{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9983489268024215,
  "eval_steps": 500,
  "global_step": 2724,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01100715465052284,
      "grad_norm": 11.982968764493194,
      "learning_rate": 5e-06,
      "loss": 0.7008,
      "step": 10
    },
    {
      "epoch": 0.02201430930104568,
      "grad_norm": 0.8714451433483839,
      "learning_rate": 5e-06,
      "loss": 0.6366,
      "step": 20
    },
    {
      "epoch": 0.03302146395156852,
      "grad_norm": 0.9399373490721434,
      "learning_rate": 5e-06,
      "loss": 0.6043,
      "step": 30
    },
    {
      "epoch": 0.04402861860209136,
      "grad_norm": 0.751427068876365,
      "learning_rate": 5e-06,
      "loss": 0.5955,
      "step": 40
    },
    {
      "epoch": 0.0550357732526142,
      "grad_norm": 1.3679671707366874,
      "learning_rate": 5e-06,
      "loss": 0.5702,
      "step": 50
    },
    {
      "epoch": 0.06604292790313704,
      "grad_norm": 0.6524007079355506,
      "learning_rate": 5e-06,
      "loss": 0.5644,
      "step": 60
    },
    {
      "epoch": 0.07705008255365987,
      "grad_norm": 0.9485439032325497,
      "learning_rate": 5e-06,
      "loss": 0.5613,
      "step": 70
    },
    {
      "epoch": 0.08805723720418272,
      "grad_norm": 0.6650206723532959,
      "learning_rate": 5e-06,
      "loss": 0.5517,
      "step": 80
    },
    {
      "epoch": 0.09906439185470556,
      "grad_norm": 0.612480075347656,
      "learning_rate": 5e-06,
      "loss": 0.549,
      "step": 90
    },
    {
      "epoch": 0.1100715465052284,
      "grad_norm": 0.6478769173502603,
      "learning_rate": 5e-06,
      "loss": 0.5514,
      "step": 100
    },
    {
      "epoch": 0.12107870115575124,
      "grad_norm": 0.7433352586160162,
      "learning_rate": 5e-06,
      "loss": 0.5413,
      "step": 110
    },
    {
      "epoch": 0.13208585580627408,
      "grad_norm": 0.6239970107685864,
      "learning_rate": 5e-06,
      "loss": 0.5458,
      "step": 120
    },
    {
      "epoch": 0.14309301045679693,
      "grad_norm": 0.6913632744196682,
      "learning_rate": 5e-06,
      "loss": 0.5475,
      "step": 130
    },
    {
      "epoch": 0.15410016510731975,
      "grad_norm": 0.5833635841101626,
      "learning_rate": 5e-06,
      "loss": 0.5359,
      "step": 140
    },
    {
      "epoch": 0.1651073197578426,
      "grad_norm": 0.9786355012067047,
      "learning_rate": 5e-06,
      "loss": 0.5404,
      "step": 150
    },
    {
      "epoch": 0.17611447440836545,
      "grad_norm": 0.5856753856518442,
      "learning_rate": 5e-06,
      "loss": 0.5384,
      "step": 160
    },
    {
      "epoch": 0.18712162905888827,
      "grad_norm": 1.1882823501076132,
      "learning_rate": 5e-06,
      "loss": 0.5378,
      "step": 170
    },
    {
      "epoch": 0.19812878370941112,
      "grad_norm": 1.0789678120584427,
      "learning_rate": 5e-06,
      "loss": 0.53,
      "step": 180
    },
    {
      "epoch": 0.20913593835993396,
      "grad_norm": 0.5803493080254133,
      "learning_rate": 5e-06,
      "loss": 0.5296,
      "step": 190
    },
    {
      "epoch": 0.2201430930104568,
      "grad_norm": 1.4089855222157843,
      "learning_rate": 5e-06,
      "loss": 0.538,
      "step": 200
    },
    {
      "epoch": 0.23115024766097964,
      "grad_norm": 0.6740281868911948,
      "learning_rate": 5e-06,
      "loss": 0.5249,
      "step": 210
    },
    {
      "epoch": 0.24215740231150248,
      "grad_norm": 0.6003523815855626,
      "learning_rate": 5e-06,
      "loss": 0.5243,
      "step": 220
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.572144692190536,
      "learning_rate": 5e-06,
      "loss": 0.5213,
      "step": 230
    },
    {
      "epoch": 0.26417171161254815,
      "grad_norm": 0.7910181593285891,
      "learning_rate": 5e-06,
      "loss": 0.5241,
      "step": 240
    },
    {
      "epoch": 0.275178866263071,
      "grad_norm": 0.6177641321673707,
      "learning_rate": 5e-06,
      "loss": 0.5214,
      "step": 250
    },
    {
      "epoch": 0.28618602091359385,
      "grad_norm": 0.7500304055501509,
      "learning_rate": 5e-06,
      "loss": 0.5227,
      "step": 260
    },
    {
      "epoch": 0.2971931755641167,
      "grad_norm": 0.5759260480918272,
      "learning_rate": 5e-06,
      "loss": 0.5215,
      "step": 270
    },
    {
      "epoch": 0.3082003302146395,
      "grad_norm": 0.6952958522767039,
      "learning_rate": 5e-06,
      "loss": 0.5204,
      "step": 280
    },
    {
      "epoch": 0.31920748486516237,
      "grad_norm": 0.5697348053794516,
      "learning_rate": 5e-06,
      "loss": 0.5191,
      "step": 290
    },
    {
      "epoch": 0.3302146395156852,
      "grad_norm": 0.6937290596232556,
      "learning_rate": 5e-06,
      "loss": 0.5218,
      "step": 300
    },
    {
      "epoch": 0.341221794166208,
      "grad_norm": 0.6529534559675694,
      "learning_rate": 5e-06,
      "loss": 0.519,
      "step": 310
    },
    {
      "epoch": 0.3522289488167309,
      "grad_norm": 0.5948102411026203,
      "learning_rate": 5e-06,
      "loss": 0.5123,
      "step": 320
    },
    {
      "epoch": 0.3632361034672537,
      "grad_norm": 0.6173941636375055,
      "learning_rate": 5e-06,
      "loss": 0.5173,
      "step": 330
    },
    {
      "epoch": 0.37424325811777653,
      "grad_norm": 0.5820501361251,
      "learning_rate": 5e-06,
      "loss": 0.5118,
      "step": 340
    },
    {
      "epoch": 0.3852504127682994,
      "grad_norm": 0.6192352814883568,
      "learning_rate": 5e-06,
      "loss": 0.5098,
      "step": 350
    },
    {
      "epoch": 0.39625756741882223,
      "grad_norm": 0.6679576082120485,
      "learning_rate": 5e-06,
      "loss": 0.5094,
      "step": 360
    },
    {
      "epoch": 0.40726472206934505,
      "grad_norm": 0.6154704715809062,
      "learning_rate": 5e-06,
      "loss": 0.5123,
      "step": 370
    },
    {
      "epoch": 0.41827187671986793,
      "grad_norm": 0.6159721056674322,
      "learning_rate": 5e-06,
      "loss": 0.5118,
      "step": 380
    },
    {
      "epoch": 0.42927903137039075,
      "grad_norm": 0.5902415308915003,
      "learning_rate": 5e-06,
      "loss": 0.5103,
      "step": 390
    },
    {
      "epoch": 0.4402861860209136,
      "grad_norm": 0.5640413537633489,
      "learning_rate": 5e-06,
      "loss": 0.5057,
      "step": 400
    },
    {
      "epoch": 0.45129334067143645,
      "grad_norm": 0.5797805049962861,
      "learning_rate": 5e-06,
      "loss": 0.5105,
      "step": 410
    },
    {
      "epoch": 0.46230049532195927,
      "grad_norm": 0.6329053987073141,
      "learning_rate": 5e-06,
      "loss": 0.5057,
      "step": 420
    },
    {
      "epoch": 0.4733076499724821,
      "grad_norm": 0.6556394966044954,
      "learning_rate": 5e-06,
      "loss": 0.5076,
      "step": 430
    },
    {
      "epoch": 0.48431480462300497,
      "grad_norm": 0.5204872422401521,
      "learning_rate": 5e-06,
      "loss": 0.5091,
      "step": 440
    },
    {
      "epoch": 0.4953219592735278,
      "grad_norm": 0.6055071773984622,
      "learning_rate": 5e-06,
      "loss": 0.5042,
      "step": 450
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.577556213088883,
      "learning_rate": 5e-06,
      "loss": 0.5021,
      "step": 460
    },
    {
      "epoch": 0.5173362685745735,
      "grad_norm": 0.5448206353812828,
      "learning_rate": 5e-06,
      "loss": 0.5031,
      "step": 470
    },
    {
      "epoch": 0.5283434232250963,
      "grad_norm": 0.765679907553655,
      "learning_rate": 5e-06,
      "loss": 0.496,
      "step": 480
    },
    {
      "epoch": 0.5393505778756191,
      "grad_norm": 0.5063752519213206,
      "learning_rate": 5e-06,
      "loss": 0.5084,
      "step": 490
    },
    {
      "epoch": 0.550357732526142,
      "grad_norm": 0.556460627879871,
      "learning_rate": 5e-06,
      "loss": 0.5058,
      "step": 500
    },
    {
      "epoch": 0.5613648871766649,
      "grad_norm": 0.5556971029690015,
      "learning_rate": 5e-06,
      "loss": 0.5042,
      "step": 510
    },
    {
      "epoch": 0.5723720418271877,
      "grad_norm": 0.5087469872433028,
      "learning_rate": 5e-06,
      "loss": 0.4981,
      "step": 520
    },
    {
      "epoch": 0.5833791964777105,
      "grad_norm": 0.5740838855840336,
      "learning_rate": 5e-06,
      "loss": 0.5,
      "step": 530
    },
    {
      "epoch": 0.5943863511282333,
      "grad_norm": 0.6071027341675969,
      "learning_rate": 5e-06,
      "loss": 0.5058,
      "step": 540
    },
    {
      "epoch": 0.6053935057787562,
      "grad_norm": 0.6287150636622116,
      "learning_rate": 5e-06,
      "loss": 0.499,
      "step": 550
    },
    {
      "epoch": 0.616400660429279,
      "grad_norm": 0.5372391906405078,
      "learning_rate": 5e-06,
      "loss": 0.5012,
      "step": 560
    },
    {
      "epoch": 0.6274078150798019,
      "grad_norm": 0.5104155395282183,
      "learning_rate": 5e-06,
      "loss": 0.4965,
      "step": 570
    },
    {
      "epoch": 0.6384149697303247,
      "grad_norm": 0.5503463972044907,
      "learning_rate": 5e-06,
      "loss": 0.5002,
      "step": 580
    },
    {
      "epoch": 0.6494221243808476,
      "grad_norm": 0.6059048518346142,
      "learning_rate": 5e-06,
      "loss": 0.5042,
      "step": 590
    },
    {
      "epoch": 0.6604292790313704,
      "grad_norm": 0.5378531428842014,
      "learning_rate": 5e-06,
      "loss": 0.5,
      "step": 600
    },
    {
      "epoch": 0.6714364336818932,
      "grad_norm": 0.5340292729753958,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 610
    },
    {
      "epoch": 0.682443588332416,
      "grad_norm": 0.5435618709432246,
      "learning_rate": 5e-06,
      "loss": 0.4923,
      "step": 620
    },
    {
      "epoch": 0.693450742982939,
      "grad_norm": 0.5570510303637648,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 630
    },
    {
      "epoch": 0.7044578976334618,
      "grad_norm": 0.5368310165336837,
      "learning_rate": 5e-06,
      "loss": 0.4892,
      "step": 640
    },
    {
      "epoch": 0.7154650522839846,
      "grad_norm": 0.5291121424739461,
      "learning_rate": 5e-06,
      "loss": 0.5006,
      "step": 650
    },
    {
      "epoch": 0.7264722069345074,
      "grad_norm": 0.5896252816232395,
      "learning_rate": 5e-06,
      "loss": 0.4941,
      "step": 660
    },
    {
      "epoch": 0.7374793615850302,
      "grad_norm": 0.5912493036469172,
      "learning_rate": 5e-06,
      "loss": 0.5,
      "step": 670
    },
    {
      "epoch": 0.7484865162355531,
      "grad_norm": 0.5900114035953407,
      "learning_rate": 5e-06,
      "loss": 0.5022,
      "step": 680
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.5900560441658592,
      "learning_rate": 5e-06,
      "loss": 0.4968,
      "step": 690
    },
    {
      "epoch": 0.7705008255365988,
      "grad_norm": 0.6833979531689708,
      "learning_rate": 5e-06,
      "loss": 0.4928,
      "step": 700
    },
    {
      "epoch": 0.7815079801871216,
      "grad_norm": 0.5042222197867751,
      "learning_rate": 5e-06,
      "loss": 0.4898,
      "step": 710
    },
    {
      "epoch": 0.7925151348376445,
      "grad_norm": 0.5569347117978443,
      "learning_rate": 5e-06,
      "loss": 0.4899,
      "step": 720
    },
    {
      "epoch": 0.8035222894881673,
      "grad_norm": 0.5571296055101981,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 730
    },
    {
      "epoch": 0.8145294441386901,
      "grad_norm": 0.5487786231782513,
      "learning_rate": 5e-06,
      "loss": 0.4936,
      "step": 740
    },
    {
      "epoch": 0.825536598789213,
      "grad_norm": 0.5361021770619736,
      "learning_rate": 5e-06,
      "loss": 0.4895,
      "step": 750
    },
    {
      "epoch": 0.8365437534397359,
      "grad_norm": 0.5010641851772664,
      "learning_rate": 5e-06,
      "loss": 0.4791,
      "step": 760
    },
    {
      "epoch": 0.8475509080902587,
      "grad_norm": 0.5961215060285896,
      "learning_rate": 5e-06,
      "loss": 0.492,
      "step": 770
    },
    {
      "epoch": 0.8585580627407815,
      "grad_norm": 0.6022142161806737,
      "learning_rate": 5e-06,
      "loss": 0.4938,
      "step": 780
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.7134051760388376,
      "learning_rate": 5e-06,
      "loss": 0.4914,
      "step": 790
    },
    {
      "epoch": 0.8805723720418271,
      "grad_norm": 0.5943061275040569,
      "learning_rate": 5e-06,
      "loss": 0.4876,
      "step": 800
    },
    {
      "epoch": 0.8915795266923501,
      "grad_norm": 0.5295163028180682,
      "learning_rate": 5e-06,
      "loss": 0.49,
      "step": 810
    },
    {
      "epoch": 0.9025866813428729,
      "grad_norm": 0.6176895623882939,
      "learning_rate": 5e-06,
      "loss": 0.4873,
      "step": 820
    },
    {
      "epoch": 0.9135938359933957,
      "grad_norm": 0.595716110723999,
      "learning_rate": 5e-06,
      "loss": 0.4876,
      "step": 830
    },
    {
      "epoch": 0.9246009906439185,
      "grad_norm": 0.575932394376346,
      "learning_rate": 5e-06,
      "loss": 0.4835,
      "step": 840
    },
    {
      "epoch": 0.9356081452944414,
      "grad_norm": 0.5776178768390061,
      "learning_rate": 5e-06,
      "loss": 0.4856,
      "step": 850
    },
    {
      "epoch": 0.9466152999449642,
      "grad_norm": 0.5228109379951298,
      "learning_rate": 5e-06,
      "loss": 0.4893,
      "step": 860
    },
    {
      "epoch": 0.9576224545954871,
      "grad_norm": 0.5142756334221203,
      "learning_rate": 5e-06,
      "loss": 0.4861,
      "step": 870
    },
    {
      "epoch": 0.9686296092460099,
      "grad_norm": 0.5560430994207315,
      "learning_rate": 5e-06,
      "loss": 0.4866,
      "step": 880
    },
    {
      "epoch": 0.9796367638965328,
      "grad_norm": 0.5236860575170247,
      "learning_rate": 5e-06,
      "loss": 0.4871,
      "step": 890
    },
    {
      "epoch": 0.9906439185470556,
      "grad_norm": 0.5346057585564113,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 900
    },
    {
      "epoch": 0.9994496422674739,
      "eval_loss": 0.4857633411884308,
      "eval_runtime": 159.3539,
      "eval_samples_per_second": 153.564,
      "eval_steps_per_second": 0.602,
      "step": 908
    },
    {
      "epoch": 1.0016510731975785,
      "grad_norm": 0.6954103915524027,
      "learning_rate": 5e-06,
      "loss": 0.4812,
      "step": 910
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.6904861508835244,
      "learning_rate": 5e-06,
      "loss": 0.4395,
      "step": 920
    },
    {
      "epoch": 1.0236653824986242,
      "grad_norm": 0.6056312466483126,
      "learning_rate": 5e-06,
      "loss": 0.4379,
      "step": 930
    },
    {
      "epoch": 1.034672537149147,
      "grad_norm": 0.5635057288110571,
      "learning_rate": 5e-06,
      "loss": 0.4388,
      "step": 940
    },
    {
      "epoch": 1.0456796917996698,
      "grad_norm": 0.6402812237362167,
      "learning_rate": 5e-06,
      "loss": 0.4374,
      "step": 950
    },
    {
      "epoch": 1.0566868464501926,
      "grad_norm": 0.6805656284406708,
      "learning_rate": 5e-06,
      "loss": 0.4358,
      "step": 960
    },
    {
      "epoch": 1.0676940011007154,
      "grad_norm": 0.6802333237610121,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 970
    },
    {
      "epoch": 1.0787011557512383,
      "grad_norm": 0.6342832305273984,
      "learning_rate": 5e-06,
      "loss": 0.4383,
      "step": 980
    },
    {
      "epoch": 1.089708310401761,
      "grad_norm": 0.673378832872309,
      "learning_rate": 5e-06,
      "loss": 0.4385,
      "step": 990
    },
    {
      "epoch": 1.100715465052284,
      "grad_norm": 0.5850001853654084,
      "learning_rate": 5e-06,
      "loss": 0.4405,
      "step": 1000
    },
    {
      "epoch": 1.1117226197028067,
      "grad_norm": 0.5633453327560388,
      "learning_rate": 5e-06,
      "loss": 0.4371,
      "step": 1010
    },
    {
      "epoch": 1.1227297743533298,
      "grad_norm": 0.5794836418349026,
      "learning_rate": 5e-06,
      "loss": 0.4345,
      "step": 1020
    },
    {
      "epoch": 1.1337369290038526,
      "grad_norm": 0.6957157037971271,
      "learning_rate": 5e-06,
      "loss": 0.4405,
      "step": 1030
    },
    {
      "epoch": 1.1447440836543754,
      "grad_norm": 0.5850311919783369,
      "learning_rate": 5e-06,
      "loss": 0.4381,
      "step": 1040
    },
    {
      "epoch": 1.1557512383048982,
      "grad_norm": 0.5786549672004206,
      "learning_rate": 5e-06,
      "loss": 0.4387,
      "step": 1050
    },
    {
      "epoch": 1.166758392955421,
      "grad_norm": 0.5453228479230924,
      "learning_rate": 5e-06,
      "loss": 0.4422,
      "step": 1060
    },
    {
      "epoch": 1.1777655476059439,
      "grad_norm": 0.5271796837376248,
      "learning_rate": 5e-06,
      "loss": 0.4341,
      "step": 1070
    },
    {
      "epoch": 1.1887727022564667,
      "grad_norm": 0.5500839123378732,
      "learning_rate": 5e-06,
      "loss": 0.4353,
      "step": 1080
    },
    {
      "epoch": 1.1997798569069895,
      "grad_norm": 0.5864810400113687,
      "learning_rate": 5e-06,
      "loss": 0.4425,
      "step": 1090
    },
    {
      "epoch": 1.2107870115575123,
      "grad_norm": 0.6180773369312172,
      "learning_rate": 5e-06,
      "loss": 0.4376,
      "step": 1100
    },
    {
      "epoch": 1.2217941662080352,
      "grad_norm": 0.5658554475197427,
      "learning_rate": 5e-06,
      "loss": 0.4323,
      "step": 1110
    },
    {
      "epoch": 1.232801320858558,
      "grad_norm": 0.6193015695020276,
      "learning_rate": 5e-06,
      "loss": 0.4394,
      "step": 1120
    },
    {
      "epoch": 1.243808475509081,
      "grad_norm": 0.5596947987184782,
      "learning_rate": 5e-06,
      "loss": 0.4395,
      "step": 1130
    },
    {
      "epoch": 1.2548156301596038,
      "grad_norm": 0.5779753915489554,
      "learning_rate": 5e-06,
      "loss": 0.4361,
      "step": 1140
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.5970567192151592,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 1150
    },
    {
      "epoch": 1.2768299394606495,
      "grad_norm": 0.6169730283837226,
      "learning_rate": 5e-06,
      "loss": 0.4381,
      "step": 1160
    },
    {
      "epoch": 1.2878370941111723,
      "grad_norm": 0.5446834081363536,
      "learning_rate": 5e-06,
      "loss": 0.4375,
      "step": 1170
    },
    {
      "epoch": 1.2988442487616951,
      "grad_norm": 0.582583999525571,
      "learning_rate": 5e-06,
      "loss": 0.44,
      "step": 1180
    },
    {
      "epoch": 1.309851403412218,
      "grad_norm": 0.5673745624093002,
      "learning_rate": 5e-06,
      "loss": 0.4321,
      "step": 1190
    },
    {
      "epoch": 1.3208585580627408,
      "grad_norm": 0.5922648552723985,
      "learning_rate": 5e-06,
      "loss": 0.4391,
      "step": 1200
    },
    {
      "epoch": 1.3318657127132636,
      "grad_norm": 0.5326676916418296,
      "learning_rate": 5e-06,
      "loss": 0.4299,
      "step": 1210
    },
    {
      "epoch": 1.3428728673637864,
      "grad_norm": 0.5641010101239504,
      "learning_rate": 5e-06,
      "loss": 0.4401,
      "step": 1220
    },
    {
      "epoch": 1.3538800220143092,
      "grad_norm": 0.5910310299336851,
      "learning_rate": 5e-06,
      "loss": 0.4368,
      "step": 1230
    },
    {
      "epoch": 1.364887176664832,
      "grad_norm": 0.5834557438322393,
      "learning_rate": 5e-06,
      "loss": 0.4382,
      "step": 1240
    },
    {
      "epoch": 1.3758943313153549,
      "grad_norm": 0.5191214693333431,
      "learning_rate": 5e-06,
      "loss": 0.4418,
      "step": 1250
    },
    {
      "epoch": 1.3869014859658777,
      "grad_norm": 0.5368395032794088,
      "learning_rate": 5e-06,
      "loss": 0.4402,
      "step": 1260
    },
    {
      "epoch": 1.3979086406164005,
      "grad_norm": 0.5673556075490349,
      "learning_rate": 5e-06,
      "loss": 0.4384,
      "step": 1270
    },
    {
      "epoch": 1.4089157952669236,
      "grad_norm": 0.6481626365833887,
      "learning_rate": 5e-06,
      "loss": 0.4358,
      "step": 1280
    },
    {
      "epoch": 1.4199229499174464,
      "grad_norm": 0.5498988973105204,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 1290
    },
    {
      "epoch": 1.4309301045679692,
      "grad_norm": 0.5302729010671943,
      "learning_rate": 5e-06,
      "loss": 0.4333,
      "step": 1300
    },
    {
      "epoch": 1.441937259218492,
      "grad_norm": 0.5388413616433102,
      "learning_rate": 5e-06,
      "loss": 0.4307,
      "step": 1310
    },
    {
      "epoch": 1.4529444138690149,
      "grad_norm": 0.5834658751113933,
      "learning_rate": 5e-06,
      "loss": 0.4375,
      "step": 1320
    },
    {
      "epoch": 1.4639515685195377,
      "grad_norm": 0.5679787510835149,
      "learning_rate": 5e-06,
      "loss": 0.4318,
      "step": 1330
    },
    {
      "epoch": 1.4749587231700605,
      "grad_norm": 0.5162203463847701,
      "learning_rate": 5e-06,
      "loss": 0.4395,
      "step": 1340
    },
    {
      "epoch": 1.4859658778205833,
      "grad_norm": 0.6126681306614338,
      "learning_rate": 5e-06,
      "loss": 0.4343,
      "step": 1350
    },
    {
      "epoch": 1.4969730324711064,
      "grad_norm": 0.5879183265228268,
      "learning_rate": 5e-06,
      "loss": 0.4358,
      "step": 1360
    },
    {
      "epoch": 1.5079801871216292,
      "grad_norm": 0.5257913985399404,
      "learning_rate": 5e-06,
      "loss": 0.4365,
      "step": 1370
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 0.576090776398715,
      "learning_rate": 5e-06,
      "loss": 0.4387,
      "step": 1380
    },
    {
      "epoch": 1.5299944964226748,
      "grad_norm": 0.5266517756543082,
      "learning_rate": 5e-06,
      "loss": 0.4275,
      "step": 1390
    },
    {
      "epoch": 1.5410016510731976,
      "grad_norm": 0.5214581761670536,
      "learning_rate": 5e-06,
      "loss": 0.4302,
      "step": 1400
    },
    {
      "epoch": 1.5520088057237205,
      "grad_norm": 0.5844587783384355,
      "learning_rate": 5e-06,
      "loss": 0.4344,
      "step": 1410
    },
    {
      "epoch": 1.5630159603742433,
      "grad_norm": 0.5184897433803842,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 1420
    },
    {
      "epoch": 1.574023115024766,
      "grad_norm": 0.603559969863826,
      "learning_rate": 5e-06,
      "loss": 0.4353,
      "step": 1430
    },
    {
      "epoch": 1.585030269675289,
      "grad_norm": 0.6150263738061312,
      "learning_rate": 5e-06,
      "loss": 0.4332,
      "step": 1440
    },
    {
      "epoch": 1.5960374243258117,
      "grad_norm": 0.5587076272635337,
      "learning_rate": 5e-06,
      "loss": 0.4297,
      "step": 1450
    },
    {
      "epoch": 1.6070445789763346,
      "grad_norm": 0.5574804742581976,
      "learning_rate": 5e-06,
      "loss": 0.4369,
      "step": 1460
    },
    {
      "epoch": 1.6180517336268574,
      "grad_norm": 0.6043925859357673,
      "learning_rate": 5e-06,
      "loss": 0.4364,
      "step": 1470
    },
    {
      "epoch": 1.6290588882773802,
      "grad_norm": 0.5613841202662139,
      "learning_rate": 5e-06,
      "loss": 0.4313,
      "step": 1480
    },
    {
      "epoch": 1.640066042927903,
      "grad_norm": 0.5875738293215998,
      "learning_rate": 5e-06,
      "loss": 0.4314,
      "step": 1490
    },
    {
      "epoch": 1.6510731975784259,
      "grad_norm": 0.5312956331787028,
      "learning_rate": 5e-06,
      "loss": 0.4334,
      "step": 1500
    },
    {
      "epoch": 1.6620803522289487,
      "grad_norm": 0.5607804337999436,
      "learning_rate": 5e-06,
      "loss": 0.4332,
      "step": 1510
    },
    {
      "epoch": 1.6730875068794715,
      "grad_norm": 0.5230353473375494,
      "learning_rate": 5e-06,
      "loss": 0.4326,
      "step": 1520
    },
    {
      "epoch": 1.6840946615299945,
      "grad_norm": 0.5965361487319844,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 1530
    },
    {
      "epoch": 1.6951018161805174,
      "grad_norm": 0.5244644152001788,
      "learning_rate": 5e-06,
      "loss": 0.4316,
      "step": 1540
    },
    {
      "epoch": 1.7061089708310402,
      "grad_norm": 0.5431321192494539,
      "learning_rate": 5e-06,
      "loss": 0.431,
      "step": 1550
    },
    {
      "epoch": 1.717116125481563,
      "grad_norm": 0.6513547108421084,
      "learning_rate": 5e-06,
      "loss": 0.4359,
      "step": 1560
    },
    {
      "epoch": 1.7281232801320858,
      "grad_norm": 0.6516507769071219,
      "learning_rate": 5e-06,
      "loss": 0.4332,
      "step": 1570
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.5795960573910671,
      "learning_rate": 5e-06,
      "loss": 0.4295,
      "step": 1580
    },
    {
      "epoch": 1.7501375894331317,
      "grad_norm": 0.5189325164302765,
      "learning_rate": 5e-06,
      "loss": 0.4366,
      "step": 1590
    },
    {
      "epoch": 1.7611447440836545,
      "grad_norm": 0.5417627672077877,
      "learning_rate": 5e-06,
      "loss": 0.4298,
      "step": 1600
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 0.6239972164472983,
      "learning_rate": 5e-06,
      "loss": 0.43,
      "step": 1610
    },
    {
      "epoch": 1.7831590533847002,
      "grad_norm": 0.4996783210981701,
      "learning_rate": 5e-06,
      "loss": 0.43,
      "step": 1620
    },
    {
      "epoch": 1.794166208035223,
      "grad_norm": 0.5104553497784724,
      "learning_rate": 5e-06,
      "loss": 0.432,
      "step": 1630
    },
    {
      "epoch": 1.8051733626857458,
      "grad_norm": 0.5647139288600611,
      "learning_rate": 5e-06,
      "loss": 0.4339,
      "step": 1640
    },
    {
      "epoch": 1.8161805173362686,
      "grad_norm": 0.5630834068994763,
      "learning_rate": 5e-06,
      "loss": 0.4372,
      "step": 1650
    },
    {
      "epoch": 1.8271876719867914,
      "grad_norm": 0.5665633902854723,
      "learning_rate": 5e-06,
      "loss": 0.4374,
      "step": 1660
    },
    {
      "epoch": 1.8381948266373143,
      "grad_norm": 0.5463406636892771,
      "learning_rate": 5e-06,
      "loss": 0.4271,
      "step": 1670
    },
    {
      "epoch": 1.849201981287837,
      "grad_norm": 0.5154981959057048,
      "learning_rate": 5e-06,
      "loss": 0.4297,
      "step": 1680
    },
    {
      "epoch": 1.86020913593836,
      "grad_norm": 0.5312549310410268,
      "learning_rate": 5e-06,
      "loss": 0.436,
      "step": 1690
    },
    {
      "epoch": 1.8712162905888827,
      "grad_norm": 0.551407654359753,
      "learning_rate": 5e-06,
      "loss": 0.4381,
      "step": 1700
    },
    {
      "epoch": 1.8822234452394055,
      "grad_norm": 0.540138846863153,
      "learning_rate": 5e-06,
      "loss": 0.4315,
      "step": 1710
    },
    {
      "epoch": 1.8932305998899284,
      "grad_norm": 0.6033253391417194,
      "learning_rate": 5e-06,
      "loss": 0.4337,
      "step": 1720
    },
    {
      "epoch": 1.9042377545404512,
      "grad_norm": 0.61160643823951,
      "learning_rate": 5e-06,
      "loss": 0.4297,
      "step": 1730
    },
    {
      "epoch": 1.915244909190974,
      "grad_norm": 0.5505886988824265,
      "learning_rate": 5e-06,
      "loss": 0.4307,
      "step": 1740
    },
    {
      "epoch": 1.9262520638414968,
      "grad_norm": 0.5989272614081892,
      "learning_rate": 5e-06,
      "loss": 0.4295,
      "step": 1750
    },
    {
      "epoch": 1.9372592184920197,
      "grad_norm": 0.5242486461915085,
      "learning_rate": 5e-06,
      "loss": 0.4276,
      "step": 1760
    },
    {
      "epoch": 1.9482663731425427,
      "grad_norm": 0.5681896345892186,
      "learning_rate": 5e-06,
      "loss": 0.4306,
      "step": 1770
    },
    {
      "epoch": 1.9592735277930655,
      "grad_norm": 0.5667700512399272,
      "learning_rate": 5e-06,
      "loss": 0.428,
      "step": 1780
    },
    {
      "epoch": 1.9702806824435883,
      "grad_norm": 0.569299516369229,
      "learning_rate": 5e-06,
      "loss": 0.4303,
      "step": 1790
    },
    {
      "epoch": 1.9812878370941112,
      "grad_norm": 0.5369184206876113,
      "learning_rate": 5e-06,
      "loss": 0.4295,
      "step": 1800
    },
    {
      "epoch": 1.992294991744634,
      "grad_norm": 0.5529747180809514,
      "learning_rate": 5e-06,
      "loss": 0.4298,
      "step": 1810
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4725576341152191,
      "eval_runtime": 160.9677,
      "eval_samples_per_second": 152.024,
      "eval_steps_per_second": 0.596,
      "step": 1817
    },
    {
      "epoch": 2.003302146395157,
      "grad_norm": 0.8861521336936925,
      "learning_rate": 5e-06,
      "loss": 0.4167,
      "step": 1820
    },
    {
      "epoch": 2.01430930104568,
      "grad_norm": 0.6892658830373809,
      "learning_rate": 5e-06,
      "loss": 0.3791,
      "step": 1830
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 0.6130982380336389,
      "learning_rate": 5e-06,
      "loss": 0.377,
      "step": 1840
    },
    {
      "epoch": 2.0363236103467255,
      "grad_norm": 0.5500141598945452,
      "learning_rate": 5e-06,
      "loss": 0.3733,
      "step": 1850
    },
    {
      "epoch": 2.0473307649972483,
      "grad_norm": 0.640976655229211,
      "learning_rate": 5e-06,
      "loss": 0.379,
      "step": 1860
    },
    {
      "epoch": 2.058337919647771,
      "grad_norm": 0.5752122188586861,
      "learning_rate": 5e-06,
      "loss": 0.3793,
      "step": 1870
    },
    {
      "epoch": 2.069345074298294,
      "grad_norm": 0.6520981163357644,
      "learning_rate": 5e-06,
      "loss": 0.379,
      "step": 1880
    },
    {
      "epoch": 2.0803522289488168,
      "grad_norm": 0.6671099473289382,
      "learning_rate": 5e-06,
      "loss": 0.378,
      "step": 1890
    },
    {
      "epoch": 2.0913593835993396,
      "grad_norm": 0.630309142743594,
      "learning_rate": 5e-06,
      "loss": 0.3777,
      "step": 1900
    },
    {
      "epoch": 2.1023665382498624,
      "grad_norm": 0.6909567500460214,
      "learning_rate": 5e-06,
      "loss": 0.3738,
      "step": 1910
    },
    {
      "epoch": 2.1133736929003852,
      "grad_norm": 0.6815956176286785,
      "learning_rate": 5e-06,
      "loss": 0.3773,
      "step": 1920
    },
    {
      "epoch": 2.124380847550908,
      "grad_norm": 0.5707426072330477,
      "learning_rate": 5e-06,
      "loss": 0.3702,
      "step": 1930
    },
    {
      "epoch": 2.135388002201431,
      "grad_norm": 0.6040074116591623,
      "learning_rate": 5e-06,
      "loss": 0.3759,
      "step": 1940
    },
    {
      "epoch": 2.1463951568519537,
      "grad_norm": 0.5670259744264411,
      "learning_rate": 5e-06,
      "loss": 0.3751,
      "step": 1950
    },
    {
      "epoch": 2.1574023115024765,
      "grad_norm": 0.5692233527320808,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 1960
    },
    {
      "epoch": 2.1684094661529993,
      "grad_norm": 0.5789493847877696,
      "learning_rate": 5e-06,
      "loss": 0.3743,
      "step": 1970
    },
    {
      "epoch": 2.179416620803522,
      "grad_norm": 0.6112232211302647,
      "learning_rate": 5e-06,
      "loss": 0.3743,
      "step": 1980
    },
    {
      "epoch": 2.190423775454045,
      "grad_norm": 0.6302887797402175,
      "learning_rate": 5e-06,
      "loss": 0.378,
      "step": 1990
    },
    {
      "epoch": 2.201430930104568,
      "grad_norm": 0.6733666822713485,
      "learning_rate": 5e-06,
      "loss": 0.377,
      "step": 2000
    },
    {
      "epoch": 2.2124380847550906,
      "grad_norm": 0.6353223463231811,
      "learning_rate": 5e-06,
      "loss": 0.3776,
      "step": 2010
    },
    {
      "epoch": 2.2234452394056134,
      "grad_norm": 0.6295504535613273,
      "learning_rate": 5e-06,
      "loss": 0.381,
      "step": 2020
    },
    {
      "epoch": 2.2344523940561363,
      "grad_norm": 0.5761239648683782,
      "learning_rate": 5e-06,
      "loss": 0.3742,
      "step": 2030
    },
    {
      "epoch": 2.2454595487066595,
      "grad_norm": 0.6271978461426522,
      "learning_rate": 5e-06,
      "loss": 0.3811,
      "step": 2040
    },
    {
      "epoch": 2.2564667033571824,
      "grad_norm": 0.5674731636449037,
      "learning_rate": 5e-06,
      "loss": 0.376,
      "step": 2050
    },
    {
      "epoch": 2.267473858007705,
      "grad_norm": 0.5454803251231741,
      "learning_rate": 5e-06,
      "loss": 0.3778,
      "step": 2060
    },
    {
      "epoch": 2.278481012658228,
      "grad_norm": 0.6148461329472565,
      "learning_rate": 5e-06,
      "loss": 0.3808,
      "step": 2070
    },
    {
      "epoch": 2.289488167308751,
      "grad_norm": 0.5696712268071389,
      "learning_rate": 5e-06,
      "loss": 0.3749,
      "step": 2080
    },
    {
      "epoch": 2.3004953219592736,
      "grad_norm": 0.6037092379724925,
      "learning_rate": 5e-06,
      "loss": 0.3776,
      "step": 2090
    },
    {
      "epoch": 2.3115024766097965,
      "grad_norm": 0.7369680694568643,
      "learning_rate": 5e-06,
      "loss": 0.3802,
      "step": 2100
    },
    {
      "epoch": 2.3225096312603193,
      "grad_norm": 0.6321419825410511,
      "learning_rate": 5e-06,
      "loss": 0.3837,
      "step": 2110
    },
    {
      "epoch": 2.333516785910842,
      "grad_norm": 0.6106978423379751,
      "learning_rate": 5e-06,
      "loss": 0.3782,
      "step": 2120
    },
    {
      "epoch": 2.344523940561365,
      "grad_norm": 0.6072740258524655,
      "learning_rate": 5e-06,
      "loss": 0.3781,
      "step": 2130
    },
    {
      "epoch": 2.3555310952118877,
      "grad_norm": 0.647753922042719,
      "learning_rate": 5e-06,
      "loss": 0.3854,
      "step": 2140
    },
    {
      "epoch": 2.3665382498624106,
      "grad_norm": 0.6082439972579275,
      "learning_rate": 5e-06,
      "loss": 0.3819,
      "step": 2150
    },
    {
      "epoch": 2.3775454045129334,
      "grad_norm": 0.5978693538094152,
      "learning_rate": 5e-06,
      "loss": 0.3818,
      "step": 2160
    },
    {
      "epoch": 2.388552559163456,
      "grad_norm": 0.6003736709173206,
      "learning_rate": 5e-06,
      "loss": 0.3771,
      "step": 2170
    },
    {
      "epoch": 2.399559713813979,
      "grad_norm": 0.6307314872816914,
      "learning_rate": 5e-06,
      "loss": 0.3811,
      "step": 2180
    },
    {
      "epoch": 2.410566868464502,
      "grad_norm": 0.6599639202292461,
      "learning_rate": 5e-06,
      "loss": 0.3783,
      "step": 2190
    },
    {
      "epoch": 2.4215740231150247,
      "grad_norm": 0.6912051261227585,
      "learning_rate": 5e-06,
      "loss": 0.3794,
      "step": 2200
    },
    {
      "epoch": 2.4325811777655475,
      "grad_norm": 0.7089464618082304,
      "learning_rate": 5e-06,
      "loss": 0.3803,
      "step": 2210
    },
    {
      "epoch": 2.4435883324160703,
      "grad_norm": 0.699533687846073,
      "learning_rate": 5e-06,
      "loss": 0.3788,
      "step": 2220
    },
    {
      "epoch": 2.454595487066593,
      "grad_norm": 0.7712301792225386,
      "learning_rate": 5e-06,
      "loss": 0.3818,
      "step": 2230
    },
    {
      "epoch": 2.465602641717116,
      "grad_norm": 0.6441985393507654,
      "learning_rate": 5e-06,
      "loss": 0.3779,
      "step": 2240
    },
    {
      "epoch": 2.476609796367639,
      "grad_norm": 0.6166692892050696,
      "learning_rate": 5e-06,
      "loss": 0.3805,
      "step": 2250
    },
    {
      "epoch": 2.487616951018162,
      "grad_norm": 0.588424438537565,
      "learning_rate": 5e-06,
      "loss": 0.3805,
      "step": 2260
    },
    {
      "epoch": 2.498624105668685,
      "grad_norm": 0.5986189719224738,
      "learning_rate": 5e-06,
      "loss": 0.378,
      "step": 2270
    },
    {
      "epoch": 2.5096312603192077,
      "grad_norm": 0.6713635474898176,
      "learning_rate": 5e-06,
      "loss": 0.382,
      "step": 2280
    },
    {
      "epoch": 2.5206384149697305,
      "grad_norm": 0.6114166378742365,
      "learning_rate": 5e-06,
      "loss": 0.3775,
      "step": 2290
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 0.5927146129909185,
      "learning_rate": 5e-06,
      "loss": 0.3788,
      "step": 2300
    },
    {
      "epoch": 2.542652724270776,
      "grad_norm": 0.6481722170233998,
      "learning_rate": 5e-06,
      "loss": 0.3827,
      "step": 2310
    },
    {
      "epoch": 2.553659878921299,
      "grad_norm": 0.6093928418805276,
      "learning_rate": 5e-06,
      "loss": 0.3827,
      "step": 2320
    },
    {
      "epoch": 2.564667033571822,
      "grad_norm": 0.5760261750722316,
      "learning_rate": 5e-06,
      "loss": 0.3794,
      "step": 2330
    },
    {
      "epoch": 2.5756741882223446,
      "grad_norm": 0.546035367442567,
      "learning_rate": 5e-06,
      "loss": 0.3801,
      "step": 2340
    },
    {
      "epoch": 2.5866813428728674,
      "grad_norm": 0.5949259270960803,
      "learning_rate": 5e-06,
      "loss": 0.3783,
      "step": 2350
    },
    {
      "epoch": 2.5976884975233903,
      "grad_norm": 0.5806746124686398,
      "learning_rate": 5e-06,
      "loss": 0.3841,
      "step": 2360
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.5919944678625259,
      "learning_rate": 5e-06,
      "loss": 0.3836,
      "step": 2370
    },
    {
      "epoch": 2.619702806824436,
      "grad_norm": 0.5980838281657921,
      "learning_rate": 5e-06,
      "loss": 0.3769,
      "step": 2380
    },
    {
      "epoch": 2.6307099614749587,
      "grad_norm": 0.6481584461041264,
      "learning_rate": 5e-06,
      "loss": 0.381,
      "step": 2390
    },
    {
      "epoch": 2.6417171161254815,
      "grad_norm": 0.5874311612757207,
      "learning_rate": 5e-06,
      "loss": 0.3791,
      "step": 2400
    },
    {
      "epoch": 2.6527242707760044,
      "grad_norm": 0.5393082329976977,
      "learning_rate": 5e-06,
      "loss": 0.3795,
      "step": 2410
    },
    {
      "epoch": 2.663731425426527,
      "grad_norm": 0.6391507361732646,
      "learning_rate": 5e-06,
      "loss": 0.3777,
      "step": 2420
    },
    {
      "epoch": 2.67473858007705,
      "grad_norm": 0.6752338448438331,
      "learning_rate": 5e-06,
      "loss": 0.3809,
      "step": 2430
    },
    {
      "epoch": 2.685745734727573,
      "grad_norm": 0.6424613862207754,
      "learning_rate": 5e-06,
      "loss": 0.3791,
      "step": 2440
    },
    {
      "epoch": 2.6967528893780957,
      "grad_norm": 0.6103493940236195,
      "learning_rate": 5e-06,
      "loss": 0.3777,
      "step": 2450
    },
    {
      "epoch": 2.7077600440286185,
      "grad_norm": 0.6015418958936961,
      "learning_rate": 5e-06,
      "loss": 0.3809,
      "step": 2460
    },
    {
      "epoch": 2.7187671986791413,
      "grad_norm": 0.593488838926255,
      "learning_rate": 5e-06,
      "loss": 0.3829,
      "step": 2470
    },
    {
      "epoch": 2.729774353329664,
      "grad_norm": 0.6036597919786563,
      "learning_rate": 5e-06,
      "loss": 0.38,
      "step": 2480
    },
    {
      "epoch": 2.740781507980187,
      "grad_norm": 0.5639219893276929,
      "learning_rate": 5e-06,
      "loss": 0.3802,
      "step": 2490
    },
    {
      "epoch": 2.7517886626307098,
      "grad_norm": 0.6130147843919902,
      "learning_rate": 5e-06,
      "loss": 0.3837,
      "step": 2500
    },
    {
      "epoch": 2.7627958172812326,
      "grad_norm": 0.6123037077664492,
      "learning_rate": 5e-06,
      "loss": 0.3771,
      "step": 2510
    },
    {
      "epoch": 2.7738029719317554,
      "grad_norm": 0.5850243924752155,
      "learning_rate": 5e-06,
      "loss": 0.3833,
      "step": 2520
    },
    {
      "epoch": 2.7848101265822782,
      "grad_norm": 0.589884075763954,
      "learning_rate": 5e-06,
      "loss": 0.3758,
      "step": 2530
    },
    {
      "epoch": 2.795817281232801,
      "grad_norm": 0.6176690347871701,
      "learning_rate": 5e-06,
      "loss": 0.3846,
      "step": 2540
    },
    {
      "epoch": 2.8068244358833243,
      "grad_norm": 0.5949996697230896,
      "learning_rate": 5e-06,
      "loss": 0.3807,
      "step": 2550
    },
    {
      "epoch": 2.817831590533847,
      "grad_norm": 0.6341629255150304,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 2560
    },
    {
      "epoch": 2.82883874518437,
      "grad_norm": 0.5975135304739316,
      "learning_rate": 5e-06,
      "loss": 0.3833,
      "step": 2570
    },
    {
      "epoch": 2.8398458998348928,
      "grad_norm": 0.7351357789320612,
      "learning_rate": 5e-06,
      "loss": 0.3786,
      "step": 2580
    },
    {
      "epoch": 2.8508530544854156,
      "grad_norm": 0.6285771692837051,
      "learning_rate": 5e-06,
      "loss": 0.3792,
      "step": 2590
    },
    {
      "epoch": 2.8618602091359384,
      "grad_norm": 0.6596485761523762,
      "learning_rate": 5e-06,
      "loss": 0.3772,
      "step": 2600
    },
    {
      "epoch": 2.8728673637864612,
      "grad_norm": 0.6164968919053221,
      "learning_rate": 5e-06,
      "loss": 0.3815,
      "step": 2610
    },
    {
      "epoch": 2.883874518436984,
      "grad_norm": 0.5945977263042338,
      "learning_rate": 5e-06,
      "loss": 0.3879,
      "step": 2620
    },
    {
      "epoch": 2.894881673087507,
      "grad_norm": 0.6196977946239451,
      "learning_rate": 5e-06,
      "loss": 0.3756,
      "step": 2630
    },
    {
      "epoch": 2.9058888277380297,
      "grad_norm": 0.5936308368510096,
      "learning_rate": 5e-06,
      "loss": 0.3792,
      "step": 2640
    },
    {
      "epoch": 2.9168959823885525,
      "grad_norm": 0.5766476508395794,
      "learning_rate": 5e-06,
      "loss": 0.383,
      "step": 2650
    },
    {
      "epoch": 2.9279031370390753,
      "grad_norm": 0.6705751923379233,
      "learning_rate": 5e-06,
      "loss": 0.3838,
      "step": 2660
    },
    {
      "epoch": 2.938910291689598,
      "grad_norm": 0.6305266614849032,
      "learning_rate": 5e-06,
      "loss": 0.3805,
      "step": 2670
    },
    {
      "epoch": 2.949917446340121,
      "grad_norm": 0.5578589567242559,
      "learning_rate": 5e-06,
      "loss": 0.379,
      "step": 2680
    },
    {
      "epoch": 2.960924600990644,
      "grad_norm": 0.5812437474960733,
      "learning_rate": 5e-06,
      "loss": 0.3779,
      "step": 2690
    },
    {
      "epoch": 2.9719317556411666,
      "grad_norm": 0.5702384575759576,
      "learning_rate": 5e-06,
      "loss": 0.3788,
      "step": 2700
    },
    {
      "epoch": 2.9829389102916894,
      "grad_norm": 0.6002094241817759,
      "learning_rate": 5e-06,
      "loss": 0.3769,
      "step": 2710
    },
    {
      "epoch": 2.9939460649422127,
      "grad_norm": 0.5761233457133683,
      "learning_rate": 5e-06,
      "loss": 0.3804,
      "step": 2720
    },
    {
      "epoch": 2.9983489268024215,
      "eval_loss": 0.4722456932067871,
      "eval_runtime": 159.4748,
      "eval_samples_per_second": 153.447,
      "eval_steps_per_second": 0.602,
      "step": 2724
    },
    {
      "epoch": 2.9983489268024215,
      "step": 2724,
      "total_flos": 4561963937955840.0,
      "train_loss": 0.4431529876156525,
      "train_runtime": 23524.7066,
      "train_samples_per_second": 59.291,
      "train_steps_per_second": 0.116
    }
  ],
  "logging_steps": 10,
  "max_steps": 2724,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4561963937955840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}