00011967741935483871,
      "loss": 0.568655252456665,
      "step": 255
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.07056798785924911,
      "learning_rate": 0.00011806451612903227,
      "loss": 0.5712923049926758,
      "step": 260
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.06752821058034897,
      "learning_rate": 0.00011645161290322581,
      "loss": 0.574179744720459,
      "step": 265
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.06757891923189163,
      "learning_rate": 0.00011483870967741937,
      "loss": 0.568781852722168,
      "step": 270
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.06529594212770462,
      "learning_rate": 0.00011322580645161291,
      "loss": 0.5763449668884277,
      "step": 275
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.06725391000509262,
      "learning_rate": 0.00011161290322580646,
      "loss": 0.5555770397186279,
      "step": 280
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.06466025859117508,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.558352279663086,
      "step": 285
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.0675201490521431,
      "learning_rate": 0.00010838709677419356,
      "loss": 0.5610656261444091,
      "step": 290
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.06591981649398804,
      "learning_rate": 0.00010677419354838709,
      "loss": 0.5565807819366455,
      "step": 295
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.06528247147798538,
      "learning_rate": 0.00010516129032258064,
      "loss": 0.5542235851287842,
      "step": 300
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.07089075446128845,
      "learning_rate": 0.0001035483870967742,
      "loss": 0.5591094017028808,
      "step": 305
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.07118254154920578,
      "learning_rate": 0.00010193548387096774,
      "loss": 0.5636035919189453,
      "step": 310
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.06858668476343155,
      "learning_rate": 0.00010032258064516129,
      "loss": 0.5677674770355224,
      "step": 315
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.06893937289714813,
      "learning_rate": 9.870967741935484e-05,
      "loss": 0.5631217956542969,
      "step": 320
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.07015130668878555,
      "learning_rate": 9.709677419354839e-05,
      "loss": 0.5573655605316162,
      "step": 325
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.07102397829294205,
      "learning_rate": 9.548387096774195e-05,
      "loss": 0.5720638751983642,
      "step": 330
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.08668693155050278,
      "learning_rate": 9.387096774193549e-05,
      "loss": 0.5595195770263672,
      "step": 335
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.0652279481291771,
      "learning_rate": 9.225806451612904e-05,
      "loss": 0.5633126258850097,
      "step": 340
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.07421018183231354,
      "learning_rate": 9.06451612903226e-05,
      "loss": 0.5664429187774658,
      "step": 345
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.07819076627492905,
      "learning_rate": 8.903225806451614e-05,
      "loss": 0.5585434913635254,
      "step": 350
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.07451411336660385,
      "learning_rate": 8.741935483870968e-05,
      "loss": 0.5587696552276611,
      "step": 355
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.07057429850101471,
      "learning_rate": 8.580645161290323e-05,
      "loss": 0.557004737854004,
      "step": 360
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.06424684822559357,
      "learning_rate": 8.419354838709677e-05,
      "loss": 0.5569393157958984,
      "step": 365
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.06557153165340424,
      "learning_rate": 8.258064516129033e-05,
      "loss": 0.563733434677124,
      "step": 370
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.06546968221664429,
      "learning_rate": 8.096774193548387e-05,
      "loss": 0.570366907119751,
      "step": 375
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.06591956317424774,
      "learning_rate": 7.935483870967743e-05,
      "loss": 0.5555679798126221,
      "step": 380
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.06823961436748505,
      "learning_rate": 7.774193548387098e-05,
      "loss": 0.5626004219055176,
      "step": 385
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.07176834344863892,
      "learning_rate": 7.612903225806451e-05,
      "loss": 0.575939130783081,
      "step": 390
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.06666567921638489,
      "learning_rate": 7.451612903225807e-05,
      "loss": 0.5563110828399658,
      "step": 395
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.06764642894268036,
      "learning_rate": 7.290322580645161e-05,
      "loss": 0.5638130187988282,
      "step": 400
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.06829249113798141,
      "learning_rate": 7.129032258064517e-05,
      "loss": 0.5660825252532959,
      "step": 405
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.09068518131971359,
      "learning_rate": 6.967741935483871e-05,
      "loss": 0.5557247638702393,
      "step": 410
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.0700569748878479,
      "learning_rate": 6.806451612903226e-05,
      "loss": 0.5440712451934815,
      "step": 415
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.06983818113803864,
      "learning_rate": 6.645161290322582e-05,
      "loss": 0.5671990871429443,
      "step": 420
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.0715850442647934,
      "learning_rate": 6.483870967741936e-05,
      "loss": 0.5637064933776855,
      "step": 425
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.06824701279401779,
      "learning_rate": 6.32258064516129e-05,
      "loss": 0.5788649559020996,
      "step": 430
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.07091919332742691,
      "learning_rate": 6.161290322580645e-05,
      "loss": 0.5736388683319091,
      "step": 435
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.07010844349861145,
      "learning_rate": 6e-05,
      "loss": 0.55319185256958,
      "step": 440
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.06883524358272552,
      "learning_rate": 5.838709677419355e-05,
      "loss": 0.5780259132385254,
      "step": 445
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.07393763959407806,
      "learning_rate": 5.67741935483871e-05,
      "loss": 0.557044792175293,
      "step": 450
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.06950511038303375,
      "learning_rate": 5.516129032258065e-05,
      "loss": 0.5620320796966553,
      "step": 455
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.06649049371480942,
      "learning_rate": 5.35483870967742e-05,
      "loss": 0.5640514373779297,
      "step": 460
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.0654178038239479,
      "learning_rate": 5.193548387096775e-05,
      "loss": 0.567882776260376,
      "step": 465
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.06904909759759903,
      "learning_rate": 5.032258064516129e-05,
      "loss": 0.5655563831329345,
      "step": 470
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.06747818738222122,
      "learning_rate": 4.870967741935484e-05,
      "loss": 0.5671658515930176,
      "step": 475
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.06916290521621704,
      "learning_rate": 4.7096774193548385e-05,
      "loss": 0.570194673538208,
      "step": 480
    },
    {
      "epoch": 0.776,
      "grad_norm": 0.07048875093460083,
      "learning_rate": 4.548387096774194e-05,
      "loss": 0.5832510948181152,
      "step": 485
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.06946586817502975,
      "learning_rate": 4.387096774193549e-05,
      "loss": 0.5504323959350585,
      "step": 490
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.06650974601507187,
      "learning_rate": 4.225806451612904e-05,
      "loss": 0.5517677307128906,
      "step": 495
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.06879310309886932,
      "learning_rate": 4.0645161290322584e-05,
      "loss": 0.5599205017089843,
      "step": 500
    },
    {
      "epoch": 0.808,
      "grad_norm": 0.06860392540693283,
      "learning_rate": 3.903225806451613e-05,
      "loss": 0.5657797813415527,
      "step": 505
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.06568386405706406,
      "learning_rate": 3.741935483870968e-05,
      "loss": 0.5563346385955811,
      "step": 510
    },
    {
      "epoch": 0.824,
      "grad_norm": 0.07192289084196091,
      "learning_rate": 3.580645161290323e-05,
      "loss": 0.5695600032806396,
      "step": 515
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.07968848198652267,
      "learning_rate": 3.4193548387096776e-05,
      "loss": 0.5501180648803711,
      "step": 520
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.06926244497299194,
      "learning_rate": 3.258064516129033e-05,
      "loss": 0.5559171676635742,
      "step": 525
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.06760943681001663,
      "learning_rate": 3.096774193548387e-05,
      "loss": 0.5637694835662842,
      "step": 530
    },
    {
      "epoch": 0.856,
      "grad_norm": 0.06881634145975113,
      "learning_rate": 2.9354838709677417e-05,
      "loss": 0.562023115158081,
      "step": 535
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.06764361262321472,
      "learning_rate": 2.7741935483870968e-05,
      "loss": 0.5580467224121094,
      "step": 540
    },
    {
      "epoch": 0.872,
      "grad_norm": 0.06766146421432495,
      "learning_rate": 2.6129032258064516e-05,
      "loss": 0.5589831352233887,
      "step": 545
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.0757446140050888,
      "learning_rate": 2.4516129032258064e-05,
      "loss": 0.5543781757354737,
      "step": 550
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.06817227602005005,
      "learning_rate": 2.2903225806451615e-05,
      "loss": 0.5628514289855957,
      "step": 555
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.07092993706464767,
      "learning_rate": 2.129032258064516e-05,
      "loss": 0.5675341606140136,
      "step": 560
    },
    {
      "epoch": 0.904,
      "grad_norm": 0.06779942661523819,
      "learning_rate": 1.967741935483871e-05,
      "loss": 0.5614606857299804,
      "step": 565
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.07492519170045853,
      "learning_rate": 1.806451612903226e-05,
      "loss": 0.5568675994873047,
      "step": 570
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.06805197149515152,
      "learning_rate": 1.6451612903225807e-05,
      "loss": 0.5574911117553711,
      "step": 575
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.06900990754365921,
      "learning_rate": 1.4838709677419355e-05,
      "loss": 0.565622091293335,
      "step": 580
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.07820545136928558,
      "learning_rate": 1.3225806451612905e-05,
      "loss": 0.5542529106140137,
      "step": 585
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.06747955828905106,
      "learning_rate": 1.1612903225806453e-05,
      "loss": 0.5684441089630127,
      "step": 590
    },
    {
      "epoch": 0.952,
      "grad_norm": 0.0708058774471283,
      "learning_rate": 1e-05,
      "loss": 0.5612256050109863,
      "step": 595
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.06703224778175354,
      "learning_rate": 8.387096774193549e-06,
      "loss": 0.5605002880096436,
      "step": 600
    }
  ],
  "logging_steps": 5,
  "max_steps": 625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4619999375204176e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}